1 /*
2 * Copyright (c) 1994, 2015, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import java.io.ObjectStreamField;
29 import java.io.UnsupportedEncodingException;
30 import java.nio.charset.Charset;
31 import java.util.ArrayList;
32 import java.util.Arrays;
33 import java.util.Comparator;
34 import java.util.Formatter;
35 import java.util.Locale;
36 import java.util.Objects;
37 import java.util.Spliterator;
38 import java.util.StringJoiner;
39 import java.util.regex.Matcher;
40 import java.util.regex.Pattern;
41 import java.util.regex.PatternSyntaxException;
42 import java.util.stream.IntStream;
43 import java.util.stream.StreamSupport;
44 import jdk.internal.HotSpotIntrinsicCandidate;
45 import jdk.internal.vm.annotation.Stable;
46
47 /**
48 * The {@code String} class represents character strings. All
49 * string literals in Java programs, such as {@code "abc"}, are
50 * implemented as instances of this class.
51 * <p>
52 * Strings are constant; their values cannot be changed after they
53 * are created. String buffers support mutable strings.
54 * Because String objects are immutable they can be shared. For example:
55 * <blockquote><pre>
56 * String str = "abc";
57 * </pre></blockquote><p>
58 * is equivalent to:
59 * <blockquote><pre>
60 * char data[] = {'a', 'b', 'c'};
61 * String str = new String(data);
62 * </pre></blockquote><p>
63 * Here are some more examples of how strings can be used:
64 * <blockquote><pre>
65 * System.out.println("abc");
66 * String cde = "cde";
67 * System.out.println("abc" + cde);
68 * String c = "abc".substring(2,3);
69 * String d = cde.substring(1, 2);
70 * </pre></blockquote>
71 * <p>
72 * The class {@code String} includes methods for examining
73 * individual characters of the sequence, for comparing strings, for
74 * searching strings, for extracting substrings, and for creating a
75 * copy of a string with all characters translated to uppercase or to
76 * lowercase. Case mapping is based on the Unicode Standard version
77 * specified by the {@link java.lang.Character Character} class.
78 * <p>
79 * The Java language provides special support for the string
80 * concatenation operator ( + ), and for conversion of
81 * other objects to strings. For additional information on string
82 * concatenation and conversion, see <i>The Java™ Language Specification</i>.
83 *
84 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor
85 * or method in this class will cause a {@link NullPointerException} to be
86 * thrown.
87 *
88 * <p>A {@code String} represents a string in the UTF-16 format
89 * in which <em>supplementary characters</em> are represented by <em>surrogate
90 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
91 * Character Representations</a> in the {@code Character} class for
92 * more information).
93 * Index values refer to {@code char} code units, so a supplementary
94 * character uses two positions in a {@code String}.
95 * <p>The {@code String} class provides methods for dealing with
96 * Unicode code points (i.e., characters), in addition to those for
97 * dealing with Unicode code units (i.e., {@code char} values).
98 *
99 * <p>Unless otherwise noted, methods for comparing Strings do not take locale
100 * into account. The {@link java.text.Collator} class provides methods for
101 * finer-grain, locale-sensitive String comparison.
102 *
103 * @implNote The implementation of the string concatenation operator is left to
104 * the discretion of a Java compiler, as long as the compiler ultimately conforms
105 * to <i>The Java™ Language Specification</i>. For example, the {@code javac} compiler
106 * may implement the operator with {@code StringBuffer}, {@code StringBuilder},
107 * or {@code java.lang.invoke.StringConcatFactory} depending on the JDK version. The
108 * implementation of string conversion is typically through the method {@code toString},
109 * defined by {@code Object} and inherited by all classes in Java.
110 *
111 * @author Lee Boynton
112 * @author Arthur van Hoff
113 * @author Martin Buchholz
114 * @author Ulf Zibis
115 * @see java.lang.Object#toString()
116 * @see java.lang.StringBuffer
117 * @see java.lang.StringBuilder
118 * @see java.nio.charset.Charset
119 * @since 1.0
120 */
121
122 public final class String
123 implements java.io.Serializable, Comparable<String>, CharSequence {
124
125 /**
126 * The value is used for character storage.
127 *
128 * @implNote This field is trusted by the VM, and is a subject to
129 * constant folding if String instance is constant. Overwriting this
130 * field after construction will cause problems.
131 *
132 * Additionally, it is marked with {@link Stable} to trust the contents
133 * of the array. No other facility in JDK provides this functionality (yet).
134 * {@link Stable} is safe here, because value is never null.
135 */
136 @Stable
137 private final byte[] value;
138
139 /**
140 * The identifier of the encoding used to encode the bytes in
141 * {@code value}. The supported values in this implementation are
142 *
143 * LATIN1
144 * UTF16
145 *
146 * @implNote This field is trusted by the VM, and is a subject to
147 * constant folding if String instance is constant. Overwriting this
148 * field after construction will cause problems.
149 */
150 private final byte coder;
151
152 /** Cache the hash code for the string */
153 private int hash; // Default to 0
154
155 /** use serialVersionUID from JDK 1.0.2 for interoperability */
156 private static final long serialVersionUID = -6849794470754667710L;
157
158 /**
159 * If String compaction is disabled, the bytes in {@code value} are
160 * always encoded in UTF16.
161 *
162 * For methods with several possible implementation paths, when String
163 * compaction is disabled, only one code path is taken.
164 *
165 * The instance field value is generally opaque to optimizing JIT
166 * compilers. Therefore, in performance-sensitive place, an explicit
167 * check of the static boolean {@code COMPACT_STRINGS} is done first
168 * before checking the {@code coder} field since the static boolean
169 * {@code COMPACT_STRINGS} would be constant folded away by an
170 * optimizing JIT compiler. The idioms for these cases are as follows.
171 *
172 * For code such as:
173 *
174 * if (coder == LATIN1) { ... }
175 *
176 * can be written more optimally as
177 *
178 * if (coder() == LATIN1) { ... }
179 *
180 * or:
181 *
182 * if (COMPACT_STRINGS && coder == LATIN1) { ... }
183 *
184 * An optimizing JIT compiler can fold the above conditional as:
185 *
186 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... }
187 * COMPACT_STRINGS == false => if (false) { ... }
188 *
189 * @implNote
190 * The actual value for this field is injected by JVM. The static
191 * initialization block is used to set the value here to communicate
192 * that this static final field is not statically foldable, and to
193 * avoid any possible circular dependency during vm initialization.
194 */
195 static final boolean COMPACT_STRINGS;
196
197 static {
198 COMPACT_STRINGS = true;
199 }
200
201 /**
202 * Class String is special cased within the Serialization Stream Protocol.
203 *
204 * A String instance is written into an ObjectOutputStream according to
205 * <a href="{@docRoot}/../platform/serialization/spec/output.html">
206 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
207 */
208 private static final ObjectStreamField[] serialPersistentFields =
209 new ObjectStreamField[0];
210
211 /**
212 * Initializes a newly created {@code String} object so that it represents
213 * an empty character sequence. Note that use of this constructor is
214 * unnecessary since Strings are immutable.
215 */
216 public String() {
217 this.value = "".value;
218 this.coder = "".coder;
219 }
220
221 /**
222 * Initializes a newly created {@code String} object so that it represents
223 * the same sequence of characters as the argument; in other words, the
224 * newly created string is a copy of the argument string. Unless an
225 * explicit copy of {@code original} is needed, use of this constructor is
226 * unnecessary since Strings are immutable.
227 *
228 * @param original
229 * A {@code String}
230 */
231 @HotSpotIntrinsicCandidate
232 public String(String original) {
233 this.value = original.value;
234 this.coder = original.coder;
235 this.hash = original.hash;
236 }
237
238 /**
239 * Allocates a new {@code String} so that it represents the sequence of
240 * characters currently contained in the character array argument. The
241 * contents of the character array are copied; subsequent modification of
242 * the character array does not affect the newly created string.
243 *
244 * @param value
245 * The initial value of the string
246 */
247 public String(char value[]) {
248 this(value, 0, value.length, null);
249 }
250
251 /**
252 * Allocates a new {@code String} that contains characters from a subarray
253 * of the character array argument. The {@code offset} argument is the
254 * index of the first character of the subarray and the {@code count}
255 * argument specifies the length of the subarray. The contents of the
256 * subarray are copied; subsequent modification of the character array does
257 * not affect the newly created string.
258 *
259 * @param value
260 * Array that is the source of characters
261 *
262 * @param offset
263 * The initial offset
264 *
265 * @param count
266 * The length
267 *
268 * @throws IndexOutOfBoundsException
269 * If {@code offset} is negative, {@code count} is negative, or
270 * {@code offset} is greater than {@code value.length - count}
271 */
272 public String(char value[], int offset, int count) {
273 this(value, offset, count, rangeCheck(value, offset, count));
274 }
275
276 private static Void rangeCheck(char[] value, int offset, int count) {
277 checkBoundsOffCount(offset, count, value.length);
278 return null;
279 }
280
281 /**
282 * Allocates a new {@code String} that contains characters from a subarray
283 * of the <a href="Character.html#unicode">Unicode code point</a> array
284 * argument. The {@code offset} argument is the index of the first code
285 * point of the subarray and the {@code count} argument specifies the
286 * length of the subarray. The contents of the subarray are converted to
287 * {@code char}s; subsequent modification of the {@code int} array does not
288 * affect the newly created string.
289 *
290 * @param codePoints
291 * Array that is the source of Unicode code points
292 *
293 * @param offset
294 * The initial offset
295 *
296 * @param count
297 * The length
298 *
299 * @throws IllegalArgumentException
300 * If any invalid Unicode code point is found in {@code
301 * codePoints}
302 *
303 * @throws IndexOutOfBoundsException
304 * If {@code offset} is negative, {@code count} is negative, or
305 * {@code offset} is greater than {@code codePoints.length - count}
306 *
307 * @since 1.5
308 */
309 public String(int[] codePoints, int offset, int count) {
310 checkBoundsOffCount(offset, count, codePoints.length);
311 if (count == 0) {
312 this.value = "".value;
313 this.coder = "".coder;
314 return;
315 }
316 if (COMPACT_STRINGS) {
317 byte[] val = StringLatin1.toBytes(codePoints, offset, count);
318 if (val != null) {
319 this.coder = LATIN1;
320 this.value = val;
321 return;
322 }
323 }
324 this.coder = UTF16;
325 this.value = StringUTF16.toBytes(codePoints, offset, count);
326 }
327
328 /**
329 * Allocates a new {@code String} constructed from a subarray of an array
330 * of 8-bit integer values.
331 *
332 * <p> The {@code offset} argument is the index of the first byte of the
333 * subarray, and the {@code count} argument specifies the length of the
334 * subarray.
335 *
336 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
337 * specified in the method above.
338 *
339 * @deprecated This method does not properly convert bytes into characters.
340 * As of JDK 1.1, the preferred way to do this is via the
341 * {@code String} constructors that take a {@link
342 * java.nio.charset.Charset}, charset name, or that use the platform's
343 * default charset.
344 *
345 * @param ascii
346 * The bytes to be converted to characters
347 *
348 * @param hibyte
349 * The top 8 bits of each 16-bit Unicode code unit
350 *
351 * @param offset
352 * The initial offset
353 * @param count
354 * The length
355 *
356 * @throws IndexOutOfBoundsException
357 * If {@code offset} is negative, {@code count} is negative, or
358 * {@code offset} is greater than {@code ascii.length - count}
359 *
360 * @see #String(byte[], int)
361 * @see #String(byte[], int, int, java.lang.String)
362 * @see #String(byte[], int, int, java.nio.charset.Charset)
363 * @see #String(byte[], int, int)
364 * @see #String(byte[], java.lang.String)
365 * @see #String(byte[], java.nio.charset.Charset)
366 * @see #String(byte[])
367 */
368 @Deprecated(since="1.1")
369 public String(byte ascii[], int hibyte, int offset, int count) {
370 checkBoundsOffCount(offset, count, ascii.length);
371 if (count == 0) {
372 this.value = "".value;
373 this.coder = "".coder;
374 return;
375 }
376 if (COMPACT_STRINGS && (byte)hibyte == 0) {
377 this.value = Arrays.copyOfRange(ascii, offset, offset + count);
378 this.coder = LATIN1;
379 } else {
380 hibyte <<= 8;
381 byte[] val = StringUTF16.newBytesFor(count);
382 for (int i = 0; i < count; i++) {
383 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff));
384 }
385 this.value = val;
386 this.coder = UTF16;
387 }
388 }
389
390 /**
391 * Allocates a new {@code String} containing characters constructed from
392 * an array of 8-bit integer values. Each character <i>c</i>in the
393 * resulting string is constructed from the corresponding component
394 * <i>b</i> in the byte array such that:
395 *
396 * <blockquote><pre>
397 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
398 * | (<b><i>b</i></b> & 0xff))
399 * </pre></blockquote>
400 *
401 * @deprecated This method does not properly convert bytes into
402 * characters. As of JDK 1.1, the preferred way to do this is via the
403 * {@code String} constructors that take a {@link
404 * java.nio.charset.Charset}, charset name, or that use the platform's
405 * default charset.
406 *
407 * @param ascii
408 * The bytes to be converted to characters
409 *
410 * @param hibyte
411 * The top 8 bits of each 16-bit Unicode code unit
412 *
413 * @see #String(byte[], int, int, java.lang.String)
414 * @see #String(byte[], int, int, java.nio.charset.Charset)
415 * @see #String(byte[], int, int)
416 * @see #String(byte[], java.lang.String)
417 * @see #String(byte[], java.nio.charset.Charset)
418 * @see #String(byte[])
419 */
420 @Deprecated(since="1.1")
421 public String(byte ascii[], int hibyte) {
422 this(ascii, hibyte, 0, ascii.length);
423 }
424
425 /**
426 * Constructs a new {@code String} by decoding the specified subarray of
427 * bytes using the specified charset. The length of the new {@code String}
428 * is a function of the charset, and hence may not be equal to the length
429 * of the subarray.
430 *
431 * <p> The behavior of this constructor when the given bytes are not valid
432 * in the given charset is unspecified. The {@link
433 * java.nio.charset.CharsetDecoder} class should be used when more control
434 * over the decoding process is required.
435 *
436 * @param bytes
437 * The bytes to be decoded into characters
438 *
439 * @param offset
440 * The index of the first byte to decode
441 *
442 * @param length
443 * The number of bytes to decode
444
445 * @param charsetName
446 * The name of a supported {@linkplain java.nio.charset.Charset
447 * charset}
448 *
449 * @throws UnsupportedEncodingException
450 * If the named charset is not supported
451 *
452 * @throws IndexOutOfBoundsException
453 * If {@code offset} is negative, {@code length} is negative, or
454 * {@code offset} is greater than {@code bytes.length - length}
455 *
456 * @since 1.1
457 */
458 public String(byte bytes[], int offset, int length, String charsetName)
459 throws UnsupportedEncodingException {
460 if (charsetName == null)
461 throw new NullPointerException("charsetName");
462 checkBoundsOffCount(offset, length, bytes.length);
463 StringCoding.Result ret =
464 StringCoding.decode(charsetName, bytes, offset, length);
465 this.value = ret.value;
466 this.coder = ret.coder;
467 }
468
469 /**
470 * Constructs a new {@code String} by decoding the specified subarray of
471 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
472 * The length of the new {@code String} is a function of the charset, and
473 * hence may not be equal to the length of the subarray.
474 *
475 * <p> This method always replaces malformed-input and unmappable-character
476 * sequences with this charset's default replacement string. The {@link
477 * java.nio.charset.CharsetDecoder} class should be used when more control
478 * over the decoding process is required.
479 *
480 * @param bytes
481 * The bytes to be decoded into characters
482 *
483 * @param offset
484 * The index of the first byte to decode
485 *
486 * @param length
487 * The number of bytes to decode
488 *
489 * @param charset
490 * The {@linkplain java.nio.charset.Charset charset} to be used to
491 * decode the {@code bytes}
492 *
493 * @throws IndexOutOfBoundsException
494 * If {@code offset} is negative, {@code length} is negative, or
495 * {@code offset} is greater than {@code bytes.length - length}
496 *
497 * @since 1.6
498 */
499 public String(byte bytes[], int offset, int length, Charset charset) {
500 if (charset == null)
501 throw new NullPointerException("charset");
502 checkBoundsOffCount(offset, length, bytes.length);
503 StringCoding.Result ret =
504 StringCoding.decode(charset, bytes, offset, length);
505 this.value = ret.value;
506 this.coder = ret.coder;
507 }
508
509 /**
510 * Constructs a new {@code String} by decoding the specified array of bytes
511 * using the specified {@linkplain java.nio.charset.Charset charset}. The
512 * length of the new {@code String} is a function of the charset, and hence
513 * may not be equal to the length of the byte array.
514 *
515 * <p> The behavior of this constructor when the given bytes are not valid
516 * in the given charset is unspecified. The {@link
517 * java.nio.charset.CharsetDecoder} class should be used when more control
518 * over the decoding process is required.
519 *
520 * @param bytes
521 * The bytes to be decoded into characters
522 *
523 * @param charsetName
524 * The name of a supported {@linkplain java.nio.charset.Charset
525 * charset}
526 *
527 * @throws UnsupportedEncodingException
528 * If the named charset is not supported
529 *
530 * @since 1.1
531 */
532 public String(byte bytes[], String charsetName)
533 throws UnsupportedEncodingException {
534 this(bytes, 0, bytes.length, charsetName);
535 }
536
537 /**
538 * Constructs a new {@code String} by decoding the specified array of
539 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
540 * The length of the new {@code String} is a function of the charset, and
541 * hence may not be equal to the length of the byte array.
542 *
543 * <p> This method always replaces malformed-input and unmappable-character
544 * sequences with this charset's default replacement string. The {@link
545 * java.nio.charset.CharsetDecoder} class should be used when more control
546 * over the decoding process is required.
547 *
548 * @param bytes
549 * The bytes to be decoded into characters
550 *
551 * @param charset
552 * The {@linkplain java.nio.charset.Charset charset} to be used to
553 * decode the {@code bytes}
554 *
555 * @since 1.6
556 */
557 public String(byte bytes[], Charset charset) {
558 this(bytes, 0, bytes.length, charset);
559 }
560
561 /**
562 * Constructs a new {@code String} by decoding the specified subarray of
563 * bytes using the platform's default charset. The length of the new
564 * {@code String} is a function of the charset, and hence may not be equal
565 * to the length of the subarray.
566 *
567 * <p> The behavior of this constructor when the given bytes are not valid
568 * in the default charset is unspecified. The {@link
569 * java.nio.charset.CharsetDecoder} class should be used when more control
570 * over the decoding process is required.
571 *
572 * @param bytes
573 * The bytes to be decoded into characters
574 *
575 * @param offset
576 * The index of the first byte to decode
577 *
578 * @param length
579 * The number of bytes to decode
580 *
581 * @throws IndexOutOfBoundsException
582 * If {@code offset} is negative, {@code length} is negative, or
583 * {@code offset} is greater than {@code bytes.length - length}
584 *
585 * @since 1.1
586 */
587 public String(byte bytes[], int offset, int length) {
588 checkBoundsOffCount(offset, length, bytes.length);
589 StringCoding.Result ret = StringCoding.decode(bytes, offset, length);
590 this.value = ret.value;
591 this.coder = ret.coder;
592 }
593
594 /**
595 * Constructs a new {@code String} by decoding the specified array of bytes
596 * using the platform's default charset. The length of the new {@code
597 * String} is a function of the charset, and hence may not be equal to the
598 * length of the byte array.
599 *
600 * <p> The behavior of this constructor when the given bytes are not valid
601 * in the default charset is unspecified. The {@link
602 * java.nio.charset.CharsetDecoder} class should be used when more control
603 * over the decoding process is required.
604 *
605 * @param bytes
606 * The bytes to be decoded into characters
607 *
608 * @since 1.1
609 */
610 public String(byte[] bytes) {
611 this(bytes, 0, bytes.length);
612 }
613
614 /**
615 * Allocates a new string that contains the sequence of characters
616 * currently contained in the string buffer argument. The contents of the
617 * string buffer are copied; subsequent modification of the string buffer
618 * does not affect the newly created string.
619 *
620 * @param buffer
621 * A {@code StringBuffer}
622 */
623 public String(StringBuffer buffer) {
624 this(buffer.toString());
625 }
626
627 /**
628 * Allocates a new string that contains the sequence of characters
629 * currently contained in the string builder argument. The contents of the
630 * string builder are copied; subsequent modification of the string builder
631 * does not affect the newly created string.
632 *
633 * <p> This constructor is provided to ease migration to {@code
634 * StringBuilder}. Obtaining a string from a string builder via the {@code
635 * toString} method is likely to run faster and is generally preferred.
636 *
637 * @param builder
638 * A {@code StringBuilder}
639 *
640 * @since 1.5
641 */
642 public String(StringBuilder builder) {
643 this(builder, null);
644 }
645
646 /*
647 * Package private constructor which shares value array for speed.
648 * this constructor is always expected to be called with share==true.
649 * a separate constructor is needed because we already have a public
650 * String(char[]) constructor that makes a copy of the given char[].
651 */
652 // TBD: this is kept for package internal use (Thread/System),
653 // should be removed if they all have a byte[] version
654 String(char[] val, boolean share) {
655 // assert share : "unshared not supported";
656 this(val, 0, val.length, null);
657 }
658
659 /**
660 * Returns the length of this string.
661 * The length is equal to the number of <a href="Character.html#unicode">Unicode
662 * code units</a> in the string.
663 *
664 * @return the length of the sequence of characters represented by this
665 * object.
666 */
667 public int length() {
668 return value.length >> coder();
669 }
670
671 /**
672 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
673 *
674 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
675 * {@code false}
676 *
677 * @since 1.6
678 */
679 public boolean isEmpty() {
680 return value.length == 0;
681 }
682
683 /**
684 * Returns the {@code char} value at the
685 * specified index. An index ranges from {@code 0} to
686 * {@code length() - 1}. The first {@code char} value of the sequence
687 * is at index {@code 0}, the next at index {@code 1},
688 * and so on, as for array indexing.
689 *
690 * <p>If the {@code char} value specified by the index is a
691 * <a href="Character.html#unicode">surrogate</a>, the surrogate
692 * value is returned.
693 *
694 * @param index the index of the {@code char} value.
695 * @return the {@code char} value at the specified index of this string.
696 * The first {@code char} value is at index {@code 0}.
697 * @exception IndexOutOfBoundsException if the {@code index}
698 * argument is negative or not less than the length of this
699 * string.
700 */
701 public char charAt(int index) {
702 if (isLatin1()) {
703 return StringLatin1.charAt(value, index);
704 } else {
705 return StringUTF16.charAt(value, index);
706 }
707 }
708
709 /**
710 * Returns the character (Unicode code point) at the specified
711 * index. The index refers to {@code char} values
712 * (Unicode code units) and ranges from {@code 0} to
713 * {@link #length()}{@code - 1}.
714 *
715 * <p> If the {@code char} value specified at the given index
716 * is in the high-surrogate range, the following index is less
717 * than the length of this {@code String}, and the
718 * {@code char} value at the following index is in the
719 * low-surrogate range, then the supplementary code point
720 * corresponding to this surrogate pair is returned. Otherwise,
721 * the {@code char} value at the given index is returned.
722 *
723 * @param index the index to the {@code char} values
724 * @return the code point value of the character at the
725 * {@code index}
726 * @exception IndexOutOfBoundsException if the {@code index}
727 * argument is negative or not less than the length of this
728 * string.
729 * @since 1.5
730 */
731 public int codePointAt(int index) {
732 if (isLatin1()) {
733 checkIndex(index, value.length);
734 return value[index] & 0xff;
735 }
736 int length = value.length >> 1;
737 checkIndex(index, length);
738 return StringUTF16.codePointAt(value, index, length);
739 }
740
741 /**
742 * Returns the character (Unicode code point) before the specified
743 * index. The index refers to {@code char} values
744 * (Unicode code units) and ranges from {@code 1} to {@link
745 * CharSequence#length() length}.
746 *
747 * <p> If the {@code char} value at {@code (index - 1)}
748 * is in the low-surrogate range, {@code (index - 2)} is not
749 * negative, and the {@code char} value at {@code (index -
750 * 2)} is in the high-surrogate range, then the
751 * supplementary code point value of the surrogate pair is
752 * returned. If the {@code char} value at {@code index -
753 * 1} is an unpaired low-surrogate or a high-surrogate, the
754 * surrogate value is returned.
755 *
756 * @param index the index following the code point that should be returned
757 * @return the Unicode code point value before the given index.
758 * @exception IndexOutOfBoundsException if the {@code index}
759 * argument is less than 1 or greater than the length
760 * of this string.
761 * @since 1.5
762 */
763 public int codePointBefore(int index) {
764 int i = index - 1;
765 if (i < 0 || i >= length()) {
766 throw new StringIndexOutOfBoundsException(index);
767 }
768 if (isLatin1()) {
769 return (value[i] & 0xff);
770 }
771 return StringUTF16.codePointBefore(value, index);
772 }
773
774 /**
775 * Returns the number of Unicode code points in the specified text
776 * range of this {@code String}. The text range begins at the
777 * specified {@code beginIndex} and extends to the
778 * {@code char} at index {@code endIndex - 1}. Thus the
779 * length (in {@code char}s) of the text range is
780 * {@code endIndex-beginIndex}. Unpaired surrogates within
781 * the text range count as one code point each.
782 *
783 * @param beginIndex the index to the first {@code char} of
784 * the text range.
785 * @param endIndex the index after the last {@code char} of
786 * the text range.
787 * @return the number of Unicode code points in the specified text
788 * range
789 * @exception IndexOutOfBoundsException if the
790 * {@code beginIndex} is negative, or {@code endIndex}
791 * is larger than the length of this {@code String}, or
792 * {@code beginIndex} is larger than {@code endIndex}.
793 * @since 1.5
794 */
795 public int codePointCount(int beginIndex, int endIndex) {
796 if (beginIndex < 0 || beginIndex > endIndex ||
797 endIndex > length()) {
798 throw new IndexOutOfBoundsException();
799 }
800 if (isLatin1()) {
801 return endIndex - beginIndex;
802 }
803 return StringUTF16.codePointCount(value, beginIndex, endIndex);
804 }
805
806 /**
807 * Returns the index within this {@code String} that is
808 * offset from the given {@code index} by
809 * {@code codePointOffset} code points. Unpaired surrogates
810 * within the text range given by {@code index} and
811 * {@code codePointOffset} count as one code point each.
812 *
813 * @param index the index to be offset
814 * @param codePointOffset the offset in code points
815 * @return the index within this {@code String}
816 * @exception IndexOutOfBoundsException if {@code index}
817 * is negative or larger then the length of this
818 * {@code String}, or if {@code codePointOffset} is positive
819 * and the substring starting with {@code index} has fewer
820 * than {@code codePointOffset} code points,
821 * or if {@code codePointOffset} is negative and the substring
822 * before {@code index} has fewer than the absolute value
823 * of {@code codePointOffset} code points.
824 * @since 1.5
825 */
826 public int offsetByCodePoints(int index, int codePointOffset) {
827 if (index < 0 || index > length()) {
828 throw new IndexOutOfBoundsException();
829 }
830 return Character.offsetByCodePoints(this, index, codePointOffset);
831 }
832
833 /**
834 * Copies characters from this string into the destination character
835 * array.
836 * <p>
837 * The first character to be copied is at index {@code srcBegin};
838 * the last character to be copied is at index {@code srcEnd-1}
839 * (thus the total number of characters to be copied is
840 * {@code srcEnd-srcBegin}). The characters are copied into the
841 * subarray of {@code dst} starting at index {@code dstBegin}
842 * and ending at index:
843 * <blockquote><pre>
844 * dstBegin + (srcEnd-srcBegin) - 1
845 * </pre></blockquote>
846 *
847 * @param srcBegin index of the first character in the string
848 * to copy.
849 * @param srcEnd index after the last character in the string
850 * to copy.
851 * @param dst the destination array.
852 * @param dstBegin the start offset in the destination array.
853 * @exception IndexOutOfBoundsException If any of the following
854 * is true:
855 * <ul><li>{@code srcBegin} is negative.
856 * <li>{@code srcBegin} is greater than {@code srcEnd}
857 * <li>{@code srcEnd} is greater than the length of this
858 * string
859 * <li>{@code dstBegin} is negative
860 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
861 * {@code dst.length}</ul>
862 */
863 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
864 checkBoundsBeginEnd(srcBegin, srcEnd, length());
865 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
866 if (isLatin1()) {
867 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin);
868 } else {
869 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin);
870 }
871 }
872
873 /**
874 * Copies characters from this string into the destination byte array. Each
875 * byte receives the 8 low-order bits of the corresponding character. The
876 * eight high-order bits of each character are not copied and do not
877 * participate in the transfer in any way.
878 *
879 * <p> The first character to be copied is at index {@code srcBegin}; the
880 * last character to be copied is at index {@code srcEnd-1}. The total
881 * number of characters to be copied is {@code srcEnd-srcBegin}. The
882 * characters, converted to bytes, are copied into the subarray of {@code
883 * dst} starting at index {@code dstBegin} and ending at index:
884 *
885 * <blockquote><pre>
886 * dstBegin + (srcEnd-srcBegin) - 1
887 * </pre></blockquote>
888 *
889 * @deprecated This method does not properly convert characters into
890 * bytes. As of JDK 1.1, the preferred way to do this is via the
891 * {@link #getBytes()} method, which uses the platform's default charset.
892 *
893 * @param srcBegin
894 * Index of the first character in the string to copy
895 *
896 * @param srcEnd
897 * Index after the last character in the string to copy
898 *
899 * @param dst
900 * The destination array
901 *
902 * @param dstBegin
903 * The start offset in the destination array
904 *
905 * @throws IndexOutOfBoundsException
906 * If any of the following is true:
907 * <ul>
908 * <li> {@code srcBegin} is negative
909 * <li> {@code srcBegin} is greater than {@code srcEnd}
910 * <li> {@code srcEnd} is greater than the length of this String
911 * <li> {@code dstBegin} is negative
912 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
913 * dst.length}
914 * </ul>
915 */
916 @Deprecated(since="1.1")
917 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
918 checkBoundsBeginEnd(srcBegin, srcEnd, length());
919 Objects.requireNonNull(dst);
920 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
921 if (isLatin1()) {
922 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
923 } else {
924 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
925 }
926 }
927
928 /**
929 * Encodes this {@code String} into a sequence of bytes using the named
930 * charset, storing the result into a new byte array.
931 *
932 * <p> The behavior of this method when this string cannot be encoded in
933 * the given charset is unspecified. The {@link
934 * java.nio.charset.CharsetEncoder} class should be used when more control
935 * over the encoding process is required.
936 *
937 * @param charsetName
938 * The name of a supported {@linkplain java.nio.charset.Charset
939 * charset}
940 *
941 * @return The resultant byte array
942 *
943 * @throws UnsupportedEncodingException
944 * If the named charset is not supported
945 *
946 * @since 1.1
947 */
948 public byte[] getBytes(String charsetName)
949 throws UnsupportedEncodingException {
950 if (charsetName == null) throw new NullPointerException();
951 return StringCoding.encode(charsetName, coder(), value);
952 }
953
954 /**
955 * Encodes this {@code String} into a sequence of bytes using the given
956 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
957 * new byte array.
958 *
959 * <p> This method always replaces malformed-input and unmappable-character
960 * sequences with this charset's default replacement byte array. The
961 * {@link java.nio.charset.CharsetEncoder} class should be used when more
962 * control over the encoding process is required.
963 *
964 * @param charset
965 * The {@linkplain java.nio.charset.Charset} to be used to encode
966 * the {@code String}
967 *
968 * @return The resultant byte array
969 *
970 * @since 1.6
971 */
972 public byte[] getBytes(Charset charset) {
973 if (charset == null) throw new NullPointerException();
974 return StringCoding.encode(charset, coder(), value);
975 }
976
977 /**
978 * Encodes this {@code String} into a sequence of bytes using the
979 * platform's default charset, storing the result into a new byte array.
980 *
981 * <p> The behavior of this method when this string cannot be encoded in
982 * the default charset is unspecified. The {@link
983 * java.nio.charset.CharsetEncoder} class should be used when more control
984 * over the encoding process is required.
985 *
986 * @return The resultant byte array
987 *
988 * @since 1.1
989 */
990 public byte[] getBytes() {
991 return StringCoding.encode(coder(), value);
992 }
993
994 /**
995 * Compares this string to the specified object. The result is {@code
996 * true} if and only if the argument is not {@code null} and is a {@code
997 * String} object that represents the same sequence of characters as this
998 * object.
999 *
1000 * <p>For finer-grained String comparison, refer to
1001 * {@link java.text.Collator}.
1002 *
1003 * @param anObject
1004 * The object to compare this {@code String} against
1005 *
1006 * @return {@code true} if the given object represents a {@code String}
1007 * equivalent to this string, {@code false} otherwise
1008 *
1009 * @see #compareTo(String)
1010 * @see #equalsIgnoreCase(String)
1011 */
1012 public boolean equals(Object anObject) {
1013 if (this == anObject) {
1014 return true;
1015 }
1016 if (anObject instanceof String) {
1017 String aString = (String)anObject;
1018 if (coder() == aString.coder()) {
1019 return isLatin1() ? StringLatin1.equals(value, aString.value)
1020 : StringUTF16.equals(value, aString.value);
1021 }
1022 }
1023 return false;
1024 }
1025
1026 /**
1027 * Compares this string to the specified {@code StringBuffer}. The result
1028 * is {@code true} if and only if this {@code String} represents the same
1029 * sequence of characters as the specified {@code StringBuffer}. This method
1030 * synchronizes on the {@code StringBuffer}.
1031 *
1032 * <p>For finer-grained String comparison, refer to
1033 * {@link java.text.Collator}.
1034 *
1035 * @param sb
1036 * The {@code StringBuffer} to compare this {@code String} against
1037 *
1038 * @return {@code true} if this {@code String} represents the same
1039 * sequence of characters as the specified {@code StringBuffer},
1040 * {@code false} otherwise
1041 *
1042 * @since 1.4
1043 */
1044 public boolean contentEquals(StringBuffer sb) {
1045 return contentEquals((CharSequence)sb);
1046 }
1047
1048 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1049 int len = length();
1050 if (len != sb.length()) {
1051 return false;
1052 }
1053 byte v1[] = value;
1054 byte v2[] = sb.getValue();
1055 if (coder() == sb.getCoder()) {
1056 int n = v1.length;
1057 for (int i = 0; i < n; i++) {
1058 if (v1[i] != v2[i]) {
1059 return false;
1060 }
1061 }
1062 } else {
1063 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal"
1064 return false;
1065 }
1066 for (int i = 0; i < len; i++) {
1067 if ((char)(v1[i] & 0xff) != StringUTF16.getChar(v2, i)) {
1068 return false;
1069 }
1070 }
1071 }
1072 return true;
1073 }
1074
1075 /**
1076 * Compares this string to the specified {@code CharSequence}. The
1077 * result is {@code true} if and only if this {@code String} represents the
1078 * same sequence of char values as the specified sequence. Note that if the
1079 * {@code CharSequence} is a {@code StringBuffer} then the method
1080 * synchronizes on it.
1081 *
1082 * <p>For finer-grained String comparison, refer to
1083 * {@link java.text.Collator}.
1084 *
1085 * @param cs
1086 * The sequence to compare this {@code String} against
1087 *
1088 * @return {@code true} if this {@code String} represents the same
1089 * sequence of char values as the specified sequence, {@code
1090 * false} otherwise
1091 *
1092 * @since 1.5
1093 */
1094 public boolean contentEquals(CharSequence cs) {
1095 // Argument is a StringBuffer, StringBuilder
1096 if (cs instanceof AbstractStringBuilder) {
1097 if (cs instanceof StringBuffer) {
1098 synchronized(cs) {
1099 return nonSyncContentEquals((AbstractStringBuilder)cs);
1100 }
1101 } else {
1102 return nonSyncContentEquals((AbstractStringBuilder)cs);
1103 }
1104 }
1105 // Argument is a String
1106 if (cs instanceof String) {
1107 return equals(cs);
1108 }
1109 // Argument is a generic CharSequence
1110 int n = cs.length();
1111 if (n != length()) {
1112 return false;
1113 }
1114 byte[] val = this.value;
1115 if (isLatin1()) {
1116 for (int i = 0; i < n; i++) {
1117 if ((val[i] & 0xff) != cs.charAt(i)) {
1118 return false;
1119 }
1120 }
1121 } else {
1122 for (int i = 0; i < n; i++) {
1123 if (StringUTF16.getChar(val, i) != cs.charAt(i)) {
1124 return false;
1125 }
1126 }
1127 }
1128 return true;
1129 }
1130
1131 /**
1132 * Compares this {@code String} to another {@code String}, ignoring case
1133 * considerations. Two strings are considered equal ignoring case if they
1134 * are of the same length and corresponding characters in the two strings
1135 * are equal ignoring case.
1136 *
1137 * <p> Two characters {@code c1} and {@code c2} are considered the same
1138 * ignoring case if at least one of the following is true:
1139 * <ul>
1140 * <li> The two characters are the same (as compared by the
1141 * {@code ==} operator)
1142 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))}
1143 * on each character produces the same result
1144 * </ul>
1145 *
1146 * <p>Note that this method does <em>not</em> take locale into account, and
1147 * will result in unsatisfactory results for certain locales. The
1148 * {@link java.text.Collator} class provides locale-sensitive comparison.
1149 *
1150 * @param anotherString
1151 * The {@code String} to compare this {@code String} against
1152 *
1153 * @return {@code true} if the argument is not {@code null} and it
1154 * represents an equivalent {@code String} ignoring case; {@code
1155 * false} otherwise
1156 *
1157 * @see #equals(Object)
1158 */
1159 public boolean equalsIgnoreCase(String anotherString) {
1160 return (this == anotherString) ? true
1161 : (anotherString != null)
1162 && (anotherString.length() == length())
1163 && regionMatches(true, 0, anotherString, 0, length());
1164 }
1165
1166 /**
1167 * Compares two strings lexicographically.
1168 * The comparison is based on the Unicode value of each character in
1169 * the strings. The character sequence represented by this
1170 * {@code String} object is compared lexicographically to the
1171 * character sequence represented by the argument string. The result is
1172 * a negative integer if this {@code String} object
1173 * lexicographically precedes the argument string. The result is a
1174 * positive integer if this {@code String} object lexicographically
1175 * follows the argument string. The result is zero if the strings
1176 * are equal; {@code compareTo} returns {@code 0} exactly when
1177 * the {@link #equals(Object)} method would return {@code true}.
1178 * <p>
1179 * This is the definition of lexicographic ordering. If two strings are
1180 * different, then either they have different characters at some index
1181 * that is a valid index for both strings, or their lengths are different,
1182 * or both. If they have different characters at one or more index
1183 * positions, let <i>k</i> be the smallest such index; then the string
1184 * whose character at position <i>k</i> has the smaller value, as
1185 * determined by using the {@code <} operator, lexicographically precedes the
1186 * other string. In this case, {@code compareTo} returns the
1187 * difference of the two character values at position {@code k} in
1188 * the two string -- that is, the value:
1189 * <blockquote><pre>
1190 * this.charAt(k)-anotherString.charAt(k)
1191 * </pre></blockquote>
1192 * If there is no index position at which they differ, then the shorter
1193 * string lexicographically precedes the longer string. In this case,
1194 * {@code compareTo} returns the difference of the lengths of the
1195 * strings -- that is, the value:
1196 * <blockquote><pre>
1197 * this.length()-anotherString.length()
1198 * </pre></blockquote>
1199 *
1200 * <p>For finer-grained String comparison, refer to
1201 * {@link java.text.Collator}.
1202 *
1203 * @param anotherString the {@code String} to be compared.
1204 * @return the value {@code 0} if the argument string is equal to
1205 * this string; a value less than {@code 0} if this string
1206 * is lexicographically less than the string argument; and a
1207 * value greater than {@code 0} if this string is
1208 * lexicographically greater than the string argument.
1209 */
1210 public int compareTo(String anotherString) {
1211 byte v1[] = value;
1212 byte v2[] = anotherString.value;
1213 if (coder() == anotherString.coder()) {
1214 return isLatin1() ? StringLatin1.compareTo(v1, v2)
1215 : StringUTF16.compareTo(v1, v2);
1216 }
1217 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2)
1218 : StringUTF16.compareToLatin1(v1, v2);
1219 }
1220
1221 /**
1222 * A Comparator that orders {@code String} objects as by
1223 * {@code compareToIgnoreCase}. This comparator is serializable.
1224 * <p>
1225 * Note that this Comparator does <em>not</em> take locale into account,
1226 * and will result in an unsatisfactory ordering for certain locales.
1227 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1228 *
1229 * @see java.text.Collator
1230 * @since 1.2
1231 */
1232 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1233 = new CaseInsensitiveComparator();
1234 private static class CaseInsensitiveComparator
1235 implements Comparator<String>, java.io.Serializable {
1236 // use serialVersionUID from JDK 1.2.2 for interoperability
1237 private static final long serialVersionUID = 8575799808933029326L;
1238
1239 public int compare(String s1, String s2) {
1240 byte v1[] = s1.value;
1241 byte v2[] = s2.value;
1242 if (s1.coder() == s2.coder()) {
1243 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2)
1244 : StringUTF16.compareToCI(v1, v2);
1245 }
1246 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2)
1247 : StringUTF16.compareToCI_Latin1(v1, v2);
1248 }
1249
1250 /** Replaces the de-serialized object. */
1251 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1252 }
1253
1254 /**
1255 * Compares two strings lexicographically, ignoring case
1256 * differences. This method returns an integer whose sign is that of
1257 * calling {@code compareTo} with normalized versions of the strings
1258 * where case differences have been eliminated by calling
1259 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1260 * each character.
1261 * <p>
1262 * Note that this method does <em>not</em> take locale into account,
1263 * and will result in an unsatisfactory ordering for certain locales.
1264 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1265 *
1266 * @param str the {@code String} to be compared.
1267 * @return a negative integer, zero, or a positive integer as the
1268 * specified String is greater than, equal to, or less
1269 * than this String, ignoring case considerations.
1270 * @see java.text.Collator
1271 * @since 1.2
1272 */
1273 public int compareToIgnoreCase(String str) {
1274 return CASE_INSENSITIVE_ORDER.compare(this, str);
1275 }
1276
1277 /**
1278 * Tests if two string regions are equal.
1279 * <p>
1280 * A substring of this {@code String} object is compared to a substring
1281 * of the argument other. The result is true if these substrings
1282 * represent identical character sequences. The substring of this
1283 * {@code String} object to be compared begins at index {@code toffset}
1284 * and has length {@code len}. The substring of other to be compared
1285 * begins at index {@code ooffset} and has length {@code len}. The
1286 * result is {@code false} if and only if at least one of the following
1287 * is true:
1288 * <ul><li>{@code toffset} is negative.
1289 * <li>{@code ooffset} is negative.
1290 * <li>{@code toffset+len} is greater than the length of this
1291 * {@code String} object.
1292 * <li>{@code ooffset+len} is greater than the length of the other
1293 * argument.
1294 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1295 * such that:
1296 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1297 * <i>k</i>{@code )}
1298 * </ul>
1299 *
1300 * <p>Note that this method does <em>not</em> take locale into account. The
1301 * {@link java.text.Collator} class provides locale-sensitive comparison.
1302 *
1303 * @param toffset the starting offset of the subregion in this string.
1304 * @param other the string argument.
1305 * @param ooffset the starting offset of the subregion in the string
1306 * argument.
1307 * @param len the number of characters to compare.
1308 * @return {@code true} if the specified subregion of this string
1309 * exactly matches the specified subregion of the string argument;
1310 * {@code false} otherwise.
1311 */
1312 public boolean regionMatches(int toffset, String other, int ooffset, int len) {
1313 byte tv[] = value;
1314 byte ov[] = other.value;
1315 // Note: toffset, ooffset, or len might be near -1>>>1.
1316 if ((ooffset < 0) || (toffset < 0) ||
1317 (toffset > (long)length() - len) ||
1318 (ooffset > (long)other.length() - len)) {
1319 return false;
1320 }
1321 if (coder() == other.coder()) {
1322 if (!isLatin1() && (len > 0)) {
1323 toffset = toffset << 1;
1324 ooffset = ooffset << 1;
1325 len = len << 1;
1326 }
1327 while (len-- > 0) {
1328 if (tv[toffset++] != ov[ooffset++]) {
1329 return false;
1330 }
1331 }
1332 } else {
1333 if (coder() == LATIN1) {
1334 while (len-- > 0) {
1335 if (StringLatin1.getChar(tv, toffset++) !=
1336 StringUTF16.getChar(ov, ooffset++)) {
1337 return false;
1338 }
1339 }
1340 } else {
1341 while (len-- > 0) {
1342 if (StringUTF16.getChar(tv, toffset++) !=
1343 StringLatin1.getChar(ov, ooffset++)) {
1344 return false;
1345 }
1346 }
1347 }
1348 }
1349 return true;
1350 }
1351
1352 /**
1353 * Tests if two string regions are equal.
1354 * <p>
1355 * A substring of this {@code String} object is compared to a substring
1356 * of the argument {@code other}. The result is {@code true} if these
1357 * substrings represent character sequences that are the same, ignoring
1358 * case if and only if {@code ignoreCase} is true. The substring of
1359 * this {@code String} object to be compared begins at index
1360 * {@code toffset} and has length {@code len}. The substring of
1361 * {@code other} to be compared begins at index {@code ooffset} and
1362 * has length {@code len}. The result is {@code false} if and only if
1363 * at least one of the following is true:
1364 * <ul><li>{@code toffset} is negative.
1365 * <li>{@code ooffset} is negative.
1366 * <li>{@code toffset+len} is greater than the length of this
1367 * {@code String} object.
1368 * <li>{@code ooffset+len} is greater than the length of the other
1369 * argument.
1370 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1371 * integer <i>k</i> less than {@code len} such that:
1372 * <blockquote><pre>
1373 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1374 * </pre></blockquote>
1375 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1376 * integer <i>k</i> less than {@code len} such that:
1377 * <blockquote><pre>
1378 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) !=
1379 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k)))
1380 * </pre></blockquote>
1381 * </ul>
1382 *
1383 * <p>Note that this method does <em>not</em> take locale into account,
1384 * and will result in unsatisfactory results for certain locales when
1385 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class
1386 * provides locale-sensitive comparison.
1387 *
1388 * @param ignoreCase if {@code true}, ignore case when comparing
1389 * characters.
1390 * @param toffset the starting offset of the subregion in this
1391 * string.
1392 * @param other the string argument.
1393 * @param ooffset the starting offset of the subregion in the string
1394 * argument.
1395 * @param len the number of characters to compare.
1396 * @return {@code true} if the specified subregion of this string
1397 * matches the specified subregion of the string argument;
1398 * {@code false} otherwise. Whether the matching is exact
1399 * or case insensitive depends on the {@code ignoreCase}
1400 * argument.
1401 */
1402 public boolean regionMatches(boolean ignoreCase, int toffset,
1403 String other, int ooffset, int len) {
1404 if (!ignoreCase) {
1405 return regionMatches(toffset, other, ooffset, len);
1406 }
1407 // Note: toffset, ooffset, or len might be near -1>>>1.
1408 if ((ooffset < 0) || (toffset < 0)
1409 || (toffset > (long)length() - len)
1410 || (ooffset > (long)other.length() - len)) {
1411 return false;
1412 }
1413 byte tv[] = value;
1414 byte ov[] = other.value;
1415 if (coder() == other.coder()) {
1416 return isLatin1()
1417 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len)
1418 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len);
1419 }
1420 return isLatin1()
1421 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len)
1422 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len);
1423 }
1424
1425 /**
1426 * Tests if the substring of this string beginning at the
1427 * specified index starts with the specified prefix.
1428 *
1429 * @param prefix the prefix.
1430 * @param toffset where to begin looking in this string.
1431 * @return {@code true} if the character sequence represented by the
1432 * argument is a prefix of the substring of this object starting
1433 * at index {@code toffset}; {@code false} otherwise.
1434 * The result is {@code false} if {@code toffset} is
1435 * negative or greater than the length of this
1436 * {@code String} object; otherwise the result is the same
1437 * as the result of the expression
1438 * <pre>
1439 * this.substring(toffset).startsWith(prefix)
1440 * </pre>
1441 */
1442 public boolean startsWith(String prefix, int toffset) {
1443 // Note: toffset might be near -1>>>1.
1444 if (toffset < 0 || toffset > length() - prefix.length()) {
1445 return false;
1446 }
1447 byte ta[] = value;
1448 byte pa[] = prefix.value;
1449 int po = 0;
1450 int pc = pa.length;
1451 if (coder() == prefix.coder()) {
1452 int to = isLatin1() ? toffset : toffset << 1;
1453 while (po < pc) {
1454 if (ta[to++] != pa[po++]) {
1455 return false;
1456 }
1457 }
1458 } else {
1459 if (isLatin1()) { // && pcoder == UTF16
1460 return false;
1461 }
1462 // coder == UTF16 && pcoder == LATIN1)
1463 while (po < pc) {
1464 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) {
1465 return false;
1466 }
1467 }
1468 }
1469 return true;
1470 }
1471
1472 /**
1473 * Tests if this string starts with the specified prefix.
1474 *
1475 * @param prefix the prefix.
1476 * @return {@code true} if the character sequence represented by the
1477 * argument is a prefix of the character sequence represented by
1478 * this string; {@code false} otherwise.
1479 * Note also that {@code true} will be returned if the
1480 * argument is an empty string or is equal to this
1481 * {@code String} object as determined by the
1482 * {@link #equals(Object)} method.
1483 * @since 1.0
1484 */
1485 public boolean startsWith(String prefix) {
1486 return startsWith(prefix, 0);
1487 }
1488
1489 /**
1490 * Tests if this string ends with the specified suffix.
1491 *
1492 * @param suffix the suffix.
1493 * @return {@code true} if the character sequence represented by the
1494 * argument is a suffix of the character sequence represented by
1495 * this object; {@code false} otherwise. Note that the
1496 * result will be {@code true} if the argument is the
1497 * empty string or is equal to this {@code String} object
1498 * as determined by the {@link #equals(Object)} method.
1499 */
1500 public boolean endsWith(String suffix) {
1501 return startsWith(suffix, length() - suffix.length());
1502 }
1503
1504 /**
1505 * Returns a hash code for this string. The hash code for a
1506 * {@code String} object is computed as
1507 * <blockquote><pre>
1508 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1509 * </pre></blockquote>
1510 * using {@code int} arithmetic, where {@code s[i]} is the
1511 * <i>i</i>th character of the string, {@code n} is the length of
1512 * the string, and {@code ^} indicates exponentiation.
1513 * (The hash value of the empty string is zero.)
1514 *
1515 * @return a hash code value for this object.
1516 */
1517 public int hashCode() {
1518 if (hash == 0 && value.length > 0) {
1519 hash = isLatin1() ? StringLatin1.hashCode(value)
1520 : StringUTF16.hashCode(value);
1521 }
1522 return hash;
1523 }
1524
1525 /**
1526 * Returns the index within this string of the first occurrence of
1527 * the specified character. If a character with value
1528 * {@code ch} occurs in the character sequence represented by
1529 * this {@code String} object, then the index (in Unicode
1530 * code units) of the first such occurrence is returned. For
1531 * values of {@code ch} in the range from 0 to 0xFFFF
1532 * (inclusive), this is the smallest value <i>k</i> such that:
1533 * <blockquote><pre>
1534 * this.charAt(<i>k</i>) == ch
1535 * </pre></blockquote>
1536 * is true. For other values of {@code ch}, it is the
1537 * smallest value <i>k</i> such that:
1538 * <blockquote><pre>
1539 * this.codePointAt(<i>k</i>) == ch
1540 * </pre></blockquote>
1541 * is true. In either case, if no such character occurs in this
1542 * string, then {@code -1} is returned.
1543 *
1544 * @param ch a character (Unicode code point).
1545 * @return the index of the first occurrence of the character in the
1546 * character sequence represented by this object, or
1547 * {@code -1} if the character does not occur.
1548 */
1549 public int indexOf(int ch) {
1550 return indexOf(ch, 0);
1551 }
1552
1553 /**
1554 * Returns the index within this string of the first occurrence of the
1555 * specified character, starting the search at the specified index.
1556 * <p>
1557 * If a character with value {@code ch} occurs in the
1558 * character sequence represented by this {@code String}
1559 * object at an index no smaller than {@code fromIndex}, then
1560 * the index of the first such occurrence is returned. For values
1561 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1562 * this is the smallest value <i>k</i> such that:
1563 * <blockquote><pre>
1564 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1565 * </pre></blockquote>
1566 * is true. For other values of {@code ch}, it is the
1567 * smallest value <i>k</i> such that:
1568 * <blockquote><pre>
1569 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1570 * </pre></blockquote>
1571 * is true. In either case, if no such character occurs in this
1572 * string at or after position {@code fromIndex}, then
1573 * {@code -1} is returned.
1574 *
1575 * <p>
1576 * There is no restriction on the value of {@code fromIndex}. If it
1577 * is negative, it has the same effect as if it were zero: this entire
1578 * string may be searched. If it is greater than the length of this
1579 * string, it has the same effect as if it were equal to the length of
1580 * this string: {@code -1} is returned.
1581 *
1582 * <p>All indices are specified in {@code char} values
1583 * (Unicode code units).
1584 *
1585 * @param ch a character (Unicode code point).
1586 * @param fromIndex the index to start the search from.
1587 * @return the index of the first occurrence of the character in the
1588 * character sequence represented by this object that is greater
1589 * than or equal to {@code fromIndex}, or {@code -1}
1590 * if the character does not occur.
1591 */
1592 public int indexOf(int ch, int fromIndex) {
1593 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex)
1594 : StringUTF16.indexOf(value, ch, fromIndex);
1595 }
1596
1597 /**
1598 * Returns the index within this string of the last occurrence of
1599 * the specified character. For values of {@code ch} in the
1600 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1601 * units) returned is the largest value <i>k</i> such that:
1602 * <blockquote><pre>
1603 * this.charAt(<i>k</i>) == ch
1604 * </pre></blockquote>
1605 * is true. For other values of {@code ch}, it is the
1606 * largest value <i>k</i> such that:
1607 * <blockquote><pre>
1608 * this.codePointAt(<i>k</i>) == ch
1609 * </pre></blockquote>
1610 * is true. In either case, if no such character occurs in this
1611 * string, then {@code -1} is returned. The
1612 * {@code String} is searched backwards starting at the last
1613 * character.
1614 *
1615 * @param ch a character (Unicode code point).
1616 * @return the index of the last occurrence of the character in the
1617 * character sequence represented by this object, or
1618 * {@code -1} if the character does not occur.
1619 */
1620 public int lastIndexOf(int ch) {
1621 return lastIndexOf(ch, length() - 1);
1622 }
1623
1624 /**
1625 * Returns the index within this string of the last occurrence of
1626 * the specified character, searching backward starting at the
1627 * specified index. For values of {@code ch} in the range
1628 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1629 * value <i>k</i> such that:
1630 * <blockquote><pre>
1631 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1632 * </pre></blockquote>
1633 * is true. For other values of {@code ch}, it is the
1634 * largest value <i>k</i> such that:
1635 * <blockquote><pre>
1636 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1637 * </pre></blockquote>
1638 * is true. In either case, if no such character occurs in this
1639 * string at or before position {@code fromIndex}, then
1640 * {@code -1} is returned.
1641 *
1642 * <p>All indices are specified in {@code char} values
1643 * (Unicode code units).
1644 *
1645 * @param ch a character (Unicode code point).
1646 * @param fromIndex the index to start the search from. There is no
1647 * restriction on the value of {@code fromIndex}. If it is
1648 * greater than or equal to the length of this string, it has
1649 * the same effect as if it were equal to one less than the
1650 * length of this string: this entire string may be searched.
1651 * If it is negative, it has the same effect as if it were -1:
1652 * -1 is returned.
1653 * @return the index of the last occurrence of the character in the
1654 * character sequence represented by this object that is less
1655 * than or equal to {@code fromIndex}, or {@code -1}
1656 * if the character does not occur before that point.
1657 */
1658 public int lastIndexOf(int ch, int fromIndex) {
1659 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex)
1660 : StringUTF16.lastIndexOf(value, ch, fromIndex);
1661 }
1662
1663 /**
1664 * Returns the index within this string of the first occurrence of the
1665 * specified substring.
1666 *
1667 * <p>The returned index is the smallest value {@code k} for which:
1668 * <pre>{@code
1669 * this.startsWith(str, k)
1670 * }</pre>
1671 * If no such value of {@code k} exists, then {@code -1} is returned.
1672 *
1673 * @param str the substring to search for.
1674 * @return the index of the first occurrence of the specified substring,
1675 * or {@code -1} if there is no such occurrence.
1676 */
1677 public int indexOf(String str) {
1678 if (coder() == str.coder()) {
1679 return isLatin1() ? StringLatin1.indexOf(value, str.value)
1680 : StringUTF16.indexOf(value, str.value);
1681 }
1682 if (coder() == LATIN1) { // str.coder == UTF16
1683 return -1;
1684 }
1685 return StringUTF16.indexOfLatin1(value, str.value);
1686 }
1687
1688 /**
1689 * Returns the index within this string of the first occurrence of the
1690 * specified substring, starting at the specified index.
1691 *
1692 * <p>The returned index is the smallest value {@code k} for which:
1693 * <pre>{@code
1694 * k >= Math.min(fromIndex, this.length()) &&
1695 * this.startsWith(str, k)
1696 * }</pre>
1697 * If no such value of {@code k} exists, then {@code -1} is returned.
1698 *
1699 * @param str the substring to search for.
1700 * @param fromIndex the index from which to start the search.
1701 * @return the index of the first occurrence of the specified substring,
1702 * starting at the specified index,
1703 * or {@code -1} if there is no such occurrence.
1704 */
1705 public int indexOf(String str, int fromIndex) {
1706 return indexOf(value, coder(), length(), str, fromIndex);
1707 }
1708
1709 /**
1710 * Code shared by String and AbstractStringBuilder to do searches. The
1711 * source is the character array being searched, and the target
1712 * is the string being searched for.
1713 *
1714 * @param src the characters being searched.
1715 * @param srcCoder the coder of the source string.
1716 * @param srcCount length of the source string.
1717 * @param tgtStr the characters being searched for.
1718 * @param fromIndex the index to begin searching from.
1719 */
1720 static int indexOf(byte[] src, byte srcCoder, int srcCount,
1721 String tgtStr, int fromIndex) {
1722 byte[] tgt = tgtStr.value;
1723 byte tgtCoder = tgtStr.coder();
1724 int tgtCount = tgtStr.length();
1725
1726 if (fromIndex >= srcCount) {
1727 return (tgtCount == 0 ? srcCount : -1);
1728 }
1729 if (fromIndex < 0) {
1730 fromIndex = 0;
1731 }
1732 if (tgtCount == 0) {
1733 return fromIndex;
1734 }
1735 if (srcCoder == tgtCoder) {
1736 return srcCoder == LATIN1
1737 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex)
1738 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex);
1739 }
1740 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1741 return -1;
1742 }
1743 // srcCoder == UTF16 && tgtCoder == LATIN1) {
1744 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1745 }
1746
1747 /**
1748 * Returns the index within this string of the last occurrence of the
1749 * specified substring. The last occurrence of the empty string ""
1750 * is considered to occur at the index value {@code this.length()}.
1751 *
1752 * <p>The returned index is the largest value {@code k} for which:
1753 * <pre>{@code
1754 * this.startsWith(str, k)
1755 * }</pre>
1756 * If no such value of {@code k} exists, then {@code -1} is returned.
1757 *
1758 * @param str the substring to search for.
1759 * @return the index of the last occurrence of the specified substring,
1760 * or {@code -1} if there is no such occurrence.
1761 */
1762 public int lastIndexOf(String str) {
1763 return lastIndexOf(str, length());
1764 }
1765
1766 /**
1767 * Returns the index within this string of the last occurrence of the
1768 * specified substring, searching backward starting at the specified index.
1769 *
1770 * <p>The returned index is the largest value {@code k} for which:
1771 * <pre>{@code
1772 * k <= Math.min(fromIndex, this.length()) &&
1773 * this.startsWith(str, k)
1774 * }</pre>
1775 * If no such value of {@code k} exists, then {@code -1} is returned.
1776 *
1777 * @param str the substring to search for.
1778 * @param fromIndex the index to start the search from.
1779 * @return the index of the last occurrence of the specified substring,
1780 * searching backward from the specified index,
1781 * or {@code -1} if there is no such occurrence.
1782 */
1783 public int lastIndexOf(String str, int fromIndex) {
1784 return lastIndexOf(value, coder(), length(), str, fromIndex);
1785 }
1786
1787 /**
1788 * Code shared by String and AbstractStringBuilder to do searches. The
1789 * source is the character array being searched, and the target
1790 * is the string being searched for.
1791 *
1792 * @param src the characters being searched.
1793 * @param srcCoder coder handles the mapping between bytes/chars
1794 * @param srcCount count of the source string.
1795 * @param tgt the characters being searched for.
1796 * @param fromIndex the index to begin searching from.
1797 */
1798 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount,
1799 String tgtStr, int fromIndex) {
1800 byte[] tgt = tgtStr.value;
1801 byte tgtCoder = tgtStr.coder();
1802 int tgtCount = tgtStr.length();
1803 /*
1804 * Check arguments; return immediately where possible. For
1805 * consistency, don't check for null str.
1806 */
1807 int rightIndex = srcCount - tgtCount;
1808 if (fromIndex < 0) {
1809 return -1;
1810 }
1811 if (fromIndex > rightIndex) {
1812 fromIndex = rightIndex;
1813 }
1814 /* Empty string always matches. */
1815 if (tgtCount == 0) {
1816 return fromIndex;
1817 }
1818 if (srcCoder == tgtCoder) {
1819 return srcCoder == LATIN1
1820 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex)
1821 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex);
1822 }
1823 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1824 return -1;
1825 }
1826 // srcCoder == UTF16 && tgtCoder == LATIN1
1827 int min = tgtCount - 1;
1828 int i = min + fromIndex;
1829 int strLastIndex = tgtCount - 1;
1830
1831 char strLastChar = (char)(tgt[strLastIndex] & 0xff);
1832 startSearchForLastChar:
1833 while (true) {
1834 while (i >= min && StringUTF16.getChar(src, i) != strLastChar) {
1835 i--;
1836 }
1837 if (i < min) {
1838 return -1;
1839 }
1840 int j = i - 1;
1841 int start = j - strLastIndex;
1842 int k = strLastIndex - 1;
1843 while (j > start) {
1844 if (StringUTF16.getChar(src, j--) != (tgt[k--] & 0xff)) {
1845 i--;
1846 continue startSearchForLastChar;
1847 }
1848 }
1849 return start + 1;
1850 }
1851 }
1852
1853 /**
1854 * Returns a string that is a substring of this string. The
1855 * substring begins with the character at the specified index and
1856 * extends to the end of this string. <p>
1857 * Examples:
1858 * <blockquote><pre>
1859 * "unhappy".substring(2) returns "happy"
1860 * "Harbison".substring(3) returns "bison"
1861 * "emptiness".substring(9) returns "" (an empty string)
1862 * </pre></blockquote>
1863 *
1864 * @param beginIndex the beginning index, inclusive.
1865 * @return the specified substring.
1866 * @exception IndexOutOfBoundsException if
1867 * {@code beginIndex} is negative or larger than the
1868 * length of this {@code String} object.
1869 */
1870 public String substring(int beginIndex) {
1871 if (beginIndex < 0) {
1872 throw new StringIndexOutOfBoundsException(beginIndex);
1873 }
1874 int subLen = length() - beginIndex;
1875 if (subLen < 0) {
1876 throw new StringIndexOutOfBoundsException(subLen);
1877 }
1878 if (beginIndex == 0) {
1879 return this;
1880 }
1881 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1882 : StringUTF16.newString(value, beginIndex, subLen);
1883 }
1884
1885 /**
1886 * Returns a string that is a substring of this string. The
1887 * substring begins at the specified {@code beginIndex} and
1888 * extends to the character at index {@code endIndex - 1}.
1889 * Thus the length of the substring is {@code endIndex-beginIndex}.
1890 * <p>
1891 * Examples:
1892 * <blockquote><pre>
1893 * "hamburger".substring(4, 8) returns "urge"
1894 * "smiles".substring(1, 5) returns "mile"
1895 * </pre></blockquote>
1896 *
1897 * @param beginIndex the beginning index, inclusive.
1898 * @param endIndex the ending index, exclusive.
1899 * @return the specified substring.
1900 * @exception IndexOutOfBoundsException if the
1901 * {@code beginIndex} is negative, or
1902 * {@code endIndex} is larger than the length of
1903 * this {@code String} object, or
1904 * {@code beginIndex} is larger than
1905 * {@code endIndex}.
1906 */
1907 public String substring(int beginIndex, int endIndex) {
1908 int length = length();
1909 checkBoundsBeginEnd(beginIndex, endIndex, length);
1910 int subLen = endIndex - beginIndex;
1911 if (beginIndex == 0 && endIndex == length) {
1912 return this;
1913 }
1914 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1915 : StringUTF16.newString(value, beginIndex, subLen);
1916 }
1917
1918 /**
1919 * Returns a character sequence that is a subsequence of this sequence.
1920 *
1921 * <p> An invocation of this method of the form
1922 *
1923 * <blockquote><pre>
1924 * str.subSequence(begin, end)</pre></blockquote>
1925 *
1926 * behaves in exactly the same way as the invocation
1927 *
1928 * <blockquote><pre>
1929 * str.substring(begin, end)</pre></blockquote>
1930 *
1931 * @apiNote
1932 * This method is defined so that the {@code String} class can implement
1933 * the {@link CharSequence} interface.
1934 *
1935 * @param beginIndex the begin index, inclusive.
1936 * @param endIndex the end index, exclusive.
1937 * @return the specified subsequence.
1938 *
1939 * @throws IndexOutOfBoundsException
1940 * if {@code beginIndex} or {@code endIndex} is negative,
1941 * if {@code endIndex} is greater than {@code length()},
1942 * or if {@code beginIndex} is greater than {@code endIndex}
1943 *
1944 * @since 1.4
1945 * @spec JSR-51
1946 */
1947 public CharSequence subSequence(int beginIndex, int endIndex) {
1948 return this.substring(beginIndex, endIndex);
1949 }
1950
1951 /**
1952 * Concatenates the specified string to the end of this string.
1953 * <p>
1954 * If the length of the argument string is {@code 0}, then this
1955 * {@code String} object is returned. Otherwise, a
1956 * {@code String} object is returned that represents a character
1957 * sequence that is the concatenation of the character sequence
1958 * represented by this {@code String} object and the character
1959 * sequence represented by the argument string.<p>
1960 * Examples:
1961 * <blockquote><pre>
1962 * "cares".concat("s") returns "caress"
1963 * "to".concat("get").concat("her") returns "together"
1964 * </pre></blockquote>
1965 *
1966 * @param str the {@code String} that is concatenated to the end
1967 * of this {@code String}.
1968 * @return a string that represents the concatenation of this object's
1969 * characters followed by the string argument's characters.
1970 */
1971 public String concat(String str) {
1972 int olen = str.length();
1973 if (olen == 0) {
1974 return this;
1975 }
1976 if (coder() == str.coder()) {
1977 byte[] val = this.value;
1978 byte[] oval = str.value;
1979 int len = val.length + oval.length;
1980 byte[] buf = Arrays.copyOf(val, len);
1981 System.arraycopy(oval, 0, buf, val.length, oval.length);
1982 return new String(buf, coder);
1983 }
1984 int len = length();
1985 byte[] buf = StringUTF16.newBytesFor(len + olen);
1986 getBytes(buf, 0, UTF16);
1987 str.getBytes(buf, len, UTF16);
1988 return new String(buf, UTF16);
1989 }
1990
1991 /**
1992 * Returns a string resulting from replacing all occurrences of
1993 * {@code oldChar} in this string with {@code newChar}.
1994 * <p>
1995 * If the character {@code oldChar} does not occur in the
1996 * character sequence represented by this {@code String} object,
1997 * then a reference to this {@code String} object is returned.
1998 * Otherwise, a {@code String} object is returned that
1999 * represents a character sequence identical to the character sequence
2000 * represented by this {@code String} object, except that every
2001 * occurrence of {@code oldChar} is replaced by an occurrence
2002 * of {@code newChar}.
2003 * <p>
2004 * Examples:
2005 * <blockquote><pre>
2006 * "mesquite in your cellar".replace('e', 'o')
2007 * returns "mosquito in your collar"
2008 * "the war of baronets".replace('r', 'y')
2009 * returns "the way of bayonets"
2010 * "sparring with a purple porpoise".replace('p', 't')
2011 * returns "starring with a turtle tortoise"
2012 * "JonL".replace('q', 'x') returns "JonL" (no change)
2013 * </pre></blockquote>
2014 *
2015 * @param oldChar the old character.
2016 * @param newChar the new character.
2017 * @return a string derived from this string by replacing every
2018 * occurrence of {@code oldChar} with {@code newChar}.
2019 */
2020 public String replace(char oldChar, char newChar) {
2021 if (oldChar != newChar) {
2022 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar)
2023 : StringUTF16.replace(value, oldChar, newChar);
2024 if (ret != null) {
2025 return ret;
2026 }
2027 }
2028 return this;
2029 }
2030
2031 /**
2032 * Tells whether or not this string matches the given <a
2033 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2034 *
2035 * <p> An invocation of this method of the form
2036 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2037 * same result as the expression
2038 *
2039 * <blockquote>
2040 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2041 * matches(<i>regex</i>, <i>str</i>)}
2042 * </blockquote>
2043 *
2044 * @param regex
2045 * the regular expression to which this string is to be matched
2046 *
2047 * @return {@code true} if, and only if, this string matches the
2048 * given regular expression
2049 *
2050 * @throws PatternSyntaxException
2051 * if the regular expression's syntax is invalid
2052 *
2053 * @see java.util.regex.Pattern
2054 *
2055 * @since 1.4
2056 * @spec JSR-51
2057 */
2058 public boolean matches(String regex) {
2059 return Pattern.matches(regex, this);
2060 }
2061
2062 /**
2063 * Returns true if and only if this string contains the specified
2064 * sequence of char values.
2065 *
2066 * @param s the sequence to search for
2067 * @return true if this string contains {@code s}, false otherwise
2068 * @since 1.5
2069 */
2070 public boolean contains(CharSequence s) {
2071 return indexOf(s.toString()) >= 0;
2072 }
2073
2074 /**
2075 * Replaces the first substring of this string that matches the given <a
2076 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2077 * given replacement.
2078 *
2079 * <p> An invocation of this method of the form
2080 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2081 * yields exactly the same result as the expression
2082 *
2083 * <blockquote>
2084 * <code>
2085 * {@link java.util.regex.Pattern}.{@link
2086 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2087 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2088 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2089 * </code>
2090 * </blockquote>
2091 *
2092 *<p>
2093 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2094 * replacement string may cause the results to be different than if it were
2095 * being treated as a literal replacement string; see
2096 * {@link java.util.regex.Matcher#replaceFirst}.
2097 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2098 * meaning of these characters, if desired.
2099 *
2100 * @param regex
2101 * the regular expression to which this string is to be matched
2102 * @param replacement
2103 * the string to be substituted for the first match
2104 *
2105 * @return The resulting {@code String}
2106 *
2107 * @throws PatternSyntaxException
2108 * if the regular expression's syntax is invalid
2109 *
2110 * @see java.util.regex.Pattern
2111 *
2112 * @since 1.4
2113 * @spec JSR-51
2114 */
2115 public String replaceFirst(String regex, String replacement) {
2116 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2117 }
2118
2119 /**
2120 * Replaces each substring of this string that matches the given <a
2121 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2122 * given replacement.
2123 *
2124 * <p> An invocation of this method of the form
2125 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2126 * yields exactly the same result as the expression
2127 *
2128 * <blockquote>
2129 * <code>
2130 * {@link java.util.regex.Pattern}.{@link
2131 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2132 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2133 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2134 * </code>
2135 * </blockquote>
2136 *
2137 *<p>
2138 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2139 * replacement string may cause the results to be different than if it were
2140 * being treated as a literal replacement string; see
2141 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2142 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2143 * meaning of these characters, if desired.
2144 *
2145 * @param regex
2146 * the regular expression to which this string is to be matched
2147 * @param replacement
2148 * the string to be substituted for each match
2149 *
2150 * @return The resulting {@code String}
2151 *
2152 * @throws PatternSyntaxException
2153 * if the regular expression's syntax is invalid
2154 *
2155 * @see java.util.regex.Pattern
2156 *
2157 * @since 1.4
2158 * @spec JSR-51
2159 */
2160 public String replaceAll(String regex, String replacement) {
2161 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2162 }
2163
2164 /**
2165 * Replaces each substring of this string that matches the literal target
2166 * sequence with the specified literal replacement sequence. The
2167 * replacement proceeds from the beginning of the string to the end, for
2168 * example, replacing "aa" with "b" in the string "aaa" will result in
2169 * "ba" rather than "ab".
2170 *
2171 * @param target The sequence of char values to be replaced
2172 * @param replacement The replacement sequence of char values
2173 * @return The resulting string
2174 * @since 1.5
2175 */
2176 public String replace(CharSequence target, CharSequence replacement) {
2177 String tgtStr = target.toString();
2178 String replStr = replacement.toString();
2179 int j = indexOf(tgtStr);
2180 if (j < 0) {
2181 return this;
2182 }
2183 int tgtLen = tgtStr.length();
2184 int tgtLen1 = Math.max(tgtLen, 1);
2185 int thisLen = length();
2186
2187 int newLenHint = thisLen - tgtLen + replStr.length();
2188 if (newLenHint < 0) {
2189 throw new OutOfMemoryError();
2190 }
2191 StringBuilder sb = new StringBuilder(newLenHint);
2192 int i = 0;
2193 do {
2194 sb.append(this, i, j).append(replStr);
2195 i = j + tgtLen;
2196 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0);
2197 return sb.append(this, i, thisLen).toString();
2198 }
2199
2200 /**
2201 * Splits this string around matches of the given
2202 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2203 *
2204 * <p> The array returned by this method contains each substring of this
2205 * string that is terminated by another substring that matches the given
2206 * expression or is terminated by the end of the string. The substrings in
2207 * the array are in the order in which they occur in this string. If the
2208 * expression does not match any part of the input then the resulting array
2209 * has just one element, namely this string.
2210 *
2211 * <p> When there is a positive-width match at the beginning of this
2212 * string then an empty leading substring is included at the beginning
2213 * of the resulting array. A zero-width match at the beginning however
2214 * never produces such empty leading substring.
2215 *
2216 * <p> The {@code limit} parameter controls the number of times the
2217 * pattern is applied and therefore affects the length of the resulting
2218 * array. If the limit <i>n</i> is greater than zero then the pattern
2219 * will be applied at most <i>n</i> - 1 times, the array's
2220 * length will be no greater than <i>n</i>, and the array's last entry
2221 * will contain all input beyond the last matched delimiter. If <i>n</i>
2222 * is non-positive then the pattern will be applied as many times as
2223 * possible and the array can have any length. If <i>n</i> is zero then
2224 * the pattern will be applied as many times as possible, the array can
2225 * have any length, and trailing empty strings will be discarded.
2226 *
2227 * <p> The string {@code "boo:and:foo"}, for example, yields the
2228 * following results with these parameters:
2229 *
2230 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2231 * <tr>
2232 * <th>Regex</th>
2233 * <th>Limit</th>
2234 * <th>Result</th>
2235 * </tr>
2236 * <tr><td align=center>:</td>
2237 * <td align=center>2</td>
2238 * <td>{@code { "boo", "and:foo" }}</td></tr>
2239 * <tr><td align=center>:</td>
2240 * <td align=center>5</td>
2241 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2242 * <tr><td align=center>:</td>
2243 * <td align=center>-2</td>
2244 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2245 * <tr><td align=center>o</td>
2246 * <td align=center>5</td>
2247 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2248 * <tr><td align=center>o</td>
2249 * <td align=center>-2</td>
2250 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2251 * <tr><td align=center>o</td>
2252 * <td align=center>0</td>
2253 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2254 * </table></blockquote>
2255 *
2256 * <p> An invocation of this method of the form
2257 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2258 * yields the same result as the expression
2259 *
2260 * <blockquote>
2261 * <code>
2262 * {@link java.util.regex.Pattern}.{@link
2263 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2264 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2265 * </code>
2266 * </blockquote>
2267 *
2268 *
2269 * @param regex
2270 * the delimiting regular expression
2271 *
2272 * @param limit
2273 * the result threshold, as described above
2274 *
2275 * @return the array of strings computed by splitting this string
2276 * around matches of the given regular expression
2277 *
2278 * @throws PatternSyntaxException
2279 * if the regular expression's syntax is invalid
2280 *
2281 * @see java.util.regex.Pattern
2282 *
2283 * @since 1.4
2284 * @spec JSR-51
2285 */
2286 public String[] split(String regex, int limit) {
2287 /* fastpath if the regex is a
2288 (1)one-char String and this character is not one of the
2289 RegEx's meta characters ".$|()[{^?*+\\", or
2290 (2)two-char String and the first char is the backslash and
2291 the second is not the ascii digit or ascii letter.
2292 */
2293 char ch = 0;
2294 if (((regex.length() == 1 &&
2295 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2296 (regex.length() == 2 &&
2297 regex.charAt(0) == '\\' &&
2298 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2299 ((ch-'a')|('z'-ch)) < 0 &&
2300 ((ch-'A')|('Z'-ch)) < 0)) &&
2301 (ch < Character.MIN_HIGH_SURROGATE ||
2302 ch > Character.MAX_LOW_SURROGATE))
2303 {
2304 int off = 0;
2305 int next = 0;
2306 boolean limited = limit > 0;
2307 ArrayList<String> list = new ArrayList<>();
2308 while ((next = indexOf(ch, off)) != -1) {
2309 if (!limited || list.size() < limit - 1) {
2310 list.add(substring(off, next));
2311 off = next + 1;
2312 } else { // last one
2313 //assert (list.size() == limit - 1);
2314 int last = length();
2315 list.add(substring(off, last));
2316 off = last;
2317 break;
2318 }
2319 }
2320 // If no match was found, return this
2321 if (off == 0)
2322 return new String[]{this};
2323
2324 // Add remaining segment
2325 if (!limited || list.size() < limit)
2326 list.add(substring(off, length()));
2327
2328 // Construct result
2329 int resultSize = list.size();
2330 if (limit == 0) {
2331 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2332 resultSize--;
2333 }
2334 }
2335 String[] result = new String[resultSize];
2336 return list.subList(0, resultSize).toArray(result);
2337 }
2338 return Pattern.compile(regex).split(this, limit);
2339 }
2340
2341 /**
2342 * Splits this string around matches of the given <a
2343 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2344 *
2345 * <p> This method works as if by invoking the two-argument {@link
2346 * #split(String, int) split} method with the given expression and a limit
2347 * argument of zero. Trailing empty strings are therefore not included in
2348 * the resulting array.
2349 *
2350 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2351 * results with these expressions:
2352 *
2353 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2354 * <tr>
2355 * <th>Regex</th>
2356 * <th>Result</th>
2357 * </tr>
2358 * <tr><td align=center>:</td>
2359 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2360 * <tr><td align=center>o</td>
2361 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2362 * </table></blockquote>
2363 *
2364 *
2365 * @param regex
2366 * the delimiting regular expression
2367 *
2368 * @return the array of strings computed by splitting this string
2369 * around matches of the given regular expression
2370 *
2371 * @throws PatternSyntaxException
2372 * if the regular expression's syntax is invalid
2373 *
2374 * @see java.util.regex.Pattern
2375 *
2376 * @since 1.4
2377 * @spec JSR-51
2378 */
2379 public String[] split(String regex) {
2380 return split(regex, 0);
2381 }
2382
2383 /**
2384 * Returns a new String composed of copies of the
2385 * {@code CharSequence elements} joined together with a copy of
2386 * the specified {@code delimiter}.
2387 *
2388 * <blockquote>For example,
2389 * <pre>{@code
2390 * String message = String.join("-", "Java", "is", "cool");
2391 * // message returned is: "Java-is-cool"
2392 * }</pre></blockquote>
2393 *
2394 * Note that if an element is null, then {@code "null"} is added.
2395 *
2396 * @param delimiter the delimiter that separates each element
2397 * @param elements the elements to join together.
2398 *
2399 * @return a new {@code String} that is composed of the {@code elements}
2400 * separated by the {@code delimiter}
2401 *
2402 * @throws NullPointerException If {@code delimiter} or {@code elements}
2403 * is {@code null}
2404 *
2405 * @see java.util.StringJoiner
2406 * @since 1.8
2407 */
2408 public static String join(CharSequence delimiter, CharSequence... elements) {
2409 Objects.requireNonNull(delimiter);
2410 Objects.requireNonNull(elements);
2411 // Number of elements not likely worth Arrays.stream overhead.
2412 StringJoiner joiner = new StringJoiner(delimiter);
2413 for (CharSequence cs: elements) {
2414 joiner.add(cs);
2415 }
2416 return joiner.toString();
2417 }
2418
2419 /**
2420 * Returns a new {@code String} composed of copies of the
2421 * {@code CharSequence elements} joined together with a copy of the
2422 * specified {@code delimiter}.
2423 *
2424 * <blockquote>For example,
2425 * <pre>{@code
2426 * List<String> strings = new LinkedList<>();
2427 * strings.add("Java");strings.add("is");
2428 * strings.add("cool");
2429 * String message = String.join(" ", strings);
2430 * //message returned is: "Java is cool"
2431 *
2432 * Set<String> strings = new LinkedHashSet<>();
2433 * strings.add("Java"); strings.add("is");
2434 * strings.add("very"); strings.add("cool");
2435 * String message = String.join("-", strings);
2436 * //message returned is: "Java-is-very-cool"
2437 * }</pre></blockquote>
2438 *
2439 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2440 *
2441 * @param delimiter a sequence of characters that is used to separate each
2442 * of the {@code elements} in the resulting {@code String}
2443 * @param elements an {@code Iterable} that will have its {@code elements}
2444 * joined together.
2445 *
2446 * @return a new {@code String} that is composed from the {@code elements}
2447 * argument
2448 *
2449 * @throws NullPointerException If {@code delimiter} or {@code elements}
2450 * is {@code null}
2451 *
2452 * @see #join(CharSequence,CharSequence...)
2453 * @see java.util.StringJoiner
2454 * @since 1.8
2455 */
2456 public static String join(CharSequence delimiter,
2457 Iterable<? extends CharSequence> elements) {
2458 Objects.requireNonNull(delimiter);
2459 Objects.requireNonNull(elements);
2460 StringJoiner joiner = new StringJoiner(delimiter);
2461 for (CharSequence cs: elements) {
2462 joiner.add(cs);
2463 }
2464 return joiner.toString();
2465 }
2466
2467 /**
2468 * Converts all of the characters in this {@code String} to lower
2469 * case using the rules of the given {@code Locale}. Case mapping is based
2470 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2471 * class. Since case mappings are not always 1:1 char mappings, the resulting
2472 * {@code String} may be a different length than the original {@code String}.
2473 * <p>
2474 * Examples of lowercase mappings are in the following table:
2475 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2476 * <tr>
2477 * <th>Language Code of Locale</th>
2478 * <th>Upper Case</th>
2479 * <th>Lower Case</th>
2480 * <th>Description</th>
2481 * </tr>
2482 * <tr>
2483 * <td>tr (Turkish)</td>
2484 * <td>\u0130</td>
2485 * <td>\u0069</td>
2486 * <td>capital letter I with dot above -> small letter i</td>
2487 * </tr>
2488 * <tr>
2489 * <td>tr (Turkish)</td>
2490 * <td>\u0049</td>
2491 * <td>\u0131</td>
2492 * <td>capital letter I -> small letter dotless i </td>
2493 * </tr>
2494 * <tr>
2495 * <td>(all)</td>
2496 * <td>French Fries</td>
2497 * <td>french fries</td>
2498 * <td>lowercased all chars in String</td>
2499 * </tr>
2500 * <tr>
2501 * <td>(all)</td>
2502 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2503 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2504 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2505 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2506 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2507 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2508 * <td>lowercased all chars in String</td>
2509 * </tr>
2510 * </table>
2511 *
2512 * @param locale use the case transformation rules for this locale
2513 * @return the {@code String}, converted to lowercase.
2514 * @see java.lang.String#toLowerCase()
2515 * @see java.lang.String#toUpperCase()
2516 * @see java.lang.String#toUpperCase(Locale)
2517 * @since 1.1
2518 */
2519 public String toLowerCase(Locale locale) {
2520 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale)
2521 : StringUTF16.toLowerCase(this, value, locale);
2522 }
2523
2524 /**
2525 * Converts all of the characters in this {@code String} to lower
2526 * case using the rules of the default locale. This is equivalent to calling
2527 * {@code toLowerCase(Locale.getDefault())}.
2528 * <p>
2529 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2530 * results if used for strings that are intended to be interpreted locale
2531 * independently.
2532 * Examples are programming language identifiers, protocol keys, and HTML
2533 * tags.
2534 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2535 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2536 * LATIN SMALL LETTER DOTLESS I character.
2537 * To obtain correct results for locale insensitive strings, use
2538 * {@code toLowerCase(Locale.ROOT)}.
2539 *
2540 * @return the {@code String}, converted to lowercase.
2541 * @see java.lang.String#toLowerCase(Locale)
2542 */
2543 public String toLowerCase() {
2544 return toLowerCase(Locale.getDefault());
2545 }
2546
2547 /**
2548 * Converts all of the characters in this {@code String} to upper
2549 * case using the rules of the given {@code Locale}. Case mapping is based
2550 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2551 * class. Since case mappings are not always 1:1 char mappings, the resulting
2552 * {@code String} may be a different length than the original {@code String}.
2553 * <p>
2554 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2555 *
2556 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2557 * <tr>
2558 * <th>Language Code of Locale</th>
2559 * <th>Lower Case</th>
2560 * <th>Upper Case</th>
2561 * <th>Description</th>
2562 * </tr>
2563 * <tr>
2564 * <td>tr (Turkish)</td>
2565 * <td>\u0069</td>
2566 * <td>\u0130</td>
2567 * <td>small letter i -> capital letter I with dot above</td>
2568 * </tr>
2569 * <tr>
2570 * <td>tr (Turkish)</td>
2571 * <td>\u0131</td>
2572 * <td>\u0049</td>
2573 * <td>small letter dotless i -> capital letter I</td>
2574 * </tr>
2575 * <tr>
2576 * <td>(all)</td>
2577 * <td>\u00df</td>
2578 * <td>\u0053 \u0053</td>
2579 * <td>small letter sharp s -> two letters: SS</td>
2580 * </tr>
2581 * <tr>
2582 * <td>(all)</td>
2583 * <td>Fahrvergnügen</td>
2584 * <td>FAHRVERGNÜGEN</td>
2585 * <td></td>
2586 * </tr>
2587 * </table>
2588 * @param locale use the case transformation rules for this locale
2589 * @return the {@code String}, converted to uppercase.
2590 * @see java.lang.String#toUpperCase()
2591 * @see java.lang.String#toLowerCase()
2592 * @see java.lang.String#toLowerCase(Locale)
2593 * @since 1.1
2594 */
2595 public String toUpperCase(Locale locale) {
2596 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale)
2597 : StringUTF16.toUpperCase(this, value, locale);
2598 }
2599
2600 /**
2601 * Converts all of the characters in this {@code String} to upper
2602 * case using the rules of the default locale. This method is equivalent to
2603 * {@code toUpperCase(Locale.getDefault())}.
2604 * <p>
2605 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2606 * results if used for strings that are intended to be interpreted locale
2607 * independently.
2608 * Examples are programming language identifiers, protocol keys, and HTML
2609 * tags.
2610 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2611 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2612 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2613 * To obtain correct results for locale insensitive strings, use
2614 * {@code toUpperCase(Locale.ROOT)}.
2615 *
2616 * @return the {@code String}, converted to uppercase.
2617 * @see java.lang.String#toUpperCase(Locale)
2618 */
2619 public String toUpperCase() {
2620 return toUpperCase(Locale.getDefault());
2621 }
2622
2623 /**
2624 * Returns a string whose value is this string, with any leading and trailing
2625 * whitespace removed.
2626 * <p>
2627 * If this {@code String} object represents an empty character
2628 * sequence, or the first and last characters of character sequence
2629 * represented by this {@code String} object both have codes
2630 * greater than {@code '\u005Cu0020'} (the space character), then a
2631 * reference to this {@code String} object is returned.
2632 * <p>
2633 * Otherwise, if there is no character with a code greater than
2634 * {@code '\u005Cu0020'} in the string, then a
2635 * {@code String} object representing an empty string is
2636 * returned.
2637 * <p>
2638 * Otherwise, let <i>k</i> be the index of the first character in the
2639 * string whose code is greater than {@code '\u005Cu0020'}, and let
2640 * <i>m</i> be the index of the last character in the string whose code
2641 * is greater than {@code '\u005Cu0020'}. A {@code String}
2642 * object is returned, representing the substring of this string that
2643 * begins with the character at index <i>k</i> and ends with the
2644 * character at index <i>m</i>-that is, the result of
2645 * {@code this.substring(k, m + 1)}.
2646 * <p>
2647 * This method may be used to trim whitespace (as defined above) from
2648 * the beginning and end of a string.
2649 *
2650 * @return A string whose value is this string, with any leading and trailing white
2651 * space removed, or this string if it has no leading or
2652 * trailing white space.
2653 */
2654 public String trim() {
2655 String ret = isLatin1() ? StringLatin1.trim(value)
2656 : StringUTF16.trim(value);
2657 return ret == null ? this : ret;
2658 }
2659
2660 /**
2661 * This object (which is already a string!) is itself returned.
2662 *
2663 * @return the string itself.
2664 */
2665 public String toString() {
2666 return this;
2667 }
2668
2669 /**
2670 * Returns a stream of {@code int} zero-extending the {@code char} values
2671 * from this sequence. Any char which maps to a <a
2672 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code
2673 * point</a> is passed through uninterpreted.
2674 *
2675 * @return an IntStream of char values from this sequence
2676 * @since 9
2677 */
2678 @Override
2679 public IntStream chars() {
2680 return StreamSupport.intStream(
2681 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
2682 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE),
2683 false);
2684 }
2685
2686
2687 /**
2688 * Returns a stream of code point values from this sequence. Any surrogate
2689 * pairs encountered in the sequence are combined as if by {@linkplain
2690 * Character#toCodePoint Character.toCodePoint} and the result is passed
2691 * to the stream. Any other code units, including ordinary BMP characters,
2692 * unpaired surrogates, and undefined code units, are zero-extended to
2693 * {@code int} values which are then passed to the stream.
2694 *
2695 * @return an IntStream of Unicode code points from this sequence
2696 * @since 9
2697 */
2698 @Override
2699 public IntStream codePoints() {
2700 return StreamSupport.intStream(
2701 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
2702 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE),
2703 false);
2704 }
2705
2706 /**
2707 * Converts this string to a new character array.
2708 *
2709 * @return a newly allocated character array whose length is the length
2710 * of this string and whose contents are initialized to contain
2711 * the character sequence represented by this string.
2712 */
2713 public char[] toCharArray() {
2714 return isLatin1() ? StringLatin1.toChars(value)
2715 : StringUTF16.toChars(value);
2716 }
2717
2718 /**
2719 * Returns a formatted string using the specified format string and
2720 * arguments.
2721 *
2722 * <p> The locale always used is the one returned by {@link
2723 * java.util.Locale#getDefault() Locale.getDefault()}.
2724 *
2725 * @param format
2726 * A <a href="../util/Formatter.html#syntax">format string</a>
2727 *
2728 * @param args
2729 * Arguments referenced by the format specifiers in the format
2730 * string. If there are more arguments than format specifiers, the
2731 * extra arguments are ignored. The number of arguments is
2732 * variable and may be zero. The maximum number of arguments is
2733 * limited by the maximum dimension of a Java array as defined by
2734 * <cite>The Java™ Virtual Machine Specification</cite>.
2735 * The behaviour on a
2736 * {@code null} argument depends on the <a
2737 * href="../util/Formatter.html#syntax">conversion</a>.
2738 *
2739 * @throws java.util.IllegalFormatException
2740 * If a format string contains an illegal syntax, a format
2741 * specifier that is incompatible with the given arguments,
2742 * insufficient arguments given the format string, or other
2743 * illegal conditions. For specification of all possible
2744 * formatting errors, see the <a
2745 * href="../util/Formatter.html#detail">Details</a> section of the
2746 * formatter class specification.
2747 *
2748 * @return A formatted string
2749 *
2750 * @see java.util.Formatter
2751 * @since 1.5
2752 */
2753 public static String format(String format, Object... args) {
2754 return new Formatter().format(format, args).toString();
2755 }
2756
2757 /**
2758 * Returns a formatted string using the specified locale, format string,
2759 * and arguments.
2760 *
2761 * @param l
2762 * The {@linkplain java.util.Locale locale} to apply during
2763 * formatting. If {@code l} is {@code null} then no localization
2764 * is applied.
2765 *
2766 * @param format
2767 * A <a href="../util/Formatter.html#syntax">format string</a>
2768 *
2769 * @param args
2770 * Arguments referenced by the format specifiers in the format
2771 * string. If there are more arguments than format specifiers, the
2772 * extra arguments are ignored. The number of arguments is
2773 * variable and may be zero. The maximum number of arguments is
2774 * limited by the maximum dimension of a Java array as defined by
2775 * <cite>The Java™ Virtual Machine Specification</cite>.
2776 * The behaviour on a
2777 * {@code null} argument depends on the
2778 * <a href="../util/Formatter.html#syntax">conversion</a>.
2779 *
2780 * @throws java.util.IllegalFormatException
2781 * If a format string contains an illegal syntax, a format
2782 * specifier that is incompatible with the given arguments,
2783 * insufficient arguments given the format string, or other
2784 * illegal conditions. For specification of all possible
2785 * formatting errors, see the <a
2786 * href="../util/Formatter.html#detail">Details</a> section of the
2787 * formatter class specification
2788 *
2789 * @return A formatted string
2790 *
2791 * @see java.util.Formatter
2792 * @since 1.5
2793 */
2794 public static String format(Locale l, String format, Object... args) {
2795 return new Formatter(l).format(format, args).toString();
2796 }
2797
2798 /**
2799 * Returns the string representation of the {@code Object} argument.
2800 *
2801 * @param obj an {@code Object}.
2802 * @return if the argument is {@code null}, then a string equal to
2803 * {@code "null"}; otherwise, the value of
2804 * {@code obj.toString()} is returned.
2805 * @see java.lang.Object#toString()
2806 */
2807 public static String valueOf(Object obj) {
2808 return (obj == null) ? "null" : obj.toString();
2809 }
2810
2811 /**
2812 * Returns the string representation of the {@code char} array
2813 * argument. The contents of the character array are copied; subsequent
2814 * modification of the character array does not affect the returned
2815 * string.
2816 *
2817 * @param data the character array.
2818 * @return a {@code String} that contains the characters of the
2819 * character array.
2820 */
2821 public static String valueOf(char data[]) {
2822 return new String(data);
2823 }
2824
2825 /**
2826 * Returns the string representation of a specific subarray of the
2827 * {@code char} array argument.
2828 * <p>
2829 * The {@code offset} argument is the index of the first
2830 * character of the subarray. The {@code count} argument
2831 * specifies the length of the subarray. The contents of the subarray
2832 * are copied; subsequent modification of the character array does not
2833 * affect the returned string.
2834 *
2835 * @param data the character array.
2836 * @param offset initial offset of the subarray.
2837 * @param count length of the subarray.
2838 * @return a {@code String} that contains the characters of the
2839 * specified subarray of the character array.
2840 * @exception IndexOutOfBoundsException if {@code offset} is
2841 * negative, or {@code count} is negative, or
2842 * {@code offset+count} is larger than
2843 * {@code data.length}.
2844 */
2845 public static String valueOf(char data[], int offset, int count) {
2846 return new String(data, offset, count);
2847 }
2848
2849 /**
2850 * Equivalent to {@link #valueOf(char[], int, int)}.
2851 *
2852 * @param data the character array.
2853 * @param offset initial offset of the subarray.
2854 * @param count length of the subarray.
2855 * @return a {@code String} that contains the characters of the
2856 * specified subarray of the character array.
2857 * @exception IndexOutOfBoundsException if {@code offset} is
2858 * negative, or {@code count} is negative, or
2859 * {@code offset+count} is larger than
2860 * {@code data.length}.
2861 */
2862 public static String copyValueOf(char data[], int offset, int count) {
2863 return new String(data, offset, count);
2864 }
2865
2866 /**
2867 * Equivalent to {@link #valueOf(char[])}.
2868 *
2869 * @param data the character array.
2870 * @return a {@code String} that contains the characters of the
2871 * character array.
2872 */
2873 public static String copyValueOf(char data[]) {
2874 return new String(data);
2875 }
2876
2877 /**
2878 * Returns the string representation of the {@code boolean} argument.
2879 *
2880 * @param b a {@code boolean}.
2881 * @return if the argument is {@code true}, a string equal to
2882 * {@code "true"} is returned; otherwise, a string equal to
2883 * {@code "false"} is returned.
2884 */
2885 public static String valueOf(boolean b) {
2886 return b ? "true" : "false";
2887 }
2888
2889 /**
2890 * Returns the string representation of the {@code char}
2891 * argument.
2892 *
2893 * @param c a {@code char}.
2894 * @return a string of length {@code 1} containing
2895 * as its single character the argument {@code c}.
2896 */
2897 public static String valueOf(char c) {
2898 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) {
2899 return new String(StringLatin1.toBytes(c), LATIN1);
2900 }
2901 return new String(StringUTF16.toBytes(c), UTF16);
2902 }
2903
2904 /**
2905 * Returns the string representation of the {@code int} argument.
2906 * <p>
2907 * The representation is exactly the one returned by the
2908 * {@code Integer.toString} method of one argument.
2909 *
2910 * @param i an {@code int}.
2911 * @return a string representation of the {@code int} argument.
2912 * @see java.lang.Integer#toString(int, int)
2913 */
2914 public static String valueOf(int i) {
2915 return Integer.toString(i);
2916 }
2917
2918 /**
2919 * Returns the string representation of the {@code long} argument.
2920 * <p>
2921 * The representation is exactly the one returned by the
2922 * {@code Long.toString} method of one argument.
2923 *
2924 * @param l a {@code long}.
2925 * @return a string representation of the {@code long} argument.
2926 * @see java.lang.Long#toString(long)
2927 */
2928 public static String valueOf(long l) {
2929 return Long.toString(l);
2930 }
2931
2932 /**
2933 * Returns the string representation of the {@code float} argument.
2934 * <p>
2935 * The representation is exactly the one returned by the
2936 * {@code Float.toString} method of one argument.
2937 *
2938 * @param f a {@code float}.
2939 * @return a string representation of the {@code float} argument.
2940 * @see java.lang.Float#toString(float)
2941 */
2942 public static String valueOf(float f) {
2943 return Float.toString(f);
2944 }
2945
2946 /**
2947 * Returns the string representation of the {@code double} argument.
2948 * <p>
2949 * The representation is exactly the one returned by the
2950 * {@code Double.toString} method of one argument.
2951 *
2952 * @param d a {@code double}.
2953 * @return a string representation of the {@code double} argument.
2954 * @see java.lang.Double#toString(double)
2955 */
2956 public static String valueOf(double d) {
2957 return Double.toString(d);
2958 }
2959
2960 /**
2961 * Returns a canonical representation for the string object.
2962 * <p>
2963 * A pool of strings, initially empty, is maintained privately by the
2964 * class {@code String}.
2965 * <p>
2966 * When the intern method is invoked, if the pool already contains a
2967 * string equal to this {@code String} object as determined by
2968 * the {@link #equals(Object)} method, then the string from the pool is
2969 * returned. Otherwise, this {@code String} object is added to the
2970 * pool and a reference to this {@code String} object is returned.
2971 * <p>
2972 * It follows that for any two strings {@code s} and {@code t},
2973 * {@code s.intern() == t.intern()} is {@code true}
2974 * if and only if {@code s.equals(t)} is {@code true}.
2975 * <p>
2976 * All literal strings and string-valued constant expressions are
2977 * interned. String literals are defined in section 3.10.5 of the
2978 * <cite>The Java™ Language Specification</cite>.
2979 *
2980 * @return a string that has the same contents as this string, but is
2981 * guaranteed to be from a pool of unique strings.
2982 */
2983 public native String intern();
2984
2985 ////////////////////////////////////////////////////////////////
2986
2987 /**
2988 * Copy character bytes from this string into dst starting at dstBegin.
2989 * This method doesn't perform any range checking.
2990 *
2991 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two
2992 * coders are different, and dst is big enough (range check)
2993 *
2994 * @param dstBegin the char index, not offset of byte[]
2995 * @param coder the coder of dst[]
2996 */
2997 void getBytes(byte dst[], int dstBegin, byte coder) {
2998 if (coder() == coder) {
2999 System.arraycopy(value, 0, dst, dstBegin << coder, value.length);
3000 } else { // this.coder == LATIN && coder == UTF16
3001 StringLatin1.inflate(value, 0, dst, dstBegin, value.length);
3002 }
3003 }
3004
3005 /*
3006 * Package private constructor. Trailing Void argument is there for
3007 * disambiguating it against other (public) constructors.
3008 *
3009 * Stores the char[] value into a byte[] that each byte represents
3010 * the8 low-order bits of the corresponding character, if the char[]
3011 * contains only latin1 character. Or a byte[] that stores all
3012 * characters in their byte sequences defined by the {@code StringUTF16}.
3013 */
3014 String(char[] value, int off, int len, Void sig) {
3015 if (len == 0) {
3016 this.value = "".value;
3017 this.coder = "".coder;
3018 return;
3019 }
3020 if (COMPACT_STRINGS) {
3021 byte[] val = StringUTF16.compress(value, off, len);
3022 if (val != null) {
3023 this.value = val;
3024 this.coder = LATIN1;
3025 return;
3026 }
3027 }
3028 this.coder = UTF16;
3029 this.value = StringUTF16.toBytes(value, off, len);
3030 }
3031
3032 /*
3033 * Package private constructor. Trailing Void argument is there for
3034 * disambiguating it against other (public) constructors.
3035 */
3036 String(AbstractStringBuilder asb, Void sig) {
3037 byte[] val = asb.getValue();
3038 int length = asb.length();
3039 if (asb.isLatin1()) {
3040 this.coder = LATIN1;
3041 this.value = Arrays.copyOfRange(val, 0, length);
3042 } else {
3043 if (COMPACT_STRINGS) {
3044 byte[] buf = StringUTF16.compress(val, 0, length);
3045 if (buf != null) {
3046 this.coder = LATIN1;
3047 this.value = buf;
3048 return;
3049 }
3050 }
3051 this.coder = UTF16;
3052 this.value = Arrays.copyOfRange(val, 0, length << 1);
3053 }
3054 }
3055
3056 /*
3057 * Package private constructor which shares value array for speed.
3058 */
3059 String(byte[] value, byte coder) {
3060 this.value = value;
3061 this.coder = coder;
3062 }
3063
3064 byte coder() {
3065 return COMPACT_STRINGS ? coder : UTF16;
3066 }
3067
3068 private boolean isLatin1() {
3069 return COMPACT_STRINGS && coder == LATIN1;
3070 }
3071
3072 static final byte LATIN1 = 0;
3073 static final byte UTF16 = 1;
3074
3075 /*
3076 * StringIndexOutOfBoundsException if {@code index} is
3077 * negative or greater than or equal to {@code length}.
3078 */
3079 static void checkIndex(int index, int length) {
3080 if (index < 0 || index >= length) {
3081 throw new StringIndexOutOfBoundsException("index " + index);
3082 }
3083 }
3084
3085 /*
3086 * StringIndexOutOfBoundsException if {@code offset}
3087 * is negative or greater than {@code length}.
3088 */
3089 static void checkOffset(int offset, int length) {
3090 if (offset < 0 || offset > length) {
3091 throw new StringIndexOutOfBoundsException("offset " + offset +
3092 ",length " + length);
3093 }
3094 }
3095
3096 /*
3097 * Check {@code offset}, {@code count} against {@code 0} and {@code length}
3098 * bounds.
3099 *
3100 * @throws StringIndexOutOfBoundsException
3101 * If {@code offset} is negative, {@code count} is negative,
3102 * or {@code offset} is greater than {@code length - count}
3103 */
3104 static void checkBoundsOffCount(int offset, int count, int length) {
3105 if (offset < 0 || count < 0 || offset > length - count) {
3106 throw new StringIndexOutOfBoundsException(
3107 "offset " + offset + ", count " + count + ", length " + length);
3108 }
3109 }
3110
3111 /*
3112 * Check {@code begin}, {@code end} against {@code 0} and {@code length}
3113 * bounds.
3114 *
3115 * @throws StringIndexOutOfBoundsException
3116 * If {@code begin} is negative, {@code begin} is greater than
3117 * {@code end}, or {@code end} is greater than {@code length}.
3118 */
3119 private static void checkBoundsBeginEnd(int begin, int end, int length) {
3120 if (begin < 0 || begin > end || end > length) {
3121 throw new StringIndexOutOfBoundsException(
3122 "begin " + begin + ", end " + end + ", length " + length);
3123 }
3124 }
3125 }