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