1 /*
2 * Copyright (c) 1994, 2015, 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.nio.charset.Charset;
31 import java.util.ArrayList;
32 import java.util.Arrays;
33 import java.util.Comparator;
34 import java.util.Formatter;
35 import java.util.Locale;
36 import java.util.Objects;
37 import java.util.Spliterator;
38 import java.util.StringJoiner;
39 import java.util.function.ToIntFunction;
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.StreamSupport;
45 import jdk.internal.HotSpotIntrinsicCandidate;
46 import jdk.internal.vm.annotation.Stable;
47
48 /**
49 * The {@code String} class represents character strings. All
50 * string literals in Java programs, such as {@code "abc"}, are
51 * implemented as instances of this class.
52 * <p>
53 * Strings are constant; their values cannot be changed after they
54 * are created. String buffers support mutable strings.
55 * Because String objects are immutable they can be shared. For example:
56 * <blockquote><pre>
57 * String str = "abc";
58 * </pre></blockquote><p>
59 * is equivalent to:
60 * <blockquote><pre>
61 * char data[] = {'a', 'b', 'c'};
62 * String str = new String(data);
63 * </pre></blockquote><p>
64 * Here are some more examples of how strings can be used:
65 * <blockquote><pre>
66 * System.out.println("abc");
67 * String cde = "cde";
68 * System.out.println("abc" + cde);
69 * String c = "abc".substring(2,3);
70 * String d = cde.substring(1, 2);
71 * </pre></blockquote>
72 * <p>
73 * The class {@code String} includes methods for examining
74 * individual characters of the sequence, for comparing strings, for
75 * searching strings, for extracting substrings, and for creating a
76 * copy of a string with all characters translated to uppercase or to
77 * lowercase. Case mapping is based on the Unicode Standard version
78 * specified by the {@link java.lang.Character Character} class.
79 * <p>
80 * The Java language provides special support for the string
81 * concatenation operator ( + ), and for conversion of
82 * other objects to strings. String concatenation is implemented
83 * through the {@code StringBuilder}(or {@code StringBuffer})
84 * class and its {@code append} method.
85 * String conversions are implemented through the method
86 * {@code toString}, defined by {@code Object} and
87 * inherited by all classes in Java. For additional information on
88 * string concatenation and conversion, see Gosling, Joy, and Steele,
89 * <i>The Java Language Specification</i>.
90 *
91 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor
92 * or method in this class will cause a {@link NullPointerException} to be
93 * thrown.
94 *
95 * <p>A {@code String} represents a string in the UTF-16 format
96 * in which <em>supplementary characters</em> are represented by <em>surrogate
97 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
98 * Character Representations</a> in the {@code Character} class for
99 * more information).
100 * Index values refer to {@code char} code units, so a supplementary
101 * character uses two positions in a {@code String}.
102 * <p>The {@code String} class provides methods for dealing with
103 * Unicode code points (i.e., characters), in addition to those for
104 * dealing with Unicode code units (i.e., {@code char} values).
105 *
106 * <p>Unless otherwise noted, methods for comparing Strings do not take locale
107 * into account. The {@link java.text.Collator} class provides methods for
108 * finer-grain, locale-sensitive String comparison.
109 *
110 * @author Lee Boynton
111 * @author Arthur van Hoff
112 * @author Martin Buchholz
113 * @author Ulf Zibis
114 * @see java.lang.Object#toString()
115 * @see java.lang.StringBuffer
116 * @see java.lang.StringBuilder
117 * @see java.nio.charset.Charset
118 * @since 1.0
119 */
120
121 public final class String
122 implements java.io.Serializable, Comparable<String>, CharSequence {
123
124 /**
125 * The value is used for character storage.
126 *
127 * @implNote This field is trusted by the VM, and is a subject to
128 * constant folding if String instance is constant. Overwriting this
129 * field after construction will cause problems.
130 *
131 * Additionally, it is marked with {@link Stable} to trust the contents
132 * of the array. No other facility in JDK provides this functionality (yet).
133 * {@link Stable} is safe here, because value is never null.
134 */
135 @Stable
136 private final byte[] value;
137
138 /**
139 * The identifier of the encoding used to encode the bytes in
140 * {@code value}. The supported values in this implementation are
141 *
142 * LATIN1
143 * UTF16
144 *
145 * @implNote This field is trusted by the VM, and is a subject to
146 * constant folding if String instance is constant. Overwriting this
147 * field after construction will cause problems.
148 */
149 private final byte coder;
150
151 /** Cache the hash code for the string */
152 private int hash; // Default to 0
153
154 /** use serialVersionUID from JDK 1.0.2 for interoperability */
155 private static final long serialVersionUID = -6849794470754667710L;
156
157 /**
158 * If String compaction is disabled, the bytes in {@code value} are
159 * always encoded in UTF16.
160 *
161 * For methods with several possible implementation paths, when String
162 * compaction is disabled, only one code path is taken.
163 *
164 * The instance field value is generally opaque to optimizing JIT
165 * compilers. Therefore, in performance-sensitive place, an explicit
166 * check of the static boolean {@code COMPACT_STRINGS} is done first
167 * before checking the {@code coder} field since the static boolean
168 * {@code COMPACT_STRINGS} would be constant folded away by an
169 * optimizing JIT compiler. The idioms for these cases are as follows.
170 *
171 * For code such as:
172 *
173 * if (coder == LATIN1) { ... }
174 *
175 * can be written more optimally as
176 *
177 * if (coder() == LATIN1) { ... }
178 *
179 * or:
180 *
181 * if (COMPACT_STRINGS && coder == LATIN1) { ... }
182 *
183 * An optimizing JIT compiler can fold the above conditional as:
184 *
185 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... }
186 * COMPACT_STRINGS == false => if (false) { ... }
187 *
188 * @implNote
189 * The actual value for this field is injected by JVM. The static
190 * initialization block is used to set the value here to communicate
191 * that this static final field is not statically foldable, and to
192 * avoid any possible circular dependency during vm initialization.
193 */
194 static final boolean COMPACT_STRINGS;
195
196 static {
197 COMPACT_STRINGS = true;
198 }
199
200 /**
201 * Class String is special cased within the Serialization Stream Protocol.
202 *
203 * A String instance is written into an ObjectOutputStream according to
204 * <a href="{@docRoot}/../platform/serialization/spec/output.html">
205 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
206 */
207 private static final ObjectStreamField[] serialPersistentFields =
208 new ObjectStreamField[0];
209
210 /**
211 * Initializes a newly created {@code String} object so that it represents
212 * an empty character sequence. Note that use of this constructor is
213 * unnecessary since Strings are immutable.
214 */
215 public String() {
216 this.value = "".value;
217 this.coder = "".coder;
218 }
219
220 /**
221 * Initializes a newly created {@code String} object so that it represents
222 * the same sequence of characters as the argument; in other words, the
223 * newly created string is a copy of the argument string. Unless an
224 * explicit copy of {@code original} is needed, use of this constructor is
225 * unnecessary since Strings are immutable.
226 *
227 * @param original
228 * A {@code String}
229 */
230 @HotSpotIntrinsicCandidate
231 public String(String original) {
232 this.value = original.value;
233 this.coder = original.coder;
234 this.hash = original.hash;
235 }
236
237 /**
238 * Allocates a new {@code String} so that it represents the sequence of
239 * characters currently contained in the character array argument. The
240 * contents of the character array are copied; subsequent modification of
241 * the character array does not affect the newly created string.
242 *
243 * @param value
244 * The initial value of the string
245 */
246 public String(char value[]) {
247 this(value, 0, value.length, null);
248 }
249
250 /**
251 * Allocates a new {@code String} that contains characters from a subarray
252 * of the character array argument. The {@code offset} argument is the
253 * index of the first character of the subarray and the {@code count}
254 * argument specifies the length of the subarray. The contents of the
255 * subarray are copied; subsequent modification of the character array does
256 * not affect the newly created string.
257 *
258 * @param value
259 * Array that is the source of characters
260 *
261 * @param offset
262 * The initial offset
263 *
264 * @param count
265 * The length
266 *
267 * @throws IndexOutOfBoundsException
268 * If {@code offset} is negative, {@code count} is negative, or
269 * {@code offset} is greater than {@code value.length - count}
270 */
271 public String(char value[], int offset, int count) {
272 this(value, offset, count, rangeCheck(value, offset, count));
273 }
274
275 private static Void rangeCheck(char[] value, int offset, int count) {
276 checkBoundsOffCount(offset, count, value.length);
277 return null;
278 }
279
280 /**
281 * Allocates a new {@code String} that contains characters from a subarray
282 * of the <a href="Character.html#unicode">Unicode code point</a> array
283 * argument. The {@code offset} argument is the index of the first code
284 * point of the subarray and the {@code count} argument specifies the
285 * length of the subarray. The contents of the subarray are converted to
286 * {@code char}s; subsequent modification of the {@code int} array does not
287 * affect the newly created string.
288 *
289 * @param codePoints
290 * Array that is the source of Unicode code points
291 *
292 * @param offset
293 * The initial offset
294 *
295 * @param count
296 * The length
297 *
298 * @throws IllegalArgumentException
299 * If any invalid Unicode code point is found in {@code
300 * codePoints}
301 *
302 * @throws IndexOutOfBoundsException
303 * If {@code offset} is negative, {@code count} is negative, or
304 * {@code offset} is greater than {@code codePoints.length - count}
305 *
306 * @since 1.5
307 */
308 public String(int[] codePoints, int offset, int count) {
309 checkBoundsOffCount(offset, count, codePoints.length);
310 if (count == 0) {
311 this.value = "".value;
312 this.coder = "".coder;
313 return;
314 }
315 if (COMPACT_STRINGS) {
316 byte[] val = StringLatin1.toBytes(codePoints, offset, count);
317 if (val != null) {
318 this.coder = LATIN1;
319 this.value = val;
320 return;
321 }
322 }
323 this.coder = UTF16;
324 this.value = StringUTF16.toBytes(codePoints, offset, count);
325 }
326
327 /**
328 * Allocates a new {@code String} constructed from a subarray of an array
329 * of 8-bit integer values.
330 *
331 * <p> The {@code offset} argument is the index of the first byte of the
332 * subarray, and the {@code count} argument specifies the length of the
333 * subarray.
334 *
335 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
336 * specified in the method above.
337 *
338 * @deprecated This method does not properly convert bytes into characters.
339 * As of JDK 1.1, the preferred way to do this is via the
340 * {@code String} constructors that take a {@link
341 * java.nio.charset.Charset}, charset name, or that use the platform's
342 * default charset.
343 *
344 * @param ascii
345 * The bytes to be converted to characters
346 *
347 * @param hibyte
348 * The top 8 bits of each 16-bit Unicode code unit
349 *
350 * @param offset
351 * The initial offset
352 * @param count
353 * The length
354 *
355 * @throws IndexOutOfBoundsException
356 * If {@code offset} is negative, {@code count} is negative, or
357 * {@code offset} is greater than {@code ascii.length - count}
358 *
359 * @see #String(byte[], int)
360 * @see #String(byte[], int, int, java.lang.String)
361 * @see #String(byte[], int, int, java.nio.charset.Charset)
362 * @see #String(byte[], int, int)
363 * @see #String(byte[], java.lang.String)
364 * @see #String(byte[], java.nio.charset.Charset)
365 * @see #String(byte[])
366 */
367 @Deprecated
368 public String(byte ascii[], int hibyte, int offset, int count) {
369 checkBoundsOffCount(offset, count, ascii.length);
370 if (count == 0) {
371 this.value = "".value;
372 this.coder = "".coder;
373 return;
374 }
375 if (COMPACT_STRINGS && (byte)hibyte == 0) {
376 this.value = Arrays.copyOfRange(ascii, offset, offset + count);
377 this.coder = LATIN1;
378 } else {
379 hibyte <<= 8;
380 byte[] val = StringUTF16.newBytesFor(count);
381 for (int i = 0; i < count; i++) {
382 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff));
383 }
384 this.value = val;
385 this.coder = UTF16;
386 }
387 }
388
389 /**
390 * Allocates a new {@code String} containing characters constructed from
391 * an array of 8-bit integer values. Each character <i>c</i>in the
392 * resulting string is constructed from the corresponding component
393 * <i>b</i> in the byte array such that:
394 *
395 * <blockquote><pre>
396 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
397 * | (<b><i>b</i></b> & 0xff))
398 * </pre></blockquote>
399 *
400 * @deprecated This method does not properly convert bytes into
401 * characters. As of JDK 1.1, the preferred way to do this is via the
402 * {@code String} constructors that take a {@link
403 * java.nio.charset.Charset}, charset name, or that use the platform's
404 * default charset.
405 *
406 * @param ascii
407 * The bytes to be converted to characters
408 *
409 * @param hibyte
410 * The top 8 bits of each 16-bit Unicode code unit
411 *
412 * @see #String(byte[], int, int, java.lang.String)
413 * @see #String(byte[], int, int, java.nio.charset.Charset)
414 * @see #String(byte[], int, int)
415 * @see #String(byte[], java.lang.String)
416 * @see #String(byte[], java.nio.charset.Charset)
417 * @see #String(byte[])
418 */
419 @Deprecated
420 public String(byte ascii[], int hibyte) {
421 this(ascii, hibyte, 0, ascii.length);
422 }
423
424 /**
425 * Constructs a new {@code String} by decoding the specified subarray of
426 * bytes using the specified charset. The length of the new {@code String}
427 * is a function of the charset, and hence may not be equal to the length
428 * of the subarray.
429 *
430 * <p> The behavior of this constructor when the given bytes are not valid
431 * in the given charset is unspecified. The {@link
432 * java.nio.charset.CharsetDecoder} class should be used when more control
433 * over the decoding process is required.
434 *
435 * @param bytes
436 * The bytes to be decoded into characters
437 *
438 * @param offset
439 * The index of the first byte to decode
440 *
441 * @param length
442 * The number of bytes to decode
443
444 * @param charsetName
445 * The name of a supported {@linkplain java.nio.charset.Charset
446 * charset}
447 *
448 * @throws UnsupportedEncodingException
449 * If the named charset is not supported
450 *
451 * @throws IndexOutOfBoundsException
452 * If {@code offset} is negative, {@code length} is negative, or
453 * {@code offset} is greater than {@code bytes.length - length}
454 *
455 * @since 1.1
456 */
457 public String(byte bytes[], int offset, int length, String charsetName)
458 throws UnsupportedEncodingException {
459 if (charsetName == null)
460 throw new NullPointerException("charsetName");
461 checkBoundsOffCount(offset, length, bytes.length);
462 StringCoding.Result ret =
463 StringCoding.decode(charsetName, bytes, offset, length);
464 this.value = ret.value;
465 this.coder = ret.coder;
466 }
467
468 /**
469 * Constructs a new {@code String} by decoding the specified subarray of
470 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
471 * The length of the new {@code String} is a function of the charset, and
472 * hence may not be equal to the length of the subarray.
473 *
474 * <p> This method always replaces malformed-input and unmappable-character
475 * sequences with this charset's default replacement string. The {@link
476 * java.nio.charset.CharsetDecoder} class should be used when more control
477 * over the decoding process is required.
478 *
479 * @param bytes
480 * The bytes to be decoded into characters
481 *
482 * @param offset
483 * The index of the first byte to decode
484 *
485 * @param length
486 * The number of bytes to decode
487 *
488 * @param charset
489 * The {@linkplain java.nio.charset.Charset charset} to be used to
490 * decode the {@code bytes}
491 *
492 * @throws IndexOutOfBoundsException
493 * If {@code offset} is negative, {@code length} is negative, or
494 * {@code offset} is greater than {@code bytes.length - length}
495 *
496 * @since 1.6
497 */
498 public String(byte bytes[], int offset, int length, Charset charset) {
499 if (charset == null)
500 throw new NullPointerException("charset");
501 checkBoundsOffCount(offset, length, bytes.length);
502 StringCoding.Result ret =
503 StringCoding.decode(charset, bytes, offset, length);
504 this.value = ret.value;
505 this.coder = ret.coder;
506 }
507
508 /**
509 * Constructs a new {@code String} by decoding the specified array of bytes
510 * using the specified {@linkplain java.nio.charset.Charset charset}. The
511 * length of the new {@code String} is a function of the charset, and hence
512 * may not be equal to the length of the byte array.
513 *
514 * <p> The behavior of this constructor when the given bytes are not valid
515 * in the given charset is unspecified. The {@link
516 * java.nio.charset.CharsetDecoder} class should be used when more control
517 * over the decoding process is required.
518 *
519 * @param bytes
520 * The bytes to be decoded into characters
521 *
522 * @param charsetName
523 * The name of a supported {@linkplain java.nio.charset.Charset
524 * charset}
525 *
526 * @throws UnsupportedEncodingException
527 * If the named charset is not supported
528 *
529 * @since 1.1
530 */
531 public String(byte bytes[], String charsetName)
532 throws UnsupportedEncodingException {
533 this(bytes, 0, bytes.length, charsetName);
534 }
535
536 /**
537 * Constructs a new {@code String} by decoding the specified array of
538 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
539 * The length of the new {@code String} is a function of the charset, and
540 * hence may not be equal to the length of the byte array.
541 *
542 * <p> This method always replaces malformed-input and unmappable-character
543 * sequences with this charset's default replacement string. The {@link
544 * java.nio.charset.CharsetDecoder} class should be used when more control
545 * over the decoding process is required.
546 *
547 * @param bytes
548 * The bytes to be decoded into characters
549 *
550 * @param charset
551 * The {@linkplain java.nio.charset.Charset charset} to be used to
552 * decode the {@code bytes}
553 *
554 * @since 1.6
555 */
556 public String(byte bytes[], Charset charset) {
557 this(bytes, 0, bytes.length, charset);
558 }
559
560 /**
561 * Constructs a new {@code String} by decoding the specified subarray of
562 * bytes using the platform's default charset. The length of the new
563 * {@code String} is a function of the charset, and hence may not be equal
564 * to the length of the subarray.
565 *
566 * <p> The behavior of this constructor when the given bytes are not valid
567 * in the default charset is unspecified. The {@link
568 * java.nio.charset.CharsetDecoder} class should be used when more control
569 * over the decoding process is required.
570 *
571 * @param bytes
572 * The bytes to be decoded into characters
573 *
574 * @param offset
575 * The index of the first byte to decode
576 *
577 * @param length
578 * The number of bytes to decode
579 *
580 * @throws IndexOutOfBoundsException
581 * If {@code offset} is negative, {@code length} is negative, or
582 * {@code offset} is greater than {@code bytes.length - length}
583 *
584 * @since 1.1
585 */
586 public String(byte bytes[], int offset, int length) {
587 checkBoundsOffCount(offset, length, bytes.length);
588 StringCoding.Result ret = StringCoding.decode(bytes, offset, length);
589 this.value = ret.value;
590 this.coder = ret.coder;
591 }
592
593 /**
594 * Constructs a new {@code String} by decoding the specified array of bytes
595 * using the platform's default charset. The length of the new {@code
596 * String} is a function of the charset, and hence may not be equal to the
597 * length of the byte array.
598 *
599 * <p> The behavior of this constructor when the given bytes are not valid
600 * in the default charset is unspecified. The {@link
601 * java.nio.charset.CharsetDecoder} class should be used when more control
602 * over the decoding process is required.
603 *
604 * @param bytes
605 * The bytes to be decoded into characters
606 *
607 * @since 1.1
608 */
609 public String(byte[] bytes) {
610 this(bytes, 0, bytes.length);
611 }
612
613 /**
614 * Allocates a new string that contains the sequence of characters
615 * currently contained in the string buffer argument. The contents of the
616 * string buffer are copied; subsequent modification of the string buffer
617 * does not affect the newly created string.
618 *
619 * @param buffer
620 * A {@code StringBuffer}
621 */
622 public String(StringBuffer buffer) {
623 this(buffer.toString());
624 }
625
626 /**
627 * Allocates a new string that contains the sequence of characters
628 * currently contained in the string builder argument. The contents of the
629 * string builder are copied; subsequent modification of the string builder
630 * does not affect the newly created string.
631 *
632 * <p> This constructor is provided to ease migration to {@code
633 * StringBuilder}. Obtaining a string from a string builder via the {@code
634 * toString} method is likely to run faster and is generally preferred.
635 *
636 * @param builder
637 * A {@code StringBuilder}
638 *
639 * @since 1.5
640 */
641 public String(StringBuilder builder) {
642 this(builder, null);
643 }
644
645 /*
646 * Package private constructor which shares value array for speed.
647 * this constructor is always expected to be called with share==true.
648 * a separate constructor is needed because we already have a public
649 * String(char[]) constructor that makes a copy of the given char[].
650 */
651 // TBD: this is kept for package internal use (Thread/System),
652 // should be removed if they all have a byte[] version
653 String(char[] val, boolean share) {
654 // assert share : "unshared not supported";
655 this(val, 0, val.length, null);
656 }
657
658 /**
659 * Returns the length of this string.
660 * The length is equal to the number of <a href="Character.html#unicode">Unicode
661 * code units</a> in the string.
662 *
663 * @return the length of the sequence of characters represented by this
664 * object.
665 */
666 public int length() {
667 return value.length >> coder();
668 }
669
670 /**
671 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
672 *
673 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
674 * {@code false}
675 *
676 * @since 1.6
677 */
678 public boolean isEmpty() {
679 return value.length == 0;
680 }
681
682 /**
683 * Returns the {@code char} value at the
684 * specified index. An index ranges from {@code 0} to
685 * {@code length() - 1}. The first {@code char} value of the sequence
686 * is at index {@code 0}, the next at index {@code 1},
687 * and so on, as for array indexing.
688 *
689 * <p>If the {@code char} value specified by the index is a
690 * <a href="Character.html#unicode">surrogate</a>, the surrogate
691 * value is returned.
692 *
693 * @param index the index of the {@code char} value.
694 * @return the {@code char} value at the specified index of this string.
695 * The first {@code char} value is at index {@code 0}.
696 * @exception IndexOutOfBoundsException if the {@code index}
697 * argument is negative or not less than the length of this
698 * string.
699 */
700 public char charAt(int index) {
701 if (isLatin1()) {
702 return StringLatin1.charAt(value, index);
703 } else {
704 return StringUTF16.charAt(value, index);
705 }
706 }
707
708 /**
709 * Returns the character (Unicode code point) at the specified
710 * index. The index refers to {@code char} values
711 * (Unicode code units) and ranges from {@code 0} to
712 * {@link #length()}{@code - 1}.
713 *
714 * <p> If the {@code char} value specified at the given index
715 * is in the high-surrogate range, the following index is less
716 * than the length of this {@code String}, and the
717 * {@code char} value at the following index is in the
718 * low-surrogate range, then the supplementary code point
719 * corresponding to this surrogate pair is returned. Otherwise,
720 * the {@code char} value at the given index is returned.
721 *
722 * @param index the index to the {@code char} values
723 * @return the code point value of the character at the
724 * {@code index}
725 * @exception IndexOutOfBoundsException if the {@code index}
726 * argument is negative or not less than the length of this
727 * string.
728 * @since 1.5
729 */
730 public int codePointAt(int index) {
731 if (isLatin1()) {
732 checkIndex(index, value.length);
733 return value[index] & 0xff;
734 }
735 int length = value.length >> 1;
736 checkIndex(index, length);
737 return StringUTF16.codePointAt(value, index, length);
738 }
739
740 /**
741 * Returns the character (Unicode code point) before the specified
742 * index. The index refers to {@code char} values
743 * (Unicode code units) and ranges from {@code 1} to {@link
744 * CharSequence#length() length}.
745 *
746 * <p> If the {@code char} value at {@code (index - 1)}
747 * is in the low-surrogate range, {@code (index - 2)} is not
748 * negative, and the {@code char} value at {@code (index -
749 * 2)} is in the high-surrogate range, then the
750 * supplementary code point value of the surrogate pair is
751 * returned. If the {@code char} value at {@code index -
752 * 1} is an unpaired low-surrogate or a high-surrogate, the
753 * surrogate value is returned.
754 *
755 * @param index the index following the code point that should be returned
756 * @return the Unicode code point value before the given index.
757 * @exception IndexOutOfBoundsException if the {@code index}
758 * argument is less than 1 or greater than the length
759 * of this string.
760 * @since 1.5
761 */
762 public int codePointBefore(int index) {
763 int i = index - 1;
764 if (i < 0 || i >= length()) {
765 throw new StringIndexOutOfBoundsException(index);
766 }
767 if (isLatin1()) {
768 return (value[i] & 0xff);
769 }
770 return StringUTF16.codePointBefore(value, index);
771 }
772
773 /**
774 * Returns the number of Unicode code points in the specified text
775 * range of this {@code String}. The text range begins at the
776 * specified {@code beginIndex} and extends to the
777 * {@code char} at index {@code endIndex - 1}. Thus the
778 * length (in {@code char}s) of the text range is
779 * {@code endIndex-beginIndex}. Unpaired surrogates within
780 * the text range count as one code point each.
781 *
782 * @param beginIndex the index to the first {@code char} of
783 * the text range.
784 * @param endIndex the index after the last {@code char} of
785 * the text range.
786 * @return the number of Unicode code points in the specified text
787 * range
788 * @exception IndexOutOfBoundsException if the
789 * {@code beginIndex} is negative, or {@code endIndex}
790 * is larger than the length of this {@code String}, or
791 * {@code beginIndex} is larger than {@code endIndex}.
792 * @since 1.5
793 */
794 public int codePointCount(int beginIndex, int endIndex) {
795 if (beginIndex < 0 || beginIndex > endIndex ||
796 endIndex > length()) {
797 throw new IndexOutOfBoundsException();
798 }
799 if (isLatin1()) {
800 return endIndex - beginIndex;
801 }
802 return StringUTF16.codePointCount(value, beginIndex, endIndex);
803 }
804
805 /**
806 * Returns the index within this {@code String} that is
807 * offset from the given {@code index} by
808 * {@code codePointOffset} code points. Unpaired surrogates
809 * within the text range given by {@code index} and
810 * {@code codePointOffset} count as one code point each.
811 *
812 * @param index the index to be offset
813 * @param codePointOffset the offset in code points
814 * @return the index within this {@code String}
815 * @exception IndexOutOfBoundsException if {@code index}
816 * is negative or larger then the length of this
817 * {@code String}, or if {@code codePointOffset} is positive
818 * and the substring starting with {@code index} has fewer
819 * than {@code codePointOffset} code points,
820 * or if {@code codePointOffset} is negative and the substring
821 * before {@code index} has fewer than the absolute value
822 * of {@code codePointOffset} code points.
823 * @since 1.5
824 */
825 public int offsetByCodePoints(int index, int codePointOffset) {
826 if (index < 0 || index > length()) {
827 throw new IndexOutOfBoundsException();
828 }
829 return Character.offsetByCodePoints(this, index, codePointOffset);
830 }
831
832 /**
833 * Copies characters from this string into the destination character
834 * array.
835 * <p>
836 * The first character to be copied is at index {@code srcBegin};
837 * the last character to be copied is at index {@code srcEnd-1}
838 * (thus the total number of characters to be copied is
839 * {@code srcEnd-srcBegin}). The characters are copied into the
840 * subarray of {@code dst} starting at index {@code dstBegin}
841 * and ending at index:
842 * <blockquote><pre>
843 * dstBegin + (srcEnd-srcBegin) - 1
844 * </pre></blockquote>
845 *
846 * @param srcBegin index of the first character in the string
847 * to copy.
848 * @param srcEnd index after the last character in the string
849 * to copy.
850 * @param dst the destination array.
851 * @param dstBegin the start offset in the destination array.
852 * @exception IndexOutOfBoundsException If any of the following
853 * is true:
854 * <ul><li>{@code srcBegin} is negative.
855 * <li>{@code srcBegin} is greater than {@code srcEnd}
856 * <li>{@code srcEnd} is greater than the length of this
857 * string
858 * <li>{@code dstBegin} is negative
859 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
860 * {@code dst.length}</ul>
861 */
862 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
863 checkBoundsBeginEnd(srcBegin, srcEnd, length());
864 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
865 if (isLatin1()) {
866 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin);
867 } else {
868 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin);
869 }
870 }
871
872 /**
873 * Copies characters from this string into the destination byte array. Each
874 * byte receives the 8 low-order bits of the corresponding character. The
875 * eight high-order bits of each character are not copied and do not
876 * participate in the transfer in any way.
877 *
878 * <p> The first character to be copied is at index {@code srcBegin}; the
879 * last character to be copied is at index {@code srcEnd-1}. The total
880 * number of characters to be copied is {@code srcEnd-srcBegin}. The
881 * characters, converted to bytes, are copied into the subarray of {@code
882 * dst} starting at index {@code dstBegin} and ending at index:
883 *
884 * <blockquote><pre>
885 * dstBegin + (srcEnd-srcBegin) - 1
886 * </pre></blockquote>
887 *
888 * @deprecated This method does not properly convert characters into
889 * bytes. As of JDK 1.1, the preferred way to do this is via the
890 * {@link #getBytes()} method, which uses the platform's default charset.
891 *
892 * @param srcBegin
893 * Index of the first character in the string to copy
894 *
895 * @param srcEnd
896 * Index after the last character in the string to copy
897 *
898 * @param dst
899 * The destination array
900 *
901 * @param dstBegin
902 * The start offset in the destination array
903 *
904 * @throws IndexOutOfBoundsException
905 * If any of the following is true:
906 * <ul>
907 * <li> {@code srcBegin} is negative
908 * <li> {@code srcBegin} is greater than {@code srcEnd}
909 * <li> {@code srcEnd} is greater than the length of this String
910 * <li> {@code dstBegin} is negative
911 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
912 * dst.length}
913 * </ul>
914 */
915 @Deprecated
916 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
917 checkBoundsBeginEnd(srcBegin, srcEnd, length());
918 Objects.requireNonNull(dst);
919 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
920 if (isLatin1()) {
921 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
922 } else {
923 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
924 }
925 }
926
927 /**
928 * Encodes this {@code String} into a sequence of bytes using the named
929 * charset, storing the result into a new byte array.
930 *
931 * <p> The behavior of this method when this string cannot be encoded in
932 * the given charset is unspecified. The {@link
933 * java.nio.charset.CharsetEncoder} class should be used when more control
934 * over the encoding process is required.
935 *
936 * @param charsetName
937 * The name of a supported {@linkplain java.nio.charset.Charset
938 * charset}
939 *
940 * @return The resultant byte array
941 *
942 * @throws UnsupportedEncodingException
943 * If the named charset is not supported
944 *
945 * @since 1.1
946 */
947 public byte[] getBytes(String charsetName)
948 throws UnsupportedEncodingException {
949 if (charsetName == null) throw new NullPointerException();
950 return StringCoding.encode(charsetName, coder(), value);
951 }
952
953 /**
954 * Encodes this {@code String} into a sequence of bytes using the given
955 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
956 * new byte array.
957 *
958 * <p> This method always replaces malformed-input and unmappable-character
959 * sequences with this charset's default replacement byte array. The
960 * {@link java.nio.charset.CharsetEncoder} class should be used when more
961 * control over the encoding process is required.
962 *
963 * @param charset
964 * The {@linkplain java.nio.charset.Charset} to be used to encode
965 * the {@code String}
966 *
967 * @return The resultant byte array
968 *
969 * @since 1.6
970 */
971 public byte[] getBytes(Charset charset) {
972 if (charset == null) throw new NullPointerException();
973 return StringCoding.encode(charset, coder(), value);
974 }
975
976 /**
977 * Encodes this {@code String} into a sequence of bytes using the
978 * platform's default charset, storing the result into a new byte array.
979 *
980 * <p> The behavior of this method when this string cannot be encoded in
981 * the default charset is unspecified. The {@link
982 * java.nio.charset.CharsetEncoder} class should be used when more control
983 * over the encoding process is required.
984 *
985 * @return The resultant byte array
986 *
987 * @since 1.1
988 */
989 public byte[] getBytes() {
990 return StringCoding.encode(coder(), value);
991 }
992
993 /**
994 * Compares this string to the specified object. The result is {@code
995 * true} if and only if the argument is not {@code null} and is a {@code
996 * String} object that represents the same sequence of characters as this
997 * object.
998 *
999 * <p>For finer-grained String comparison, refer to
1000 * {@link java.text.Collator}.
1001 *
1002 * @param anObject
1003 * The object to compare this {@code String} against
1004 *
1005 * @return {@code true} if the given object represents a {@code String}
1006 * equivalent to this string, {@code false} otherwise
1007 *
1008 * @see #compareTo(String)
1009 * @see #equalsIgnoreCase(String)
1010 */
1011 public boolean equals(Object anObject) {
1012 if (this == anObject) {
1013 return true;
1014 }
1015 if (anObject instanceof String) {
1016 String aString = (String)anObject;
1017 if (coder() == aString.coder()) {
1018 return isLatin1() ? StringLatin1.equals(value, aString.value)
1019 : StringUTF16.equals(value, aString.value);
1020 }
1021 }
1022 return false;
1023 }
1024
1025 /**
1026 * Compares this string to the specified {@code StringBuffer}. The result
1027 * is {@code true} if and only if this {@code String} represents the same
1028 * sequence of characters as the specified {@code StringBuffer}. This method
1029 * synchronizes on the {@code StringBuffer}.
1030 *
1031 * <p>For finer-grained String comparison, refer to
1032 * {@link java.text.Collator}.
1033 *
1034 * @param sb
1035 * The {@code StringBuffer} to compare this {@code String} against
1036 *
1037 * @return {@code true} if this {@code String} represents the same
1038 * sequence of characters as the specified {@code StringBuffer},
1039 * {@code false} otherwise
1040 *
1041 * @since 1.4
1042 */
1043 public boolean contentEquals(StringBuffer sb) {
1044 return contentEquals((CharSequence)sb);
1045 }
1046
1047 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1048 int len = length();
1049 if (len != sb.length()) {
1050 return false;
1051 }
1052 byte v1[] = value;
1053 byte v2[] = sb.getValue();
1054 if (coder() == sb.getCoder()) {
1055 int n = v1.length;
1056 for (int i = 0; i < n; i++) {
1057 if (v1[i] != v2[i]) {
1058 return false;
1059 }
1060 }
1061 } else {
1062 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal"
1063 return false;
1064 }
1065 for (int i = 0; i < len; i++) {
1066 if ((char)(v1[i] & 0xff) != StringUTF16.getChar(v2, i)) {
1067 return false;
1068 }
1069 }
1070 }
1071 return true;
1072 }
1073
1074 /**
1075 * Compares this string to the specified {@code CharSequence}. The
1076 * result is {@code true} if and only if this {@code String} represents the
1077 * same sequence of char values as the specified sequence. Note that if the
1078 * {@code CharSequence} is a {@code StringBuffer} then the method
1079 * synchronizes on it.
1080 *
1081 * <p>For finer-grained String comparison, refer to
1082 * {@link java.text.Collator}.
1083 *
1084 * @param cs
1085 * The sequence to compare this {@code String} against
1086 *
1087 * @return {@code true} if this {@code String} represents the same
1088 * sequence of char values as the specified sequence, {@code
1089 * false} otherwise
1090 *
1091 * @since 1.5
1092 */
1093 public boolean contentEquals(CharSequence cs) {
1094 // Argument is a StringBuffer, StringBuilder
1095 if (cs instanceof AbstractStringBuilder) {
1096 if (cs instanceof StringBuffer) {
1097 synchronized(cs) {
1098 return nonSyncContentEquals((AbstractStringBuilder)cs);
1099 }
1100 } else {
1101 return nonSyncContentEquals((AbstractStringBuilder)cs);
1102 }
1103 }
1104 // Argument is a String
1105 if (cs instanceof String) {
1106 return equals(cs);
1107 }
1108 // Argument is a generic CharSequence
1109 int n = cs.length();
1110 if (n != length()) {
1111 return false;
1112 }
1113 byte[] val = this.value;
1114 if (isLatin1()) {
1115 for (int i = 0; i < n; i++) {
1116 if ((val[i] & 0xff) != cs.charAt(i)) {
1117 return false;
1118 }
1119 }
1120 } else {
1121 for (int i = 0; i < n; i++) {
1122 if (StringUTF16.getChar(val, i) != cs.charAt(i)) {
1123 return false;
1124 }
1125 }
1126 }
1127 return true;
1128 }
1129
1130 /**
1131 * Compares this {@code String} to another {@code String}, ignoring case
1132 * considerations. Two strings are considered equal ignoring case if they
1133 * are of the same length and corresponding characters in the two strings
1134 * are equal ignoring case.
1135 *
1136 * <p> Two characters {@code c1} and {@code c2} are considered the same
1137 * ignoring case if at least one of the following is true:
1138 * <ul>
1139 * <li> The two characters are the same (as compared by the
1140 * {@code ==} operator)
1141 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))}
1142 * on each character produces the same result
1143 * </ul>
1144 *
1145 * <p>Note that this method does <em>not</em> take locale into account, and
1146 * will result in unsatisfactory results for certain locales. The
1147 * {@link java.text.Collator} class provides locale-sensitive comparison.
1148 *
1149 * @param anotherString
1150 * The {@code String} to compare this {@code String} against
1151 *
1152 * @return {@code true} if the argument is not {@code null} and it
1153 * represents an equivalent {@code String} ignoring case; {@code
1154 * false} otherwise
1155 *
1156 * @see #equals(Object)
1157 */
1158 public boolean equalsIgnoreCase(String anotherString) {
1159 return (this == anotherString) ? true
1160 : (anotherString != null)
1161 && (anotherString.length() == length())
1162 && regionMatches(true, 0, anotherString, 0, length());
1163 }
1164
1165 /**
1166 * Compares two strings lexicographically.
1167 * The comparison is based on the Unicode value of each character in
1168 * the strings. The character sequence represented by this
1169 * {@code String} object is compared lexicographically to the
1170 * character sequence represented by the argument string. The result is
1171 * a negative integer if this {@code String} object
1172 * lexicographically precedes the argument string. The result is a
1173 * positive integer if this {@code String} object lexicographically
1174 * follows the argument string. The result is zero if the strings
1175 * are equal; {@code compareTo} returns {@code 0} exactly when
1176 * the {@link #equals(Object)} method would return {@code true}.
1177 * <p>
1178 * This is the definition of lexicographic ordering. If two strings are
1179 * different, then either they have different characters at some index
1180 * that is a valid index for both strings, or their lengths are different,
1181 * or both. If they have different characters at one or more index
1182 * positions, let <i>k</i> be the smallest such index; then the string
1183 * whose character at position <i>k</i> has the smaller value, as
1184 * determined by using the {@code <} operator, lexicographically precedes the
1185 * other string. In this case, {@code compareTo} returns the
1186 * difference of the two character values at position {@code k} in
1187 * the two string -- that is, the value:
1188 * <blockquote><pre>
1189 * this.charAt(k)-anotherString.charAt(k)
1190 * </pre></blockquote>
1191 * If there is no index position at which they differ, then the shorter
1192 * string lexicographically precedes the longer string. In this case,
1193 * {@code compareTo} returns the difference of the lengths of the
1194 * strings -- that is, the value:
1195 * <blockquote><pre>
1196 * this.length()-anotherString.length()
1197 * </pre></blockquote>
1198 *
1199 * <p>For finer-grained String comparison, refer to
1200 * {@link java.text.Collator}.
1201 *
1202 * @param anotherString the {@code String} to be compared.
1203 * @return the value {@code 0} if the argument string is equal to
1204 * this string; a value less than {@code 0} if this string
1205 * is lexicographically less than the string argument; and a
1206 * value greater than {@code 0} if this string is
1207 * lexicographically greater than the string argument.
1208 */
1209 public int compareTo(String anotherString) {
1210 byte v1[] = value;
1211 byte v2[] = anotherString.value;
1212 if (coder() == anotherString.coder()) {
1213 return isLatin1() ? StringLatin1.compareTo(v1, v2)
1214 : StringUTF16.compareTo(v1, v2);
1215 }
1216 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2)
1217 : StringUTF16.compareToLatin1(v1, v2);
1218 }
1219
1220 /**
1221 * A Comparator that orders {@code String} objects as by
1222 * {@code compareToIgnoreCase}. This comparator is serializable.
1223 * <p>
1224 * Note that this Comparator does <em>not</em> take locale into account,
1225 * and will result in an unsatisfactory ordering for certain locales.
1226 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1227 *
1228 * @see java.text.Collator
1229 * @since 1.2
1230 */
1231 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1232 = new CaseInsensitiveComparator();
1233
1234 /**
1235 * A hashCode computing function that is consistent with
1236 * {@link #CASE_INSENSITIVE_ORDER} {@code Comparator}.
1237 *
1238 * @since 9
1239 */
1240 @SuppressWarnings("unchecked")
1241 public static final ToIntFunction<String> CASE_INSENSITIVE_HASHER
1242 = (ToIntFunction<String>) CASE_INSENSITIVE_ORDER;
1243
1244 private static class CaseInsensitiveComparator
1245 implements Comparator<String>, java.io.Serializable,
1246 ToIntFunction<String> /* hasher */ {
1247 // use serialVersionUID from JDK 1.2.2 for interoperability
1248 private static final long serialVersionUID = 8575799808933029326L;
1249
1250 @Override
1251 public int compare(String s1, String s2) {
1252 byte v1[] = s1.value;
1253 byte v2[] = s2.value;
1254 if (s1.coder() == s2.coder()) {
1255 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2)
1256 : StringUTF16.compareToCI(v1, v2);
1257 }
1258 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2)
1259 : StringUTF16.compareToCI_Latin1(v1, v2);
1260 }
1261
1262 /**
1263 * Compute hashCode consistent with {@link #compare(String, String)}
1264 */
1265 @Override
1266 public int applyAsInt(String s) {
1267 return s.isLatin1() ? StringLatin1.hashCodeCI(s.value)
1268 : StringUTF16.hashCodeCI(s.value);
1269 }
1270
1271 /** Replaces the de-serialized object. */
1272 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1273 }
1274
1275 /**
1276 * Compares two strings lexicographically, ignoring case
1277 * differences. This method returns an integer whose sign is that of
1278 * calling {@code compareTo} with normalized versions of the strings
1279 * where case differences have been eliminated by calling
1280 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1281 * each character.
1282 * <p>
1283 * Note that this method does <em>not</em> take locale into account,
1284 * and will result in an unsatisfactory ordering for certain locales.
1285 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1286 *
1287 * @param str the {@code String} to be compared.
1288 * @return a negative integer, zero, or a positive integer as the
1289 * specified String is greater than, equal to, or less
1290 * than this String, ignoring case considerations.
1291 * @see java.text.Collator
1292 * @since 1.2
1293 */
1294 public int compareToIgnoreCase(String str) {
1295 return CASE_INSENSITIVE_ORDER.compare(this, str);
1296 }
1297
1298 /**
1299 * Tests if two string regions are equal.
1300 * <p>
1301 * A substring of this {@code String} object is compared to a substring
1302 * of the argument other. The result is true if these substrings
1303 * represent identical character sequences. The substring of this
1304 * {@code String} object to be compared begins at index {@code toffset}
1305 * and has length {@code len}. The substring of other to be compared
1306 * begins at index {@code ooffset} and has length {@code len}. The
1307 * result is {@code false} if and only if at least one of the following
1308 * is true:
1309 * <ul><li>{@code toffset} is negative.
1310 * <li>{@code ooffset} is negative.
1311 * <li>{@code toffset+len} is greater than the length of this
1312 * {@code String} object.
1313 * <li>{@code ooffset+len} is greater than the length of the other
1314 * argument.
1315 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1316 * such that:
1317 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1318 * <i>k</i>{@code )}
1319 * </ul>
1320 *
1321 * <p>Note that this method does <em>not</em> take locale into account. The
1322 * {@link java.text.Collator} class provides locale-sensitive comparison.
1323 *
1324 * @param toffset the starting offset of the subregion in this string.
1325 * @param other the string argument.
1326 * @param ooffset the starting offset of the subregion in the string
1327 * argument.
1328 * @param len the number of characters to compare.
1329 * @return {@code true} if the specified subregion of this string
1330 * exactly matches the specified subregion of the string argument;
1331 * {@code false} otherwise.
1332 */
1333 public boolean regionMatches(int toffset, String other, int ooffset, int len) {
1334 byte tv[] = value;
1335 byte ov[] = other.value;
1336 // Note: toffset, ooffset, or len might be near -1>>>1.
1337 if ((ooffset < 0) || (toffset < 0) ||
1338 (toffset > (long)length() - len) ||
1339 (ooffset > (long)other.length() - len)) {
1340 return false;
1341 }
1342 if (coder() == other.coder()) {
1343 if (!isLatin1() && (len > 0)) {
1344 toffset = toffset << 1;
1345 ooffset = ooffset << 1;
1346 len = len << 1;
1347 }
1348 while (len-- > 0) {
1349 if (tv[toffset++] != ov[ooffset++]) {
1350 return false;
1351 }
1352 }
1353 } else {
1354 if (coder() == LATIN1) {
1355 while (len-- > 0) {
1356 if (StringLatin1.getChar(tv, toffset++) !=
1357 StringUTF16.getChar(ov, ooffset++)) {
1358 return false;
1359 }
1360 }
1361 } else {
1362 while (len-- > 0) {
1363 if (StringUTF16.getChar(tv, toffset++) !=
1364 StringLatin1.getChar(ov, ooffset++)) {
1365 return false;
1366 }
1367 }
1368 }
1369 }
1370 return true;
1371 }
1372
1373 /**
1374 * Tests if two string regions are equal.
1375 * <p>
1376 * A substring of this {@code String} object is compared to a substring
1377 * of the argument {@code other}. The result is {@code true} if these
1378 * substrings represent character sequences that are the same, ignoring
1379 * case if and only if {@code ignoreCase} is true. The substring of
1380 * this {@code String} object to be compared begins at index
1381 * {@code toffset} and has length {@code len}. The substring of
1382 * {@code other} to be compared begins at index {@code ooffset} and
1383 * has length {@code len}. The result is {@code false} if and only if
1384 * at least one of the following is true:
1385 * <ul><li>{@code toffset} is negative.
1386 * <li>{@code ooffset} is negative.
1387 * <li>{@code toffset+len} is greater than the length of this
1388 * {@code String} object.
1389 * <li>{@code ooffset+len} is greater than the length of the other
1390 * argument.
1391 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1392 * integer <i>k</i> less than {@code len} such that:
1393 * <blockquote><pre>
1394 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1395 * </pre></blockquote>
1396 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1397 * integer <i>k</i> less than {@code len} such that:
1398 * <blockquote><pre>
1399 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) !=
1400 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k)))
1401 * </pre></blockquote>
1402 * </ul>
1403 *
1404 * <p>Note that this method does <em>not</em> take locale into account,
1405 * and will result in unsatisfactory results for certain locales when
1406 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class
1407 * provides locale-sensitive comparison.
1408 *
1409 * @param ignoreCase if {@code true}, ignore case when comparing
1410 * characters.
1411 * @param toffset the starting offset of the subregion in this
1412 * string.
1413 * @param other the string argument.
1414 * @param ooffset the starting offset of the subregion in the string
1415 * argument.
1416 * @param len the number of characters to compare.
1417 * @return {@code true} if the specified subregion of this string
1418 * matches the specified subregion of the string argument;
1419 * {@code false} otherwise. Whether the matching is exact
1420 * or case insensitive depends on the {@code ignoreCase}
1421 * argument.
1422 */
1423 public boolean regionMatches(boolean ignoreCase, int toffset,
1424 String other, int ooffset, int len) {
1425 if (!ignoreCase) {
1426 return regionMatches(toffset, other, ooffset, len);
1427 }
1428 // Note: toffset, ooffset, or len might be near -1>>>1.
1429 if ((ooffset < 0) || (toffset < 0)
1430 || (toffset > (long)length() - len)
1431 || (ooffset > (long)other.length() - len)) {
1432 return false;
1433 }
1434 byte tv[] = value;
1435 byte ov[] = other.value;
1436 if (coder() == other.coder()) {
1437 return isLatin1()
1438 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len)
1439 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len);
1440 }
1441 return isLatin1()
1442 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len)
1443 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len);
1444 }
1445
1446 /**
1447 * Tests if the substring of this string beginning at the
1448 * specified index starts with the specified prefix.
1449 *
1450 * @param prefix the prefix.
1451 * @param toffset where to begin looking in this string.
1452 * @return {@code true} if the character sequence represented by the
1453 * argument is a prefix of the substring of this object starting
1454 * at index {@code toffset}; {@code false} otherwise.
1455 * The result is {@code false} if {@code toffset} is
1456 * negative or greater than the length of this
1457 * {@code String} object; otherwise the result is the same
1458 * as the result of the expression
1459 * <pre>
1460 * this.substring(toffset).startsWith(prefix)
1461 * </pre>
1462 */
1463 public boolean startsWith(String prefix, int toffset) {
1464 // Note: toffset might be near -1>>>1.
1465 if (toffset < 0 || toffset > length() - prefix.length()) {
1466 return false;
1467 }
1468 byte ta[] = value;
1469 byte pa[] = prefix.value;
1470 int po = 0;
1471 int pc = pa.length;
1472 if (coder() == prefix.coder()) {
1473 int to = isLatin1() ? toffset : toffset << 1;
1474 while (po < pc) {
1475 if (ta[to++] != pa[po++]) {
1476 return false;
1477 }
1478 }
1479 } else {
1480 if (isLatin1()) { // && pcoder == UTF16
1481 return false;
1482 }
1483 // coder == UTF16 && pcoder == LATIN1)
1484 while (po < pc) {
1485 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) {
1486 return false;
1487 }
1488 }
1489 }
1490 return true;
1491 }
1492
1493 /**
1494 * Tests if this string starts with the specified prefix.
1495 *
1496 * @param prefix the prefix.
1497 * @return {@code true} if the character sequence represented by the
1498 * argument is a prefix of the character sequence represented by
1499 * this string; {@code false} otherwise.
1500 * Note also that {@code true} will be returned if the
1501 * argument is an empty string or is equal to this
1502 * {@code String} object as determined by the
1503 * {@link #equals(Object)} method.
1504 * @since 1.0
1505 */
1506 public boolean startsWith(String prefix) {
1507 return startsWith(prefix, 0);
1508 }
1509
1510 /**
1511 * Tests if this string ends with the specified suffix.
1512 *
1513 * @param suffix the suffix.
1514 * @return {@code true} if the character sequence represented by the
1515 * argument is a suffix of the character sequence represented by
1516 * this object; {@code false} otherwise. Note that the
1517 * result will be {@code true} if the argument is the
1518 * empty string or is equal to this {@code String} object
1519 * as determined by the {@link #equals(Object)} method.
1520 */
1521 public boolean endsWith(String suffix) {
1522 return startsWith(suffix, length() - suffix.length());
1523 }
1524
1525 /**
1526 * Returns a hash code for this string. The hash code for a
1527 * {@code String} object is computed as
1528 * <blockquote><pre>
1529 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1530 * </pre></blockquote>
1531 * using {@code int} arithmetic, where {@code s[i]} is the
1532 * <i>i</i>th character of the string, {@code n} is the length of
1533 * the string, and {@code ^} indicates exponentiation.
1534 * (The hash value of the empty string is zero.)
1535 *
1536 * @return a hash code value for this object.
1537 */
1538 public int hashCode() {
1539 if (hash == 0 && value.length > 0) {
1540 hash = isLatin1() ? StringLatin1.hashCode(value)
1541 : StringUTF16.hashCode(value);
1542 }
1543 return hash;
1544 }
1545
1546 /**
1547 * Returns the index within this string of the first occurrence of
1548 * the specified character. If a character with value
1549 * {@code ch} occurs in the character sequence represented by
1550 * this {@code String} object, then the index (in Unicode
1551 * code units) of the first such occurrence is returned. For
1552 * values of {@code ch} in the range from 0 to 0xFFFF
1553 * (inclusive), this is the smallest value <i>k</i> such that:
1554 * <blockquote><pre>
1555 * this.charAt(<i>k</i>) == ch
1556 * </pre></blockquote>
1557 * is true. For other values of {@code ch}, it is the
1558 * smallest value <i>k</i> such that:
1559 * <blockquote><pre>
1560 * this.codePointAt(<i>k</i>) == ch
1561 * </pre></blockquote>
1562 * is true. In either case, if no such character occurs in this
1563 * string, then {@code -1} is returned.
1564 *
1565 * @param ch a character (Unicode code point).
1566 * @return the index of the first occurrence of the character in the
1567 * character sequence represented by this object, or
1568 * {@code -1} if the character does not occur.
1569 */
1570 public int indexOf(int ch) {
1571 return indexOf(ch, 0);
1572 }
1573
1574 /**
1575 * Returns the index within this string of the first occurrence of the
1576 * specified character, starting the search at the specified index.
1577 * <p>
1578 * If a character with value {@code ch} occurs in the
1579 * character sequence represented by this {@code String}
1580 * object at an index no smaller than {@code fromIndex}, then
1581 * the index of the first such occurrence is returned. For values
1582 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1583 * this is the smallest value <i>k</i> such that:
1584 * <blockquote><pre>
1585 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1586 * </pre></blockquote>
1587 * is true. For other values of {@code ch}, it is the
1588 * smallest value <i>k</i> such that:
1589 * <blockquote><pre>
1590 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1591 * </pre></blockquote>
1592 * is true. In either case, if no such character occurs in this
1593 * string at or after position {@code fromIndex}, then
1594 * {@code -1} is returned.
1595 *
1596 * <p>
1597 * There is no restriction on the value of {@code fromIndex}. If it
1598 * is negative, it has the same effect as if it were zero: this entire
1599 * string may be searched. If it is greater than the length of this
1600 * string, it has the same effect as if it were equal to the length of
1601 * this string: {@code -1} is returned.
1602 *
1603 * <p>All indices are specified in {@code char} values
1604 * (Unicode code units).
1605 *
1606 * @param ch a character (Unicode code point).
1607 * @param fromIndex the index to start the search from.
1608 * @return the index of the first occurrence of the character in the
1609 * character sequence represented by this object that is greater
1610 * than or equal to {@code fromIndex}, or {@code -1}
1611 * if the character does not occur.
1612 */
1613 public int indexOf(int ch, int fromIndex) {
1614 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex)
1615 : StringUTF16.indexOf(value, ch, fromIndex);
1616 }
1617
1618 /**
1619 * Returns the index within this string of the last occurrence of
1620 * the specified character. For values of {@code ch} in the
1621 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1622 * units) returned is the largest value <i>k</i> such that:
1623 * <blockquote><pre>
1624 * this.charAt(<i>k</i>) == ch
1625 * </pre></blockquote>
1626 * is true. For other values of {@code ch}, it is the
1627 * largest value <i>k</i> such that:
1628 * <blockquote><pre>
1629 * this.codePointAt(<i>k</i>) == ch
1630 * </pre></blockquote>
1631 * is true. In either case, if no such character occurs in this
1632 * string, then {@code -1} is returned. The
1633 * {@code String} is searched backwards starting at the last
1634 * character.
1635 *
1636 * @param ch a character (Unicode code point).
1637 * @return the index of the last occurrence of the character in the
1638 * character sequence represented by this object, or
1639 * {@code -1} if the character does not occur.
1640 */
1641 public int lastIndexOf(int ch) {
1642 return lastIndexOf(ch, length() - 1);
1643 }
1644
1645 /**
1646 * Returns the index within this string of the last occurrence of
1647 * the specified character, searching backward starting at the
1648 * specified index. For values of {@code ch} in the range
1649 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1650 * value <i>k</i> such that:
1651 * <blockquote><pre>
1652 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1653 * </pre></blockquote>
1654 * is true. For other values of {@code ch}, it is the
1655 * largest value <i>k</i> such that:
1656 * <blockquote><pre>
1657 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1658 * </pre></blockquote>
1659 * is true. In either case, if no such character occurs in this
1660 * string at or before position {@code fromIndex}, then
1661 * {@code -1} is returned.
1662 *
1663 * <p>All indices are specified in {@code char} values
1664 * (Unicode code units).
1665 *
1666 * @param ch a character (Unicode code point).
1667 * @param fromIndex the index to start the search from. There is no
1668 * restriction on the value of {@code fromIndex}. If it is
1669 * greater than or equal to the length of this string, it has
1670 * the same effect as if it were equal to one less than the
1671 * length of this string: this entire string may be searched.
1672 * If it is negative, it has the same effect as if it were -1:
1673 * -1 is returned.
1674 * @return the index of the last occurrence of the character in the
1675 * character sequence represented by this object that is less
1676 * than or equal to {@code fromIndex}, or {@code -1}
1677 * if the character does not occur before that point.
1678 */
1679 public int lastIndexOf(int ch, int fromIndex) {
1680 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex)
1681 : StringUTF16.lastIndexOf(value, ch, fromIndex);
1682 }
1683
1684 /**
1685 * Returns the index within this string of the first occurrence of the
1686 * specified substring.
1687 *
1688 * <p>The returned index is the smallest value {@code k} for which:
1689 * <pre>{@code
1690 * this.startsWith(str, k)
1691 * }</pre>
1692 * If no such value of {@code k} exists, then {@code -1} is returned.
1693 *
1694 * @param str the substring to search for.
1695 * @return the index of the first occurrence of the specified substring,
1696 * or {@code -1} if there is no such occurrence.
1697 */
1698 public int indexOf(String str) {
1699 if (coder() == str.coder()) {
1700 return isLatin1() ? StringLatin1.indexOf(value, str.value)
1701 : StringUTF16.indexOf(value, str.value);
1702 }
1703 if (coder() == LATIN1) { // str.coder == UTF16
1704 return -1;
1705 }
1706 return StringUTF16.indexOfLatin1(value, str.value);
1707 }
1708
1709 /**
1710 * Returns the index within this string of the first occurrence of the
1711 * specified substring, starting at the specified index.
1712 *
1713 * <p>The returned index is the smallest value {@code k} for which:
1714 * <pre>{@code
1715 * k >= Math.min(fromIndex, this.length()) &&
1716 * this.startsWith(str, k)
1717 * }</pre>
1718 * If no such value of {@code k} exists, then {@code -1} is returned.
1719 *
1720 * @param str the substring to search for.
1721 * @param fromIndex the index from which to start the search.
1722 * @return the index of the first occurrence of the specified substring,
1723 * starting at the specified index,
1724 * or {@code -1} if there is no such occurrence.
1725 */
1726 public int indexOf(String str, int fromIndex) {
1727 return indexOf(value, coder(), length(), str, fromIndex);
1728 }
1729
1730 /**
1731 * Code shared by String and AbstractStringBuilder to do searches. The
1732 * source is the character array being searched, and the target
1733 * is the string being searched for.
1734 *
1735 * @param src the characters being searched.
1736 * @param srcCoder the coder of the source string.
1737 * @param srcCount length of the source string.
1738 * @param tgtStr the characters being searched for.
1739 * @param fromIndex the index to begin searching from.
1740 */
1741 static int indexOf(byte[] src, byte srcCoder, int srcCount,
1742 String tgtStr, int fromIndex) {
1743 byte[] tgt = tgtStr.value;
1744 byte tgtCoder = tgtStr.coder();
1745 int tgtCount = tgtStr.length();
1746
1747 if (fromIndex >= srcCount) {
1748 return (tgtCount == 0 ? srcCount : -1);
1749 }
1750 if (fromIndex < 0) {
1751 fromIndex = 0;
1752 }
1753 if (tgtCount == 0) {
1754 return fromIndex;
1755 }
1756 if (srcCoder == tgtCoder) {
1757 return srcCoder == LATIN1
1758 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex)
1759 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex);
1760 }
1761 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1762 return -1;
1763 }
1764 // srcCoder == UTF16 && tgtCoder == LATIN1) {
1765 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1766 }
1767
1768 /**
1769 * Returns the index within this string of the last occurrence of the
1770 * specified substring. The last occurrence of the empty string ""
1771 * is considered to occur at the index value {@code this.length()}.
1772 *
1773 * <p>The returned index is the largest value {@code k} for which:
1774 * <pre>{@code
1775 * this.startsWith(str, k)
1776 * }</pre>
1777 * If no such value of {@code k} exists, then {@code -1} is returned.
1778 *
1779 * @param str the substring to search for.
1780 * @return the index of the last occurrence of the specified substring,
1781 * or {@code -1} if there is no such occurrence.
1782 */
1783 public int lastIndexOf(String str) {
1784 return lastIndexOf(str, length());
1785 }
1786
1787 /**
1788 * Returns the index within this string of the last occurrence of the
1789 * specified substring, searching backward starting at the specified index.
1790 *
1791 * <p>The returned index is the largest value {@code k} for which:
1792 * <pre>{@code
1793 * k <= Math.min(fromIndex, this.length()) &&
1794 * this.startsWith(str, k)
1795 * }</pre>
1796 * If no such value of {@code k} exists, then {@code -1} is returned.
1797 *
1798 * @param str the substring to search for.
1799 * @param fromIndex the index to start the search from.
1800 * @return the index of the last occurrence of the specified substring,
1801 * searching backward from the specified index,
1802 * or {@code -1} if there is no such occurrence.
1803 */
1804 public int lastIndexOf(String str, int fromIndex) {
1805 return lastIndexOf(value, coder(), length(), str, fromIndex);
1806 }
1807
1808 /**
1809 * Code shared by String and AbstractStringBuilder to do searches. The
1810 * source is the character array being searched, and the target
1811 * is the string being searched for.
1812 *
1813 * @param src the characters being searched.
1814 * @param srcCoder coder handles the mapping between bytes/chars
1815 * @param srcCount count of the source string.
1816 * @param tgt the characters being searched for.
1817 * @param fromIndex the index to begin searching from.
1818 */
1819 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount,
1820 String tgtStr, int fromIndex) {
1821 byte[] tgt = tgtStr.value;
1822 byte tgtCoder = tgtStr.coder();
1823 int tgtCount = tgtStr.length();
1824 /*
1825 * Check arguments; return immediately where possible. For
1826 * consistency, don't check for null str.
1827 */
1828 int rightIndex = srcCount - tgtCount;
1829 if (fromIndex < 0) {
1830 return -1;
1831 }
1832 if (fromIndex > rightIndex) {
1833 fromIndex = rightIndex;
1834 }
1835 /* Empty string always matches. */
1836 if (tgtCount == 0) {
1837 return fromIndex;
1838 }
1839 if (srcCoder == tgtCoder) {
1840 return srcCoder == LATIN1
1841 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex)
1842 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex);
1843 }
1844 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1845 return -1;
1846 }
1847 // srcCoder == UTF16 && tgtCoder == LATIN1
1848 int min = tgtCount - 1;
1849 int i = min + fromIndex;
1850 int strLastIndex = tgtCount - 1;
1851
1852 char strLastChar = (char)(tgt[strLastIndex] & 0xff);
1853 startSearchForLastChar:
1854 while (true) {
1855 while (i >= min && StringUTF16.getChar(src, i) != strLastChar) {
1856 i--;
1857 }
1858 if (i < min) {
1859 return -1;
1860 }
1861 int j = i - 1;
1862 int start = j - strLastIndex;
1863 int k = strLastIndex - 1;
1864 while (j > start) {
1865 if (StringUTF16.getChar(src, j--) != (tgt[k--] & 0xff)) {
1866 i--;
1867 continue startSearchForLastChar;
1868 }
1869 }
1870 return start + 1;
1871 }
1872 }
1873
1874 /**
1875 * Returns a string that is a substring of this string. The
1876 * substring begins with the character at the specified index and
1877 * extends to the end of this string. <p>
1878 * Examples:
1879 * <blockquote><pre>
1880 * "unhappy".substring(2) returns "happy"
1881 * "Harbison".substring(3) returns "bison"
1882 * "emptiness".substring(9) returns "" (an empty string)
1883 * </pre></blockquote>
1884 *
1885 * @param beginIndex the beginning index, inclusive.
1886 * @return the specified substring.
1887 * @exception IndexOutOfBoundsException if
1888 * {@code beginIndex} is negative or larger than the
1889 * length of this {@code String} object.
1890 */
1891 public String substring(int beginIndex) {
1892 if (beginIndex < 0) {
1893 throw new StringIndexOutOfBoundsException(beginIndex);
1894 }
1895 int subLen = length() - beginIndex;
1896 if (subLen < 0) {
1897 throw new StringIndexOutOfBoundsException(subLen);
1898 }
1899 if (beginIndex == 0) {
1900 return this;
1901 }
1902 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1903 : StringUTF16.newString(value, beginIndex, subLen);
1904 }
1905
1906 /**
1907 * Returns a string that is a substring of this string. The
1908 * substring begins at the specified {@code beginIndex} and
1909 * extends to the character at index {@code endIndex - 1}.
1910 * Thus the length of the substring is {@code endIndex-beginIndex}.
1911 * <p>
1912 * Examples:
1913 * <blockquote><pre>
1914 * "hamburger".substring(4, 8) returns "urge"
1915 * "smiles".substring(1, 5) returns "mile"
1916 * </pre></blockquote>
1917 *
1918 * @param beginIndex the beginning index, inclusive.
1919 * @param endIndex the ending index, exclusive.
1920 * @return the specified substring.
1921 * @exception IndexOutOfBoundsException if the
1922 * {@code beginIndex} is negative, or
1923 * {@code endIndex} is larger than the length of
1924 * this {@code String} object, or
1925 * {@code beginIndex} is larger than
1926 * {@code endIndex}.
1927 */
1928 public String substring(int beginIndex, int endIndex) {
1929 int length = length();
1930 checkBoundsBeginEnd(beginIndex, endIndex, length);
1931 int subLen = endIndex - beginIndex;
1932 if (beginIndex == 0 && endIndex == length) {
1933 return this;
1934 }
1935 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1936 : StringUTF16.newString(value, beginIndex, subLen);
1937 }
1938
1939 /**
1940 * Returns a character sequence that is a subsequence of this sequence.
1941 *
1942 * <p> An invocation of this method of the form
1943 *
1944 * <blockquote><pre>
1945 * str.subSequence(begin, end)</pre></blockquote>
1946 *
1947 * behaves in exactly the same way as the invocation
1948 *
1949 * <blockquote><pre>
1950 * str.substring(begin, end)</pre></blockquote>
1951 *
1952 * @apiNote
1953 * This method is defined so that the {@code String} class can implement
1954 * the {@link CharSequence} interface.
1955 *
1956 * @param beginIndex the begin index, inclusive.
1957 * @param endIndex the end index, exclusive.
1958 * @return the specified subsequence.
1959 *
1960 * @throws IndexOutOfBoundsException
1961 * if {@code beginIndex} or {@code endIndex} is negative,
1962 * if {@code endIndex} is greater than {@code length()},
1963 * or if {@code beginIndex} is greater than {@code endIndex}
1964 *
1965 * @since 1.4
1966 * @spec JSR-51
1967 */
1968 public CharSequence subSequence(int beginIndex, int endIndex) {
1969 return this.substring(beginIndex, endIndex);
1970 }
1971
1972 /**
1973 * Concatenates the specified string to the end of this string.
1974 * <p>
1975 * If the length of the argument string is {@code 0}, then this
1976 * {@code String} object is returned. Otherwise, a
1977 * {@code String} object is returned that represents a character
1978 * sequence that is the concatenation of the character sequence
1979 * represented by this {@code String} object and the character
1980 * sequence represented by the argument string.<p>
1981 * Examples:
1982 * <blockquote><pre>
1983 * "cares".concat("s") returns "caress"
1984 * "to".concat("get").concat("her") returns "together"
1985 * </pre></blockquote>
1986 *
1987 * @param str the {@code String} that is concatenated to the end
1988 * of this {@code String}.
1989 * @return a string that represents the concatenation of this object's
1990 * characters followed by the string argument's characters.
1991 */
1992 public String concat(String str) {
1993 int olen = str.length();
1994 if (olen == 0) {
1995 return this;
1996 }
1997 if (coder() == str.coder()) {
1998 byte[] val = this.value;
1999 byte[] oval = str.value;
2000 int len = val.length + oval.length;
2001 byte[] buf = Arrays.copyOf(val, len);
2002 System.arraycopy(oval, 0, buf, val.length, oval.length);
2003 return new String(buf, coder);
2004 }
2005 int len = length();
2006 byte[] buf = StringUTF16.newBytesFor(len + olen);
2007 getBytes(buf, 0, UTF16);
2008 str.getBytes(buf, len, UTF16);
2009 return new String(buf, UTF16);
2010 }
2011
2012 /**
2013 * Returns a string resulting from replacing all occurrences of
2014 * {@code oldChar} in this string with {@code newChar}.
2015 * <p>
2016 * If the character {@code oldChar} does not occur in the
2017 * character sequence represented by this {@code String} object,
2018 * then a reference to this {@code String} object is returned.
2019 * Otherwise, a {@code String} object is returned that
2020 * represents a character sequence identical to the character sequence
2021 * represented by this {@code String} object, except that every
2022 * occurrence of {@code oldChar} is replaced by an occurrence
2023 * of {@code newChar}.
2024 * <p>
2025 * Examples:
2026 * <blockquote><pre>
2027 * "mesquite in your cellar".replace('e', 'o')
2028 * returns "mosquito in your collar"
2029 * "the war of baronets".replace('r', 'y')
2030 * returns "the way of bayonets"
2031 * "sparring with a purple porpoise".replace('p', 't')
2032 * returns "starring with a turtle tortoise"
2033 * "JonL".replace('q', 'x') returns "JonL" (no change)
2034 * </pre></blockquote>
2035 *
2036 * @param oldChar the old character.
2037 * @param newChar the new character.
2038 * @return a string derived from this string by replacing every
2039 * occurrence of {@code oldChar} with {@code newChar}.
2040 */
2041 public String replace(char oldChar, char newChar) {
2042 if (oldChar != newChar) {
2043 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar)
2044 : StringUTF16.replace(value, oldChar, newChar);
2045 if (ret != null) {
2046 return ret;
2047 }
2048 }
2049 return this;
2050 }
2051
2052 /**
2053 * Tells whether or not this string matches the given <a
2054 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2055 *
2056 * <p> An invocation of this method of the form
2057 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2058 * same result as the expression
2059 *
2060 * <blockquote>
2061 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2062 * matches(<i>regex</i>, <i>str</i>)}
2063 * </blockquote>
2064 *
2065 * @param regex
2066 * the regular expression to which this string is to be matched
2067 *
2068 * @return {@code true} if, and only if, this string matches the
2069 * given regular expression
2070 *
2071 * @throws PatternSyntaxException
2072 * if the regular expression's syntax is invalid
2073 *
2074 * @see java.util.regex.Pattern
2075 *
2076 * @since 1.4
2077 * @spec JSR-51
2078 */
2079 public boolean matches(String regex) {
2080 return Pattern.matches(regex, this);
2081 }
2082
2083 /**
2084 * Returns true if and only if this string contains the specified
2085 * sequence of char values.
2086 *
2087 * @param s the sequence to search for
2088 * @return true if this string contains {@code s}, false otherwise
2089 * @since 1.5
2090 */
2091 public boolean contains(CharSequence s) {
2092 return indexOf(s.toString()) >= 0;
2093 }
2094
2095 /**
2096 * Replaces the first substring of this string that matches the given <a
2097 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2098 * given replacement.
2099 *
2100 * <p> An invocation of this method of the form
2101 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2102 * yields exactly the same result as the expression
2103 *
2104 * <blockquote>
2105 * <code>
2106 * {@link java.util.regex.Pattern}.{@link
2107 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2108 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2109 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2110 * </code>
2111 * </blockquote>
2112 *
2113 *<p>
2114 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2115 * replacement string may cause the results to be different than if it were
2116 * being treated as a literal replacement string; see
2117 * {@link java.util.regex.Matcher#replaceFirst}.
2118 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2119 * meaning of these characters, if desired.
2120 *
2121 * @param regex
2122 * the regular expression to which this string is to be matched
2123 * @param replacement
2124 * the string to be substituted for the first match
2125 *
2126 * @return The resulting {@code String}
2127 *
2128 * @throws PatternSyntaxException
2129 * if the regular expression's syntax is invalid
2130 *
2131 * @see java.util.regex.Pattern
2132 *
2133 * @since 1.4
2134 * @spec JSR-51
2135 */
2136 public String replaceFirst(String regex, String replacement) {
2137 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2138 }
2139
2140 /**
2141 * Replaces each substring of this string that matches the given <a
2142 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2143 * given replacement.
2144 *
2145 * <p> An invocation of this method of the form
2146 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2147 * yields exactly the same result as the expression
2148 *
2149 * <blockquote>
2150 * <code>
2151 * {@link java.util.regex.Pattern}.{@link
2152 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2153 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2154 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2155 * </code>
2156 * </blockquote>
2157 *
2158 *<p>
2159 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2160 * replacement string may cause the results to be different than if it were
2161 * being treated as a literal replacement string; see
2162 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2163 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2164 * meaning of these characters, if desired.
2165 *
2166 * @param regex
2167 * the regular expression to which this string is to be matched
2168 * @param replacement
2169 * the string to be substituted for each match
2170 *
2171 * @return The resulting {@code String}
2172 *
2173 * @throws PatternSyntaxException
2174 * if the regular expression's syntax is invalid
2175 *
2176 * @see java.util.regex.Pattern
2177 *
2178 * @since 1.4
2179 * @spec JSR-51
2180 */
2181 public String replaceAll(String regex, String replacement) {
2182 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2183 }
2184
2185 /**
2186 * Replaces each substring of this string that matches the literal target
2187 * sequence with the specified literal replacement sequence. The
2188 * replacement proceeds from the beginning of the string to the end, for
2189 * example, replacing "aa" with "b" in the string "aaa" will result in
2190 * "ba" rather than "ab".
2191 *
2192 * @param target The sequence of char values to be replaced
2193 * @param replacement The replacement sequence of char values
2194 * @return The resulting string
2195 * @since 1.5
2196 */
2197 public String replace(CharSequence target, CharSequence replacement) {
2198 String tgtStr = target.toString();
2199 String replStr = replacement.toString();
2200 int j = indexOf(tgtStr);
2201 if (j < 0) {
2202 return this;
2203 }
2204 int tgtLen = tgtStr.length();
2205 int tgtLen1 = Math.max(tgtLen, 1);
2206 int thisLen = length();
2207
2208 int newLenHint = thisLen - tgtLen + replStr.length();
2209 if (newLenHint < 0) {
2210 throw new OutOfMemoryError();
2211 }
2212 StringBuilder sb = new StringBuilder(newLenHint);
2213 int i = 0;
2214 do {
2215 sb.append(this, i, j).append(replStr);
2216 i = j + tgtLen;
2217 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0);
2218 return sb.append(this, i, thisLen).toString();
2219 }
2220
2221 /**
2222 * Splits this string around matches of the given
2223 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2224 *
2225 * <p> The array returned by this method contains each substring of this
2226 * string that is terminated by another substring that matches the given
2227 * expression or is terminated by the end of the string. The substrings in
2228 * the array are in the order in which they occur in this string. If the
2229 * expression does not match any part of the input then the resulting array
2230 * has just one element, namely this string.
2231 *
2232 * <p> When there is a positive-width match at the beginning of this
2233 * string then an empty leading substring is included at the beginning
2234 * of the resulting array. A zero-width match at the beginning however
2235 * never produces such empty leading substring.
2236 *
2237 * <p> The {@code limit} parameter controls the number of times the
2238 * pattern is applied and therefore affects the length of the resulting
2239 * array. If the limit <i>n</i> is greater than zero then the pattern
2240 * will be applied at most <i>n</i> - 1 times, the array's
2241 * length will be no greater than <i>n</i>, and the array's last entry
2242 * will contain all input beyond the last matched delimiter. If <i>n</i>
2243 * is non-positive then the pattern will be applied as many times as
2244 * possible and the array can have any length. If <i>n</i> is zero then
2245 * the pattern will be applied as many times as possible, the array can
2246 * have any length, and trailing empty strings will be discarded.
2247 *
2248 * <p> The string {@code "boo:and:foo"}, for example, yields the
2249 * following results with these parameters:
2250 *
2251 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2252 * <tr>
2253 * <th>Regex</th>
2254 * <th>Limit</th>
2255 * <th>Result</th>
2256 * </tr>
2257 * <tr><td align=center>:</td>
2258 * <td align=center>2</td>
2259 * <td>{@code { "boo", "and:foo" }}</td></tr>
2260 * <tr><td align=center>:</td>
2261 * <td align=center>5</td>
2262 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2263 * <tr><td align=center>:</td>
2264 * <td align=center>-2</td>
2265 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2266 * <tr><td align=center>o</td>
2267 * <td align=center>5</td>
2268 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2269 * <tr><td align=center>o</td>
2270 * <td align=center>-2</td>
2271 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2272 * <tr><td align=center>o</td>
2273 * <td align=center>0</td>
2274 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2275 * </table></blockquote>
2276 *
2277 * <p> An invocation of this method of the form
2278 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2279 * yields the same result as the expression
2280 *
2281 * <blockquote>
2282 * <code>
2283 * {@link java.util.regex.Pattern}.{@link
2284 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2285 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2286 * </code>
2287 * </blockquote>
2288 *
2289 *
2290 * @param regex
2291 * the delimiting regular expression
2292 *
2293 * @param limit
2294 * the result threshold, as described above
2295 *
2296 * @return the array of strings computed by splitting this string
2297 * around matches of the given regular expression
2298 *
2299 * @throws PatternSyntaxException
2300 * if the regular expression's syntax is invalid
2301 *
2302 * @see java.util.regex.Pattern
2303 *
2304 * @since 1.4
2305 * @spec JSR-51
2306 */
2307 public String[] split(String regex, int limit) {
2308 /* fastpath if the regex is a
2309 (1)one-char String and this character is not one of the
2310 RegEx's meta characters ".$|()[{^?*+\\", or
2311 (2)two-char String and the first char is the backslash and
2312 the second is not the ascii digit or ascii letter.
2313 */
2314 char ch = 0;
2315 if (((regex.length() == 1 &&
2316 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2317 (regex.length() == 2 &&
2318 regex.charAt(0) == '\\' &&
2319 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2320 ((ch-'a')|('z'-ch)) < 0 &&
2321 ((ch-'A')|('Z'-ch)) < 0)) &&
2322 (ch < Character.MIN_HIGH_SURROGATE ||
2323 ch > Character.MAX_LOW_SURROGATE))
2324 {
2325 int off = 0;
2326 int next = 0;
2327 boolean limited = limit > 0;
2328 ArrayList<String> list = new ArrayList<>();
2329 while ((next = indexOf(ch, off)) != -1) {
2330 if (!limited || list.size() < limit - 1) {
2331 list.add(substring(off, next));
2332 off = next + 1;
2333 } else { // last one
2334 //assert (list.size() == limit - 1);
2335 int last = length();
2336 list.add(substring(off, last));
2337 off = last;
2338 break;
2339 }
2340 }
2341 // If no match was found, return this
2342 if (off == 0)
2343 return new String[]{this};
2344
2345 // Add remaining segment
2346 if (!limited || list.size() < limit)
2347 list.add(substring(off, length()));
2348
2349 // Construct result
2350 int resultSize = list.size();
2351 if (limit == 0) {
2352 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2353 resultSize--;
2354 }
2355 }
2356 String[] result = new String[resultSize];
2357 return list.subList(0, resultSize).toArray(result);
2358 }
2359 return Pattern.compile(regex).split(this, limit);
2360 }
2361
2362 /**
2363 * Splits this string around matches of the given <a
2364 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2365 *
2366 * <p> This method works as if by invoking the two-argument {@link
2367 * #split(String, int) split} method with the given expression and a limit
2368 * argument of zero. Trailing empty strings are therefore not included in
2369 * the resulting array.
2370 *
2371 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2372 * results with these expressions:
2373 *
2374 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2375 * <tr>
2376 * <th>Regex</th>
2377 * <th>Result</th>
2378 * </tr>
2379 * <tr><td align=center>:</td>
2380 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2381 * <tr><td align=center>o</td>
2382 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2383 * </table></blockquote>
2384 *
2385 *
2386 * @param regex
2387 * the delimiting regular expression
2388 *
2389 * @return the array of strings computed by splitting this string
2390 * around matches of the given regular expression
2391 *
2392 * @throws PatternSyntaxException
2393 * if the regular expression's syntax is invalid
2394 *
2395 * @see java.util.regex.Pattern
2396 *
2397 * @since 1.4
2398 * @spec JSR-51
2399 */
2400 public String[] split(String regex) {
2401 return split(regex, 0);
2402 }
2403
2404 /**
2405 * Returns a new String composed of copies of the
2406 * {@code CharSequence elements} joined together with a copy of
2407 * the specified {@code delimiter}.
2408 *
2409 * <blockquote>For example,
2410 * <pre>{@code
2411 * String message = String.join("-", "Java", "is", "cool");
2412 * // message returned is: "Java-is-cool"
2413 * }</pre></blockquote>
2414 *
2415 * Note that if an element is null, then {@code "null"} is added.
2416 *
2417 * @param delimiter the delimiter that separates each element
2418 * @param elements the elements to join together.
2419 *
2420 * @return a new {@code String} that is composed of the {@code elements}
2421 * separated by the {@code delimiter}
2422 *
2423 * @throws NullPointerException If {@code delimiter} or {@code elements}
2424 * is {@code null}
2425 *
2426 * @see java.util.StringJoiner
2427 * @since 1.8
2428 */
2429 public static String join(CharSequence delimiter, CharSequence... elements) {
2430 Objects.requireNonNull(delimiter);
2431 Objects.requireNonNull(elements);
2432 // Number of elements not likely worth Arrays.stream overhead.
2433 StringJoiner joiner = new StringJoiner(delimiter);
2434 for (CharSequence cs: elements) {
2435 joiner.add(cs);
2436 }
2437 return joiner.toString();
2438 }
2439
2440 /**
2441 * Returns a new {@code String} composed of copies of the
2442 * {@code CharSequence elements} joined together with a copy of the
2443 * specified {@code delimiter}.
2444 *
2445 * <blockquote>For example,
2446 * <pre>{@code
2447 * List<String> strings = new LinkedList<>();
2448 * strings.add("Java");strings.add("is");
2449 * strings.add("cool");
2450 * String message = String.join(" ", strings);
2451 * //message returned is: "Java is cool"
2452 *
2453 * Set<String> strings = new LinkedHashSet<>();
2454 * strings.add("Java"); strings.add("is");
2455 * strings.add("very"); strings.add("cool");
2456 * String message = String.join("-", strings);
2457 * //message returned is: "Java-is-very-cool"
2458 * }</pre></blockquote>
2459 *
2460 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2461 *
2462 * @param delimiter a sequence of characters that is used to separate each
2463 * of the {@code elements} in the resulting {@code String}
2464 * @param elements an {@code Iterable} that will have its {@code elements}
2465 * joined together.
2466 *
2467 * @return a new {@code String} that is composed from the {@code elements}
2468 * argument
2469 *
2470 * @throws NullPointerException If {@code delimiter} or {@code elements}
2471 * is {@code null}
2472 *
2473 * @see #join(CharSequence,CharSequence...)
2474 * @see java.util.StringJoiner
2475 * @since 1.8
2476 */
2477 public static String join(CharSequence delimiter,
2478 Iterable<? extends CharSequence> elements) {
2479 Objects.requireNonNull(delimiter);
2480 Objects.requireNonNull(elements);
2481 StringJoiner joiner = new StringJoiner(delimiter);
2482 for (CharSequence cs: elements) {
2483 joiner.add(cs);
2484 }
2485 return joiner.toString();
2486 }
2487
2488 /**
2489 * Converts all of the characters in this {@code String} to lower
2490 * case using the rules of the given {@code Locale}. Case mapping is based
2491 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2492 * class. Since case mappings are not always 1:1 char mappings, the resulting
2493 * {@code String} may be a different length than the original {@code String}.
2494 * <p>
2495 * Examples of lowercase mappings are in the following table:
2496 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2497 * <tr>
2498 * <th>Language Code of Locale</th>
2499 * <th>Upper Case</th>
2500 * <th>Lower Case</th>
2501 * <th>Description</th>
2502 * </tr>
2503 * <tr>
2504 * <td>tr (Turkish)</td>
2505 * <td>\u0130</td>
2506 * <td>\u0069</td>
2507 * <td>capital letter I with dot above -> small letter i</td>
2508 * </tr>
2509 * <tr>
2510 * <td>tr (Turkish)</td>
2511 * <td>\u0049</td>
2512 * <td>\u0131</td>
2513 * <td>capital letter I -> small letter dotless i </td>
2514 * </tr>
2515 * <tr>
2516 * <td>(all)</td>
2517 * <td>French Fries</td>
2518 * <td>french fries</td>
2519 * <td>lowercased all chars in String</td>
2520 * </tr>
2521 * <tr>
2522 * <td>(all)</td>
2523 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2524 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2525 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2526 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2527 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2528 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2529 * <td>lowercased all chars in String</td>
2530 * </tr>
2531 * </table>
2532 *
2533 * @param locale use the case transformation rules for this locale
2534 * @return the {@code String}, converted to lowercase.
2535 * @see java.lang.String#toLowerCase()
2536 * @see java.lang.String#toUpperCase()
2537 * @see java.lang.String#toUpperCase(Locale)
2538 * @since 1.1
2539 */
2540 public String toLowerCase(Locale locale) {
2541 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale)
2542 : StringUTF16.toLowerCase(this, value, locale);
2543 }
2544
2545 /**
2546 * Converts all of the characters in this {@code String} to lower
2547 * case using the rules of the default locale. This is equivalent to calling
2548 * {@code toLowerCase(Locale.getDefault())}.
2549 * <p>
2550 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2551 * results if used for strings that are intended to be interpreted locale
2552 * independently.
2553 * Examples are programming language identifiers, protocol keys, and HTML
2554 * tags.
2555 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2556 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2557 * LATIN SMALL LETTER DOTLESS I character.
2558 * To obtain correct results for locale insensitive strings, use
2559 * {@code toLowerCase(Locale.ROOT)}.
2560 *
2561 * @return the {@code String}, converted to lowercase.
2562 * @see java.lang.String#toLowerCase(Locale)
2563 */
2564 public String toLowerCase() {
2565 return toLowerCase(Locale.getDefault());
2566 }
2567
2568 /**
2569 * Converts all of the characters in this {@code String} to upper
2570 * case using the rules of the given {@code Locale}. Case mapping is based
2571 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2572 * class. Since case mappings are not always 1:1 char mappings, the resulting
2573 * {@code String} may be a different length than the original {@code String}.
2574 * <p>
2575 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2576 *
2577 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2578 * <tr>
2579 * <th>Language Code of Locale</th>
2580 * <th>Lower Case</th>
2581 * <th>Upper Case</th>
2582 * <th>Description</th>
2583 * </tr>
2584 * <tr>
2585 * <td>tr (Turkish)</td>
2586 * <td>\u0069</td>
2587 * <td>\u0130</td>
2588 * <td>small letter i -> capital letter I with dot above</td>
2589 * </tr>
2590 * <tr>
2591 * <td>tr (Turkish)</td>
2592 * <td>\u0131</td>
2593 * <td>\u0049</td>
2594 * <td>small letter dotless i -> capital letter I</td>
2595 * </tr>
2596 * <tr>
2597 * <td>(all)</td>
2598 * <td>\u00df</td>
2599 * <td>\u0053 \u0053</td>
2600 * <td>small letter sharp s -> two letters: SS</td>
2601 * </tr>
2602 * <tr>
2603 * <td>(all)</td>
2604 * <td>Fahrvergnügen</td>
2605 * <td>FAHRVERGNÜGEN</td>
2606 * <td></td>
2607 * </tr>
2608 * </table>
2609 * @param locale use the case transformation rules for this locale
2610 * @return the {@code String}, converted to uppercase.
2611 * @see java.lang.String#toUpperCase()
2612 * @see java.lang.String#toLowerCase()
2613 * @see java.lang.String#toLowerCase(Locale)
2614 * @since 1.1
2615 */
2616 public String toUpperCase(Locale locale) {
2617 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale)
2618 : StringUTF16.toUpperCase(this, value, locale);
2619 }
2620
2621 /**
2622 * Converts all of the characters in this {@code String} to upper
2623 * case using the rules of the default locale. This method is equivalent to
2624 * {@code toUpperCase(Locale.getDefault())}.
2625 * <p>
2626 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2627 * results if used for strings that are intended to be interpreted locale
2628 * independently.
2629 * Examples are programming language identifiers, protocol keys, and HTML
2630 * tags.
2631 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2632 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2633 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2634 * To obtain correct results for locale insensitive strings, use
2635 * {@code toUpperCase(Locale.ROOT)}.
2636 *
2637 * @return the {@code String}, converted to uppercase.
2638 * @see java.lang.String#toUpperCase(Locale)
2639 */
2640 public String toUpperCase() {
2641 return toUpperCase(Locale.getDefault());
2642 }
2643
2644 /**
2645 * Returns a string whose value is this string, with any leading and trailing
2646 * whitespace removed.
2647 * <p>
2648 * If this {@code String} object represents an empty character
2649 * sequence, or the first and last characters of character sequence
2650 * represented by this {@code String} object both have codes
2651 * greater than {@code '\u005Cu0020'} (the space character), then a
2652 * reference to this {@code String} object is returned.
2653 * <p>
2654 * Otherwise, if there is no character with a code greater than
2655 * {@code '\u005Cu0020'} in the string, then a
2656 * {@code String} object representing an empty string is
2657 * returned.
2658 * <p>
2659 * Otherwise, let <i>k</i> be the index of the first character in the
2660 * string whose code is greater than {@code '\u005Cu0020'}, and let
2661 * <i>m</i> be the index of the last character in the string whose code
2662 * is greater than {@code '\u005Cu0020'}. A {@code String}
2663 * object is returned, representing the substring of this string that
2664 * begins with the character at index <i>k</i> and ends with the
2665 * character at index <i>m</i>-that is, the result of
2666 * {@code this.substring(k, m + 1)}.
2667 * <p>
2668 * This method may be used to trim whitespace (as defined above) from
2669 * the beginning and end of a string.
2670 *
2671 * @return A string whose value is this string, with any leading and trailing white
2672 * space removed, or this string if it has no leading or
2673 * trailing white space.
2674 */
2675 public String trim() {
2676 String ret = isLatin1() ? StringLatin1.trim(value)
2677 : StringUTF16.trim(value);
2678 return ret == null ? this : ret;
2679 }
2680
2681 /**
2682 * This object (which is already a string!) is itself returned.
2683 *
2684 * @return the string itself.
2685 */
2686 public String toString() {
2687 return this;
2688 }
2689
2690 /**
2691 * Returns a stream of {@code int} zero-extending the {@code char} values
2692 * from this sequence. Any char which maps to a <a
2693 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code
2694 * point</a> is passed through uninterpreted.
2695 *
2696 * @return an IntStream of char values from this sequence
2697 * @since 9
2698 */
2699 @Override
2700 public IntStream chars() {
2701 return StreamSupport.intStream(
2702 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
2703 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE),
2704 false);
2705 }
2706
2707
2708 /**
2709 * Returns a stream of code point values from this sequence. Any surrogate
2710 * pairs encountered in the sequence are combined as if by {@linkplain
2711 * Character#toCodePoint Character.toCodePoint} and the result is passed
2712 * to the stream. Any other code units, including ordinary BMP characters,
2713 * unpaired surrogates, and undefined code units, are zero-extended to
2714 * {@code int} values which are then passed to the stream.
2715 *
2716 * @return an IntStream of Unicode code points from this sequence
2717 * @since 9
2718 */
2719 @Override
2720 public IntStream codePoints() {
2721 return StreamSupport.intStream(
2722 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
2723 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE),
2724 false);
2725 }
2726
2727 /**
2728 * Converts this string to a new character array.
2729 *
2730 * @return a newly allocated character array whose length is the length
2731 * of this string and whose contents are initialized to contain
2732 * the character sequence represented by this string.
2733 */
2734 public char[] toCharArray() {
2735 return isLatin1() ? StringLatin1.toChars(value)
2736 : StringUTF16.toChars(value);
2737 }
2738
2739 /**
2740 * Returns a formatted string using the specified format string and
2741 * arguments.
2742 *
2743 * <p> The locale always used is the one returned by {@link
2744 * java.util.Locale#getDefault() Locale.getDefault()}.
2745 *
2746 * @param format
2747 * A <a href="../util/Formatter.html#syntax">format string</a>
2748 *
2749 * @param args
2750 * Arguments referenced by the format specifiers in the format
2751 * string. If there are more arguments than format specifiers, the
2752 * extra arguments are ignored. The number of arguments is
2753 * variable and may be zero. The maximum number of arguments is
2754 * limited by the maximum dimension of a Java array as defined by
2755 * <cite>The Java™ Virtual Machine Specification</cite>.
2756 * The behaviour on a
2757 * {@code null} argument depends on the <a
2758 * href="../util/Formatter.html#syntax">conversion</a>.
2759 *
2760 * @throws java.util.IllegalFormatException
2761 * If a format string contains an illegal syntax, a format
2762 * specifier that is incompatible with the given arguments,
2763 * insufficient arguments given the format string, or other
2764 * illegal conditions. For specification of all possible
2765 * formatting errors, see the <a
2766 * href="../util/Formatter.html#detail">Details</a> section of the
2767 * formatter class specification.
2768 *
2769 * @return A formatted string
2770 *
2771 * @see java.util.Formatter
2772 * @since 1.5
2773 */
2774 public static String format(String format, Object... args) {
2775 return new Formatter().format(format, args).toString();
2776 }
2777
2778 /**
2779 * Returns a formatted string using the specified locale, format string,
2780 * and arguments.
2781 *
2782 * @param l
2783 * The {@linkplain java.util.Locale locale} to apply during
2784 * formatting. If {@code l} is {@code null} then no localization
2785 * is applied.
2786 *
2787 * @param format
2788 * A <a href="../util/Formatter.html#syntax">format string</a>
2789 *
2790 * @param args
2791 * Arguments referenced by the format specifiers in the format
2792 * string. If there are more arguments than format specifiers, the
2793 * extra arguments are ignored. The number of arguments is
2794 * variable and may be zero. The maximum number of arguments is
2795 * limited by the maximum dimension of a Java array as defined by
2796 * <cite>The Java™ Virtual Machine Specification</cite>.
2797 * The behaviour on a
2798 * {@code null} argument depends on the
2799 * <a href="../util/Formatter.html#syntax">conversion</a>.
2800 *
2801 * @throws java.util.IllegalFormatException
2802 * If a format string contains an illegal syntax, a format
2803 * specifier that is incompatible with the given arguments,
2804 * insufficient arguments given the format string, or other
2805 * illegal conditions. For specification of all possible
2806 * formatting errors, see the <a
2807 * href="../util/Formatter.html#detail">Details</a> section of the
2808 * formatter class specification
2809 *
2810 * @return A formatted string
2811 *
2812 * @see java.util.Formatter
2813 * @since 1.5
2814 */
2815 public static String format(Locale l, String format, Object... args) {
2816 return new Formatter(l).format(format, args).toString();
2817 }
2818
2819 /**
2820 * Returns the string representation of the {@code Object} argument.
2821 *
2822 * @param obj an {@code Object}.
2823 * @return if the argument is {@code null}, then a string equal to
2824 * {@code "null"}; otherwise, the value of
2825 * {@code obj.toString()} is returned.
2826 * @see java.lang.Object#toString()
2827 */
2828 public static String valueOf(Object obj) {
2829 return (obj == null) ? "null" : obj.toString();
2830 }
2831
2832 /**
2833 * Returns the string representation of the {@code char} array
2834 * argument. The contents of the character array are copied; subsequent
2835 * modification of the character array does not affect the returned
2836 * string.
2837 *
2838 * @param data the character array.
2839 * @return a {@code String} that contains the characters of the
2840 * character array.
2841 */
2842 public static String valueOf(char data[]) {
2843 return new String(data);
2844 }
2845
2846 /**
2847 * Returns the string representation of a specific subarray of the
2848 * {@code char} array argument.
2849 * <p>
2850 * The {@code offset} argument is the index of the first
2851 * character of the subarray. The {@code count} argument
2852 * specifies the length of the subarray. The contents of the subarray
2853 * are copied; subsequent modification of the character array does not
2854 * affect the returned string.
2855 *
2856 * @param data the character array.
2857 * @param offset initial offset of the subarray.
2858 * @param count length of the subarray.
2859 * @return a {@code String} that contains the characters of the
2860 * specified subarray of the character array.
2861 * @exception IndexOutOfBoundsException if {@code offset} is
2862 * negative, or {@code count} is negative, or
2863 * {@code offset+count} is larger than
2864 * {@code data.length}.
2865 */
2866 public static String valueOf(char data[], int offset, int count) {
2867 return new String(data, offset, count);
2868 }
2869
2870 /**
2871 * Equivalent to {@link #valueOf(char[], int, int)}.
2872 *
2873 * @param data the character array.
2874 * @param offset initial offset of the subarray.
2875 * @param count length of the subarray.
2876 * @return a {@code String} that contains the characters of the
2877 * specified subarray of the character array.
2878 * @exception IndexOutOfBoundsException if {@code offset} is
2879 * negative, or {@code count} is negative, or
2880 * {@code offset+count} is larger than
2881 * {@code data.length}.
2882 */
2883 public static String copyValueOf(char data[], int offset, int count) {
2884 return new String(data, offset, count);
2885 }
2886
2887 /**
2888 * Equivalent to {@link #valueOf(char[])}.
2889 *
2890 * @param data the character array.
2891 * @return a {@code String} that contains the characters of the
2892 * character array.
2893 */
2894 public static String copyValueOf(char data[]) {
2895 return new String(data);
2896 }
2897
2898 /**
2899 * Returns the string representation of the {@code boolean} argument.
2900 *
2901 * @param b a {@code boolean}.
2902 * @return if the argument is {@code true}, a string equal to
2903 * {@code "true"} is returned; otherwise, a string equal to
2904 * {@code "false"} is returned.
2905 */
2906 public static String valueOf(boolean b) {
2907 return b ? "true" : "false";
2908 }
2909
2910 /**
2911 * Returns the string representation of the {@code char}
2912 * argument.
2913 *
2914 * @param c a {@code char}.
2915 * @return a string of length {@code 1} containing
2916 * as its single character the argument {@code c}.
2917 */
2918 public static String valueOf(char c) {
2919 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) {
2920 return new String(StringLatin1.toBytes(c), LATIN1);
2921 }
2922 return new String(StringUTF16.toBytes(c), UTF16);
2923 }
2924
2925 /**
2926 * Returns the string representation of the {@code int} argument.
2927 * <p>
2928 * The representation is exactly the one returned by the
2929 * {@code Integer.toString} method of one argument.
2930 *
2931 * @param i an {@code int}.
2932 * @return a string representation of the {@code int} argument.
2933 * @see java.lang.Integer#toString(int, int)
2934 */
2935 public static String valueOf(int i) {
2936 return Integer.toString(i);
2937 }
2938
2939 /**
2940 * Returns the string representation of the {@code long} argument.
2941 * <p>
2942 * The representation is exactly the one returned by the
2943 * {@code Long.toString} method of one argument.
2944 *
2945 * @param l a {@code long}.
2946 * @return a string representation of the {@code long} argument.
2947 * @see java.lang.Long#toString(long)
2948 */
2949 public static String valueOf(long l) {
2950 return Long.toString(l);
2951 }
2952
2953 /**
2954 * Returns the string representation of the {@code float} argument.
2955 * <p>
2956 * The representation is exactly the one returned by the
2957 * {@code Float.toString} method of one argument.
2958 *
2959 * @param f a {@code float}.
2960 * @return a string representation of the {@code float} argument.
2961 * @see java.lang.Float#toString(float)
2962 */
2963 public static String valueOf(float f) {
2964 return Float.toString(f);
2965 }
2966
2967 /**
2968 * Returns the string representation of the {@code double} argument.
2969 * <p>
2970 * The representation is exactly the one returned by the
2971 * {@code Double.toString} method of one argument.
2972 *
2973 * @param d a {@code double}.
2974 * @return a string representation of the {@code double} argument.
2975 * @see java.lang.Double#toString(double)
2976 */
2977 public static String valueOf(double d) {
2978 return Double.toString(d);
2979 }
2980
2981 /**
2982 * Returns a canonical representation for the string object.
2983 * <p>
2984 * A pool of strings, initially empty, is maintained privately by the
2985 * class {@code String}.
2986 * <p>
2987 * When the intern method is invoked, if the pool already contains a
2988 * string equal to this {@code String} object as determined by
2989 * the {@link #equals(Object)} method, then the string from the pool is
2990 * returned. Otherwise, this {@code String} object is added to the
2991 * pool and a reference to this {@code String} object is returned.
2992 * <p>
2993 * It follows that for any two strings {@code s} and {@code t},
2994 * {@code s.intern() == t.intern()} is {@code true}
2995 * if and only if {@code s.equals(t)} is {@code true}.
2996 * <p>
2997 * All literal strings and string-valued constant expressions are
2998 * interned. String literals are defined in section 3.10.5 of the
2999 * <cite>The Java™ Language Specification</cite>.
3000 *
3001 * @return a string that has the same contents as this string, but is
3002 * guaranteed to be from a pool of unique strings.
3003 */
3004 public native String intern();
3005
3006 ////////////////////////////////////////////////////////////////
3007
3008 /**
3009 * Copy character bytes from this string into dst starting at dstBegin.
3010 * This method doesn't perform any range checking.
3011 *
3012 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two
3013 * coders are different, and dst is big enough (range check)
3014 *
3015 * @param dstBegin the char index, not offset of byte[]
3016 * @param coder the coder of dst[]
3017 */
3018 void getBytes(byte dst[], int dstBegin, byte coder) {
3019 if (coder() == coder) {
3020 System.arraycopy(value, 0, dst, dstBegin << coder, value.length);
3021 } else { // this.coder == LATIN && coder == UTF16
3022 StringLatin1.inflate(value, 0, dst, dstBegin, value.length);
3023 }
3024 }
3025
3026 /*
3027 * Package private constructor. Trailing Void argument is there for
3028 * disambiguating it against other (public) constructors.
3029 *
3030 * Stores the char[] value into a byte[] that each byte represents
3031 * the8 low-order bits of the corresponding character, if the char[]
3032 * contains only latin1 character. Or a byte[] that stores all
3033 * characters in their byte sequences defined by the {@code StringUTF16}.
3034 */
3035 String(char[] value, int off, int len, Void sig) {
3036 if (len == 0) {
3037 this.value = "".value;
3038 this.coder = "".coder;
3039 return;
3040 }
3041 if (COMPACT_STRINGS) {
3042 byte[] val = StringUTF16.compress(value, off, len);
3043 if (val != null) {
3044 this.value = val;
3045 this.coder = LATIN1;
3046 return;
3047 }
3048 }
3049 this.coder = UTF16;
3050 this.value = StringUTF16.toBytes(value, off, len);
3051 }
3052
3053 /*
3054 * Package private constructor. Trailing Void argument is there for
3055 * disambiguating it against other (public) constructors.
3056 */
3057 String(AbstractStringBuilder asb, Void sig) {
3058 byte[] val = asb.getValue();
3059 int length = asb.length();
3060 if (asb.isLatin1()) {
3061 this.coder = LATIN1;
3062 this.value = Arrays.copyOfRange(val, 0, length);
3063 } else {
3064 if (COMPACT_STRINGS) {
3065 byte[] buf = StringUTF16.compress(val, 0, length);
3066 if (buf != null) {
3067 this.coder = LATIN1;
3068 this.value = buf;
3069 return;
3070 }
3071 }
3072 this.coder = UTF16;
3073 this.value = Arrays.copyOfRange(val, 0, length << 1);
3074 }
3075 }
3076
3077 /*
3078 * Package private constructor which shares value array for speed.
3079 */
3080 String(byte[] value, byte coder) {
3081 this.value = value;
3082 this.coder = coder;
3083 }
3084
3085 byte coder() {
3086 return COMPACT_STRINGS ? coder : UTF16;
3087 }
3088
3089 private boolean isLatin1() {
3090 return COMPACT_STRINGS && coder == LATIN1;
3091 }
3092
3093 static final byte LATIN1 = 0;
3094 static final byte UTF16 = 1;
3095
3096 /*
3097 * StringIndexOutOfBoundsException if {@code index} is
3098 * negative or greater than or equal to {@code length}.
3099 */
3100 static void checkIndex(int index, int length) {
3101 if (index < 0 || index >= length) {
3102 throw new StringIndexOutOfBoundsException("index " + index);
3103 }
3104 }
3105
3106 /*
3107 * StringIndexOutOfBoundsException if {@code offset}
3108 * is negative or greater than {@code length}.
3109 */
3110 static void checkOffset(int offset, int length) {
3111 if (offset < 0 || offset > length) {
3112 throw new StringIndexOutOfBoundsException("offset " + offset +
3113 ",length " + length);
3114 }
3115 }
3116
3117 /*
3118 * Check {@code offset}, {@code count} against {@code 0} and {@code length}
3119 * bounds.
3120 *
3121 * @throws StringIndexOutOfBoundsException
3122 * If {@code offset} is negative, {@code count} is negative,
3123 * or {@code offset} is greater than {@code length - count}
3124 */
3125 static void checkBoundsOffCount(int offset, int count, int length) {
3126 if (offset < 0 || count < 0 || offset > length - count) {
3127 throw new StringIndexOutOfBoundsException(
3128 "offset " + offset + ", count " + count + ", length " + length);
3129 }
3130 }
3131
3132 /*
3133 * Check {@code begin}, {@code end} against {@code 0} and {@code length}
3134 * bounds.
3135 *
3136 * @throws StringIndexOutOfBoundsException
3137 * If {@code begin} is negative, {@code begin} is greater than
3138 * {@code end}, or {@code end} is greater than {@code length}.
3139 */
3140 private static void checkBoundsBeginEnd(int begin, int end, int length) {
3141 if (begin < 0 || begin > end || end > length) {
3142 throw new StringIndexOutOfBoundsException(
3143 "begin " + begin + ", end " + end + ", length " + length);
3144 }
3145 }
3146 }