1 /*
2 * Copyright (c) 1994, 2018, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import java.io.ObjectStreamField;
29 import java.io.UnsupportedEncodingException;
30 import java.lang.annotation.Native;
31 import java.nio.charset.Charset;
32 import java.nio.ByteBuffer;
33 import java.util.ArrayList;
34 import java.util.Arrays;
35 import java.util.Comparator;
36 import java.util.Formatter;
37 import java.util.Locale;
38 import java.util.Objects;
39 import java.util.Spliterator;
40 import java.util.StringJoiner;
41 import java.util.regex.Matcher;
42 import java.util.regex.Pattern;
43 import java.util.regex.PatternSyntaxException;
44 import java.util.stream.IntStream;
45 import java.util.stream.StreamSupport;
46 import jdk.internal.HotSpotIntrinsicCandidate;
47 import jdk.internal.vm.annotation.Stable;
48
49 /**
50 * The {@code String} class represents character strings. All
51 * string literals in Java programs, such as {@code "abc"}, are
52 * implemented as instances of this class.
53 * <p>
54 * Strings are constant; their values cannot be changed after they
55 * are created. String buffers support mutable strings.
56 * Because String objects are immutable they can be shared. For example:
57 * <blockquote><pre>
58 * String str = "abc";
59 * </pre></blockquote><p>
60 * is equivalent to:
61 * <blockquote><pre>
62 * char data[] = {'a', 'b', 'c'};
63 * String str = new String(data);
64 * </pre></blockquote><p>
65 * Here are some more examples of how strings can be used:
66 * <blockquote><pre>
67 * System.out.println("abc");
68 * String cde = "cde";
69 * System.out.println("abc" + cde);
70 * String c = "abc".substring(2,3);
71 * String d = cde.substring(1, 2);
72 * </pre></blockquote>
73 * <p>
74 * The class {@code String} includes methods for examining
75 * individual characters of the sequence, for comparing strings, for
76 * searching strings, for extracting substrings, and for creating a
77 * copy of a string with all characters translated to uppercase or to
78 * lowercase. Case mapping is based on the Unicode Standard version
79 * specified by the {@link java.lang.Character Character} class.
80 * <p>
81 * The Java language provides special support for the string
82 * concatenation operator ( + ), and for conversion of
83 * other objects to strings. For additional information on string
84 * concatenation and conversion, see <i>The Java™ Language Specification</i>.
85 *
86 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor
87 * or method in this class will cause a {@link NullPointerException} to be
88 * thrown.
89 *
90 * <p>A {@code String} represents a string in the UTF-16 format
91 * in which <em>supplementary characters</em> are represented by <em>surrogate
92 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
93 * Character Representations</a> in the {@code Character} class for
94 * more information).
95 * Index values refer to {@code char} code units, so a supplementary
96 * character uses two positions in a {@code String}.
97 * <p>The {@code String} class provides methods for dealing with
98 * Unicode code points (i.e., characters), in addition to those for
99 * dealing with Unicode code units (i.e., {@code char} values).
100 *
101 * <p>Unless otherwise noted, methods for comparing Strings do not take locale
102 * into account. The {@link java.text.Collator} class provides methods for
103 * finer-grain, locale-sensitive String comparison.
104 *
105 * @implNote The implementation of the string concatenation operator is left to
106 * the discretion of a Java compiler, as long as the compiler ultimately conforms
107 * to <i>The Java™ Language Specification</i>. For example, the {@code javac} compiler
108 * may implement the operator with {@code StringBuffer}, {@code StringBuilder},
109 * or {@code java.lang.invoke.StringConcatFactory} depending on the JDK version. The
110 * implementation of string conversion is typically through the method {@code toString},
111 * defined by {@code Object} and inherited by all classes in Java.
112 *
113 * @author Lee Boynton
114 * @author Arthur van Hoff
115 * @author Martin Buchholz
116 * @author Ulf Zibis
117 * @see java.lang.Object#toString()
118 * @see java.lang.StringBuffer
119 * @see java.lang.StringBuilder
120 * @see java.nio.charset.Charset
121 * @since 1.0
122 * @jls 15.18.1 String Concatenation Operator +
123 */
124
125 public final class String
126 implements java.io.Serializable, Comparable<String>, CharSequence {
127
128 /**
129 * The value is used for character storage.
130 *
131 * @implNote This field is trusted by the VM, and is a subject to
132 * constant folding if String instance is constant. Overwriting this
133 * field after construction will cause problems.
134 *
135 * Additionally, it is marked with {@link Stable} to trust the contents
136 * of the array. No other facility in JDK provides this functionality (yet).
137 * {@link Stable} is safe here, because value is never null.
138 */
139 @Stable
140 private final byte[] value;
141
142 /**
143 * The identifier of the encoding used to encode the bytes in
144 * {@code value}. The supported values in this implementation are
145 *
146 * LATIN1
147 * UTF16
148 *
149 * @implNote This field is trusted by the VM, and is a subject to
150 * constant folding if String instance is constant. Overwriting this
151 * field after construction will cause problems.
152 */
153 private final byte coder;
154
155 /** Cache the hash code for the string */
156 private int hash; // Default to 0
157
158 /** use serialVersionUID from JDK 1.0.2 for interoperability */
159 private static final long serialVersionUID = -6849794470754667710L;
160
161 /**
162 * If String compaction is disabled, the bytes in {@code value} are
163 * always encoded in UTF16.
164 *
165 * For methods with several possible implementation paths, when String
166 * compaction is disabled, only one code path is taken.
167 *
168 * The instance field value is generally opaque to optimizing JIT
169 * compilers. Therefore, in performance-sensitive place, an explicit
170 * check of the static boolean {@code COMPACT_STRINGS} is done first
171 * before checking the {@code coder} field since the static boolean
172 * {@code COMPACT_STRINGS} would be constant folded away by an
173 * optimizing JIT compiler. The idioms for these cases are as follows.
174 *
175 * For code such as:
176 *
177 * if (coder == LATIN1) { ... }
178 *
179 * can be written more optimally as
180 *
181 * if (coder() == LATIN1) { ... }
182 *
183 * or:
184 *
185 * if (COMPACT_STRINGS && coder == LATIN1) { ... }
186 *
187 * An optimizing JIT compiler can fold the above conditional as:
188 *
189 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... }
190 * COMPACT_STRINGS == false => if (false) { ... }
191 *
192 * @implNote
193 * The actual value for this field is injected by JVM. The static
194 * initialization block is used to set the value here to communicate
195 * that this static final field is not statically foldable, and to
196 * avoid any possible circular dependency during vm initialization.
197 */
198 static final boolean COMPACT_STRINGS;
199
200 static {
201 COMPACT_STRINGS = true;
202 }
203
204 /**
205 * Class String is special cased within the Serialization Stream Protocol.
206 *
207 * A String instance is written into an ObjectOutputStream according to
208 * <a href="{@docRoot}/../specs/serialization/protocol.html#stream-elements">
209 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
210 */
211 private static final ObjectStreamField[] serialPersistentFields =
212 new ObjectStreamField[0];
213
214 /**
215 * Initializes a newly created {@code String} object so that it represents
216 * an empty character sequence. Note that use of this constructor is
217 * unnecessary since Strings are immutable.
218 */
219 public String() {
220 this.value = "".value;
221 this.coder = "".coder;
222 }
223
224 /**
225 * Initializes a newly created {@code String} object so that it represents
226 * the same sequence of characters as the argument; in other words, the
227 * newly created string is a copy of the argument string. Unless an
228 * explicit copy of {@code original} is needed, use of this constructor is
229 * unnecessary since Strings are immutable.
230 *
231 * @param original
232 * A {@code String}
233 */
234 @HotSpotIntrinsicCandidate
235 public String(String original) {
236 this.value = original.value;
237 this.coder = original.coder;
238 this.hash = original.hash;
239 }
240
241 /**
242 * Allocates a new {@code String} so that it represents the sequence of
243 * characters currently contained in the character array argument. The
244 * contents of the character array are copied; subsequent modification of
245 * the character array does not affect the newly created string.
246 *
247 * @param value
248 * The initial value of the string
249 */
250 public String(char value[]) {
251 this(value, 0, value.length, null);
252 }
253
254 /**
255 * Allocates a new {@code String} that contains characters from a subarray
256 * of the character array argument. The {@code offset} argument is the
257 * index of the first character of the subarray and the {@code count}
258 * argument specifies the length of the subarray. The contents of the
259 * subarray are copied; subsequent modification of the character array does
260 * not affect the newly created string.
261 *
262 * @param value
263 * Array that is the source of characters
264 *
265 * @param offset
266 * The initial offset
267 *
268 * @param count
269 * The length
270 *
271 * @throws IndexOutOfBoundsException
272 * If {@code offset} is negative, {@code count} is negative, or
273 * {@code offset} is greater than {@code value.length - count}
274 */
275 public String(char value[], int offset, int count) {
276 this(value, offset, count, rangeCheck(value, offset, count));
277 }
278
279 private static Void rangeCheck(char[] value, int offset, int count) {
280 checkBoundsOffCount(offset, count, value.length);
281 return null;
282 }
283
284 /**
285 * Allocates a new {@code String} that contains characters from a subarray
286 * of the <a href="Character.html#unicode">Unicode code point</a> array
287 * argument. The {@code offset} argument is the index of the first code
288 * point of the subarray and the {@code count} argument specifies the
289 * length of the subarray. The contents of the subarray are converted to
290 * {@code char}s; subsequent modification of the {@code int} array does not
291 * affect the newly created string.
292 *
293 * @param codePoints
294 * Array that is the source of Unicode code points
295 *
296 * @param offset
297 * The initial offset
298 *
299 * @param count
300 * The length
301 *
302 * @throws IllegalArgumentException
303 * If any invalid Unicode code point is found in {@code
304 * codePoints}
305 *
306 * @throws IndexOutOfBoundsException
307 * If {@code offset} is negative, {@code count} is negative, or
308 * {@code offset} is greater than {@code codePoints.length - count}
309 *
310 * @since 1.5
311 */
312 public String(int[] codePoints, int offset, int count) {
313 checkBoundsOffCount(offset, count, codePoints.length);
314 if (count == 0) {
315 this.value = "".value;
316 this.coder = "".coder;
317 return;
318 }
319 if (COMPACT_STRINGS) {
320 byte[] val = StringLatin1.toBytes(codePoints, offset, count);
321 if (val != null) {
322 this.coder = LATIN1;
323 this.value = val;
324 return;
325 }
326 }
327 this.coder = UTF16;
328 this.value = StringUTF16.toBytes(codePoints, offset, count);
329 }
330
331 /**
332 * Allocates a new {@code String} constructed from a subarray of an array
333 * of 8-bit integer values.
334 *
335 * <p> The {@code offset} argument is the index of the first byte of the
336 * subarray, and the {@code count} argument specifies the length of the
337 * subarray.
338 *
339 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
340 * specified in the {@link #String(byte[],int) String(byte[],int)} constructor.
341 *
342 * @deprecated This method does not properly convert bytes into characters.
343 * As of JDK 1.1, the preferred way to do this is via the
344 * {@code String} constructors that take a {@link
345 * java.nio.charset.Charset}, charset name, or that use the platform's
346 * default charset.
347 *
348 * @param ascii
349 * The bytes to be converted to characters
350 *
351 * @param hibyte
352 * The top 8 bits of each 16-bit Unicode code unit
353 *
354 * @param offset
355 * The initial offset
356 * @param count
357 * The length
358 *
359 * @throws IndexOutOfBoundsException
360 * If {@code offset} is negative, {@code count} is negative, or
361 * {@code offset} is greater than {@code ascii.length - count}
362 *
363 * @see #String(byte[], int)
364 * @see #String(byte[], int, int, java.lang.String)
365 * @see #String(byte[], int, int, java.nio.charset.Charset)
366 * @see #String(byte[], int, int)
367 * @see #String(byte[], java.lang.String)
368 * @see #String(byte[], java.nio.charset.Charset)
369 * @see #String(byte[])
370 */
371 @Deprecated(since="1.1")
372 public String(byte ascii[], int hibyte, int offset, int count) {
373 checkBoundsOffCount(offset, count, ascii.length);
374 if (count == 0) {
375 this.value = "".value;
376 this.coder = "".coder;
377 return;
378 }
379 if (COMPACT_STRINGS && (byte)hibyte == 0) {
380 this.value = Arrays.copyOfRange(ascii, offset, offset + count);
381 this.coder = LATIN1;
382 } else {
383 hibyte <<= 8;
384 byte[] val = StringUTF16.newBytesFor(count);
385 for (int i = 0; i < count; i++) {
386 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff));
387 }
388 this.value = val;
389 this.coder = UTF16;
390 }
391 }
392
393 /**
394 * Allocates a new {@code String} containing characters constructed from
395 * an array of 8-bit integer values. Each character <i>c</i> in the
396 * resulting string is constructed from the corresponding component
397 * <i>b</i> in the byte array such that:
398 *
399 * <blockquote><pre>
400 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
401 * | (<b><i>b</i></b> & 0xff))
402 * </pre></blockquote>
403 *
404 * @deprecated This method does not properly convert bytes into
405 * characters. As of JDK 1.1, the preferred way to do this is via the
406 * {@code String} constructors that take a {@link
407 * java.nio.charset.Charset}, charset name, or that use the platform's
408 * default charset.
409 *
410 * @param ascii
411 * The bytes to be converted to characters
412 *
413 * @param hibyte
414 * The top 8 bits of each 16-bit Unicode code unit
415 *
416 * @see #String(byte[], int, int, java.lang.String)
417 * @see #String(byte[], int, int, java.nio.charset.Charset)
418 * @see #String(byte[], int, int)
419 * @see #String(byte[], java.lang.String)
420 * @see #String(byte[], java.nio.charset.Charset)
421 * @see #String(byte[])
422 */
423 @Deprecated(since="1.1")
424 public String(byte ascii[], int hibyte) {
425 this(ascii, hibyte, 0, ascii.length);
426 }
427
428 /**
429 * Constructs a new {@code String} by decoding the specified subarray of
430 * bytes using the specified charset. The length of the new {@code String}
431 * is a function of the charset, and hence may not be equal to the length
432 * of the subarray.
433 *
434 * <p> The behavior of this constructor when the given bytes are not valid
435 * in the given charset is unspecified. The {@link
436 * java.nio.charset.CharsetDecoder} class should be used when more control
437 * over the decoding process is required.
438 *
439 * @param bytes
440 * The bytes to be decoded into characters
441 *
442 * @param offset
443 * The index of the first byte to decode
444 *
445 * @param length
446 * The number of bytes to decode
447
448 * @param charsetName
449 * The name of a supported {@linkplain java.nio.charset.Charset
450 * charset}
451 *
452 * @throws UnsupportedEncodingException
453 * If the named charset is not supported
454 *
455 * @throws IndexOutOfBoundsException
456 * If {@code offset} is negative, {@code length} is negative, or
457 * {@code offset} is greater than {@code bytes.length - length}
458 *
459 * @since 1.1
460 */
461 public String(byte bytes[], int offset, int length, String charsetName)
462 throws UnsupportedEncodingException {
463 if (charsetName == null)
464 throw new NullPointerException("charsetName");
465 checkBoundsOffCount(offset, length, bytes.length);
466 StringCoder.Result ret =
467 StringCoder.decode(charsetName, bytes, offset, length);
468 this.value = ret.value;
469 this.coder = ret.coder;
470 }
471
472 /**
473 * Constructs a new {@code String} by decoding the specified subarray of
474 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
475 * The length of the new {@code String} is a function of the charset, and
476 * hence may not be equal to the length of the subarray.
477 *
478 * <p> This method always replaces malformed-input and unmappable-character
479 * sequences with this charset's default replacement string. The {@link
480 * java.nio.charset.CharsetDecoder} class should be used when more control
481 * over the decoding process is required.
482 *
483 * @param bytes
484 * The bytes to be decoded into characters
485 *
486 * @param offset
487 * The index of the first byte to decode
488 *
489 * @param length
490 * The number of bytes to decode
491 *
492 * @param charset
493 * The {@linkplain java.nio.charset.Charset charset} to be used to
494 * decode the {@code bytes}
495 *
496 * @throws IndexOutOfBoundsException
497 * If {@code offset} is negative, {@code length} is negative, or
498 * {@code offset} is greater than {@code bytes.length - length}
499 *
500 * @since 1.6
501 */
502 public String(byte bytes[], int offset, int length, Charset charset) {
503 if (charset == null)
504 throw new NullPointerException("charset");
505 checkBoundsOffCount(offset, length, bytes.length);
506 StringCoder.Result ret =
507 StringCoder.decode(charset, bytes, offset, length);
508 this.value = ret.value;
509 this.coder = ret.coder;
510 }
511
512 /**
513 * Constructs a new {@code String} by decoding the remaining bytes in the specified
514 * {@linkplain java.nio.ByteBuffer byte buffer} using the specified
515 * {@linkplain java.nio.charset.Charset charset}.
516 * The length of the new {@code String} is a function of the charset, and
517 * hence may not be equal to the remaining number of bytes in the
518 * {@linkplain java.nio.ByteBuffer byte buffer}.
519 *
520 * <p> This method always replaces malformed-input and unmappable-character
521 * sequences with this charset's default replacement string. The {@link
522 * java.nio.charset.CharsetDecoder} class should be used when more control
523 * over the decoding process is required.
524 *
525 * <p>
526 * Bytes are read between <code>position()</code> and <code>limit()</code>
527 * of the {@link java.nio.ByteBuffer}.
528 * After the bytes have been read the <code>position()</code> will be
529 * updated.
530 *
531 * @param src
532 * The source of bytes to be decoded into characters
533 *
534 * @param charset
535 * The {@linkplain java.nio.charset.Charset charset} to be used to
536 * decode the {@code src}
537 *
538 * @since 11
539 */
540 public String(ByteBuffer src, Charset charset) {
541 Objects.requireNonNull(src);
542 Objects.requireNonNull(charset);
543 StringCoder.Result ret = StringCoder.decode(charset, src);
544 this.value = ret.value;
545 this.coder = ret.coder;
546 }
547
548 /**
549 * Constructs a new {@code String} by decoding the specified array of bytes
550 * using the specified {@linkplain java.nio.charset.Charset charset}. The
551 * length of the new {@code String} is a function of the charset, and hence
552 * may not be equal to the length of the byte array.
553 *
554 * <p> The behavior of this constructor when the given bytes are not valid
555 * in the given charset is unspecified. The {@link
556 * java.nio.charset.CharsetDecoder} class should be used when more control
557 * over the decoding process is required.
558 *
559 * @param bytes
560 * The bytes to be decoded into characters
561 *
562 * @param charsetName
563 * The name of a supported {@linkplain java.nio.charset.Charset
564 * charset}
565 *
566 * @throws UnsupportedEncodingException
567 * If the named charset is not supported
568 *
569 * @since 1.1
570 */
571 public String(byte bytes[], String charsetName)
572 throws UnsupportedEncodingException {
573 this(bytes, 0, bytes.length, charsetName);
574 }
575
576 /**
577 * Constructs a new {@code String} by decoding the specified array of
578 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
579 * The length of the new {@code String} is a function of the charset, and
580 * hence may not be equal to the length of the byte array.
581 *
582 * <p> This method always replaces malformed-input and unmappable-character
583 * sequences with this charset's default replacement string. The {@link
584 * java.nio.charset.CharsetDecoder} class should be used when more control
585 * over the decoding process is required.
586 *
587 * @param bytes
588 * The bytes to be decoded into characters
589 *
590 * @param charset
591 * The {@linkplain java.nio.charset.Charset charset} to be used to
592 * decode the {@code bytes}
593 *
594 * @since 1.6
595 */
596 public String(byte bytes[], Charset charset) {
597 this(bytes, 0, bytes.length, charset);
598 }
599
600 /**
601 * Constructs a new {@code String} by decoding the specified subarray of
602 * bytes using the platform's default charset. The length of the new
603 * {@code String} is a function of the charset, and hence may not be equal
604 * to the length of the subarray.
605 *
606 * <p> The behavior of this constructor when the given bytes are not valid
607 * in the default charset is unspecified. The {@link
608 * java.nio.charset.CharsetDecoder} class should be used when more control
609 * over the decoding process is required.
610 *
611 * @param bytes
612 * The bytes to be decoded into characters
613 *
614 * @param offset
615 * The index of the first byte to decode
616 *
617 * @param length
618 * The number of bytes to decode
619 *
620 * @throws IndexOutOfBoundsException
621 * If {@code offset} is negative, {@code length} is negative, or
622 * {@code offset} is greater than {@code bytes.length - length}
623 *
624 * @since 1.1
625 */
626 public String(byte bytes[], int offset, int length) {
627 checkBoundsOffCount(offset, length, bytes.length);
628 StringCoder.Result ret = StringCoder.decode(bytes, offset, length);
629 this.value = ret.value;
630 this.coder = ret.coder;
631 }
632
633 /**
634 * Constructs a new {@code String} by decoding the specified array of bytes
635 * using the platform's default charset. The length of the new {@code
636 * String} is a function of the charset, and hence may not be equal to the
637 * length of the byte array.
638 *
639 * <p> The behavior of this constructor when the given bytes are not valid
640 * in the default charset is unspecified. The {@link
641 * java.nio.charset.CharsetDecoder} class should be used when more control
642 * over the decoding process is required.
643 *
644 * @param bytes
645 * The bytes to be decoded into characters
646 *
647 * @since 1.1
648 */
649 public String(byte[] bytes) {
650 this(bytes, 0, bytes.length);
651 }
652
653 /**
654 * Allocates a new string that contains the sequence of characters
655 * currently contained in the string buffer argument. The contents of the
656 * string buffer are copied; subsequent modification of the string buffer
657 * does not affect the newly created string.
658 *
659 * @param buffer
660 * A {@code StringBuffer}
661 */
662 public String(StringBuffer buffer) {
663 this(buffer.toString());
664 }
665
666 /**
667 * Allocates a new string that contains the sequence of characters
668 * currently contained in the string builder argument. The contents of the
669 * string builder are copied; subsequent modification of the string builder
670 * does not affect the newly created string.
671 *
672 * <p> This constructor is provided to ease migration to {@code
673 * StringBuilder}. Obtaining a string from a string builder via the {@code
674 * toString} method is likely to run faster and is generally preferred.
675 *
676 * @param builder
677 * A {@code StringBuilder}
678 *
679 * @since 1.5
680 */
681 public String(StringBuilder builder) {
682 this(builder, null);
683 }
684
685 /**
686 * Returns the length of this string.
687 * The length is equal to the number of <a href="Character.html#unicode">Unicode
688 * code units</a> in the string.
689 *
690 * @return the length of the sequence of characters represented by this
691 * object.
692 */
693 public int length() {
694 return value.length >> coder();
695 }
696
697 /**
698 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
699 *
700 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
701 * {@code false}
702 *
703 * @since 1.6
704 */
705 public boolean isEmpty() {
706 return value.length == 0;
707 }
708
709 /**
710 * Returns the {@code char} value at the
711 * specified index. An index ranges from {@code 0} to
712 * {@code length() - 1}. The first {@code char} value of the sequence
713 * is at index {@code 0}, the next at index {@code 1},
714 * and so on, as for array indexing.
715 *
716 * <p>If the {@code char} value specified by the index is a
717 * <a href="Character.html#unicode">surrogate</a>, the surrogate
718 * value is returned.
719 *
720 * @param index the index of the {@code char} value.
721 * @return the {@code char} value at the specified index of this string.
722 * The first {@code char} value is at index {@code 0}.
723 * @exception IndexOutOfBoundsException if the {@code index}
724 * argument is negative or not less than the length of this
725 * string.
726 */
727 public char charAt(int index) {
728 if (isLatin1()) {
729 return StringLatin1.charAt(value, index);
730 } else {
731 return StringUTF16.charAt(value, index);
732 }
733 }
734
735 /**
736 * Returns the character (Unicode code point) at the specified
737 * index. The index refers to {@code char} values
738 * (Unicode code units) and ranges from {@code 0} to
739 * {@link #length()}{@code - 1}.
740 *
741 * <p> If the {@code char} value specified at the given index
742 * is in the high-surrogate range, the following index is less
743 * than the length of this {@code String}, and the
744 * {@code char} value at the following index is in the
745 * low-surrogate range, then the supplementary code point
746 * corresponding to this surrogate pair is returned. Otherwise,
747 * the {@code char} value at the given index is returned.
748 *
749 * @param index the index to the {@code char} values
750 * @return the code point value of the character at the
751 * {@code index}
752 * @exception IndexOutOfBoundsException if the {@code index}
753 * argument is negative or not less than the length of this
754 * string.
755 * @since 1.5
756 */
757 public int codePointAt(int index) {
758 if (isLatin1()) {
759 checkIndex(index, value.length);
760 return value[index] & 0xff;
761 }
762 int length = value.length >> 1;
763 checkIndex(index, length);
764 return StringUTF16.codePointAt(value, index, length);
765 }
766
767 /**
768 * Returns the character (Unicode code point) before the specified
769 * index. The index refers to {@code char} values
770 * (Unicode code units) and ranges from {@code 1} to {@link
771 * CharSequence#length() length}.
772 *
773 * <p> If the {@code char} value at {@code (index - 1)}
774 * is in the low-surrogate range, {@code (index - 2)} is not
775 * negative, and the {@code char} value at {@code (index -
776 * 2)} is in the high-surrogate range, then the
777 * supplementary code point value of the surrogate pair is
778 * returned. If the {@code char} value at {@code index -
779 * 1} is an unpaired low-surrogate or a high-surrogate, the
780 * surrogate value is returned.
781 *
782 * @param index the index following the code point that should be returned
783 * @return the Unicode code point value before the given index.
784 * @exception IndexOutOfBoundsException if the {@code index}
785 * argument is less than 1 or greater than the length
786 * of this string.
787 * @since 1.5
788 */
789 public int codePointBefore(int index) {
790 int i = index - 1;
791 if (i < 0 || i >= length()) {
792 throw new StringIndexOutOfBoundsException(index);
793 }
794 if (isLatin1()) {
795 return (value[i] & 0xff);
796 }
797 return StringUTF16.codePointBefore(value, index);
798 }
799
800 /**
801 * Returns the number of Unicode code points in the specified text
802 * range of this {@code String}. The text range begins at the
803 * specified {@code beginIndex} and extends to the
804 * {@code char} at index {@code endIndex - 1}. Thus the
805 * length (in {@code char}s) of the text range is
806 * {@code endIndex-beginIndex}. Unpaired surrogates within
807 * the text range count as one code point each.
808 *
809 * @param beginIndex the index to the first {@code char} of
810 * the text range.
811 * @param endIndex the index after the last {@code char} of
812 * the text range.
813 * @return the number of Unicode code points in the specified text
814 * range
815 * @exception IndexOutOfBoundsException if the
816 * {@code beginIndex} is negative, or {@code endIndex}
817 * is larger than the length of this {@code String}, or
818 * {@code beginIndex} is larger than {@code endIndex}.
819 * @since 1.5
820 */
821 public int codePointCount(int beginIndex, int endIndex) {
822 if (beginIndex < 0 || beginIndex > endIndex ||
823 endIndex > length()) {
824 throw new IndexOutOfBoundsException();
825 }
826 if (isLatin1()) {
827 return endIndex - beginIndex;
828 }
829 return StringUTF16.codePointCount(value, beginIndex, endIndex);
830 }
831
832 /**
833 * Returns the index within this {@code String} that is
834 * offset from the given {@code index} by
835 * {@code codePointOffset} code points. Unpaired surrogates
836 * within the text range given by {@code index} and
837 * {@code codePointOffset} count as one code point each.
838 *
839 * @param index the index to be offset
840 * @param codePointOffset the offset in code points
841 * @return the index within this {@code String}
842 * @exception IndexOutOfBoundsException if {@code index}
843 * is negative or larger then the length of this
844 * {@code String}, or if {@code codePointOffset} is positive
845 * and the substring starting with {@code index} has fewer
846 * than {@code codePointOffset} code points,
847 * or if {@code codePointOffset} is negative and the substring
848 * before {@code index} has fewer than the absolute value
849 * of {@code codePointOffset} code points.
850 * @since 1.5
851 */
852 public int offsetByCodePoints(int index, int codePointOffset) {
853 if (index < 0 || index > length()) {
854 throw new IndexOutOfBoundsException();
855 }
856 return Character.offsetByCodePoints(this, index, codePointOffset);
857 }
858
859 /**
860 * Copies characters from this string into the destination character
861 * array.
862 * <p>
863 * The first character to be copied is at index {@code srcBegin};
864 * the last character to be copied is at index {@code srcEnd-1}
865 * (thus the total number of characters to be copied is
866 * {@code srcEnd-srcBegin}). The characters are copied into the
867 * subarray of {@code dst} starting at index {@code dstBegin}
868 * and ending at index:
869 * <blockquote><pre>
870 * dstBegin + (srcEnd-srcBegin) - 1
871 * </pre></blockquote>
872 *
873 * @param srcBegin index of the first character in the string
874 * to copy.
875 * @param srcEnd index after the last character in the string
876 * to copy.
877 * @param dst the destination array.
878 * @param dstBegin the start offset in the destination array.
879 * @exception IndexOutOfBoundsException If any of the following
880 * is true:
881 * <ul><li>{@code srcBegin} is negative.
882 * <li>{@code srcBegin} is greater than {@code srcEnd}
883 * <li>{@code srcEnd} is greater than the length of this
884 * string
885 * <li>{@code dstBegin} is negative
886 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
887 * {@code dst.length}</ul>
888 */
889 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
890 checkBoundsBeginEnd(srcBegin, srcEnd, length());
891 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
892 if (isLatin1()) {
893 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin);
894 } else {
895 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin);
896 }
897 }
898
899 /**
900 * Copies characters from this string into the destination byte array. Each
901 * byte receives the 8 low-order bits of the corresponding character. The
902 * eight high-order bits of each character are not copied and do not
903 * participate in the transfer in any way.
904 *
905 * <p> The first character to be copied is at index {@code srcBegin}; the
906 * last character to be copied is at index {@code srcEnd-1}. The total
907 * number of characters to be copied is {@code srcEnd-srcBegin}. The
908 * characters, converted to bytes, are copied into the subarray of {@code
909 * dst} starting at index {@code dstBegin} and ending at index:
910 *
911 * <blockquote><pre>
912 * dstBegin + (srcEnd-srcBegin) - 1
913 * </pre></blockquote>
914 *
915 * @deprecated This method does not properly convert characters into
916 * bytes. As of JDK 1.1, the preferred way to do this is via the
917 * {@link #getBytes()} method, which uses the platform's default charset.
918 *
919 * @param srcBegin
920 * Index of the first character in the string to copy
921 *
922 * @param srcEnd
923 * Index after the last character in the string to copy
924 *
925 * @param dst
926 * The destination array
927 *
928 * @param dstBegin
929 * The start offset in the destination array
930 *
931 * @throws IndexOutOfBoundsException
932 * If any of the following is true:
933 * <ul>
934 * <li> {@code srcBegin} is negative
935 * <li> {@code srcBegin} is greater than {@code srcEnd}
936 * <li> {@code srcEnd} is greater than the length of this String
937 * <li> {@code dstBegin} is negative
938 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
939 * dst.length}
940 * </ul>
941 */
942 @Deprecated(since="1.1")
943 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
944 checkBoundsBeginEnd(srcBegin, srcEnd, length());
945 Objects.requireNonNull(dst);
946 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
947 if (isLatin1()) {
948 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
949 } else {
950 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
951 }
952 }
953
954 /**
955 * Encodes this {@code String} into a sequence of bytes using the named
956 * charset, storing the result into a new byte array.
957 *
958 * <p> The behavior of this method when this string cannot be encoded in
959 * the given charset is unspecified. The {@link
960 * java.nio.charset.CharsetEncoder} class should be used when more control
961 * over the encoding process is required.
962 *
963 * @param charsetName
964 * The name of a supported {@linkplain java.nio.charset.Charset
965 * charset}
966 *
967 * @return The resultant byte array
968 *
969 * @throws UnsupportedEncodingException
970 * If the named charset is not supported
971 *
972 * @since 1.1
973 */
974 public byte[] getBytes(String charsetName)
975 throws UnsupportedEncodingException {
976 if (charsetName == null) throw new NullPointerException();
977 return StringCoder.encode(charsetName, coder(), value);
978 }
979
980 /**
981 * Encodes this {@code String} into a sequence of bytes using the given
982 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
983 * new byte array.
984 *
985 * <p> This method always replaces malformed-input and unmappable-character
986 * sequences with this charset's default replacement byte array. The
987 * {@link java.nio.charset.CharsetEncoder} class should be used when more
988 * control over the encoding process is required.
989 *
990 * @param charset
991 * The {@linkplain java.nio.charset.Charset} to be used to encode
992 * the {@code String}
993 *
994 * @return The resultant byte array
995 *
996 * @since 1.6
997 */
998 public byte[] getBytes(Charset charset) {
999 if (charset == null) throw new NullPointerException();
1000 return StringCoder.encode(charset, coder(), value);
1001 }
1002
1003 /**
1004 * Encodes characters from this string into a sequence of bytes using the given
1005 * {@linkplain java.nio.charset.Charset charset}, storing the result into the
1006 * given destination {@linkplain java.nio.ByteBuffer byte buffer}.
1007 *
1008 * <p> The first character to be encoded is at index {@code srcBegin};
1009 * the last character to be encoded is at index {@code srcEnd-1}. At most
1010 * {@code srcEnd-srcBegin}) of characters will be encoded, and at most
1011 * {@link java.nio.Buffer#remaining dstBuffer.remaining()} bytes will be written.
1012 * The position of the {@code dstBuffer} will be advanced to reflect the bytes
1013 * written, but its mark and limit will not be modified.
1014 *
1015 * <p> This method always replaces malformed-input and unmappable-character
1016 * sequences with this charset's default replacement string. The {@link
1017 * java.nio.charset.CharsetDecoder} class should be used when more control
1018 * over the decoding process is required.
1019 *
1020 * @param srcBegin
1021 * index of the first character in the string to encode
1022 * @param srcEnd
1023 * index after the last character in the string to encode
1024 * @param dstBuffer
1025 * The destination {@linkplain java.nio.ByteBuffer}
1026 * @param charset
1027 * The {@linkplain java.nio.charset.Charset} to be used to encode
1028 * the {@code String}
1029 * @return the number of characters encoded into the {code dstBuffer};
1030 *
1031 * @since 11
1032 */
1033 public int getBytes(int srcBegin, int srcEnd, ByteBuffer dstBuffer, Charset charset) {
1034 Objects.requireNonNull(dstBuffer);
1035 Objects.requireNonNull(charset);
1036 checkBoundsBeginEnd(srcBegin, srcEnd, length());
1037 return StringCoder.encode(charset, coder(), value, srcBegin, srcEnd, dstBuffer);
1038 }
1039
1040 /**
1041 * Encodes this {@code String} into a sequence of bytes using the
1042 * platform's default charset, storing the result into a new byte array.
1043 *
1044 * <p> The behavior of this method when this string cannot be encoded in
1045 * the default charset is unspecified. The {@link
1046 * java.nio.charset.CharsetEncoder} class should be used when more control
1047 * over the encoding process is required.
1048 *
1049 * @return The resultant byte array
1050 *
1051 * @since 1.1
1052 */
1053 public byte[] getBytes() {
1054 return StringCoder.encode(coder(), value);
1055 }
1056
1057 /**
1058 * Compares this string to the specified object. The result is {@code
1059 * true} if and only if the argument is not {@code null} and is a {@code
1060 * String} object that represents the same sequence of characters as this
1061 * object.
1062 *
1063 * <p>For finer-grained String comparison, refer to
1064 * {@link java.text.Collator}.
1065 *
1066 * @param anObject
1067 * The object to compare this {@code String} against
1068 *
1069 * @return {@code true} if the given object represents a {@code String}
1070 * equivalent to this string, {@code false} otherwise
1071 *
1072 * @see #compareTo(String)
1073 * @see #equalsIgnoreCase(String)
1074 */
1075 public boolean equals(Object anObject) {
1076 if (this == anObject) {
1077 return true;
1078 }
1079 if (anObject instanceof String) {
1080 String aString = (String)anObject;
1081 if (coder() == aString.coder()) {
1082 return isLatin1() ? StringLatin1.equals(value, aString.value)
1083 : StringUTF16.equals(value, aString.value);
1084 }
1085 }
1086 return false;
1087 }
1088
1089 /**
1090 * Compares this string to the specified {@code StringBuffer}. The result
1091 * is {@code true} if and only if this {@code String} represents the same
1092 * sequence of characters as the specified {@code StringBuffer}. This method
1093 * synchronizes on the {@code StringBuffer}.
1094 *
1095 * <p>For finer-grained String comparison, refer to
1096 * {@link java.text.Collator}.
1097 *
1098 * @param sb
1099 * The {@code StringBuffer} to compare this {@code String} against
1100 *
1101 * @return {@code true} if this {@code String} represents the same
1102 * sequence of characters as the specified {@code StringBuffer},
1103 * {@code false} otherwise
1104 *
1105 * @since 1.4
1106 */
1107 public boolean contentEquals(StringBuffer sb) {
1108 return contentEquals((CharSequence)sb);
1109 }
1110
1111 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1112 int len = length();
1113 if (len != sb.length()) {
1114 return false;
1115 }
1116 byte v1[] = value;
1117 byte v2[] = sb.getValue();
1118 if (coder() == sb.getCoder()) {
1119 int n = v1.length;
1120 for (int i = 0; i < n; i++) {
1121 if (v1[i] != v2[i]) {
1122 return false;
1123 }
1124 }
1125 } else {
1126 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal"
1127 return false;
1128 }
1129 return StringUTF16.contentEquals(v1, v2, len);
1130 }
1131 return true;
1132 }
1133
1134 /**
1135 * Compares this string to the specified {@code CharSequence}. The
1136 * result is {@code true} if and only if this {@code String} represents the
1137 * same sequence of char values as the specified sequence. Note that if the
1138 * {@code CharSequence} is a {@code StringBuffer} then the method
1139 * synchronizes on it.
1140 *
1141 * <p>For finer-grained String comparison, refer to
1142 * {@link java.text.Collator}.
1143 *
1144 * @param cs
1145 * The sequence to compare this {@code String} against
1146 *
1147 * @return {@code true} if this {@code String} represents the same
1148 * sequence of char values as the specified sequence, {@code
1149 * false} otherwise
1150 *
1151 * @since 1.5
1152 */
1153 public boolean contentEquals(CharSequence cs) {
1154 // Argument is a StringBuffer, StringBuilder
1155 if (cs instanceof AbstractStringBuilder) {
1156 if (cs instanceof StringBuffer) {
1157 synchronized(cs) {
1158 return nonSyncContentEquals((AbstractStringBuilder)cs);
1159 }
1160 } else {
1161 return nonSyncContentEquals((AbstractStringBuilder)cs);
1162 }
1163 }
1164 // Argument is a String
1165 if (cs instanceof String) {
1166 return equals(cs);
1167 }
1168 // Argument is a generic CharSequence
1169 int n = cs.length();
1170 if (n != length()) {
1171 return false;
1172 }
1173 byte[] val = this.value;
1174 if (isLatin1()) {
1175 for (int i = 0; i < n; i++) {
1176 if ((val[i] & 0xff) != cs.charAt(i)) {
1177 return false;
1178 }
1179 }
1180 } else {
1181 if (!StringUTF16.contentEquals(val, cs, n)) {
1182 return false;
1183 }
1184 }
1185 return true;
1186 }
1187
1188 /**
1189 * Compares this {@code String} to another {@code String}, ignoring case
1190 * considerations. Two strings are considered equal ignoring case if they
1191 * are of the same length and corresponding characters in the two strings
1192 * are equal ignoring case.
1193 *
1194 * <p> Two characters {@code c1} and {@code c2} are considered the same
1195 * ignoring case if at least one of the following is true:
1196 * <ul>
1197 * <li> The two characters are the same (as compared by the
1198 * {@code ==} operator)
1199 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))}
1200 * on each character produces the same result
1201 * </ul>
1202 *
1203 * <p>Note that this method does <em>not</em> take locale into account, and
1204 * will result in unsatisfactory results for certain locales. The
1205 * {@link java.text.Collator} class provides locale-sensitive comparison.
1206 *
1207 * @param anotherString
1208 * The {@code String} to compare this {@code String} against
1209 *
1210 * @return {@code true} if the argument is not {@code null} and it
1211 * represents an equivalent {@code String} ignoring case; {@code
1212 * false} otherwise
1213 *
1214 * @see #equals(Object)
1215 */
1216 public boolean equalsIgnoreCase(String anotherString) {
1217 return (this == anotherString) ? true
1218 : (anotherString != null)
1219 && (anotherString.length() == length())
1220 && regionMatches(true, 0, anotherString, 0, length());
1221 }
1222
1223 /**
1224 * Compares two strings lexicographically.
1225 * The comparison is based on the Unicode value of each character in
1226 * the strings. The character sequence represented by this
1227 * {@code String} object is compared lexicographically to the
1228 * character sequence represented by the argument string. The result is
1229 * a negative integer if this {@code String} object
1230 * lexicographically precedes the argument string. The result is a
1231 * positive integer if this {@code String} object lexicographically
1232 * follows the argument string. The result is zero if the strings
1233 * are equal; {@code compareTo} returns {@code 0} exactly when
1234 * the {@link #equals(Object)} method would return {@code true}.
1235 * <p>
1236 * This is the definition of lexicographic ordering. If two strings are
1237 * different, then either they have different characters at some index
1238 * that is a valid index for both strings, or their lengths are different,
1239 * or both. If they have different characters at one or more index
1240 * positions, let <i>k</i> be the smallest such index; then the string
1241 * whose character at position <i>k</i> has the smaller value, as
1242 * determined by using the {@code <} operator, lexicographically precedes the
1243 * other string. In this case, {@code compareTo} returns the
1244 * difference of the two character values at position {@code k} in
1245 * the two string -- that is, the value:
1246 * <blockquote><pre>
1247 * this.charAt(k)-anotherString.charAt(k)
1248 * </pre></blockquote>
1249 * If there is no index position at which they differ, then the shorter
1250 * string lexicographically precedes the longer string. In this case,
1251 * {@code compareTo} returns the difference of the lengths of the
1252 * strings -- that is, the value:
1253 * <blockquote><pre>
1254 * this.length()-anotherString.length()
1255 * </pre></blockquote>
1256 *
1257 * <p>For finer-grained String comparison, refer to
1258 * {@link java.text.Collator}.
1259 *
1260 * @param anotherString the {@code String} to be compared.
1261 * @return the value {@code 0} if the argument string is equal to
1262 * this string; a value less than {@code 0} if this string
1263 * is lexicographically less than the string argument; and a
1264 * value greater than {@code 0} if this string is
1265 * lexicographically greater than the string argument.
1266 */
1267 public int compareTo(String anotherString) {
1268 byte v1[] = value;
1269 byte v2[] = anotherString.value;
1270 if (coder() == anotherString.coder()) {
1271 return isLatin1() ? StringLatin1.compareTo(v1, v2)
1272 : StringUTF16.compareTo(v1, v2);
1273 }
1274 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2)
1275 : StringUTF16.compareToLatin1(v1, v2);
1276 }
1277
1278 /**
1279 * A Comparator that orders {@code String} objects as by
1280 * {@code compareToIgnoreCase}. This comparator is serializable.
1281 * <p>
1282 * Note that this Comparator does <em>not</em> take locale into account,
1283 * and will result in an unsatisfactory ordering for certain locales.
1284 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1285 *
1286 * @see java.text.Collator
1287 * @since 1.2
1288 */
1289 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1290 = new CaseInsensitiveComparator();
1291 private static class CaseInsensitiveComparator
1292 implements Comparator<String>, java.io.Serializable {
1293 // use serialVersionUID from JDK 1.2.2 for interoperability
1294 private static final long serialVersionUID = 8575799808933029326L;
1295
1296 public int compare(String s1, String s2) {
1297 byte v1[] = s1.value;
1298 byte v2[] = s2.value;
1299 if (s1.coder() == s2.coder()) {
1300 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2)
1301 : StringUTF16.compareToCI(v1, v2);
1302 }
1303 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2)
1304 : StringUTF16.compareToCI_Latin1(v1, v2);
1305 }
1306
1307 /** Replaces the de-serialized object. */
1308 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1309 }
1310
1311 /**
1312 * Compares two strings lexicographically, ignoring case
1313 * differences. This method returns an integer whose sign is that of
1314 * calling {@code compareTo} with normalized versions of the strings
1315 * where case differences have been eliminated by calling
1316 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1317 * each character.
1318 * <p>
1319 * Note that this method does <em>not</em> take locale into account,
1320 * and will result in an unsatisfactory ordering for certain locales.
1321 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1322 *
1323 * @param str the {@code String} to be compared.
1324 * @return a negative integer, zero, or a positive integer as the
1325 * specified String is greater than, equal to, or less
1326 * than this String, ignoring case considerations.
1327 * @see java.text.Collator
1328 * @since 1.2
1329 */
1330 public int compareToIgnoreCase(String str) {
1331 return CASE_INSENSITIVE_ORDER.compare(this, str);
1332 }
1333
1334 /**
1335 * Tests if two string regions are equal.
1336 * <p>
1337 * A substring of this {@code String} object is compared to a substring
1338 * of the argument other. The result is true if these substrings
1339 * represent identical character sequences. The substring of this
1340 * {@code String} object to be compared begins at index {@code toffset}
1341 * and has length {@code len}. The substring of other to be compared
1342 * begins at index {@code ooffset} and has length {@code len}. The
1343 * result is {@code false} if and only if at least one of the following
1344 * is true:
1345 * <ul><li>{@code toffset} is negative.
1346 * <li>{@code ooffset} is negative.
1347 * <li>{@code toffset+len} is greater than the length of this
1348 * {@code String} object.
1349 * <li>{@code ooffset+len} is greater than the length of the other
1350 * argument.
1351 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1352 * such that:
1353 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1354 * <i>k</i>{@code )}
1355 * </ul>
1356 *
1357 * <p>Note that this method does <em>not</em> take locale into account. The
1358 * {@link java.text.Collator} class provides locale-sensitive comparison.
1359 *
1360 * @param toffset the starting offset of the subregion in this string.
1361 * @param other the string argument.
1362 * @param ooffset the starting offset of the subregion in the string
1363 * argument.
1364 * @param len the number of characters to compare.
1365 * @return {@code true} if the specified subregion of this string
1366 * exactly matches the specified subregion of the string argument;
1367 * {@code false} otherwise.
1368 */
1369 public boolean regionMatches(int toffset, String other, int ooffset, int len) {
1370 byte tv[] = value;
1371 byte ov[] = other.value;
1372 // Note: toffset, ooffset, or len might be near -1>>>1.
1373 if ((ooffset < 0) || (toffset < 0) ||
1374 (toffset > (long)length() - len) ||
1375 (ooffset > (long)other.length() - len)) {
1376 return false;
1377 }
1378 if (coder() == other.coder()) {
1379 if (!isLatin1() && (len > 0)) {
1380 toffset = toffset << 1;
1381 ooffset = ooffset << 1;
1382 len = len << 1;
1383 }
1384 while (len-- > 0) {
1385 if (tv[toffset++] != ov[ooffset++]) {
1386 return false;
1387 }
1388 }
1389 } else {
1390 if (coder() == LATIN1) {
1391 while (len-- > 0) {
1392 if (StringLatin1.getChar(tv, toffset++) !=
1393 StringUTF16.getChar(ov, ooffset++)) {
1394 return false;
1395 }
1396 }
1397 } else {
1398 while (len-- > 0) {
1399 if (StringUTF16.getChar(tv, toffset++) !=
1400 StringLatin1.getChar(ov, ooffset++)) {
1401 return false;
1402 }
1403 }
1404 }
1405 }
1406 return true;
1407 }
1408
1409 /**
1410 * Tests if two string regions are equal.
1411 * <p>
1412 * A substring of this {@code String} object is compared to a substring
1413 * of the argument {@code other}. The result is {@code true} if these
1414 * substrings represent character sequences that are the same, ignoring
1415 * case if and only if {@code ignoreCase} is true. The substring of
1416 * this {@code String} object to be compared begins at index
1417 * {@code toffset} and has length {@code len}. The substring of
1418 * {@code other} to be compared begins at index {@code ooffset} and
1419 * has length {@code len}. The result is {@code false} if and only if
1420 * at least one of the following is true:
1421 * <ul><li>{@code toffset} is negative.
1422 * <li>{@code ooffset} is negative.
1423 * <li>{@code toffset+len} is greater than the length of this
1424 * {@code String} object.
1425 * <li>{@code ooffset+len} is greater than the length of the other
1426 * argument.
1427 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1428 * integer <i>k</i> less than {@code len} such that:
1429 * <blockquote><pre>
1430 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1431 * </pre></blockquote>
1432 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1433 * integer <i>k</i> less than {@code len} such that:
1434 * <blockquote><pre>
1435 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) !=
1436 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k)))
1437 * </pre></blockquote>
1438 * </ul>
1439 *
1440 * <p>Note that this method does <em>not</em> take locale into account,
1441 * and will result in unsatisfactory results for certain locales when
1442 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class
1443 * provides locale-sensitive comparison.
1444 *
1445 * @param ignoreCase if {@code true}, ignore case when comparing
1446 * characters.
1447 * @param toffset the starting offset of the subregion in this
1448 * string.
1449 * @param other the string argument.
1450 * @param ooffset the starting offset of the subregion in the string
1451 * argument.
1452 * @param len the number of characters to compare.
1453 * @return {@code true} if the specified subregion of this string
1454 * matches the specified subregion of the string argument;
1455 * {@code false} otherwise. Whether the matching is exact
1456 * or case insensitive depends on the {@code ignoreCase}
1457 * argument.
1458 */
1459 public boolean regionMatches(boolean ignoreCase, int toffset,
1460 String other, int ooffset, int len) {
1461 if (!ignoreCase) {
1462 return regionMatches(toffset, other, ooffset, len);
1463 }
1464 // Note: toffset, ooffset, or len might be near -1>>>1.
1465 if ((ooffset < 0) || (toffset < 0)
1466 || (toffset > (long)length() - len)
1467 || (ooffset > (long)other.length() - len)) {
1468 return false;
1469 }
1470 byte tv[] = value;
1471 byte ov[] = other.value;
1472 if (coder() == other.coder()) {
1473 return isLatin1()
1474 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len)
1475 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len);
1476 }
1477 return isLatin1()
1478 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len)
1479 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len);
1480 }
1481
1482 /**
1483 * Tests if the substring of this string beginning at the
1484 * specified index starts with the specified prefix.
1485 *
1486 * @param prefix the prefix.
1487 * @param toffset where to begin looking in this string.
1488 * @return {@code true} if the character sequence represented by the
1489 * argument is a prefix of the substring of this object starting
1490 * at index {@code toffset}; {@code false} otherwise.
1491 * The result is {@code false} if {@code toffset} is
1492 * negative or greater than the length of this
1493 * {@code String} object; otherwise the result is the same
1494 * as the result of the expression
1495 * <pre>
1496 * this.substring(toffset).startsWith(prefix)
1497 * </pre>
1498 */
1499 public boolean startsWith(String prefix, int toffset) {
1500 // Note: toffset might be near -1>>>1.
1501 if (toffset < 0 || toffset > length() - prefix.length()) {
1502 return false;
1503 }
1504 byte ta[] = value;
1505 byte pa[] = prefix.value;
1506 int po = 0;
1507 int pc = pa.length;
1508 if (coder() == prefix.coder()) {
1509 int to = isLatin1() ? toffset : toffset << 1;
1510 while (po < pc) {
1511 if (ta[to++] != pa[po++]) {
1512 return false;
1513 }
1514 }
1515 } else {
1516 if (isLatin1()) { // && pcoder == UTF16
1517 return false;
1518 }
1519 // coder == UTF16 && pcoder == LATIN1)
1520 while (po < pc) {
1521 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) {
1522 return false;
1523 }
1524 }
1525 }
1526 return true;
1527 }
1528
1529 /**
1530 * Tests if this string starts with the specified prefix.
1531 *
1532 * @param prefix the prefix.
1533 * @return {@code true} if the character sequence represented by the
1534 * argument is a prefix of the character sequence represented by
1535 * this string; {@code false} otherwise.
1536 * Note also that {@code true} will be returned if the
1537 * argument is an empty string or is equal to this
1538 * {@code String} object as determined by the
1539 * {@link #equals(Object)} method.
1540 * @since 1.0
1541 */
1542 public boolean startsWith(String prefix) {
1543 return startsWith(prefix, 0);
1544 }
1545
1546 /**
1547 * Tests if this string ends with the specified suffix.
1548 *
1549 * @param suffix the suffix.
1550 * @return {@code true} if the character sequence represented by the
1551 * argument is a suffix of the character sequence represented by
1552 * this object; {@code false} otherwise. Note that the
1553 * result will be {@code true} if the argument is the
1554 * empty string or is equal to this {@code String} object
1555 * as determined by the {@link #equals(Object)} method.
1556 */
1557 public boolean endsWith(String suffix) {
1558 return startsWith(suffix, length() - suffix.length());
1559 }
1560
1561 /**
1562 * Returns a hash code for this string. The hash code for a
1563 * {@code String} object is computed as
1564 * <blockquote><pre>
1565 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1566 * </pre></blockquote>
1567 * using {@code int} arithmetic, where {@code s[i]} is the
1568 * <i>i</i>th character of the string, {@code n} is the length of
1569 * the string, and {@code ^} indicates exponentiation.
1570 * (The hash value of the empty string is zero.)
1571 *
1572 * @return a hash code value for this object.
1573 */
1574 public int hashCode() {
1575 int h = hash;
1576 if (h == 0 && value.length > 0) {
1577 hash = h = isLatin1() ? StringLatin1.hashCode(value)
1578 : StringUTF16.hashCode(value);
1579 }
1580 return h;
1581 }
1582
1583 /**
1584 * Returns the index within this string of the first occurrence of
1585 * the specified character. If a character with value
1586 * {@code ch} occurs in the character sequence represented by
1587 * this {@code String} object, then the index (in Unicode
1588 * code units) of the first such occurrence is returned. For
1589 * values of {@code ch} in the range from 0 to 0xFFFF
1590 * (inclusive), this is the smallest value <i>k</i> such that:
1591 * <blockquote><pre>
1592 * this.charAt(<i>k</i>) == ch
1593 * </pre></blockquote>
1594 * is true. For other values of {@code ch}, it is the
1595 * smallest value <i>k</i> such that:
1596 * <blockquote><pre>
1597 * this.codePointAt(<i>k</i>) == ch
1598 * </pre></blockquote>
1599 * is true. In either case, if no such character occurs in this
1600 * string, then {@code -1} is returned.
1601 *
1602 * @param ch a character (Unicode code point).
1603 * @return the index of the first occurrence of the character in the
1604 * character sequence represented by this object, or
1605 * {@code -1} if the character does not occur.
1606 */
1607 public int indexOf(int ch) {
1608 return indexOf(ch, 0);
1609 }
1610
1611 /**
1612 * Returns the index within this string of the first occurrence of the
1613 * specified character, starting the search at the specified index.
1614 * <p>
1615 * If a character with value {@code ch} occurs in the
1616 * character sequence represented by this {@code String}
1617 * object at an index no smaller than {@code fromIndex}, then
1618 * the index of the first such occurrence is returned. For values
1619 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1620 * this is the smallest value <i>k</i> such that:
1621 * <blockquote><pre>
1622 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1623 * </pre></blockquote>
1624 * is true. For other values of {@code ch}, it is the
1625 * smallest value <i>k</i> such that:
1626 * <blockquote><pre>
1627 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1628 * </pre></blockquote>
1629 * is true. In either case, if no such character occurs in this
1630 * string at or after position {@code fromIndex}, then
1631 * {@code -1} is returned.
1632 *
1633 * <p>
1634 * There is no restriction on the value of {@code fromIndex}. If it
1635 * is negative, it has the same effect as if it were zero: this entire
1636 * string may be searched. If it is greater than the length of this
1637 * string, it has the same effect as if it were equal to the length of
1638 * this string: {@code -1} is returned.
1639 *
1640 * <p>All indices are specified in {@code char} values
1641 * (Unicode code units).
1642 *
1643 * @param ch a character (Unicode code point).
1644 * @param fromIndex the index to start the search from.
1645 * @return the index of the first occurrence of the character in the
1646 * character sequence represented by this object that is greater
1647 * than or equal to {@code fromIndex}, or {@code -1}
1648 * if the character does not occur.
1649 */
1650 public int indexOf(int ch, int fromIndex) {
1651 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex)
1652 : StringUTF16.indexOf(value, ch, fromIndex);
1653 }
1654
1655 /**
1656 * Returns the index within this string of the last occurrence of
1657 * the specified character. For values of {@code ch} in the
1658 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1659 * units) returned is the largest value <i>k</i> such that:
1660 * <blockquote><pre>
1661 * this.charAt(<i>k</i>) == ch
1662 * </pre></blockquote>
1663 * is true. For other values of {@code ch}, it is the
1664 * largest value <i>k</i> such that:
1665 * <blockquote><pre>
1666 * this.codePointAt(<i>k</i>) == ch
1667 * </pre></blockquote>
1668 * is true. In either case, if no such character occurs in this
1669 * string, then {@code -1} is returned. The
1670 * {@code String} is searched backwards starting at the last
1671 * character.
1672 *
1673 * @param ch a character (Unicode code point).
1674 * @return the index of the last occurrence of the character in the
1675 * character sequence represented by this object, or
1676 * {@code -1} if the character does not occur.
1677 */
1678 public int lastIndexOf(int ch) {
1679 return lastIndexOf(ch, length() - 1);
1680 }
1681
1682 /**
1683 * Returns the index within this string of the last occurrence of
1684 * the specified character, searching backward starting at the
1685 * specified index. For values of {@code ch} in the range
1686 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1687 * value <i>k</i> such that:
1688 * <blockquote><pre>
1689 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1690 * </pre></blockquote>
1691 * is true. For other values of {@code ch}, it is the
1692 * largest value <i>k</i> such that:
1693 * <blockquote><pre>
1694 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1695 * </pre></blockquote>
1696 * is true. In either case, if no such character occurs in this
1697 * string at or before position {@code fromIndex}, then
1698 * {@code -1} is returned.
1699 *
1700 * <p>All indices are specified in {@code char} values
1701 * (Unicode code units).
1702 *
1703 * @param ch a character (Unicode code point).
1704 * @param fromIndex the index to start the search from. There is no
1705 * restriction on the value of {@code fromIndex}. If it is
1706 * greater than or equal to the length of this string, it has
1707 * the same effect as if it were equal to one less than the
1708 * length of this string: this entire string may be searched.
1709 * If it is negative, it has the same effect as if it were -1:
1710 * -1 is returned.
1711 * @return the index of the last occurrence of the character in the
1712 * character sequence represented by this object that is less
1713 * than or equal to {@code fromIndex}, or {@code -1}
1714 * if the character does not occur before that point.
1715 */
1716 public int lastIndexOf(int ch, int fromIndex) {
1717 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex)
1718 : StringUTF16.lastIndexOf(value, ch, fromIndex);
1719 }
1720
1721 /**
1722 * Returns the index within this string of the first occurrence of the
1723 * specified substring.
1724 *
1725 * <p>The returned index is the smallest value {@code k} for which:
1726 * <pre>{@code
1727 * this.startsWith(str, k)
1728 * }</pre>
1729 * If no such value of {@code k} exists, then {@code -1} is returned.
1730 *
1731 * @param str the substring to search for.
1732 * @return the index of the first occurrence of the specified substring,
1733 * or {@code -1} if there is no such occurrence.
1734 */
1735 public int indexOf(String str) {
1736 if (coder() == str.coder()) {
1737 return isLatin1() ? StringLatin1.indexOf(value, str.value)
1738 : StringUTF16.indexOf(value, str.value);
1739 }
1740 if (coder() == LATIN1) { // str.coder == UTF16
1741 return -1;
1742 }
1743 return StringUTF16.indexOfLatin1(value, str.value);
1744 }
1745
1746 /**
1747 * Returns the index within this string of the first occurrence of the
1748 * specified substring, starting at the specified index.
1749 *
1750 * <p>The returned index is the smallest value {@code k} for which:
1751 * <pre>{@code
1752 * k >= Math.min(fromIndex, this.length()) &&
1753 * this.startsWith(str, k)
1754 * }</pre>
1755 * If no such value of {@code k} exists, then {@code -1} is returned.
1756 *
1757 * @param str the substring to search for.
1758 * @param fromIndex the index from which to start the search.
1759 * @return the index of the first occurrence of the specified substring,
1760 * starting at the specified index,
1761 * or {@code -1} if there is no such occurrence.
1762 */
1763 public int indexOf(String str, int fromIndex) {
1764 return indexOf(value, coder(), length(), str, fromIndex);
1765 }
1766
1767 /**
1768 * Code shared by String and AbstractStringBuilder to do searches. The
1769 * source is the character array being searched, and the target
1770 * is the string being searched for.
1771 *
1772 * @param src the characters being searched.
1773 * @param srcCoder the coder of the source string.
1774 * @param srcCount length of the source string.
1775 * @param tgtStr the characters being searched for.
1776 * @param fromIndex the index to begin searching from.
1777 */
1778 static int indexOf(byte[] src, byte srcCoder, int srcCount,
1779 String tgtStr, int fromIndex) {
1780 byte[] tgt = tgtStr.value;
1781 byte tgtCoder = tgtStr.coder();
1782 int tgtCount = tgtStr.length();
1783
1784 if (fromIndex >= srcCount) {
1785 return (tgtCount == 0 ? srcCount : -1);
1786 }
1787 if (fromIndex < 0) {
1788 fromIndex = 0;
1789 }
1790 if (tgtCount == 0) {
1791 return fromIndex;
1792 }
1793 if (tgtCount > srcCount) {
1794 return -1;
1795 }
1796 if (srcCoder == tgtCoder) {
1797 return srcCoder == LATIN1
1798 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex)
1799 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex);
1800 }
1801 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1802 return -1;
1803 }
1804 // srcCoder == UTF16 && tgtCoder == LATIN1) {
1805 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1806 }
1807
1808 /**
1809 * Returns the index within this string of the last occurrence of the
1810 * specified substring. The last occurrence of the empty string ""
1811 * is considered to occur at the index value {@code this.length()}.
1812 *
1813 * <p>The returned index is the largest value {@code k} for which:
1814 * <pre>{@code
1815 * this.startsWith(str, k)
1816 * }</pre>
1817 * If no such value of {@code k} exists, then {@code -1} is returned.
1818 *
1819 * @param str the substring to search for.
1820 * @return the index of the last occurrence of the specified substring,
1821 * or {@code -1} if there is no such occurrence.
1822 */
1823 public int lastIndexOf(String str) {
1824 return lastIndexOf(str, length());
1825 }
1826
1827 /**
1828 * Returns the index within this string of the last occurrence of the
1829 * specified substring, searching backward starting at the specified index.
1830 *
1831 * <p>The returned index is the largest value {@code k} for which:
1832 * <pre>{@code
1833 * k <= Math.min(fromIndex, this.length()) &&
1834 * this.startsWith(str, k)
1835 * }</pre>
1836 * If no such value of {@code k} exists, then {@code -1} is returned.
1837 *
1838 * @param str the substring to search for.
1839 * @param fromIndex the index to start the search from.
1840 * @return the index of the last occurrence of the specified substring,
1841 * searching backward from the specified index,
1842 * or {@code -1} if there is no such occurrence.
1843 */
1844 public int lastIndexOf(String str, int fromIndex) {
1845 return lastIndexOf(value, coder(), length(), str, fromIndex);
1846 }
1847
1848 /**
1849 * Code shared by String and AbstractStringBuilder to do searches. The
1850 * source is the character array being searched, and the target
1851 * is the string being searched for.
1852 *
1853 * @param src the characters being searched.
1854 * @param srcCoder coder handles the mapping between bytes/chars
1855 * @param srcCount count of the source string.
1856 * @param tgt the characters being searched for.
1857 * @param fromIndex the index to begin searching from.
1858 */
1859 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount,
1860 String tgtStr, int fromIndex) {
1861 byte[] tgt = tgtStr.value;
1862 byte tgtCoder = tgtStr.coder();
1863 int tgtCount = tgtStr.length();
1864 /*
1865 * Check arguments; return immediately where possible. For
1866 * consistency, don't check for null str.
1867 */
1868 int rightIndex = srcCount - tgtCount;
1869 if (fromIndex > rightIndex) {
1870 fromIndex = rightIndex;
1871 }
1872 if (fromIndex < 0) {
1873 return -1;
1874 }
1875 /* Empty string always matches. */
1876 if (tgtCount == 0) {
1877 return fromIndex;
1878 }
1879 if (srcCoder == tgtCoder) {
1880 return srcCoder == LATIN1
1881 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex)
1882 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex);
1883 }
1884 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1885 return -1;
1886 }
1887 // srcCoder == UTF16 && tgtCoder == LATIN1
1888 return StringUTF16.lastIndexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1889 }
1890
1891 /**
1892 * Returns a string that is a substring of this string. The
1893 * substring begins with the character at the specified index and
1894 * extends to the end of this string. <p>
1895 * Examples:
1896 * <blockquote><pre>
1897 * "unhappy".substring(2) returns "happy"
1898 * "Harbison".substring(3) returns "bison"
1899 * "emptiness".substring(9) returns "" (an empty string)
1900 * </pre></blockquote>
1901 *
1902 * @param beginIndex the beginning index, inclusive.
1903 * @return the specified substring.
1904 * @exception IndexOutOfBoundsException if
1905 * {@code beginIndex} is negative or larger than the
1906 * length of this {@code String} object.
1907 */
1908 public String substring(int beginIndex) {
1909 if (beginIndex < 0) {
1910 throw new StringIndexOutOfBoundsException(beginIndex);
1911 }
1912 int subLen = length() - beginIndex;
1913 if (subLen < 0) {
1914 throw new StringIndexOutOfBoundsException(subLen);
1915 }
1916 if (beginIndex == 0) {
1917 return this;
1918 }
1919 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1920 : StringUTF16.newString(value, beginIndex, subLen);
1921 }
1922
1923 /**
1924 * Returns a string that is a substring of this string. The
1925 * substring begins at the specified {@code beginIndex} and
1926 * extends to the character at index {@code endIndex - 1}.
1927 * Thus the length of the substring is {@code endIndex-beginIndex}.
1928 * <p>
1929 * Examples:
1930 * <blockquote><pre>
1931 * "hamburger".substring(4, 8) returns "urge"
1932 * "smiles".substring(1, 5) returns "mile"
1933 * </pre></blockquote>
1934 *
1935 * @param beginIndex the beginning index, inclusive.
1936 * @param endIndex the ending index, exclusive.
1937 * @return the specified substring.
1938 * @exception IndexOutOfBoundsException if the
1939 * {@code beginIndex} is negative, or
1940 * {@code endIndex} is larger than the length of
1941 * this {@code String} object, or
1942 * {@code beginIndex} is larger than
1943 * {@code endIndex}.
1944 */
1945 public String substring(int beginIndex, int endIndex) {
1946 int length = length();
1947 checkBoundsBeginEnd(beginIndex, endIndex, length);
1948 int subLen = endIndex - beginIndex;
1949 if (beginIndex == 0 && endIndex == length) {
1950 return this;
1951 }
1952 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1953 : StringUTF16.newString(value, beginIndex, subLen);
1954 }
1955
1956 /**
1957 * Returns a character sequence that is a subsequence of this sequence.
1958 *
1959 * <p> An invocation of this method of the form
1960 *
1961 * <blockquote><pre>
1962 * str.subSequence(begin, end)</pre></blockquote>
1963 *
1964 * behaves in exactly the same way as the invocation
1965 *
1966 * <blockquote><pre>
1967 * str.substring(begin, end)</pre></blockquote>
1968 *
1969 * @apiNote
1970 * This method is defined so that the {@code String} class can implement
1971 * the {@link CharSequence} interface.
1972 *
1973 * @param beginIndex the begin index, inclusive.
1974 * @param endIndex the end index, exclusive.
1975 * @return the specified subsequence.
1976 *
1977 * @throws IndexOutOfBoundsException
1978 * if {@code beginIndex} or {@code endIndex} is negative,
1979 * if {@code endIndex} is greater than {@code length()},
1980 * or if {@code beginIndex} is greater than {@code endIndex}
1981 *
1982 * @since 1.4
1983 * @spec JSR-51
1984 */
1985 public CharSequence subSequence(int beginIndex, int endIndex) {
1986 return this.substring(beginIndex, endIndex);
1987 }
1988
1989 /**
1990 * Concatenates the specified string to the end of this string.
1991 * <p>
1992 * If the length of the argument string is {@code 0}, then this
1993 * {@code String} object is returned. Otherwise, a
1994 * {@code String} object is returned that represents a character
1995 * sequence that is the concatenation of the character sequence
1996 * represented by this {@code String} object and the character
1997 * sequence represented by the argument string.<p>
1998 * Examples:
1999 * <blockquote><pre>
2000 * "cares".concat("s") returns "caress"
2001 * "to".concat("get").concat("her") returns "together"
2002 * </pre></blockquote>
2003 *
2004 * @param str the {@code String} that is concatenated to the end
2005 * of this {@code String}.
2006 * @return a string that represents the concatenation of this object's
2007 * characters followed by the string argument's characters.
2008 */
2009 public String concat(String str) {
2010 int olen = str.length();
2011 if (olen == 0) {
2012 return this;
2013 }
2014 if (coder() == str.coder()) {
2015 byte[] val = this.value;
2016 byte[] oval = str.value;
2017 int len = val.length + oval.length;
2018 byte[] buf = Arrays.copyOf(val, len);
2019 System.arraycopy(oval, 0, buf, val.length, oval.length);
2020 return new String(buf, coder);
2021 }
2022 int len = length();
2023 byte[] buf = StringUTF16.newBytesFor(len + olen);
2024 getBytes(buf, 0, UTF16);
2025 str.getBytes(buf, len, UTF16);
2026 return new String(buf, UTF16);
2027 }
2028
2029 /**
2030 * Returns a string resulting from replacing all occurrences of
2031 * {@code oldChar} in this string with {@code newChar}.
2032 * <p>
2033 * If the character {@code oldChar} does not occur in the
2034 * character sequence represented by this {@code String} object,
2035 * then a reference to this {@code String} object is returned.
2036 * Otherwise, a {@code String} object is returned that
2037 * represents a character sequence identical to the character sequence
2038 * represented by this {@code String} object, except that every
2039 * occurrence of {@code oldChar} is replaced by an occurrence
2040 * of {@code newChar}.
2041 * <p>
2042 * Examples:
2043 * <blockquote><pre>
2044 * "mesquite in your cellar".replace('e', 'o')
2045 * returns "mosquito in your collar"
2046 * "the war of baronets".replace('r', 'y')
2047 * returns "the way of bayonets"
2048 * "sparring with a purple porpoise".replace('p', 't')
2049 * returns "starring with a turtle tortoise"
2050 * "JonL".replace('q', 'x') returns "JonL" (no change)
2051 * </pre></blockquote>
2052 *
2053 * @param oldChar the old character.
2054 * @param newChar the new character.
2055 * @return a string derived from this string by replacing every
2056 * occurrence of {@code oldChar} with {@code newChar}.
2057 */
2058 public String replace(char oldChar, char newChar) {
2059 if (oldChar != newChar) {
2060 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar)
2061 : StringUTF16.replace(value, oldChar, newChar);
2062 if (ret != null) {
2063 return ret;
2064 }
2065 }
2066 return this;
2067 }
2068
2069 /**
2070 * Tells whether or not this string matches the given <a
2071 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2072 *
2073 * <p> An invocation of this method of the form
2074 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2075 * same result as the expression
2076 *
2077 * <blockquote>
2078 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2079 * matches(<i>regex</i>, <i>str</i>)}
2080 * </blockquote>
2081 *
2082 * @param regex
2083 * the regular expression to which this string is to be matched
2084 *
2085 * @return {@code true} if, and only if, this string matches the
2086 * given regular expression
2087 *
2088 * @throws PatternSyntaxException
2089 * if the regular expression's syntax is invalid
2090 *
2091 * @see java.util.regex.Pattern
2092 *
2093 * @since 1.4
2094 * @spec JSR-51
2095 */
2096 public boolean matches(String regex) {
2097 return Pattern.matches(regex, this);
2098 }
2099
2100 /**
2101 * Returns true if and only if this string contains the specified
2102 * sequence of char values.
2103 *
2104 * @param s the sequence to search for
2105 * @return true if this string contains {@code s}, false otherwise
2106 * @since 1.5
2107 */
2108 public boolean contains(CharSequence s) {
2109 return indexOf(s.toString()) >= 0;
2110 }
2111
2112 /**
2113 * Replaces the first substring of this string that matches the given <a
2114 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2115 * given replacement.
2116 *
2117 * <p> An invocation of this method of the form
2118 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2119 * yields exactly the same result as the expression
2120 *
2121 * <blockquote>
2122 * <code>
2123 * {@link java.util.regex.Pattern}.{@link
2124 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2125 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2126 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2127 * </code>
2128 * </blockquote>
2129 *
2130 *<p>
2131 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2132 * replacement string may cause the results to be different than if it were
2133 * being treated as a literal replacement string; see
2134 * {@link java.util.regex.Matcher#replaceFirst}.
2135 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2136 * meaning of these characters, if desired.
2137 *
2138 * @param regex
2139 * the regular expression to which this string is to be matched
2140 * @param replacement
2141 * the string to be substituted for the first match
2142 *
2143 * @return The resulting {@code String}
2144 *
2145 * @throws PatternSyntaxException
2146 * if the regular expression's syntax is invalid
2147 *
2148 * @see java.util.regex.Pattern
2149 *
2150 * @since 1.4
2151 * @spec JSR-51
2152 */
2153 public String replaceFirst(String regex, String replacement) {
2154 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2155 }
2156
2157 /**
2158 * Replaces each substring of this string that matches the given <a
2159 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2160 * given replacement.
2161 *
2162 * <p> An invocation of this method of the form
2163 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2164 * yields exactly the same result as the expression
2165 *
2166 * <blockquote>
2167 * <code>
2168 * {@link java.util.regex.Pattern}.{@link
2169 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2170 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2171 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2172 * </code>
2173 * </blockquote>
2174 *
2175 *<p>
2176 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2177 * replacement string may cause the results to be different than if it were
2178 * being treated as a literal replacement string; see
2179 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2180 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2181 * meaning of these characters, if desired.
2182 *
2183 * @param regex
2184 * the regular expression to which this string is to be matched
2185 * @param replacement
2186 * the string to be substituted for each match
2187 *
2188 * @return The resulting {@code String}
2189 *
2190 * @throws PatternSyntaxException
2191 * if the regular expression's syntax is invalid
2192 *
2193 * @see java.util.regex.Pattern
2194 *
2195 * @since 1.4
2196 * @spec JSR-51
2197 */
2198 public String replaceAll(String regex, String replacement) {
2199 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2200 }
2201
2202 /**
2203 * Replaces each substring of this string that matches the literal target
2204 * sequence with the specified literal replacement sequence. The
2205 * replacement proceeds from the beginning of the string to the end, for
2206 * example, replacing "aa" with "b" in the string "aaa" will result in
2207 * "ba" rather than "ab".
2208 *
2209 * @param target The sequence of char values to be replaced
2210 * @param replacement The replacement sequence of char values
2211 * @return The resulting string
2212 * @since 1.5
2213 */
2214 public String replace(CharSequence target, CharSequence replacement) {
2215 String tgtStr = target.toString();
2216 String replStr = replacement.toString();
2217 int j = indexOf(tgtStr);
2218 if (j < 0) {
2219 return this;
2220 }
2221 int tgtLen = tgtStr.length();
2222 int tgtLen1 = Math.max(tgtLen, 1);
2223 int thisLen = length();
2224
2225 int newLenHint = thisLen - tgtLen + replStr.length();
2226 if (newLenHint < 0) {
2227 throw new OutOfMemoryError();
2228 }
2229 StringBuilder sb = new StringBuilder(newLenHint);
2230 int i = 0;
2231 do {
2232 sb.append(this, i, j).append(replStr);
2233 i = j + tgtLen;
2234 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0);
2235 return sb.append(this, i, thisLen).toString();
2236 }
2237
2238 /**
2239 * Splits this string around matches of the given
2240 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2241 *
2242 * <p> The array returned by this method contains each substring of this
2243 * string that is terminated by another substring that matches the given
2244 * expression or is terminated by the end of the string. The substrings in
2245 * the array are in the order in which they occur in this string. If the
2246 * expression does not match any part of the input then the resulting array
2247 * has just one element, namely this string.
2248 *
2249 * <p> When there is a positive-width match at the beginning of this
2250 * string then an empty leading substring is included at the beginning
2251 * of the resulting array. A zero-width match at the beginning however
2252 * never produces such empty leading substring.
2253 *
2254 * <p> The {@code limit} parameter controls the number of times the
2255 * pattern is applied and therefore affects the length of the resulting
2256 * array. If the limit <i>n</i> is greater than zero then the pattern
2257 * will be applied at most <i>n</i> - 1 times, the array's
2258 * length will be no greater than <i>n</i>, and the array's last entry
2259 * will contain all input beyond the last matched delimiter. If <i>n</i>
2260 * is non-positive then the pattern will be applied as many times as
2261 * possible and the array can have any length. If <i>n</i> is zero then
2262 * the pattern will be applied as many times as possible, the array can
2263 * have any length, and trailing empty strings will be discarded.
2264 *
2265 * <p> The string {@code "boo:and:foo"}, for example, yields the
2266 * following results with these parameters:
2267 *
2268 * <blockquote><table class="plain">
2269 * <caption style="display:none">Split example showing regex, limit, and result</caption>
2270 * <thead>
2271 * <tr>
2272 * <th scope="col">Regex</th>
2273 * <th scope="col">Limit</th>
2274 * <th scope="col">Result</th>
2275 * </tr>
2276 * </thead>
2277 * <tbody>
2278 * <tr><th scope="row" rowspan="3" style="font-weight:normal">:</th>
2279 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">2</th>
2280 * <td>{@code { "boo", "and:foo" }}</td></tr>
2281 * <tr><!-- : -->
2282 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th>
2283 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2284 * <tr><!-- : -->
2285 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th>
2286 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2287 * <tr><th scope="row" rowspan="3" style="font-weight:normal">o</th>
2288 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th>
2289 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2290 * <tr><!-- o -->
2291 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th>
2292 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2293 * <tr><!-- o -->
2294 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">0</th>
2295 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2296 * </tbody>
2297 * </table></blockquote>
2298 *
2299 * <p> An invocation of this method of the form
2300 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2301 * yields the same result as the expression
2302 *
2303 * <blockquote>
2304 * <code>
2305 * {@link java.util.regex.Pattern}.{@link
2306 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2307 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2308 * </code>
2309 * </blockquote>
2310 *
2311 *
2312 * @param regex
2313 * the delimiting regular expression
2314 *
2315 * @param limit
2316 * the result threshold, as described above
2317 *
2318 * @return the array of strings computed by splitting this string
2319 * around matches of the given regular expression
2320 *
2321 * @throws PatternSyntaxException
2322 * if the regular expression's syntax is invalid
2323 *
2324 * @see java.util.regex.Pattern
2325 *
2326 * @since 1.4
2327 * @spec JSR-51
2328 */
2329 public String[] split(String regex, int limit) {
2330 /* fastpath if the regex is a
2331 (1)one-char String and this character is not one of the
2332 RegEx's meta characters ".$|()[{^?*+\\", or
2333 (2)two-char String and the first char is the backslash and
2334 the second is not the ascii digit or ascii letter.
2335 */
2336 char ch = 0;
2337 if (((regex.length() == 1 &&
2338 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2339 (regex.length() == 2 &&
2340 regex.charAt(0) == '\\' &&
2341 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2342 ((ch-'a')|('z'-ch)) < 0 &&
2343 ((ch-'A')|('Z'-ch)) < 0)) &&
2344 (ch < Character.MIN_HIGH_SURROGATE ||
2345 ch > Character.MAX_LOW_SURROGATE))
2346 {
2347 int off = 0;
2348 int next = 0;
2349 boolean limited = limit > 0;
2350 ArrayList<String> list = new ArrayList<>();
2351 while ((next = indexOf(ch, off)) != -1) {
2352 if (!limited || list.size() < limit - 1) {
2353 list.add(substring(off, next));
2354 off = next + 1;
2355 } else { // last one
2356 //assert (list.size() == limit - 1);
2357 int last = length();
2358 list.add(substring(off, last));
2359 off = last;
2360 break;
2361 }
2362 }
2363 // If no match was found, return this
2364 if (off == 0)
2365 return new String[]{this};
2366
2367 // Add remaining segment
2368 if (!limited || list.size() < limit)
2369 list.add(substring(off, length()));
2370
2371 // Construct result
2372 int resultSize = list.size();
2373 if (limit == 0) {
2374 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2375 resultSize--;
2376 }
2377 }
2378 String[] result = new String[resultSize];
2379 return list.subList(0, resultSize).toArray(result);
2380 }
2381 return Pattern.compile(regex).split(this, limit);
2382 }
2383
2384 /**
2385 * Splits this string around matches of the given <a
2386 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2387 *
2388 * <p> This method works as if by invoking the two-argument {@link
2389 * #split(String, int) split} method with the given expression and a limit
2390 * argument of zero. Trailing empty strings are therefore not included in
2391 * the resulting array.
2392 *
2393 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2394 * results with these expressions:
2395 *
2396 * <blockquote><table class="plain">
2397 * <caption style="display:none">Split examples showing regex and result</caption>
2398 * <thead>
2399 * <tr>
2400 * <th scope="col">Regex</th>
2401 * <th scope="col">Result</th>
2402 * </tr>
2403 * </thead>
2404 * <tbody>
2405 * <tr><th scope="row" style="text-weight:normal">:</th>
2406 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2407 * <tr><th scope="row" style="text-weight:normal">o</th>
2408 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2409 * </tbody>
2410 * </table></blockquote>
2411 *
2412 *
2413 * @param regex
2414 * the delimiting regular expression
2415 *
2416 * @return the array of strings computed by splitting this string
2417 * around matches of the given regular expression
2418 *
2419 * @throws PatternSyntaxException
2420 * if the regular expression's syntax is invalid
2421 *
2422 * @see java.util.regex.Pattern
2423 *
2424 * @since 1.4
2425 * @spec JSR-51
2426 */
2427 public String[] split(String regex) {
2428 return split(regex, 0);
2429 }
2430
2431 /**
2432 * Returns a new String composed of copies of the
2433 * {@code CharSequence elements} joined together with a copy of
2434 * the specified {@code delimiter}.
2435 *
2436 * <blockquote>For example,
2437 * <pre>{@code
2438 * String message = String.join("-", "Java", "is", "cool");
2439 * // message returned is: "Java-is-cool"
2440 * }</pre></blockquote>
2441 *
2442 * Note that if an element is null, then {@code "null"} is added.
2443 *
2444 * @param delimiter the delimiter that separates each element
2445 * @param elements the elements to join together.
2446 *
2447 * @return a new {@code String} that is composed of the {@code elements}
2448 * separated by the {@code delimiter}
2449 *
2450 * @throws NullPointerException If {@code delimiter} or {@code elements}
2451 * is {@code null}
2452 *
2453 * @see java.util.StringJoiner
2454 * @since 1.8
2455 */
2456 public static String join(CharSequence delimiter, CharSequence... elements) {
2457 Objects.requireNonNull(delimiter);
2458 Objects.requireNonNull(elements);
2459 // Number of elements not likely worth Arrays.stream overhead.
2460 StringJoiner joiner = new StringJoiner(delimiter);
2461 for (CharSequence cs: elements) {
2462 joiner.add(cs);
2463 }
2464 return joiner.toString();
2465 }
2466
2467 /**
2468 * Returns a new {@code String} composed of copies of the
2469 * {@code CharSequence elements} joined together with a copy of the
2470 * specified {@code delimiter}.
2471 *
2472 * <blockquote>For example,
2473 * <pre>{@code
2474 * List<String> strings = List.of("Java", "is", "cool");
2475 * String message = String.join(" ", strings);
2476 * //message returned is: "Java is cool"
2477 *
2478 * Set<String> strings =
2479 * new LinkedHashSet<>(List.of("Java", "is", "very", "cool"));
2480 * String message = String.join("-", strings);
2481 * //message returned is: "Java-is-very-cool"
2482 * }</pre></blockquote>
2483 *
2484 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2485 *
2486 * @param delimiter a sequence of characters that is used to separate each
2487 * of the {@code elements} in the resulting {@code String}
2488 * @param elements an {@code Iterable} that will have its {@code elements}
2489 * joined together.
2490 *
2491 * @return a new {@code String} that is composed from the {@code elements}
2492 * argument
2493 *
2494 * @throws NullPointerException If {@code delimiter} or {@code elements}
2495 * is {@code null}
2496 *
2497 * @see #join(CharSequence,CharSequence...)
2498 * @see java.util.StringJoiner
2499 * @since 1.8
2500 */
2501 public static String join(CharSequence delimiter,
2502 Iterable<? extends CharSequence> elements) {
2503 Objects.requireNonNull(delimiter);
2504 Objects.requireNonNull(elements);
2505 StringJoiner joiner = new StringJoiner(delimiter);
2506 for (CharSequence cs: elements) {
2507 joiner.add(cs);
2508 }
2509 return joiner.toString();
2510 }
2511
2512 /**
2513 * Converts all of the characters in this {@code String} to lower
2514 * case using the rules of the given {@code Locale}. Case mapping is based
2515 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2516 * class. Since case mappings are not always 1:1 char mappings, the resulting
2517 * {@code String} may be a different length than the original {@code String}.
2518 * <p>
2519 * Examples of lowercase mappings are in the following table:
2520 * <table class="plain">
2521 * <caption style="display:none">Lowercase mapping examples showing language code of locale, upper case, lower case, and description</caption>
2522 * <thead>
2523 * <tr>
2524 * <th scope="col">Language Code of Locale</th>
2525 * <th scope="col">Upper Case</th>
2526 * <th scope="col">Lower Case</th>
2527 * <th scope="col">Description</th>
2528 * </tr>
2529 * </thead>
2530 * <tbody>
2531 * <tr>
2532 * <td>tr (Turkish)</td>
2533 * <th scope="row" style="font-weight:normal; text-align:left">\u0130</th>
2534 * <td>\u0069</td>
2535 * <td>capital letter I with dot above -> small letter i</td>
2536 * </tr>
2537 * <tr>
2538 * <td>tr (Turkish)</td>
2539 * <th scope="row" style="font-weight:normal; text-align:left">\u0049</th>
2540 * <td>\u0131</td>
2541 * <td>capital letter I -> small letter dotless i </td>
2542 * </tr>
2543 * <tr>
2544 * <td>(all)</td>
2545 * <th scope="row" style="font-weight:normal; text-align:left">French Fries</th>
2546 * <td>french fries</td>
2547 * <td>lowercased all chars in String</td>
2548 * </tr>
2549 * <tr>
2550 * <td>(all)</td>
2551 * <th scope="row" style="font-weight:normal; text-align:left">
2552 * ΙΧΘΥΣ</th>
2553 * <td>ιχθυσ</td>
2554 * <td>lowercased all chars in String</td>
2555 * </tr>
2556 * </tbody>
2557 * </table>
2558 *
2559 * @param locale use the case transformation rules for this locale
2560 * @return the {@code String}, converted to lowercase.
2561 * @see java.lang.String#toLowerCase()
2562 * @see java.lang.String#toUpperCase()
2563 * @see java.lang.String#toUpperCase(Locale)
2564 * @since 1.1
2565 */
2566 public String toLowerCase(Locale locale) {
2567 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale)
2568 : StringUTF16.toLowerCase(this, value, locale);
2569 }
2570
2571 /**
2572 * Converts all of the characters in this {@code String} to lower
2573 * case using the rules of the default locale. This is equivalent to calling
2574 * {@code toLowerCase(Locale.getDefault())}.
2575 * <p>
2576 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2577 * results if used for strings that are intended to be interpreted locale
2578 * independently.
2579 * Examples are programming language identifiers, protocol keys, and HTML
2580 * tags.
2581 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2582 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2583 * LATIN SMALL LETTER DOTLESS I character.
2584 * To obtain correct results for locale insensitive strings, use
2585 * {@code toLowerCase(Locale.ROOT)}.
2586 *
2587 * @return the {@code String}, converted to lowercase.
2588 * @see java.lang.String#toLowerCase(Locale)
2589 */
2590 public String toLowerCase() {
2591 return toLowerCase(Locale.getDefault());
2592 }
2593
2594 /**
2595 * Converts all of the characters in this {@code String} to upper
2596 * case using the rules of the given {@code Locale}. Case mapping is based
2597 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2598 * class. Since case mappings are not always 1:1 char mappings, the resulting
2599 * {@code String} may be a different length than the original {@code String}.
2600 * <p>
2601 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2602 *
2603 * <table class="plain">
2604 * <caption style="display:none">Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.</caption>
2605 * <thead>
2606 * <tr>
2607 * <th scope="col">Language Code of Locale</th>
2608 * <th scope="col">Lower Case</th>
2609 * <th scope="col">Upper Case</th>
2610 * <th scope="col">Description</th>
2611 * </tr>
2612 * </thead>
2613 * <tbody>
2614 * <tr>
2615 * <td>tr (Turkish)</td>
2616 * <th scope="row" style="font-weight:normal; text-align:left">\u0069</th>
2617 * <td>\u0130</td>
2618 * <td>small letter i -> capital letter I with dot above</td>
2619 * </tr>
2620 * <tr>
2621 * <td>tr (Turkish)</td>
2622 * <th scope="row" style="font-weight:normal; text-align:left">\u0131</th>
2623 * <td>\u0049</td>
2624 * <td>small letter dotless i -> capital letter I</td>
2625 * </tr>
2626 * <tr>
2627 * <td>(all)</td>
2628 * <th scope="row" style="font-weight:normal; text-align:left">\u00df</th>
2629 * <td>\u0053 \u0053</td>
2630 * <td>small letter sharp s -> two letters: SS</td>
2631 * </tr>
2632 * <tr>
2633 * <td>(all)</td>
2634 * <th scope="row" style="font-weight:normal; text-align:left">Fahrvergnügen</th>
2635 * <td>FAHRVERGNÜGEN</td>
2636 * <td></td>
2637 * </tr>
2638 * </tbody>
2639 * </table>
2640 * @param locale use the case transformation rules for this locale
2641 * @return the {@code String}, converted to uppercase.
2642 * @see java.lang.String#toUpperCase()
2643 * @see java.lang.String#toLowerCase()
2644 * @see java.lang.String#toLowerCase(Locale)
2645 * @since 1.1
2646 */
2647 public String toUpperCase(Locale locale) {
2648 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale)
2649 : StringUTF16.toUpperCase(this, value, locale);
2650 }
2651
2652 /**
2653 * Converts all of the characters in this {@code String} to upper
2654 * case using the rules of the default locale. This method is equivalent to
2655 * {@code toUpperCase(Locale.getDefault())}.
2656 * <p>
2657 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2658 * results if used for strings that are intended to be interpreted locale
2659 * independently.
2660 * Examples are programming language identifiers, protocol keys, and HTML
2661 * tags.
2662 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2663 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2664 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2665 * To obtain correct results for locale insensitive strings, use
2666 * {@code toUpperCase(Locale.ROOT)}.
2667 *
2668 * @return the {@code String}, converted to uppercase.
2669 * @see java.lang.String#toUpperCase(Locale)
2670 */
2671 public String toUpperCase() {
2672 return toUpperCase(Locale.getDefault());
2673 }
2674
2675 /**
2676 * Returns a string whose value is this string, with any leading and trailing
2677 * whitespace removed.
2678 * <p>
2679 * If this {@code String} object represents an empty character
2680 * sequence, or the first and last characters of character sequence
2681 * represented by this {@code String} object both have codes
2682 * greater than {@code '\u005Cu0020'} (the space character), then a
2683 * reference to this {@code String} object is returned.
2684 * <p>
2685 * Otherwise, if there is no character with a code greater than
2686 * {@code '\u005Cu0020'} in the string, then a
2687 * {@code String} object representing an empty string is
2688 * returned.
2689 * <p>
2690 * Otherwise, let <i>k</i> be the index of the first character in the
2691 * string whose code is greater than {@code '\u005Cu0020'}, and let
2692 * <i>m</i> be the index of the last character in the string whose code
2693 * is greater than {@code '\u005Cu0020'}. A {@code String}
2694 * object is returned, representing the substring of this string that
2695 * begins with the character at index <i>k</i> and ends with the
2696 * character at index <i>m</i>-that is, the result of
2697 * {@code this.substring(k, m + 1)}.
2698 * <p>
2699 * This method may be used to trim whitespace (as defined above) from
2700 * the beginning and end of a string.
2701 *
2702 * @return A string whose value is this string, with any leading and trailing white
2703 * space removed, or this string if it has no leading or
2704 * trailing white space.
2705 */
2706 public String trim() {
2707 String ret = isLatin1() ? StringLatin1.trim(value)
2708 : StringUTF16.trim(value);
2709 return ret == null ? this : ret;
2710 }
2711
2712 /**
2713 * This object (which is already a string!) is itself returned.
2714 *
2715 * @return the string itself.
2716 */
2717 public String toString() {
2718 return this;
2719 }
2720
2721 /**
2722 * Returns a stream of {@code int} zero-extending the {@code char} values
2723 * from this sequence. Any char which maps to a <a
2724 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code
2725 * point</a> is passed through uninterpreted.
2726 *
2727 * @return an IntStream of char values from this sequence
2728 * @since 9
2729 */
2730 @Override
2731 public IntStream chars() {
2732 return StreamSupport.intStream(
2733 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
2734 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE),
2735 false);
2736 }
2737
2738
2739 /**
2740 * Returns a stream of code point values from this sequence. Any surrogate
2741 * pairs encountered in the sequence are combined as if by {@linkplain
2742 * Character#toCodePoint Character.toCodePoint} and the result is passed
2743 * to the stream. Any other code units, including ordinary BMP characters,
2744 * unpaired surrogates, and undefined code units, are zero-extended to
2745 * {@code int} values which are then passed to the stream.
2746 *
2747 * @return an IntStream of Unicode code points from this sequence
2748 * @since 9
2749 */
2750 @Override
2751 public IntStream codePoints() {
2752 return StreamSupport.intStream(
2753 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
2754 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE),
2755 false);
2756 }
2757
2758 /**
2759 * Converts this string to a new character array.
2760 *
2761 * @return a newly allocated character array whose length is the length
2762 * of this string and whose contents are initialized to contain
2763 * the character sequence represented by this string.
2764 */
2765 public char[] toCharArray() {
2766 return isLatin1() ? StringLatin1.toChars(value)
2767 : StringUTF16.toChars(value);
2768 }
2769
2770 /**
2771 * Returns a formatted string using the specified format string and
2772 * arguments.
2773 *
2774 * <p> The locale always used is the one returned by {@link
2775 * java.util.Locale#getDefault(java.util.Locale.Category)
2776 * Locale.getDefault(Locale.Category)} with
2777 * {@link java.util.Locale.Category#FORMAT FORMAT} category specified.
2778 *
2779 * @param format
2780 * A <a href="../util/Formatter.html#syntax">format string</a>
2781 *
2782 * @param args
2783 * Arguments referenced by the format specifiers in the format
2784 * string. If there are more arguments than format specifiers, the
2785 * extra arguments are ignored. The number of arguments is
2786 * variable and may be zero. The maximum number of arguments is
2787 * limited by the maximum dimension of a Java array as defined by
2788 * <cite>The Java™ Virtual Machine Specification</cite>.
2789 * The behaviour on a
2790 * {@code null} argument depends on the <a
2791 * href="../util/Formatter.html#syntax">conversion</a>.
2792 *
2793 * @throws java.util.IllegalFormatException
2794 * If a format string contains an illegal syntax, a format
2795 * specifier that is incompatible with the given arguments,
2796 * insufficient arguments given the format string, or other
2797 * illegal conditions. For specification of all possible
2798 * formatting errors, see the <a
2799 * href="../util/Formatter.html#detail">Details</a> section of the
2800 * formatter class specification.
2801 *
2802 * @return A formatted string
2803 *
2804 * @see java.util.Formatter
2805 * @since 1.5
2806 */
2807 public static String format(String format, Object... args) {
2808 return new Formatter().format(format, args).toString();
2809 }
2810
2811 /**
2812 * Returns a formatted string using the specified locale, format string,
2813 * and arguments.
2814 *
2815 * @param l
2816 * The {@linkplain java.util.Locale locale} to apply during
2817 * formatting. If {@code l} is {@code null} then no localization
2818 * is applied.
2819 *
2820 * @param format
2821 * A <a href="../util/Formatter.html#syntax">format string</a>
2822 *
2823 * @param args
2824 * Arguments referenced by the format specifiers in the format
2825 * string. If there are more arguments than format specifiers, the
2826 * extra arguments are ignored. The number of arguments is
2827 * variable and may be zero. The maximum number of arguments is
2828 * limited by the maximum dimension of a Java array as defined by
2829 * <cite>The Java™ Virtual Machine Specification</cite>.
2830 * The behaviour on a
2831 * {@code null} argument depends on the
2832 * <a href="../util/Formatter.html#syntax">conversion</a>.
2833 *
2834 * @throws java.util.IllegalFormatException
2835 * If a format string contains an illegal syntax, a format
2836 * specifier that is incompatible with the given arguments,
2837 * insufficient arguments given the format string, or other
2838 * illegal conditions. For specification of all possible
2839 * formatting errors, see the <a
2840 * href="../util/Formatter.html#detail">Details</a> section of the
2841 * formatter class specification
2842 *
2843 * @return A formatted string
2844 *
2845 * @see java.util.Formatter
2846 * @since 1.5
2847 */
2848 public static String format(Locale l, String format, Object... args) {
2849 return new Formatter(l).format(format, args).toString();
2850 }
2851
2852 /**
2853 * Returns the string representation of the {@code Object} argument.
2854 *
2855 * @param obj an {@code Object}.
2856 * @return if the argument is {@code null}, then a string equal to
2857 * {@code "null"}; otherwise, the value of
2858 * {@code obj.toString()} is returned.
2859 * @see java.lang.Object#toString()
2860 */
2861 public static String valueOf(Object obj) {
2862 return (obj == null) ? "null" : obj.toString();
2863 }
2864
2865 /**
2866 * Returns the string representation of the {@code char} array
2867 * argument. The contents of the character array are copied; subsequent
2868 * modification of the character array does not affect the returned
2869 * string.
2870 *
2871 * @param data the character array.
2872 * @return a {@code String} that contains the characters of the
2873 * character array.
2874 */
2875 public static String valueOf(char data[]) {
2876 return new String(data);
2877 }
2878
2879 /**
2880 * Returns the string representation of a specific subarray of the
2881 * {@code char} array argument.
2882 * <p>
2883 * The {@code offset} argument is the index of the first
2884 * character of the subarray. The {@code count} argument
2885 * specifies the length of the subarray. The contents of the subarray
2886 * are copied; subsequent modification of the character array does not
2887 * affect the returned string.
2888 *
2889 * @param data the character array.
2890 * @param offset initial offset of the subarray.
2891 * @param count length of the subarray.
2892 * @return a {@code String} that contains the characters of the
2893 * specified subarray of the character array.
2894 * @exception IndexOutOfBoundsException if {@code offset} is
2895 * negative, or {@code count} is negative, or
2896 * {@code offset+count} is larger than
2897 * {@code data.length}.
2898 */
2899 public static String valueOf(char data[], int offset, int count) {
2900 return new String(data, offset, count);
2901 }
2902
2903 /**
2904 * Equivalent to {@link #valueOf(char[], int, int)}.
2905 *
2906 * @param data the character array.
2907 * @param offset initial offset of the subarray.
2908 * @param count length of the subarray.
2909 * @return a {@code String} that contains the characters of the
2910 * specified subarray of the character array.
2911 * @exception IndexOutOfBoundsException if {@code offset} is
2912 * negative, or {@code count} is negative, or
2913 * {@code offset+count} is larger than
2914 * {@code data.length}.
2915 */
2916 public static String copyValueOf(char data[], int offset, int count) {
2917 return new String(data, offset, count);
2918 }
2919
2920 /**
2921 * Equivalent to {@link #valueOf(char[])}.
2922 *
2923 * @param data the character array.
2924 * @return a {@code String} that contains the characters of the
2925 * character array.
2926 */
2927 public static String copyValueOf(char data[]) {
2928 return new String(data);
2929 }
2930
2931 /**
2932 * Returns the string representation of the {@code boolean} argument.
2933 *
2934 * @param b a {@code boolean}.
2935 * @return if the argument is {@code true}, a string equal to
2936 * {@code "true"} is returned; otherwise, a string equal to
2937 * {@code "false"} is returned.
2938 */
2939 public static String valueOf(boolean b) {
2940 return b ? "true" : "false";
2941 }
2942
2943 /**
2944 * Returns the string representation of the {@code char}
2945 * argument.
2946 *
2947 * @param c a {@code char}.
2948 * @return a string of length {@code 1} containing
2949 * as its single character the argument {@code c}.
2950 */
2951 public static String valueOf(char c) {
2952 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) {
2953 return new String(StringLatin1.toBytes(c), LATIN1);
2954 }
2955 return new String(StringUTF16.toBytes(c), UTF16);
2956 }
2957
2958 /**
2959 * Returns the string representation of the {@code int} argument.
2960 * <p>
2961 * The representation is exactly the one returned by the
2962 * {@code Integer.toString} method of one argument.
2963 *
2964 * @param i an {@code int}.
2965 * @return a string representation of the {@code int} argument.
2966 * @see java.lang.Integer#toString(int, int)
2967 */
2968 public static String valueOf(int i) {
2969 return Integer.toString(i);
2970 }
2971
2972 /**
2973 * Returns the string representation of the {@code long} argument.
2974 * <p>
2975 * The representation is exactly the one returned by the
2976 * {@code Long.toString} method of one argument.
2977 *
2978 * @param l a {@code long}.
2979 * @return a string representation of the {@code long} argument.
2980 * @see java.lang.Long#toString(long)
2981 */
2982 public static String valueOf(long l) {
2983 return Long.toString(l);
2984 }
2985
2986 /**
2987 * Returns the string representation of the {@code float} argument.
2988 * <p>
2989 * The representation is exactly the one returned by the
2990 * {@code Float.toString} method of one argument.
2991 *
2992 * @param f a {@code float}.
2993 * @return a string representation of the {@code float} argument.
2994 * @see java.lang.Float#toString(float)
2995 */
2996 public static String valueOf(float f) {
2997 return Float.toString(f);
2998 }
2999
3000 /**
3001 * Returns the string representation of the {@code double} argument.
3002 * <p>
3003 * The representation is exactly the one returned by the
3004 * {@code Double.toString} method of one argument.
3005 *
3006 * @param d a {@code double}.
3007 * @return a string representation of the {@code double} argument.
3008 * @see java.lang.Double#toString(double)
3009 */
3010 public static String valueOf(double d) {
3011 return Double.toString(d);
3012 }
3013
3014 /**
3015 * Returns a canonical representation for the string object.
3016 * <p>
3017 * A pool of strings, initially empty, is maintained privately by the
3018 * class {@code String}.
3019 * <p>
3020 * When the intern method is invoked, if the pool already contains a
3021 * string equal to this {@code String} object as determined by
3022 * the {@link #equals(Object)} method, then the string from the pool is
3023 * returned. Otherwise, this {@code String} object is added to the
3024 * pool and a reference to this {@code String} object is returned.
3025 * <p>
3026 * It follows that for any two strings {@code s} and {@code t},
3027 * {@code s.intern() == t.intern()} is {@code true}
3028 * if and only if {@code s.equals(t)} is {@code true}.
3029 * <p>
3030 * All literal strings and string-valued constant expressions are
3031 * interned. String literals are defined in section 3.10.5 of the
3032 * <cite>The Java™ Language Specification</cite>.
3033 *
3034 * @return a string that has the same contents as this string, but is
3035 * guaranteed to be from a pool of unique strings.
3036 * @jls 3.10.5 String Literals
3037 */
3038 public native String intern();
3039
3040 /**
3041 * Returns a string whose value is the concatenation of this
3042 * string repeated {@code count} times.
3043 * <p>
3044 * If this string is empty or count is zero then the empty
3045 * string is returned.
3046 *
3047 * @param count number of times to repeat
3048 *
3049 * @return A string composed of this string repeated
3050 * {@code count} times or the empty string if this
3051 * string is empty or count is zero
3052 *
3053 * @throws IllegalArgumentException if the {@code count} is
3054 * negative.
3055 *
3056 * @since 11
3057 */
3058 public String repeat(int count) {
3059 if (count < 0) {
3060 throw new IllegalArgumentException("count is negative: " + count);
3061 }
3062 if (count == 1) {
3063 return this;
3064 }
3065 final int len = value.length;
3066 if (len == 0 || count == 0) {
3067 return "";
3068 }
3069 if (len == 1) {
3070 final byte[] single = new byte[count];
3071 Arrays.fill(single, value[0]);
3072 return new String(single, coder);
3073 }
3074 if (Integer.MAX_VALUE / count < len) {
3075 throw new OutOfMemoryError("Repeating " + len + " bytes String " + count +
3076 " times will produce a String exceeding maximum size.");
3077 }
3078 final int limit = len * count;
3079 final byte[] multiple = new byte[limit];
3080 System.arraycopy(value, 0, multiple, 0, len);
3081 int copied = len;
3082 for (; copied < limit - copied; copied <<= 1) {
3083 System.arraycopy(multiple, 0, multiple, copied, copied);
3084 }
3085 System.arraycopy(multiple, 0, multiple, copied, limit - copied);
3086 return new String(multiple, coder);
3087 }
3088
3089 ////////////////////////////////////////////////////////////////
3090
3091 /**
3092 * Copy character bytes from this string into dst starting at dstBegin.
3093 * This method doesn't perform any range checking.
3094 *
3095 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two
3096 * coders are different, and dst is big enough (range check)
3097 *
3098 * @param dstBegin the char index, not offset of byte[]
3099 * @param coder the coder of dst[]
3100 */
3101 void getBytes(byte dst[], int dstBegin, byte coder) {
3102 if (coder() == coder) {
3103 System.arraycopy(value, 0, dst, dstBegin << coder, value.length);
3104 } else { // this.coder == LATIN && coder == UTF16
3105 StringLatin1.inflate(value, 0, dst, dstBegin, value.length);
3106 }
3107 }
3108
3109 /*
3110 * Package private constructor. Trailing Void argument is there for
3111 * disambiguating it against other (public) constructors.
3112 *
3113 * Stores the char[] value into a byte[] that each byte represents
3114 * the8 low-order bits of the corresponding character, if the char[]
3115 * contains only latin1 character. Or a byte[] that stores all
3116 * characters in their byte sequences defined by the {@code StringUTF16}.
3117 */
3118 String(char[] value, int off, int len, Void sig) {
3119 if (len == 0) {
3120 this.value = "".value;
3121 this.coder = "".coder;
3122 return;
3123 }
3124 if (COMPACT_STRINGS) {
3125 byte[] val = StringUTF16.compress(value, off, len);
3126 if (val != null) {
3127 this.value = val;
3128 this.coder = LATIN1;
3129 return;
3130 }
3131 }
3132 this.coder = UTF16;
3133 this.value = StringUTF16.toBytes(value, off, len);
3134 }
3135
3136 /*
3137 * Package private constructor. Trailing Void argument is there for
3138 * disambiguating it against other (public) constructors.
3139 */
3140 String(AbstractStringBuilder asb, Void sig) {
3141 byte[] val = asb.getValue();
3142 int length = asb.length();
3143 if (asb.isLatin1()) {
3144 this.coder = LATIN1;
3145 this.value = Arrays.copyOfRange(val, 0, length);
3146 } else {
3147 if (COMPACT_STRINGS) {
3148 byte[] buf = StringUTF16.compress(val, 0, length);
3149 if (buf != null) {
3150 this.coder = LATIN1;
3151 this.value = buf;
3152 return;
3153 }
3154 }
3155 this.coder = UTF16;
3156 this.value = Arrays.copyOfRange(val, 0, length << 1);
3157 }
3158 }
3159
3160 /*
3161 * Package private constructor which shares value array for speed.
3162 */
3163 String(byte[] value, byte coder) {
3164 this.value = value;
3165 this.coder = coder;
3166 }
3167
3168 byte coder() {
3169 return COMPACT_STRINGS ? coder : UTF16;
3170 }
3171
3172 byte[] value() {
3173 return value;
3174 }
3175
3176 private boolean isLatin1() {
3177 return COMPACT_STRINGS && coder == LATIN1;
3178 }
3179
3180 @Native static final byte LATIN1 = 0;
3181 @Native static final byte UTF16 = 1;
3182
3183 /*
3184 * StringIndexOutOfBoundsException if {@code index} is
3185 * negative or greater than or equal to {@code length}.
3186 */
3187 static void checkIndex(int index, int length) {
3188 if (index < 0 || index >= length) {
3189 throw new StringIndexOutOfBoundsException("index " + index +
3190 ",length " + length);
3191 }
3192 }
3193
3194 /*
3195 * StringIndexOutOfBoundsException if {@code offset}
3196 * is negative or greater than {@code length}.
3197 */
3198 static void checkOffset(int offset, int length) {
3199 if (offset < 0 || offset > length) {
3200 throw new StringIndexOutOfBoundsException("offset " + offset +
3201 ",length " + length);
3202 }
3203 }
3204
3205 /*
3206 * Check {@code offset}, {@code count} against {@code 0} and {@code length}
3207 * bounds.
3208 *
3209 * @throws StringIndexOutOfBoundsException
3210 * If {@code offset} is negative, {@code count} is negative,
3211 * or {@code offset} is greater than {@code length - count}
3212 */
3213 static void checkBoundsOffCount(int offset, int count, int length) {
3214 if (offset < 0 || count < 0 || offset > length - count) {
3215 throw new StringIndexOutOfBoundsException(
3216 "offset " + offset + ", count " + count + ", length " + length);
3217 }
3218 }
3219
3220 /*
3221 * Check {@code begin}, {@code end} against {@code 0} and {@code length}
3222 * bounds.
3223 *
3224 * @throws StringIndexOutOfBoundsException
3225 * If {@code begin} is negative, {@code begin} is greater than
3226 * {@code end}, or {@code end} is greater than {@code length}.
3227 */
3228 static void checkBoundsBeginEnd(int begin, int end, int length) {
3229 if (begin < 0 || begin > end || end > length) {
3230 throw new StringIndexOutOfBoundsException(
3231 "begin " + begin + ", end " + end + ", length " + length);
3232 }
3233 }
3234
3235 /**
3236 * Returns the string representation of the {@code codePoint}
3237 * argument.
3238 *
3239 * @param codePoint a {@code codePoint}.
3240 * @return a string of length {@code 1} or {@code 2} containing
3241 * as its single character the argument {@code codePoint}.
3242 * @throws IllegalArgumentException if the specified
3243 * {@code codePoint} is not a {@linkplain Character#isValidCodePoint
3244 * valid Unicode code point}.
3245 */
3246 static String valueOfCodePoint(int codePoint) {
3247 if (COMPACT_STRINGS && StringLatin1.canEncode(codePoint)) {
3248 return new String(StringLatin1.toBytes((char)codePoint), LATIN1);
3249 } else if (Character.isBmpCodePoint(codePoint)) {
3250 return new String(StringUTF16.toBytes((char)codePoint), UTF16);
3251 } else if (Character.isSupplementaryCodePoint(codePoint)) {
3252 return new String(StringUTF16.toBytesSupplementary(codePoint), UTF16);
3253 }
3254
3255 throw new IllegalArgumentException(
3256 format("Not a valid Unicode code point: 0x%X", codePoint));
3257 }
3258 }