1 /*
2 * Copyright (c) 1994, 2017, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import java.io.ObjectStreamField;
29 import java.io.UnsupportedEncodingException;
30 import java.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 * @jls 15.18.1 String Concatenation Operator +
121 */
122
123 public final class String
124 implements java.io.Serializable, Comparable<String>, CharSequence {
125
126 /**
127 * The value is used for character storage.
128 *
129 * @implNote This field is trusted by the VM, and is a subject to
130 * constant folding if String instance is constant. Overwriting this
131 * field after construction will cause problems.
132 *
133 * Additionally, it is marked with {@link Stable} to trust the contents
134 * of the array. No other facility in JDK provides this functionality (yet).
135 * {@link Stable} is safe here, because value is never null.
136 */
137 @Stable
138 private final byte[] value;
139
140 /**
141 * The identifier of the encoding used to encode the bytes in
142 * {@code value}. The supported values in this implementation are
143 *
144 * LATIN1
145 * UTF16
146 *
147 * @implNote This field is trusted by the VM, and is a subject to
148 * constant folding if String instance is constant. Overwriting this
149 * field after construction will cause problems.
150 */
151 private final byte coder;
152
153 /** Cache the hash code for the string */
154 private int hash; // Default to 0
155
156 /** use serialVersionUID from JDK 1.0.2 for interoperability */
157 private static final long serialVersionUID = -6849794470754667710L;
158
159 /**
160 * If String compaction is disabled, the bytes in {@code value} are
161 * always encoded in UTF16.
162 *
163 * For methods with several possible implementation paths, when String
164 * compaction is disabled, only one code path is taken.
165 *
166 * The instance field value is generally opaque to optimizing JIT
167 * compilers. Therefore, in performance-sensitive place, an explicit
168 * check of the static boolean {@code COMPACT_STRINGS} is done first
169 * before checking the {@code coder} field since the static boolean
170 * {@code COMPACT_STRINGS} would be constant folded away by an
171 * optimizing JIT compiler. The idioms for these cases are as follows.
172 *
173 * For code such as:
174 *
175 * if (coder == LATIN1) { ... }
176 *
177 * can be written more optimally as
178 *
179 * if (coder() == LATIN1) { ... }
180 *
181 * or:
182 *
183 * if (COMPACT_STRINGS && coder == LATIN1) { ... }
184 *
185 * An optimizing JIT compiler can fold the above conditional as:
186 *
187 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... }
188 * COMPACT_STRINGS == false => if (false) { ... }
189 *
190 * @implNote
191 * The actual value for this field is injected by JVM. The static
192 * initialization block is used to set the value here to communicate
193 * that this static final field is not statically foldable, and to
194 * avoid any possible circular dependency during vm initialization.
195 */
196 static final boolean COMPACT_STRINGS;
197
198 static final boolean DEBUG_INTRINSICS;
199
200 static {
201 COMPACT_STRINGS = true;
202 DEBUG_INTRINSICS = false;
203 }
204
205 /**
206 * Class String is special cased within the Serialization Stream Protocol.
207 *
208 * A String instance is written into an ObjectOutputStream according to
209 * <a href="{@docRoot}/../platform/serialization/spec/output.html">
210 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
211 */
212 private static final ObjectStreamField[] serialPersistentFields =
213 new ObjectStreamField[0];
214
215 /**
216 * Initializes a newly created {@code String} object so that it represents
217 * an empty character sequence. Note that use of this constructor is
218 * unnecessary since Strings are immutable.
219 */
220 public String() {
221 this.value = "".value;
222 this.coder = "".coder;
223 }
224
225 /**
226 * Initializes a newly created {@code String} object so that it represents
227 * the same sequence of characters as the argument; in other words, the
228 * newly created string is a copy of the argument string. Unless an
229 * explicit copy of {@code original} is needed, use of this constructor is
230 * unnecessary since Strings are immutable.
231 *
232 * @param original
233 * A {@code String}
234 */
235 @HotSpotIntrinsicCandidate
236 public String(String original) {
237 this.value = original.value;
238 this.coder = original.coder;
239 this.hash = original.hash;
240 }
241
242 /**
243 * Allocates a new {@code String} so that it represents the sequence of
244 * characters currently contained in the character array argument. The
245 * contents of the character array are copied; subsequent modification of
246 * the character array does not affect the newly created string.
247 *
248 * @param value
249 * The initial value of the string
250 */
251 public String(char value[]) {
252 this(value, 0, value.length, null);
253 }
254
255 /**
256 * Allocates a new {@code String} that contains characters from a subarray
257 * of the character array argument. The {@code offset} argument is the
258 * index of the first character of the subarray and the {@code count}
259 * argument specifies the length of the subarray. The contents of the
260 * subarray are copied; subsequent modification of the character array does
261 * not affect the newly created string.
262 *
263 * @param value
264 * Array that is the source of characters
265 *
266 * @param offset
267 * The initial offset
268 *
269 * @param count
270 * The length
271 *
272 * @throws IndexOutOfBoundsException
273 * If {@code offset} is negative, {@code count} is negative, or
274 * {@code offset} is greater than {@code value.length - count}
275 */
276 public String(char value[], int offset, int count) {
277 this(value, offset, count, rangeCheck(value, offset, count));
278 }
279
280 private static Void rangeCheck(char[] value, int offset, int count) {
281 checkBoundsOffCount(offset, count, value.length);
282 return null;
283 }
284
285 /**
286 * Allocates a new {@code String} that contains characters from a subarray
287 * of the <a href="Character.html#unicode">Unicode code point</a> array
288 * argument. The {@code offset} argument is the index of the first code
289 * point of the subarray and the {@code count} argument specifies the
290 * length of the subarray. The contents of the subarray are converted to
291 * {@code char}s; subsequent modification of the {@code int} array does not
292 * affect the newly created string.
293 *
294 * @param codePoints
295 * Array that is the source of Unicode code points
296 *
297 * @param offset
298 * The initial offset
299 *
300 * @param count
301 * The length
302 *
303 * @throws IllegalArgumentException
304 * If any invalid Unicode code point is found in {@code
305 * codePoints}
306 *
307 * @throws IndexOutOfBoundsException
308 * If {@code offset} is negative, {@code count} is negative, or
309 * {@code offset} is greater than {@code codePoints.length - count}
310 *
311 * @since 1.5
312 */
313 public String(int[] codePoints, int offset, int count) {
314 checkBoundsOffCount(offset, count, codePoints.length);
315 if (count == 0) {
316 this.value = "".value;
317 this.coder = "".coder;
318 return;
319 }
320 if (COMPACT_STRINGS) {
321 byte[] val = StringLatin1.toBytes(codePoints, offset, count);
322 if (val != null) {
323 this.coder = LATIN1;
324 this.value = val;
325 return;
326 }
327 }
328 this.coder = UTF16;
329 this.value = StringUTF16.toBytes(codePoints, offset, count);
330 }
331
332 /**
333 * Allocates a new {@code String} constructed from a subarray of an array
334 * of 8-bit integer values.
335 *
336 * <p> The {@code offset} argument is the index of the first byte of the
337 * subarray, and the {@code count} argument specifies the length of the
338 * subarray.
339 *
340 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
341 * specified in the method above.
342 *
343 * @deprecated This method does not properly convert bytes into characters.
344 * As of JDK 1.1, the preferred way to do this is via the
345 * {@code String} constructors that take a {@link
346 * java.nio.charset.Charset}, charset name, or that use the platform's
347 * default charset.
348 *
349 * @param ascii
350 * The bytes to be converted to characters
351 *
352 * @param hibyte
353 * The top 8 bits of each 16-bit Unicode code unit
354 *
355 * @param offset
356 * The initial offset
357 * @param count
358 * The length
359 *
360 * @throws IndexOutOfBoundsException
361 * If {@code offset} is negative, {@code count} is negative, or
362 * {@code offset} is greater than {@code ascii.length - count}
363 *
364 * @see #String(byte[], int)
365 * @see #String(byte[], int, int, java.lang.String)
366 * @see #String(byte[], int, int, java.nio.charset.Charset)
367 * @see #String(byte[], int, int)
368 * @see #String(byte[], java.lang.String)
369 * @see #String(byte[], java.nio.charset.Charset)
370 * @see #String(byte[])
371 */
372 @Deprecated(since="1.1")
373 public String(byte ascii[], int hibyte, int offset, int count) {
374 checkBoundsOffCount(offset, count, ascii.length);
375 if (count == 0) {
376 this.value = "".value;
377 this.coder = "".coder;
378 return;
379 }
380 if (COMPACT_STRINGS && (byte)hibyte == 0) {
381 this.value = Arrays.copyOfRange(ascii, offset, offset + count);
382 this.coder = LATIN1;
383 } else {
384 hibyte <<= 8;
385 byte[] val = StringUTF16.newBytesFor(count);
386 for (int i = 0; i < count; i++) {
387 StringUTF16.Trusted.putChar(val, i, hibyte | (ascii[offset++] & 0xff));
388 }
389 this.value = val;
390 this.coder = UTF16;
391 }
392 }
393
394 /**
395 * Allocates a new {@code String} containing characters constructed from
396 * an array of 8-bit integer values. Each character <i>c</i>in the
397 * resulting string is constructed from the corresponding component
398 * <i>b</i> in the byte array such that:
399 *
400 * <blockquote><pre>
401 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
402 * | (<b><i>b</i></b> & 0xff))
403 * </pre></blockquote>
404 *
405 * @deprecated This method does not properly convert bytes into
406 * characters. As of JDK 1.1, the preferred way to do this is via the
407 * {@code String} constructors that take a {@link
408 * java.nio.charset.Charset}, charset name, or that use the platform's
409 * default charset.
410 *
411 * @param ascii
412 * The bytes to be converted to characters
413 *
414 * @param hibyte
415 * The top 8 bits of each 16-bit Unicode code unit
416 *
417 * @see #String(byte[], int, int, java.lang.String)
418 * @see #String(byte[], int, int, java.nio.charset.Charset)
419 * @see #String(byte[], int, int)
420 * @see #String(byte[], java.lang.String)
421 * @see #String(byte[], java.nio.charset.Charset)
422 * @see #String(byte[])
423 */
424 @Deprecated(since="1.1")
425 public String(byte ascii[], int hibyte) {
426 this(ascii, hibyte, 0, ascii.length);
427 }
428
429 /**
430 * Constructs a new {@code String} by decoding the specified subarray of
431 * bytes using the specified charset. The length of the new {@code String}
432 * is a function of the charset, and hence may not be equal to the length
433 * of the subarray.
434 *
435 * <p> The behavior of this constructor when the given bytes are not valid
436 * in the given charset is unspecified. The {@link
437 * java.nio.charset.CharsetDecoder} class should be used when more control
438 * over the decoding process is required.
439 *
440 * @param bytes
441 * The bytes to be decoded into characters
442 *
443 * @param offset
444 * The index of the first byte to decode
445 *
446 * @param length
447 * The number of bytes to decode
448
449 * @param charsetName
450 * The name of a supported {@linkplain java.nio.charset.Charset
451 * charset}
452 *
453 * @throws UnsupportedEncodingException
454 * If the named charset is not supported
455 *
456 * @throws IndexOutOfBoundsException
457 * If {@code offset} is negative, {@code length} is negative, or
458 * {@code offset} is greater than {@code bytes.length - length}
459 *
460 * @since 1.1
461 */
462 public String(byte bytes[], int offset, int length, String charsetName)
463 throws UnsupportedEncodingException {
464 if (charsetName == null)
465 throw new NullPointerException("charsetName");
466 checkBoundsOffCount(offset, length, bytes.length);
467 StringCoding.Result ret =
468 StringCoding.decode(charsetName, bytes, offset, length);
469 this.value = ret.value;
470 this.coder = ret.coder;
471 }
472
473 /**
474 * Constructs a new {@code String} by decoding the specified subarray of
475 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
476 * The length of the new {@code String} is a function of the charset, and
477 * hence may not be equal to the length of the subarray.
478 *
479 * <p> This method always replaces malformed-input and unmappable-character
480 * sequences with this charset's default replacement string. The {@link
481 * java.nio.charset.CharsetDecoder} class should be used when more control
482 * over the decoding process is required.
483 *
484 * @param bytes
485 * The bytes to be decoded into characters
486 *
487 * @param offset
488 * The index of the first byte to decode
489 *
490 * @param length
491 * The number of bytes to decode
492 *
493 * @param charset
494 * The {@linkplain java.nio.charset.Charset charset} to be used to
495 * decode the {@code bytes}
496 *
497 * @throws IndexOutOfBoundsException
498 * If {@code offset} is negative, {@code length} is negative, or
499 * {@code offset} is greater than {@code bytes.length - length}
500 *
501 * @since 1.6
502 */
503 public String(byte bytes[], int offset, int length, Charset charset) {
504 if (charset == null)
505 throw new NullPointerException("charset");
506 checkBoundsOffCount(offset, length, bytes.length);
507 StringCoding.Result ret =
508 StringCoding.decode(charset, bytes, offset, length);
509 this.value = ret.value;
510 this.coder = ret.coder;
511 }
512
513 /**
514 * Constructs a new {@code String} by decoding the specified array of bytes
515 * using the specified {@linkplain java.nio.charset.Charset charset}. The
516 * length of the new {@code String} is a function of the charset, and hence
517 * may not be equal to the length of the byte array.
518 *
519 * <p> The behavior of this constructor when the given bytes are not valid
520 * in the given charset is unspecified. The {@link
521 * java.nio.charset.CharsetDecoder} class should be used when more control
522 * over the decoding process is required.
523 *
524 * @param bytes
525 * The bytes to be decoded into characters
526 *
527 * @param charsetName
528 * The name of a supported {@linkplain java.nio.charset.Charset
529 * charset}
530 *
531 * @throws UnsupportedEncodingException
532 * If the named charset is not supported
533 *
534 * @since 1.1
535 */
536 public String(byte bytes[], String charsetName)
537 throws UnsupportedEncodingException {
538 this(bytes, 0, bytes.length, charsetName);
539 }
540
541 /**
542 * Constructs a new {@code String} by decoding the specified array of
543 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
544 * The length of the new {@code String} is a function of the charset, and
545 * hence may not be equal to the length of the byte array.
546 *
547 * <p> This method always replaces malformed-input and unmappable-character
548 * sequences with this charset's default replacement string. The {@link
549 * java.nio.charset.CharsetDecoder} class should be used when more control
550 * over the decoding process is required.
551 *
552 * @param bytes
553 * The bytes to be decoded into characters
554 *
555 * @param charset
556 * The {@linkplain java.nio.charset.Charset charset} to be used to
557 * decode the {@code bytes}
558 *
559 * @since 1.6
560 */
561 public String(byte bytes[], Charset charset) {
562 this(bytes, 0, bytes.length, charset);
563 }
564
565 /**
566 * Constructs a new {@code String} by decoding the specified subarray of
567 * bytes using the platform's default charset. The length of the new
568 * {@code String} is a function of the charset, and hence may not be equal
569 * to the length of the subarray.
570 *
571 * <p> The behavior of this constructor when the given bytes are not valid
572 * in the default charset is unspecified. The {@link
573 * java.nio.charset.CharsetDecoder} class should be used when more control
574 * over the decoding process is required.
575 *
576 * @param bytes
577 * The bytes to be decoded into characters
578 *
579 * @param offset
580 * The index of the first byte to decode
581 *
582 * @param length
583 * The number of bytes to decode
584 *
585 * @throws IndexOutOfBoundsException
586 * If {@code offset} is negative, {@code length} is negative, or
587 * {@code offset} is greater than {@code bytes.length - length}
588 *
589 * @since 1.1
590 */
591 public String(byte bytes[], int offset, int length) {
592 checkBoundsOffCount(offset, length, bytes.length);
593 StringCoding.Result ret = StringCoding.decode(bytes, offset, length);
594 this.value = ret.value;
595 this.coder = ret.coder;
596 }
597
598 /**
599 * Constructs a new {@code String} by decoding the specified array of bytes
600 * using the platform's default charset. The length of the new {@code
601 * String} is a function of the charset, and hence may not be equal to the
602 * length of the byte array.
603 *
604 * <p> The behavior of this constructor when the given bytes are not valid
605 * in the default charset is unspecified. The {@link
606 * java.nio.charset.CharsetDecoder} class should be used when more control
607 * over the decoding process is required.
608 *
609 * @param bytes
610 * The bytes to be decoded into characters
611 *
612 * @since 1.1
613 */
614 public String(byte[] bytes) {
615 this(bytes, 0, bytes.length);
616 }
617
618 /**
619 * Allocates a new string that contains the sequence of characters
620 * currently contained in the string buffer argument. The contents of the
621 * string buffer are copied; subsequent modification of the string buffer
622 * does not affect the newly created string.
623 *
624 * @param buffer
625 * A {@code StringBuffer}
626 */
627 public String(StringBuffer buffer) {
628 this(buffer.toString());
629 }
630
631 /**
632 * Allocates a new string that contains the sequence of characters
633 * currently contained in the string builder argument. The contents of the
634 * string builder are copied; subsequent modification of the string builder
635 * does not affect the newly created string.
636 *
637 * <p> This constructor is provided to ease migration to {@code
638 * StringBuilder}. Obtaining a string from a string builder via the {@code
639 * toString} method is likely to run faster and is generally preferred.
640 *
641 * @param builder
642 * A {@code StringBuilder}
643 *
644 * @since 1.5
645 */
646 public String(StringBuilder builder) {
647 this(builder, null);
648 }
649
650 /*
651 * Package private constructor which shares value array for speed.
652 * this constructor is always expected to be called with share==true.
653 * a separate constructor is needed because we already have a public
654 * String(char[]) constructor that makes a copy of the given char[].
655 */
656 // TBD: this is kept for package internal use (Thread/System),
657 // should be removed if they all have a byte[] version
658 String(char[] val, boolean share) {
659 // assert share : "unshared not supported";
660 this(val, 0, val.length, null);
661 }
662
663 /**
664 * Returns the length of this string.
665 * The length is equal to the number of <a href="Character.html#unicode">Unicode
666 * code units</a> in the string.
667 *
668 * @return the length of the sequence of characters represented by this
669 * object.
670 */
671 public int length() {
672 return value.length >> coder();
673 }
674
675 /**
676 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
677 *
678 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
679 * {@code false}
680 *
681 * @since 1.6
682 */
683 public boolean isEmpty() {
684 return value.length == 0;
685 }
686
687 /**
688 * Returns the {@code char} value at the
689 * specified index. An index ranges from {@code 0} to
690 * {@code length() - 1}. The first {@code char} value of the sequence
691 * is at index {@code 0}, the next at index {@code 1},
692 * and so on, as for array indexing.
693 *
694 * <p>If the {@code char} value specified by the index is a
695 * <a href="Character.html#unicode">surrogate</a>, the surrogate
696 * value is returned.
697 *
698 * @param index the index of the {@code char} value.
699 * @return the {@code char} value at the specified index of this string.
700 * The first {@code char} value is at index {@code 0}.
701 * @exception IndexOutOfBoundsException if the {@code index}
702 * argument is negative or not less than the length of this
703 * string.
704 */
705 public char charAt(int index) {
706 if (isLatin1()) {
707 return StringLatin1.charAt(value, index);
708 } else {
709 return StringUTF16.charAt(value, index);
710 }
711 }
712
713 /**
714 * Returns the character (Unicode code point) at the specified
715 * index. The index refers to {@code char} values
716 * (Unicode code units) and ranges from {@code 0} to
717 * {@link #length()}{@code - 1}.
718 *
719 * <p> If the {@code char} value specified at the given index
720 * is in the high-surrogate range, the following index is less
721 * than the length of this {@code String}, and the
722 * {@code char} value at the following index is in the
723 * low-surrogate range, then the supplementary code point
724 * corresponding to this surrogate pair is returned. Otherwise,
725 * the {@code char} value at the given index is returned.
726 *
727 * @param index the index to the {@code char} values
728 * @return the code point value of the character at the
729 * {@code index}
730 * @exception IndexOutOfBoundsException if the {@code index}
731 * argument is negative or not less than the length of this
732 * string.
733 * @since 1.5
734 */
735 public int codePointAt(int index) {
736 if (isLatin1()) {
737 checkIndex(index, value.length);
738 return value[index] & 0xff;
739 }
740 int length = value.length >> 1;
741 checkIndex(index, length);
742 return StringUTF16.codePointAt(value, index, length);
743 }
744
745 /**
746 * Returns the character (Unicode code point) before the specified
747 * index. The index refers to {@code char} values
748 * (Unicode code units) and ranges from {@code 1} to {@link
749 * CharSequence#length() length}.
750 *
751 * <p> If the {@code char} value at {@code (index - 1)}
752 * is in the low-surrogate range, {@code (index - 2)} is not
753 * negative, and the {@code char} value at {@code (index -
754 * 2)} is in the high-surrogate range, then the
755 * supplementary code point value of the surrogate pair is
756 * returned. If the {@code char} value at {@code index -
757 * 1} is an unpaired low-surrogate or a high-surrogate, the
758 * surrogate value is returned.
759 *
760 * @param index the index following the code point that should be returned
761 * @return the Unicode code point value before the given index.
762 * @exception IndexOutOfBoundsException if the {@code index}
763 * argument is less than 1 or greater than the length
764 * of this string.
765 * @since 1.5
766 */
767 public int codePointBefore(int index) {
768 int i = index - 1;
769 if (i < 0 || i >= length()) {
770 throw new StringIndexOutOfBoundsException(index);
771 }
772 if (isLatin1()) {
773 return (value[i] & 0xff);
774 }
775 return StringUTF16.codePointBefore(value, index);
776 }
777
778 /**
779 * Returns the number of Unicode code points in the specified text
780 * range of this {@code String}. The text range begins at the
781 * specified {@code beginIndex} and extends to the
782 * {@code char} at index {@code endIndex - 1}. Thus the
783 * length (in {@code char}s) of the text range is
784 * {@code endIndex-beginIndex}. Unpaired surrogates within
785 * the text range count as one code point each.
786 *
787 * @param beginIndex the index to the first {@code char} of
788 * the text range.
789 * @param endIndex the index after the last {@code char} of
790 * the text range.
791 * @return the number of Unicode code points in the specified text
792 * range
793 * @exception IndexOutOfBoundsException if the
794 * {@code beginIndex} is negative, or {@code endIndex}
795 * is larger than the length of this {@code String}, or
796 * {@code beginIndex} is larger than {@code endIndex}.
797 * @since 1.5
798 */
799 public int codePointCount(int beginIndex, int endIndex) {
800 if (beginIndex < 0 || beginIndex > endIndex ||
801 endIndex > length()) {
802 throw new IndexOutOfBoundsException();
803 }
804 if (isLatin1()) {
805 return endIndex - beginIndex;
806 }
807 return StringUTF16.codePointCount(value, beginIndex, endIndex);
808 }
809
810 /**
811 * Returns the index within this {@code String} that is
812 * offset from the given {@code index} by
813 * {@code codePointOffset} code points. Unpaired surrogates
814 * within the text range given by {@code index} and
815 * {@code codePointOffset} count as one code point each.
816 *
817 * @param index the index to be offset
818 * @param codePointOffset the offset in code points
819 * @return the index within this {@code String}
820 * @exception IndexOutOfBoundsException if {@code index}
821 * is negative or larger then the length of this
822 * {@code String}, or if {@code codePointOffset} is positive
823 * and the substring starting with {@code index} has fewer
824 * than {@code codePointOffset} code points,
825 * or if {@code codePointOffset} is negative and the substring
826 * before {@code index} has fewer than the absolute value
827 * of {@code codePointOffset} code points.
828 * @since 1.5
829 */
830 public int offsetByCodePoints(int index, int codePointOffset) {
831 if (index < 0 || index > length()) {
832 throw new IndexOutOfBoundsException();
833 }
834 return Character.offsetByCodePoints(this, index, codePointOffset);
835 }
836
837 /**
838 * Copies characters from this string into the destination character
839 * array.
840 * <p>
841 * The first character to be copied is at index {@code srcBegin};
842 * the last character to be copied is at index {@code srcEnd-1}
843 * (thus the total number of characters to be copied is
844 * {@code srcEnd-srcBegin}). The characters are copied into the
845 * subarray of {@code dst} starting at index {@code dstBegin}
846 * and ending at index:
847 * <blockquote><pre>
848 * dstBegin + (srcEnd-srcBegin) - 1
849 * </pre></blockquote>
850 *
851 * @param srcBegin index of the first character in the string
852 * to copy.
853 * @param srcEnd index after the last character in the string
854 * to copy.
855 * @param dst the destination array.
856 * @param dstBegin the start offset in the destination array.
857 * @exception IndexOutOfBoundsException If any of the following
858 * is true:
859 * <ul><li>{@code srcBegin} is negative.
860 * <li>{@code srcBegin} is greater than {@code srcEnd}
861 * <li>{@code srcEnd} is greater than the length of this
862 * string
863 * <li>{@code dstBegin} is negative
864 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
865 * {@code dst.length}</ul>
866 */
867 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
868 checkBoundsBeginEnd(srcBegin, srcEnd, length());
869 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
870 if (isLatin1()) {
871 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin);
872 } else {
873 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin);
874 }
875 }
876
877 /**
878 * Copies characters from this string into the destination byte array. Each
879 * byte receives the 8 low-order bits of the corresponding character. The
880 * eight high-order bits of each character are not copied and do not
881 * participate in the transfer in any way.
882 *
883 * <p> The first character to be copied is at index {@code srcBegin}; the
884 * last character to be copied is at index {@code srcEnd-1}. The total
885 * number of characters to be copied is {@code srcEnd-srcBegin}. The
886 * characters, converted to bytes, are copied into the subarray of {@code
887 * dst} starting at index {@code dstBegin} and ending at index:
888 *
889 * <blockquote><pre>
890 * dstBegin + (srcEnd-srcBegin) - 1
891 * </pre></blockquote>
892 *
893 * @deprecated This method does not properly convert characters into
894 * bytes. As of JDK 1.1, the preferred way to do this is via the
895 * {@link #getBytes()} method, which uses the platform's default charset.
896 *
897 * @param srcBegin
898 * Index of the first character in the string to copy
899 *
900 * @param srcEnd
901 * Index after the last character in the string to copy
902 *
903 * @param dst
904 * The destination array
905 *
906 * @param dstBegin
907 * The start offset in the destination array
908 *
909 * @throws IndexOutOfBoundsException
910 * If any of the following is true:
911 * <ul>
912 * <li> {@code srcBegin} is negative
913 * <li> {@code srcBegin} is greater than {@code srcEnd}
914 * <li> {@code srcEnd} is greater than the length of this String
915 * <li> {@code dstBegin} is negative
916 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
917 * dst.length}
918 * </ul>
919 */
920 @Deprecated(since="1.1")
921 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
922 checkBoundsBeginEnd(srcBegin, srcEnd, length());
923 Objects.requireNonNull(dst);
924 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
925 if (isLatin1()) {
926 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
927 } else {
928 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
929 }
930 }
931
932 /**
933 * Encodes this {@code String} into a sequence of bytes using the named
934 * charset, storing the result into a new byte array.
935 *
936 * <p> The behavior of this method when this string cannot be encoded in
937 * the given charset is unspecified. The {@link
938 * java.nio.charset.CharsetEncoder} class should be used when more control
939 * over the encoding process is required.
940 *
941 * @param charsetName
942 * The name of a supported {@linkplain java.nio.charset.Charset
943 * charset}
944 *
945 * @return The resultant byte array
946 *
947 * @throws UnsupportedEncodingException
948 * If the named charset is not supported
949 *
950 * @since 1.1
951 */
952 public byte[] getBytes(String charsetName)
953 throws UnsupportedEncodingException {
954 if (charsetName == null) throw new NullPointerException();
955 return StringCoding.encode(charsetName, coder(), value);
956 }
957
958 /**
959 * Encodes this {@code String} into a sequence of bytes using the given
960 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
961 * new byte array.
962 *
963 * <p> This method always replaces malformed-input and unmappable-character
964 * sequences with this charset's default replacement byte array. The
965 * {@link java.nio.charset.CharsetEncoder} class should be used when more
966 * control over the encoding process is required.
967 *
968 * @param charset
969 * The {@linkplain java.nio.charset.Charset} to be used to encode
970 * the {@code String}
971 *
972 * @return The resultant byte array
973 *
974 * @since 1.6
975 */
976 public byte[] getBytes(Charset charset) {
977 if (charset == null) throw new NullPointerException();
978 return StringCoding.encode(charset, coder(), value);
979 }
980
981 /**
982 * Encodes this {@code String} into a sequence of bytes using the
983 * platform's default charset, storing the result into a new byte array.
984 *
985 * <p> The behavior of this method when this string cannot be encoded in
986 * the default charset is unspecified. The {@link
987 * java.nio.charset.CharsetEncoder} class should be used when more control
988 * over the encoding process is required.
989 *
990 * @return The resultant byte array
991 *
992 * @since 1.1
993 */
994 public byte[] getBytes() {
995 return StringCoding.encode(coder(), value);
996 }
997
998 /**
999 * Compares this string to the specified object. The result is {@code
1000 * true} if and only if the argument is not {@code null} and is a {@code
1001 * String} object that represents the same sequence of characters as this
1002 * object.
1003 *
1004 * <p>For finer-grained String comparison, refer to
1005 * {@link java.text.Collator}.
1006 *
1007 * @param anObject
1008 * The object to compare this {@code String} against
1009 *
1010 * @return {@code true} if the given object represents a {@code String}
1011 * equivalent to this string, {@code false} otherwise
1012 *
1013 * @see #compareTo(String)
1014 * @see #equalsIgnoreCase(String)
1015 */
1016 public boolean equals(Object anObject) {
1017 if (this == anObject) {
1018 return true;
1019 }
1020 if (anObject instanceof String) {
1021 String aString = (String)anObject;
1022 if (coder() == aString.coder()) {
1023 return isLatin1() ? StringLatin1.equals(value, aString.value)
1024 : StringUTF16.equals(value, aString.value);
1025 }
1026 }
1027 return false;
1028 }
1029
1030 /**
1031 * Compares this string to the specified {@code StringBuffer}. The result
1032 * is {@code true} if and only if this {@code String} represents the same
1033 * sequence of characters as the specified {@code StringBuffer}. This method
1034 * synchronizes on the {@code StringBuffer}.
1035 *
1036 * <p>For finer-grained String comparison, refer to
1037 * {@link java.text.Collator}.
1038 *
1039 * @param sb
1040 * The {@code StringBuffer} to compare this {@code String} against
1041 *
1042 * @return {@code true} if this {@code String} represents the same
1043 * sequence of characters as the specified {@code StringBuffer},
1044 * {@code false} otherwise
1045 *
1046 * @since 1.4
1047 */
1048 public boolean contentEquals(StringBuffer sb) {
1049 return contentEquals((CharSequence)sb);
1050 }
1051
1052 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1053 int len = length();
1054 if (len != sb.length()) {
1055 return false;
1056 }
1057 byte v1[] = value;
1058 byte v2[] = sb.getValue();
1059 if (coder() == sb.getCoder()) {
1060 int n = v1.length;
1061 for (int i = 0; i < n; i++) {
1062 if (v1[i] != v2[i]) {
1063 return false;
1064 }
1065 }
1066 } else {
1067 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal"
1068 return false;
1069 }
1070 return StringUTF16.contentEquals(v1, v2, len);
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 if (!StringUTF16.contentEquals(val, cs, n)) {
1123 return false;
1124 }
1125 }
1126 return true;
1127 }
1128
1129 /**
1130 * Compares this {@code String} to another {@code String}, ignoring case
1131 * considerations. Two strings are considered equal ignoring case if they
1132 * are of the same length and corresponding characters in the two strings
1133 * are equal ignoring case.
1134 *
1135 * <p> Two characters {@code c1} and {@code c2} are considered the same
1136 * ignoring case if at least one of the following is true:
1137 * <ul>
1138 * <li> The two characters are the same (as compared by the
1139 * {@code ==} operator)
1140 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))}
1141 * on each character produces the same result
1142 * </ul>
1143 *
1144 * <p>Note that this method does <em>not</em> take locale into account, and
1145 * will result in unsatisfactory results for certain locales. The
1146 * {@link java.text.Collator} class provides locale-sensitive comparison.
1147 *
1148 * @param anotherString
1149 * The {@code String} to compare this {@code String} against
1150 *
1151 * @return {@code true} if the argument is not {@code null} and it
1152 * represents an equivalent {@code String} ignoring case; {@code
1153 * false} otherwise
1154 *
1155 * @see #equals(Object)
1156 */
1157 public boolean equalsIgnoreCase(String anotherString) {
1158 return (this == anotherString) ? true
1159 : (anotherString != null)
1160 && (anotherString.length() == length())
1161 && regionMatches(true, 0, anotherString, 0, length());
1162 }
1163
1164 /**
1165 * Compares two strings lexicographically.
1166 * The comparison is based on the Unicode value of each character in
1167 * the strings. The character sequence represented by this
1168 * {@code String} object is compared lexicographically to the
1169 * character sequence represented by the argument string. The result is
1170 * a negative integer if this {@code String} object
1171 * lexicographically precedes the argument string. The result is a
1172 * positive integer if this {@code String} object lexicographically
1173 * follows the argument string. The result is zero if the strings
1174 * are equal; {@code compareTo} returns {@code 0} exactly when
1175 * the {@link #equals(Object)} method would return {@code true}.
1176 * <p>
1177 * This is the definition of lexicographic ordering. If two strings are
1178 * different, then either they have different characters at some index
1179 * that is a valid index for both strings, or their lengths are different,
1180 * or both. If they have different characters at one or more index
1181 * positions, let <i>k</i> be the smallest such index; then the string
1182 * whose character at position <i>k</i> has the smaller value, as
1183 * determined by using the {@code <} operator, lexicographically precedes the
1184 * other string. In this case, {@code compareTo} returns the
1185 * difference of the two character values at position {@code k} in
1186 * the two string -- that is, the value:
1187 * <blockquote><pre>
1188 * this.charAt(k)-anotherString.charAt(k)
1189 * </pre></blockquote>
1190 * If there is no index position at which they differ, then the shorter
1191 * string lexicographically precedes the longer string. In this case,
1192 * {@code compareTo} returns the difference of the lengths of the
1193 * strings -- that is, the value:
1194 * <blockquote><pre>
1195 * this.length()-anotherString.length()
1196 * </pre></blockquote>
1197 *
1198 * <p>For finer-grained String comparison, refer to
1199 * {@link java.text.Collator}.
1200 *
1201 * @param anotherString the {@code String} to be compared.
1202 * @return the value {@code 0} if the argument string is equal to
1203 * this string; a value less than {@code 0} if this string
1204 * is lexicographically less than the string argument; and a
1205 * value greater than {@code 0} if this string is
1206 * lexicographically greater than the string argument.
1207 */
1208 public int compareTo(String anotherString) {
1209 byte v1[] = value;
1210 byte v2[] = anotherString.value;
1211 if (coder() == anotherString.coder()) {
1212 return isLatin1() ? StringLatin1.compareTo(v1, v2)
1213 : StringUTF16.compareTo(v1, v2);
1214 }
1215 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2)
1216 : StringUTF16.compareToLatin1(v1, v2);
1217 }
1218
1219 /**
1220 * A Comparator that orders {@code String} objects as by
1221 * {@code compareToIgnoreCase}. This comparator is serializable.
1222 * <p>
1223 * Note that this Comparator does <em>not</em> take locale into account,
1224 * and will result in an unsatisfactory ordering for certain locales.
1225 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1226 *
1227 * @see java.text.Collator
1228 * @since 1.2
1229 */
1230 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1231 = new CaseInsensitiveComparator();
1232 private static class CaseInsensitiveComparator
1233 implements Comparator<String>, java.io.Serializable {
1234 // use serialVersionUID from JDK 1.2.2 for interoperability
1235 private static final long serialVersionUID = 8575799808933029326L;
1236
1237 public int compare(String s1, String s2) {
1238 byte v1[] = s1.value;
1239 byte v2[] = s2.value;
1240 if (s1.coder() == s2.coder()) {
1241 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2)
1242 : StringUTF16.compareToCI(v1, v2);
1243 }
1244 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2)
1245 : StringUTF16.compareToCI_Latin1(v1, v2);
1246 }
1247
1248 /** Replaces the de-serialized object. */
1249 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1250 }
1251
1252 /**
1253 * Compares two strings lexicographically, ignoring case
1254 * differences. This method returns an integer whose sign is that of
1255 * calling {@code compareTo} with normalized versions of the strings
1256 * where case differences have been eliminated by calling
1257 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1258 * each character.
1259 * <p>
1260 * Note that this method does <em>not</em> take locale into account,
1261 * and will result in an unsatisfactory ordering for certain locales.
1262 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1263 *
1264 * @param str the {@code String} to be compared.
1265 * @return a negative integer, zero, or a positive integer as the
1266 * specified String is greater than, equal to, or less
1267 * than this String, ignoring case considerations.
1268 * @see java.text.Collator
1269 * @since 1.2
1270 */
1271 public int compareToIgnoreCase(String str) {
1272 return CASE_INSENSITIVE_ORDER.compare(this, str);
1273 }
1274
1275 /**
1276 * Tests if two string regions are equal.
1277 * <p>
1278 * A substring of this {@code String} object is compared to a substring
1279 * of the argument other. The result is true if these substrings
1280 * represent identical character sequences. The substring of this
1281 * {@code String} object to be compared begins at index {@code toffset}
1282 * and has length {@code len}. The substring of other to be compared
1283 * begins at index {@code ooffset} and has length {@code len}. The
1284 * result is {@code false} if and only if at least one of the following
1285 * is true:
1286 * <ul><li>{@code toffset} is negative.
1287 * <li>{@code ooffset} is negative.
1288 * <li>{@code toffset+len} is greater than the length of this
1289 * {@code String} object.
1290 * <li>{@code ooffset+len} is greater than the length of the other
1291 * argument.
1292 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1293 * such that:
1294 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1295 * <i>k</i>{@code )}
1296 * </ul>
1297 *
1298 * <p>Note that this method does <em>not</em> take locale into account. The
1299 * {@link java.text.Collator} class provides locale-sensitive comparison.
1300 *
1301 * @param toffset the starting offset of the subregion in this string.
1302 * @param other the string argument.
1303 * @param ooffset the starting offset of the subregion in the string
1304 * argument.
1305 * @param len the number of characters to compare.
1306 * @return {@code true} if the specified subregion of this string
1307 * exactly matches the specified subregion of the string argument;
1308 * {@code false} otherwise.
1309 */
1310 public boolean regionMatches(int toffset, String other, int ooffset, int len) {
1311 byte tv[] = value;
1312 byte ov[] = other.value;
1313 // Note: toffset, ooffset, or len might be near -1>>>1.
1314 if ((ooffset < 0) || (toffset < 0) ||
1315 (toffset > (long)length() - len) ||
1316 (ooffset > (long)other.length() - len)) {
1317 return false;
1318 }
1319 if (coder() == other.coder()) {
1320 if (!isLatin1() && (len > 0)) {
1321 toffset = toffset << 1;
1322 ooffset = ooffset << 1;
1323 len = len << 1;
1324 }
1325 while (len-- > 0) {
1326 if (tv[toffset++] != ov[ooffset++]) {
1327 return false;
1328 }
1329 }
1330 } else {
1331 if (coder() == LATIN1) {
1332 while (len-- > 0) {
1333 if (StringLatin1.getChar(tv, toffset++) !=
1334 StringUTF16.Trusted.getChar(ov, ooffset++)) {
1335 return false;
1336 }
1337 }
1338 } else {
1339 while (len-- > 0) {
1340 if (StringUTF16.Trusted.getChar(tv, toffset++) !=
1341 StringLatin1.getChar(ov, ooffset++)) {
1342 return false;
1343 }
1344 }
1345 }
1346 }
1347 return true;
1348 }
1349
1350 /**
1351 * Tests if two string regions are equal.
1352 * <p>
1353 * A substring of this {@code String} object is compared to a substring
1354 * of the argument {@code other}. The result is {@code true} if these
1355 * substrings represent character sequences that are the same, ignoring
1356 * case if and only if {@code ignoreCase} is true. The substring of
1357 * this {@code String} object to be compared begins at index
1358 * {@code toffset} and has length {@code len}. The substring of
1359 * {@code other} to be compared begins at index {@code ooffset} and
1360 * has length {@code len}. The result is {@code false} if and only if
1361 * at least one of the following is true:
1362 * <ul><li>{@code toffset} is negative.
1363 * <li>{@code ooffset} is negative.
1364 * <li>{@code toffset+len} is greater than the length of this
1365 * {@code String} object.
1366 * <li>{@code ooffset+len} is greater than the length of the other
1367 * argument.
1368 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1369 * integer <i>k</i> less than {@code len} such that:
1370 * <blockquote><pre>
1371 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1372 * </pre></blockquote>
1373 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1374 * integer <i>k</i> less than {@code len} such that:
1375 * <blockquote><pre>
1376 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) !=
1377 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k)))
1378 * </pre></blockquote>
1379 * </ul>
1380 *
1381 * <p>Note that this method does <em>not</em> take locale into account,
1382 * and will result in unsatisfactory results for certain locales when
1383 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class
1384 * provides locale-sensitive comparison.
1385 *
1386 * @param ignoreCase if {@code true}, ignore case when comparing
1387 * characters.
1388 * @param toffset the starting offset of the subregion in this
1389 * string.
1390 * @param other the string argument.
1391 * @param ooffset the starting offset of the subregion in the string
1392 * argument.
1393 * @param len the number of characters to compare.
1394 * @return {@code true} if the specified subregion of this string
1395 * matches the specified subregion of the string argument;
1396 * {@code false} otherwise. Whether the matching is exact
1397 * or case insensitive depends on the {@code ignoreCase}
1398 * argument.
1399 */
1400 public boolean regionMatches(boolean ignoreCase, int toffset,
1401 String other, int ooffset, int len) {
1402 if (!ignoreCase) {
1403 return regionMatches(toffset, other, ooffset, len);
1404 }
1405 // Note: toffset, ooffset, or len might be near -1>>>1.
1406 if ((ooffset < 0) || (toffset < 0)
1407 || (toffset > (long)length() - len)
1408 || (ooffset > (long)other.length() - len)) {
1409 return false;
1410 }
1411 byte tv[] = value;
1412 byte ov[] = other.value;
1413 if (coder() == other.coder()) {
1414 return isLatin1()
1415 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len)
1416 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len);
1417 }
1418 return isLatin1()
1419 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len)
1420 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len);
1421 }
1422
1423 /**
1424 * Tests if the substring of this string beginning at the
1425 * specified index starts with the specified prefix.
1426 *
1427 * @param prefix the prefix.
1428 * @param toffset where to begin looking in this string.
1429 * @return {@code true} if the character sequence represented by the
1430 * argument is a prefix of the substring of this object starting
1431 * at index {@code toffset}; {@code false} otherwise.
1432 * The result is {@code false} if {@code toffset} is
1433 * negative or greater than the length of this
1434 * {@code String} object; otherwise the result is the same
1435 * as the result of the expression
1436 * <pre>
1437 * this.substring(toffset).startsWith(prefix)
1438 * </pre>
1439 */
1440 public boolean startsWith(String prefix, int toffset) {
1441 // Note: toffset might be near -1>>>1.
1442 if (toffset < 0 || toffset > length() - prefix.length()) {
1443 return false;
1444 }
1445 byte ta[] = value;
1446 byte pa[] = prefix.value;
1447 int po = 0;
1448 int pc = pa.length;
1449 if (coder() == prefix.coder()) {
1450 int to = isLatin1() ? toffset : toffset << 1;
1451 while (po < pc) {
1452 if (ta[to++] != pa[po++]) {
1453 return false;
1454 }
1455 }
1456 } else {
1457 if (isLatin1()) { // && pcoder == UTF16
1458 return false;
1459 }
1460 // coder == UTF16 && pcoder == LATIN1)
1461 while (po < pc) {
1462 if (StringUTF16.Trusted.getChar(ta, toffset++) != (pa[po++] & 0xff)) {
1463 return false;
1464 }
1465 }
1466 }
1467 return true;
1468 }
1469
1470 /**
1471 * Tests if this string starts with the specified prefix.
1472 *
1473 * @param prefix the prefix.
1474 * @return {@code true} if the character sequence represented by the
1475 * argument is a prefix of the character sequence represented by
1476 * this string; {@code false} otherwise.
1477 * Note also that {@code true} will be returned if the
1478 * argument is an empty string or is equal to this
1479 * {@code String} object as determined by the
1480 * {@link #equals(Object)} method.
1481 * @since 1.0
1482 */
1483 public boolean startsWith(String prefix) {
1484 return startsWith(prefix, 0);
1485 }
1486
1487 /**
1488 * Tests if this string ends with the specified suffix.
1489 *
1490 * @param suffix the suffix.
1491 * @return {@code true} if the character sequence represented by the
1492 * argument is a suffix of the character sequence represented by
1493 * this object; {@code false} otherwise. Note that the
1494 * result will be {@code true} if the argument is the
1495 * empty string or is equal to this {@code String} object
1496 * as determined by the {@link #equals(Object)} method.
1497 */
1498 public boolean endsWith(String suffix) {
1499 return startsWith(suffix, length() - suffix.length());
1500 }
1501
1502 /**
1503 * Returns a hash code for this string. The hash code for a
1504 * {@code String} object is computed as
1505 * <blockquote><pre>
1506 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1507 * </pre></blockquote>
1508 * using {@code int} arithmetic, where {@code s[i]} is the
1509 * <i>i</i>th character of the string, {@code n} is the length of
1510 * the string, and {@code ^} indicates exponentiation.
1511 * (The hash value of the empty string is zero.)
1512 *
1513 * @return a hash code value for this object.
1514 */
1515 public int hashCode() {
1516 int h = hash;
1517 if (h == 0 && value.length > 0) {
1518 hash = h = isLatin1() ? StringLatin1.hashCode(value)
1519 : StringUTF16.hashCode(value);
1520 }
1521 return h;
1522 }
1523
1524 /**
1525 * Returns the index within this string of the first occurrence of
1526 * the specified character. If a character with value
1527 * {@code ch} occurs in the character sequence represented by
1528 * this {@code String} object, then the index (in Unicode
1529 * code units) of the first such occurrence is returned. For
1530 * values of {@code ch} in the range from 0 to 0xFFFF
1531 * (inclusive), this is the smallest value <i>k</i> such that:
1532 * <blockquote><pre>
1533 * this.charAt(<i>k</i>) == ch
1534 * </pre></blockquote>
1535 * is true. For other values of {@code ch}, it is the
1536 * smallest value <i>k</i> such that:
1537 * <blockquote><pre>
1538 * this.codePointAt(<i>k</i>) == ch
1539 * </pre></blockquote>
1540 * is true. In either case, if no such character occurs in this
1541 * string, then {@code -1} is returned.
1542 *
1543 * @param ch a character (Unicode code point).
1544 * @return the index of the first occurrence of the character in the
1545 * character sequence represented by this object, or
1546 * {@code -1} if the character does not occur.
1547 */
1548 public int indexOf(int ch) {
1549 return indexOf(ch, 0);
1550 }
1551
1552 /**
1553 * Returns the index within this string of the first occurrence of the
1554 * specified character, starting the search at the specified index.
1555 * <p>
1556 * If a character with value {@code ch} occurs in the
1557 * character sequence represented by this {@code String}
1558 * object at an index no smaller than {@code fromIndex}, then
1559 * the index of the first such occurrence is returned. For values
1560 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1561 * this is the smallest value <i>k</i> such that:
1562 * <blockquote><pre>
1563 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1564 * </pre></blockquote>
1565 * is true. For other values of {@code ch}, it is the
1566 * smallest value <i>k</i> such that:
1567 * <blockquote><pre>
1568 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1569 * </pre></blockquote>
1570 * is true. In either case, if no such character occurs in this
1571 * string at or after position {@code fromIndex}, then
1572 * {@code -1} is returned.
1573 *
1574 * <p>
1575 * There is no restriction on the value of {@code fromIndex}. If it
1576 * is negative, it has the same effect as if it were zero: this entire
1577 * string may be searched. If it is greater than the length of this
1578 * string, it has the same effect as if it were equal to the length of
1579 * this string: {@code -1} is returned.
1580 *
1581 * <p>All indices are specified in {@code char} values
1582 * (Unicode code units).
1583 *
1584 * @param ch a character (Unicode code point).
1585 * @param fromIndex the index to start the search from.
1586 * @return the index of the first occurrence of the character in the
1587 * character sequence represented by this object that is greater
1588 * than or equal to {@code fromIndex}, or {@code -1}
1589 * if the character does not occur.
1590 */
1591 public int indexOf(int ch, int fromIndex) {
1592 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex)
1593 : StringUTF16.indexOf(value, ch, fromIndex);
1594 }
1595
1596 /**
1597 * Returns the index within this string of the last occurrence of
1598 * the specified character. For values of {@code ch} in the
1599 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1600 * units) returned is the largest value <i>k</i> such that:
1601 * <blockquote><pre>
1602 * this.charAt(<i>k</i>) == ch
1603 * </pre></blockquote>
1604 * is true. For other values of {@code ch}, it is the
1605 * largest value <i>k</i> such that:
1606 * <blockquote><pre>
1607 * this.codePointAt(<i>k</i>) == ch
1608 * </pre></blockquote>
1609 * is true. In either case, if no such character occurs in this
1610 * string, then {@code -1} is returned. The
1611 * {@code String} is searched backwards starting at the last
1612 * character.
1613 *
1614 * @param ch a character (Unicode code point).
1615 * @return the index of the last occurrence of the character in the
1616 * character sequence represented by this object, or
1617 * {@code -1} if the character does not occur.
1618 */
1619 public int lastIndexOf(int ch) {
1620 return lastIndexOf(ch, length() - 1);
1621 }
1622
1623 /**
1624 * Returns the index within this string of the last occurrence of
1625 * the specified character, searching backward starting at the
1626 * specified index. For values of {@code ch} in the range
1627 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1628 * value <i>k</i> such that:
1629 * <blockquote><pre>
1630 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1631 * </pre></blockquote>
1632 * is true. For other values of {@code ch}, it is the
1633 * largest value <i>k</i> such that:
1634 * <blockquote><pre>
1635 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1636 * </pre></blockquote>
1637 * is true. In either case, if no such character occurs in this
1638 * string at or before position {@code fromIndex}, then
1639 * {@code -1} is returned.
1640 *
1641 * <p>All indices are specified in {@code char} values
1642 * (Unicode code units).
1643 *
1644 * @param ch a character (Unicode code point).
1645 * @param fromIndex the index to start the search from. There is no
1646 * restriction on the value of {@code fromIndex}. If it is
1647 * greater than or equal to the length of this string, it has
1648 * the same effect as if it were equal to one less than the
1649 * length of this string: this entire string may be searched.
1650 * If it is negative, it has the same effect as if it were -1:
1651 * -1 is returned.
1652 * @return the index of the last occurrence of the character in the
1653 * character sequence represented by this object that is less
1654 * than or equal to {@code fromIndex}, or {@code -1}
1655 * if the character does not occur before that point.
1656 */
1657 public int lastIndexOf(int ch, int fromIndex) {
1658 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex)
1659 : StringUTF16.lastIndexOf(value, ch, fromIndex);
1660 }
1661
1662 /**
1663 * Returns the index within this string of the first occurrence of the
1664 * specified substring.
1665 *
1666 * <p>The returned index is the smallest value {@code k} for which:
1667 * <pre>{@code
1668 * this.startsWith(str, k)
1669 * }</pre>
1670 * If no such value of {@code k} exists, then {@code -1} is returned.
1671 *
1672 * @param str the substring to search for.
1673 * @return the index of the first occurrence of the specified substring,
1674 * or {@code -1} if there is no such occurrence.
1675 */
1676 public int indexOf(String str) {
1677 if (coder() == str.coder()) {
1678 return isLatin1() ? StringLatin1.indexOf(value, str.value)
1679 : StringUTF16.indexOf(value, str.value);
1680 }
1681 if (coder() == LATIN1) { // str.coder == UTF16
1682 return -1;
1683 }
1684 return StringUTF16.indexOfLatin1(value, str.value);
1685 }
1686
1687 /**
1688 * Returns the index within this string of the first occurrence of the
1689 * specified substring, starting at the specified index.
1690 *
1691 * <p>The returned index is the smallest value {@code k} for which:
1692 * <pre>{@code
1693 * k >= Math.min(fromIndex, this.length()) &&
1694 * this.startsWith(str, k)
1695 * }</pre>
1696 * If no such value of {@code k} exists, then {@code -1} is returned.
1697 *
1698 * @param str the substring to search for.
1699 * @param fromIndex the index from which to start the search.
1700 * @return the index of the first occurrence of the specified substring,
1701 * starting at the specified index,
1702 * or {@code -1} if there is no such occurrence.
1703 */
1704 public int indexOf(String str, int fromIndex) {
1705 return indexOf(value, coder(), length(), str, fromIndex);
1706 }
1707
1708 /**
1709 * Code shared by String and AbstractStringBuilder to do searches. The
1710 * source is the character array being searched, and the target
1711 * is the string being searched for.
1712 *
1713 * @param src the characters being searched.
1714 * @param srcCoder the coder of the source string.
1715 * @param srcCount length of the source string.
1716 * @param tgtStr the characters being searched for.
1717 * @param fromIndex the index to begin searching from.
1718 */
1719 static int indexOf(byte[] src, byte srcCoder, int srcCount,
1720 String tgtStr, int fromIndex) {
1721 byte[] tgt = tgtStr.value;
1722 byte tgtCoder = tgtStr.coder();
1723 int tgtCount = tgtStr.length();
1724
1725 if (fromIndex >= srcCount) {
1726 return (tgtCount == 0 ? srcCount : -1);
1727 }
1728 if (fromIndex < 0) {
1729 fromIndex = 0;
1730 }
1731 if (tgtCount == 0) {
1732 return fromIndex;
1733 }
1734 if (tgtCount > srcCount) {
1735 return -1;
1736 }
1737 if (srcCoder == tgtCoder) {
1738 return srcCoder == LATIN1
1739 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex)
1740 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex);
1741 }
1742 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1743 return -1;
1744 }
1745 // srcCoder == UTF16 && tgtCoder == LATIN1) {
1746 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1747 }
1748
1749 /**
1750 * Returns the index within this string of the last occurrence of the
1751 * specified substring. The last occurrence of the empty string ""
1752 * is considered to occur at the index value {@code this.length()}.
1753 *
1754 * <p>The returned index is the largest value {@code k} for which:
1755 * <pre>{@code
1756 * this.startsWith(str, k)
1757 * }</pre>
1758 * If no such value of {@code k} exists, then {@code -1} is returned.
1759 *
1760 * @param str the substring to search for.
1761 * @return the index of the last occurrence of the specified substring,
1762 * or {@code -1} if there is no such occurrence.
1763 */
1764 public int lastIndexOf(String str) {
1765 return lastIndexOf(str, length());
1766 }
1767
1768 /**
1769 * Returns the index within this string of the last occurrence of the
1770 * specified substring, searching backward starting at the specified index.
1771 *
1772 * <p>The returned index is the largest value {@code k} for which:
1773 * <pre>{@code
1774 * k <= Math.min(fromIndex, this.length()) &&
1775 * this.startsWith(str, k)
1776 * }</pre>
1777 * If no such value of {@code k} exists, then {@code -1} is returned.
1778 *
1779 * @param str the substring to search for.
1780 * @param fromIndex the index to start the search from.
1781 * @return the index of the last occurrence of the specified substring,
1782 * searching backward from the specified index,
1783 * or {@code -1} if there is no such occurrence.
1784 */
1785 public int lastIndexOf(String str, int fromIndex) {
1786 return lastIndexOf(value, coder(), length(), str, fromIndex);
1787 }
1788
1789 /**
1790 * Code shared by String and AbstractStringBuilder to do searches. The
1791 * source is the character array being searched, and the target
1792 * is the string being searched for.
1793 *
1794 * @param src the characters being searched.
1795 * @param srcCoder coder handles the mapping between bytes/chars
1796 * @param srcCount count of the source string.
1797 * @param tgt the characters being searched for.
1798 * @param fromIndex the index to begin searching from.
1799 */
1800 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount,
1801 String tgtStr, int fromIndex) {
1802 byte[] tgt = tgtStr.value;
1803 byte tgtCoder = tgtStr.coder();
1804 int tgtCount = tgtStr.length();
1805 /*
1806 * Check arguments; return immediately where possible. For
1807 * consistency, don't check for null str.
1808 */
1809 int rightIndex = srcCount - tgtCount;
1810 if (fromIndex > rightIndex) {
1811 fromIndex = rightIndex;
1812 }
1813 if (fromIndex < 0) {
1814 return -1;
1815 }
1816 /* Empty string always matches. */
1817 if (tgtCount == 0) {
1818 return fromIndex;
1819 }
1820 if (srcCoder == tgtCoder) {
1821 return srcCoder == LATIN1
1822 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex)
1823 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex);
1824 }
1825 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1826 return -1;
1827 }
1828 // srcCoder == UTF16 && tgtCoder == LATIN1
1829 return StringUTF16.lastIndexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1830 }
1831
1832 /**
1833 * Returns a string that is a substring of this string. The
1834 * substring begins with the character at the specified index and
1835 * extends to the end of this string. <p>
1836 * Examples:
1837 * <blockquote><pre>
1838 * "unhappy".substring(2) returns "happy"
1839 * "Harbison".substring(3) returns "bison"
1840 * "emptiness".substring(9) returns "" (an empty string)
1841 * </pre></blockquote>
1842 *
1843 * @param beginIndex the beginning index, inclusive.
1844 * @return the specified substring.
1845 * @exception IndexOutOfBoundsException if
1846 * {@code beginIndex} is negative or larger than the
1847 * length of this {@code String} object.
1848 */
1849 public String substring(int beginIndex) {
1850 if (beginIndex < 0) {
1851 throw new StringIndexOutOfBoundsException(beginIndex);
1852 }
1853 int subLen = length() - beginIndex;
1854 if (subLen < 0) {
1855 throw new StringIndexOutOfBoundsException(subLen);
1856 }
1857 if (beginIndex == 0) {
1858 return this;
1859 }
1860 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1861 : StringUTF16.newString(value, beginIndex, subLen);
1862 }
1863
1864 /**
1865 * Returns a string that is a substring of this string. The
1866 * substring begins at the specified {@code beginIndex} and
1867 * extends to the character at index {@code endIndex - 1}.
1868 * Thus the length of the substring is {@code endIndex-beginIndex}.
1869 * <p>
1870 * Examples:
1871 * <blockquote><pre>
1872 * "hamburger".substring(4, 8) returns "urge"
1873 * "smiles".substring(1, 5) returns "mile"
1874 * </pre></blockquote>
1875 *
1876 * @param beginIndex the beginning index, inclusive.
1877 * @param endIndex the ending index, exclusive.
1878 * @return the specified substring.
1879 * @exception IndexOutOfBoundsException if the
1880 * {@code beginIndex} is negative, or
1881 * {@code endIndex} is larger than the length of
1882 * this {@code String} object, or
1883 * {@code beginIndex} is larger than
1884 * {@code endIndex}.
1885 */
1886 public String substring(int beginIndex, int endIndex) {
1887 int length = length();
1888 checkBoundsBeginEnd(beginIndex, endIndex, length);
1889 int subLen = endIndex - beginIndex;
1890 if (beginIndex == 0 && endIndex == length) {
1891 return this;
1892 }
1893 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1894 : StringUTF16.newString(value, beginIndex, subLen);
1895 }
1896
1897 /**
1898 * Returns a character sequence that is a subsequence of this sequence.
1899 *
1900 * <p> An invocation of this method of the form
1901 *
1902 * <blockquote><pre>
1903 * str.subSequence(begin, end)</pre></blockquote>
1904 *
1905 * behaves in exactly the same way as the invocation
1906 *
1907 * <blockquote><pre>
1908 * str.substring(begin, end)</pre></blockquote>
1909 *
1910 * @apiNote
1911 * This method is defined so that the {@code String} class can implement
1912 * the {@link CharSequence} interface.
1913 *
1914 * @param beginIndex the begin index, inclusive.
1915 * @param endIndex the end index, exclusive.
1916 * @return the specified subsequence.
1917 *
1918 * @throws IndexOutOfBoundsException
1919 * if {@code beginIndex} or {@code endIndex} is negative,
1920 * if {@code endIndex} is greater than {@code length()},
1921 * or if {@code beginIndex} is greater than {@code endIndex}
1922 *
1923 * @since 1.4
1924 * @spec JSR-51
1925 */
1926 public CharSequence subSequence(int beginIndex, int endIndex) {
1927 return this.substring(beginIndex, endIndex);
1928 }
1929
1930 /**
1931 * Concatenates the specified string to the end of this string.
1932 * <p>
1933 * If the length of the argument string is {@code 0}, then this
1934 * {@code String} object is returned. Otherwise, a
1935 * {@code String} object is returned that represents a character
1936 * sequence that is the concatenation of the character sequence
1937 * represented by this {@code String} object and the character
1938 * sequence represented by the argument string.<p>
1939 * Examples:
1940 * <blockquote><pre>
1941 * "cares".concat("s") returns "caress"
1942 * "to".concat("get").concat("her") returns "together"
1943 * </pre></blockquote>
1944 *
1945 * @param str the {@code String} that is concatenated to the end
1946 * of this {@code String}.
1947 * @return a string that represents the concatenation of this object's
1948 * characters followed by the string argument's characters.
1949 */
1950 public String concat(String str) {
1951 int olen = str.length();
1952 if (olen == 0) {
1953 return this;
1954 }
1955 if (coder() == str.coder()) {
1956 byte[] val = this.value;
1957 byte[] oval = str.value;
1958 int len = val.length + oval.length;
1959 byte[] buf = Arrays.copyOf(val, len);
1960 System.arraycopy(oval, 0, buf, val.length, oval.length);
1961 return new String(buf, coder);
1962 }
1963 int len = length();
1964 byte[] buf = StringUTF16.newBytesFor(len + olen);
1965 getBytes(buf, 0, UTF16);
1966 str.getBytes(buf, len, UTF16);
1967 return new String(buf, UTF16);
1968 }
1969
1970 /**
1971 * Returns a string resulting from replacing all occurrences of
1972 * {@code oldChar} in this string with {@code newChar}.
1973 * <p>
1974 * If the character {@code oldChar} does not occur in the
1975 * character sequence represented by this {@code String} object,
1976 * then a reference to this {@code String} object is returned.
1977 * Otherwise, a {@code String} object is returned that
1978 * represents a character sequence identical to the character sequence
1979 * represented by this {@code String} object, except that every
1980 * occurrence of {@code oldChar} is replaced by an occurrence
1981 * of {@code newChar}.
1982 * <p>
1983 * Examples:
1984 * <blockquote><pre>
1985 * "mesquite in your cellar".replace('e', 'o')
1986 * returns "mosquito in your collar"
1987 * "the war of baronets".replace('r', 'y')
1988 * returns "the way of bayonets"
1989 * "sparring with a purple porpoise".replace('p', 't')
1990 * returns "starring with a turtle tortoise"
1991 * "JonL".replace('q', 'x') returns "JonL" (no change)
1992 * </pre></blockquote>
1993 *
1994 * @param oldChar the old character.
1995 * @param newChar the new character.
1996 * @return a string derived from this string by replacing every
1997 * occurrence of {@code oldChar} with {@code newChar}.
1998 */
1999 public String replace(char oldChar, char newChar) {
2000 if (oldChar != newChar) {
2001 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar)
2002 : StringUTF16.replace(value, oldChar, newChar);
2003 if (ret != null) {
2004 return ret;
2005 }
2006 }
2007 return this;
2008 }
2009
2010 /**
2011 * Tells whether or not this string matches the given <a
2012 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2013 *
2014 * <p> An invocation of this method of the form
2015 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2016 * same result as the expression
2017 *
2018 * <blockquote>
2019 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2020 * matches(<i>regex</i>, <i>str</i>)}
2021 * </blockquote>
2022 *
2023 * @param regex
2024 * the regular expression to which this string is to be matched
2025 *
2026 * @return {@code true} if, and only if, this string matches the
2027 * given regular expression
2028 *
2029 * @throws PatternSyntaxException
2030 * if the regular expression's syntax is invalid
2031 *
2032 * @see java.util.regex.Pattern
2033 *
2034 * @since 1.4
2035 * @spec JSR-51
2036 */
2037 public boolean matches(String regex) {
2038 return Pattern.matches(regex, this);
2039 }
2040
2041 /**
2042 * Returns true if and only if this string contains the specified
2043 * sequence of char values.
2044 *
2045 * @param s the sequence to search for
2046 * @return true if this string contains {@code s}, false otherwise
2047 * @since 1.5
2048 */
2049 public boolean contains(CharSequence s) {
2050 return indexOf(s.toString()) >= 0;
2051 }
2052
2053 /**
2054 * Replaces the first substring of this string that matches the given <a
2055 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2056 * given replacement.
2057 *
2058 * <p> An invocation of this method of the form
2059 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2060 * yields exactly the same result as the expression
2061 *
2062 * <blockquote>
2063 * <code>
2064 * {@link java.util.regex.Pattern}.{@link
2065 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2066 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2067 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2068 * </code>
2069 * </blockquote>
2070 *
2071 *<p>
2072 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2073 * replacement string may cause the results to be different than if it were
2074 * being treated as a literal replacement string; see
2075 * {@link java.util.regex.Matcher#replaceFirst}.
2076 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2077 * meaning of these characters, if desired.
2078 *
2079 * @param regex
2080 * the regular expression to which this string is to be matched
2081 * @param replacement
2082 * the string to be substituted for the first match
2083 *
2084 * @return The resulting {@code String}
2085 *
2086 * @throws PatternSyntaxException
2087 * if the regular expression's syntax is invalid
2088 *
2089 * @see java.util.regex.Pattern
2090 *
2091 * @since 1.4
2092 * @spec JSR-51
2093 */
2094 public String replaceFirst(String regex, String replacement) {
2095 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2096 }
2097
2098 /**
2099 * Replaces each substring of this string that matches the given <a
2100 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2101 * given replacement.
2102 *
2103 * <p> An invocation of this method of the form
2104 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2105 * yields exactly the same result as the expression
2106 *
2107 * <blockquote>
2108 * <code>
2109 * {@link java.util.regex.Pattern}.{@link
2110 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2111 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2112 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2113 * </code>
2114 * </blockquote>
2115 *
2116 *<p>
2117 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2118 * replacement string may cause the results to be different than if it were
2119 * being treated as a literal replacement string; see
2120 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2121 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2122 * meaning of these characters, if desired.
2123 *
2124 * @param regex
2125 * the regular expression to which this string is to be matched
2126 * @param replacement
2127 * the string to be substituted for each match
2128 *
2129 * @return The resulting {@code String}
2130 *
2131 * @throws PatternSyntaxException
2132 * if the regular expression's syntax is invalid
2133 *
2134 * @see java.util.regex.Pattern
2135 *
2136 * @since 1.4
2137 * @spec JSR-51
2138 */
2139 public String replaceAll(String regex, String replacement) {
2140 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2141 }
2142
2143 /**
2144 * Replaces each substring of this string that matches the literal target
2145 * sequence with the specified literal replacement sequence. The
2146 * replacement proceeds from the beginning of the string to the end, for
2147 * example, replacing "aa" with "b" in the string "aaa" will result in
2148 * "ba" rather than "ab".
2149 *
2150 * @param target The sequence of char values to be replaced
2151 * @param replacement The replacement sequence of char values
2152 * @return The resulting string
2153 * @since 1.5
2154 */
2155 public String replace(CharSequence target, CharSequence replacement) {
2156 String tgtStr = target.toString();
2157 String replStr = replacement.toString();
2158 int j = indexOf(tgtStr);
2159 if (j < 0) {
2160 return this;
2161 }
2162 int tgtLen = tgtStr.length();
2163 int tgtLen1 = Math.max(tgtLen, 1);
2164 int thisLen = length();
2165
2166 int newLenHint = thisLen - tgtLen + replStr.length();
2167 if (newLenHint < 0) {
2168 throw new OutOfMemoryError();
2169 }
2170 StringBuilder sb = new StringBuilder(newLenHint);
2171 int i = 0;
2172 do {
2173 sb.append(this, i, j).append(replStr);
2174 i = j + tgtLen;
2175 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0);
2176 return sb.append(this, i, thisLen).toString();
2177 }
2178
2179 /**
2180 * Splits this string around matches of the given
2181 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2182 *
2183 * <p> The array returned by this method contains each substring of this
2184 * string that is terminated by another substring that matches the given
2185 * expression or is terminated by the end of the string. The substrings in
2186 * the array are in the order in which they occur in this string. If the
2187 * expression does not match any part of the input then the resulting array
2188 * has just one element, namely this string.
2189 *
2190 * <p> When there is a positive-width match at the beginning of this
2191 * string then an empty leading substring is included at the beginning
2192 * of the resulting array. A zero-width match at the beginning however
2193 * never produces such empty leading substring.
2194 *
2195 * <p> The {@code limit} parameter controls the number of times the
2196 * pattern is applied and therefore affects the length of the resulting
2197 * array. If the limit <i>n</i> is greater than zero then the pattern
2198 * will be applied at most <i>n</i> - 1 times, the array's
2199 * length will be no greater than <i>n</i>, and the array's last entry
2200 * will contain all input beyond the last matched delimiter. If <i>n</i>
2201 * is non-positive then the pattern will be applied as many times as
2202 * possible and the array can have any length. If <i>n</i> is zero then
2203 * the pattern will be applied as many times as possible, the array can
2204 * have any length, and trailing empty strings will be discarded.
2205 *
2206 * <p> The string {@code "boo:and:foo"}, for example, yields the
2207 * following results with these parameters:
2208 *
2209 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2210 * <tr>
2211 * <th>Regex</th>
2212 * <th>Limit</th>
2213 * <th>Result</th>
2214 * </tr>
2215 * <tr><td align=center>:</td>
2216 * <td align=center>2</td>
2217 * <td>{@code { "boo", "and:foo" }}</td></tr>
2218 * <tr><td align=center>:</td>
2219 * <td align=center>5</td>
2220 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2221 * <tr><td align=center>:</td>
2222 * <td align=center>-2</td>
2223 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2224 * <tr><td align=center>o</td>
2225 * <td align=center>5</td>
2226 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2227 * <tr><td align=center>o</td>
2228 * <td align=center>-2</td>
2229 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2230 * <tr><td align=center>o</td>
2231 * <td align=center>0</td>
2232 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2233 * </table></blockquote>
2234 *
2235 * <p> An invocation of this method of the form
2236 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2237 * yields the same result as the expression
2238 *
2239 * <blockquote>
2240 * <code>
2241 * {@link java.util.regex.Pattern}.{@link
2242 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2243 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2244 * </code>
2245 * </blockquote>
2246 *
2247 *
2248 * @param regex
2249 * the delimiting regular expression
2250 *
2251 * @param limit
2252 * the result threshold, as described above
2253 *
2254 * @return the array of strings computed by splitting this string
2255 * around matches of the given regular expression
2256 *
2257 * @throws PatternSyntaxException
2258 * if the regular expression's syntax is invalid
2259 *
2260 * @see java.util.regex.Pattern
2261 *
2262 * @since 1.4
2263 * @spec JSR-51
2264 */
2265 public String[] split(String regex, int limit) {
2266 /* fastpath if the regex is a
2267 (1)one-char String and this character is not one of the
2268 RegEx's meta characters ".$|()[{^?*+\\", or
2269 (2)two-char String and the first char is the backslash and
2270 the second is not the ascii digit or ascii letter.
2271 */
2272 char ch = 0;
2273 if (((regex.length() == 1 &&
2274 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2275 (regex.length() == 2 &&
2276 regex.charAt(0) == '\\' &&
2277 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2278 ((ch-'a')|('z'-ch)) < 0 &&
2279 ((ch-'A')|('Z'-ch)) < 0)) &&
2280 (ch < Character.MIN_HIGH_SURROGATE ||
2281 ch > Character.MAX_LOW_SURROGATE))
2282 {
2283 int off = 0;
2284 int next = 0;
2285 boolean limited = limit > 0;
2286 ArrayList<String> list = new ArrayList<>();
2287 while ((next = indexOf(ch, off)) != -1) {
2288 if (!limited || list.size() < limit - 1) {
2289 list.add(substring(off, next));
2290 off = next + 1;
2291 } else { // last one
2292 //assert (list.size() == limit - 1);
2293 int last = length();
2294 list.add(substring(off, last));
2295 off = last;
2296 break;
2297 }
2298 }
2299 // If no match was found, return this
2300 if (off == 0)
2301 return new String[]{this};
2302
2303 // Add remaining segment
2304 if (!limited || list.size() < limit)
2305 list.add(substring(off, length()));
2306
2307 // Construct result
2308 int resultSize = list.size();
2309 if (limit == 0) {
2310 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2311 resultSize--;
2312 }
2313 }
2314 String[] result = new String[resultSize];
2315 return list.subList(0, resultSize).toArray(result);
2316 }
2317 return Pattern.compile(regex).split(this, limit);
2318 }
2319
2320 /**
2321 * Splits this string around matches of the given <a
2322 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2323 *
2324 * <p> This method works as if by invoking the two-argument {@link
2325 * #split(String, int) split} method with the given expression and a limit
2326 * argument of zero. Trailing empty strings are therefore not included in
2327 * the resulting array.
2328 *
2329 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2330 * results with these expressions:
2331 *
2332 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2333 * <tr>
2334 * <th>Regex</th>
2335 * <th>Result</th>
2336 * </tr>
2337 * <tr><td align=center>:</td>
2338 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2339 * <tr><td align=center>o</td>
2340 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2341 * </table></blockquote>
2342 *
2343 *
2344 * @param regex
2345 * the delimiting regular expression
2346 *
2347 * @return the array of strings computed by splitting this string
2348 * around matches of the given regular expression
2349 *
2350 * @throws PatternSyntaxException
2351 * if the regular expression's syntax is invalid
2352 *
2353 * @see java.util.regex.Pattern
2354 *
2355 * @since 1.4
2356 * @spec JSR-51
2357 */
2358 public String[] split(String regex) {
2359 return split(regex, 0);
2360 }
2361
2362 /**
2363 * Returns a new String composed of copies of the
2364 * {@code CharSequence elements} joined together with a copy of
2365 * the specified {@code delimiter}.
2366 *
2367 * <blockquote>For example,
2368 * <pre>{@code
2369 * String message = String.join("-", "Java", "is", "cool");
2370 * // message returned is: "Java-is-cool"
2371 * }</pre></blockquote>
2372 *
2373 * Note that if an element is null, then {@code "null"} is added.
2374 *
2375 * @param delimiter the delimiter that separates each element
2376 * @param elements the elements to join together.
2377 *
2378 * @return a new {@code String} that is composed of the {@code elements}
2379 * separated by the {@code delimiter}
2380 *
2381 * @throws NullPointerException If {@code delimiter} or {@code elements}
2382 * is {@code null}
2383 *
2384 * @see java.util.StringJoiner
2385 * @since 1.8
2386 */
2387 public static String join(CharSequence delimiter, CharSequence... elements) {
2388 Objects.requireNonNull(delimiter);
2389 Objects.requireNonNull(elements);
2390 // Number of elements not likely worth Arrays.stream overhead.
2391 StringJoiner joiner = new StringJoiner(delimiter);
2392 for (CharSequence cs: elements) {
2393 joiner.add(cs);
2394 }
2395 return joiner.toString();
2396 }
2397
2398 /**
2399 * Returns a new {@code String} composed of copies of the
2400 * {@code CharSequence elements} joined together with a copy of the
2401 * specified {@code delimiter}.
2402 *
2403 * <blockquote>For example,
2404 * <pre>{@code
2405 * List<String> strings = List.of("Java", "is", "cool");
2406 * String message = String.join(" ", strings);
2407 * //message returned is: "Java is cool"
2408 *
2409 * Set<String> strings =
2410 * new LinkedHashSet<>(List.of("Java", "is", "very", "cool"));
2411 * String message = String.join("-", strings);
2412 * //message returned is: "Java-is-very-cool"
2413 * }</pre></blockquote>
2414 *
2415 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2416 *
2417 * @param delimiter a sequence of characters that is used to separate each
2418 * of the {@code elements} in the resulting {@code String}
2419 * @param elements an {@code Iterable} that will have its {@code elements}
2420 * joined together.
2421 *
2422 * @return a new {@code String} that is composed from the {@code elements}
2423 * argument
2424 *
2425 * @throws NullPointerException If {@code delimiter} or {@code elements}
2426 * is {@code null}
2427 *
2428 * @see #join(CharSequence,CharSequence...)
2429 * @see java.util.StringJoiner
2430 * @since 1.8
2431 */
2432 public static String join(CharSequence delimiter,
2433 Iterable<? extends CharSequence> elements) {
2434 Objects.requireNonNull(delimiter);
2435 Objects.requireNonNull(elements);
2436 StringJoiner joiner = new StringJoiner(delimiter);
2437 for (CharSequence cs: elements) {
2438 joiner.add(cs);
2439 }
2440 return joiner.toString();
2441 }
2442
2443 /**
2444 * Converts all of the characters in this {@code String} to lower
2445 * case using the rules of the given {@code Locale}. Case mapping is based
2446 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2447 * class. Since case mappings are not always 1:1 char mappings, the resulting
2448 * {@code String} may be a different length than the original {@code String}.
2449 * <p>
2450 * Examples of lowercase mappings are in the following table:
2451 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2452 * <tr>
2453 * <th>Language Code of Locale</th>
2454 * <th>Upper Case</th>
2455 * <th>Lower Case</th>
2456 * <th>Description</th>
2457 * </tr>
2458 * <tr>
2459 * <td>tr (Turkish)</td>
2460 * <td>\u0130</td>
2461 * <td>\u0069</td>
2462 * <td>capital letter I with dot above -> small letter i</td>
2463 * </tr>
2464 * <tr>
2465 * <td>tr (Turkish)</td>
2466 * <td>\u0049</td>
2467 * <td>\u0131</td>
2468 * <td>capital letter I -> small letter dotless i </td>
2469 * </tr>
2470 * <tr>
2471 * <td>(all)</td>
2472 * <td>French Fries</td>
2473 * <td>french fries</td>
2474 * <td>lowercased all chars in String</td>
2475 * </tr>
2476 * <tr>
2477 * <td>(all)</td>
2478 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2479 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2480 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2481 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2482 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2483 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2484 * <td>lowercased all chars in String</td>
2485 * </tr>
2486 * </table>
2487 *
2488 * @param locale use the case transformation rules for this locale
2489 * @return the {@code String}, converted to lowercase.
2490 * @see java.lang.String#toLowerCase()
2491 * @see java.lang.String#toUpperCase()
2492 * @see java.lang.String#toUpperCase(Locale)
2493 * @since 1.1
2494 */
2495 public String toLowerCase(Locale locale) {
2496 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale)
2497 : StringUTF16.toLowerCase(this, value, locale);
2498 }
2499
2500 /**
2501 * Converts all of the characters in this {@code String} to lower
2502 * case using the rules of the default locale. This is equivalent to calling
2503 * {@code toLowerCase(Locale.getDefault())}.
2504 * <p>
2505 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2506 * results if used for strings that are intended to be interpreted locale
2507 * independently.
2508 * Examples are programming language identifiers, protocol keys, and HTML
2509 * tags.
2510 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2511 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2512 * LATIN SMALL LETTER DOTLESS I character.
2513 * To obtain correct results for locale insensitive strings, use
2514 * {@code toLowerCase(Locale.ROOT)}.
2515 *
2516 * @return the {@code String}, converted to lowercase.
2517 * @see java.lang.String#toLowerCase(Locale)
2518 */
2519 public String toLowerCase() {
2520 return toLowerCase(Locale.getDefault());
2521 }
2522
2523 /**
2524 * Converts all of the characters in this {@code String} to upper
2525 * case using the rules of the given {@code Locale}. Case mapping is based
2526 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2527 * class. Since case mappings are not always 1:1 char mappings, the resulting
2528 * {@code String} may be a different length than the original {@code String}.
2529 * <p>
2530 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2531 *
2532 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2533 * <tr>
2534 * <th>Language Code of Locale</th>
2535 * <th>Lower Case</th>
2536 * <th>Upper Case</th>
2537 * <th>Description</th>
2538 * </tr>
2539 * <tr>
2540 * <td>tr (Turkish)</td>
2541 * <td>\u0069</td>
2542 * <td>\u0130</td>
2543 * <td>small letter i -> capital letter I with dot above</td>
2544 * </tr>
2545 * <tr>
2546 * <td>tr (Turkish)</td>
2547 * <td>\u0131</td>
2548 * <td>\u0049</td>
2549 * <td>small letter dotless i -> capital letter I</td>
2550 * </tr>
2551 * <tr>
2552 * <td>(all)</td>
2553 * <td>\u00df</td>
2554 * <td>\u0053 \u0053</td>
2555 * <td>small letter sharp s -> two letters: SS</td>
2556 * </tr>
2557 * <tr>
2558 * <td>(all)</td>
2559 * <td>Fahrvergnügen</td>
2560 * <td>FAHRVERGNÜGEN</td>
2561 * <td></td>
2562 * </tr>
2563 * </table>
2564 * @param locale use the case transformation rules for this locale
2565 * @return the {@code String}, converted to uppercase.
2566 * @see java.lang.String#toUpperCase()
2567 * @see java.lang.String#toLowerCase()
2568 * @see java.lang.String#toLowerCase(Locale)
2569 * @since 1.1
2570 */
2571 public String toUpperCase(Locale locale) {
2572 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale)
2573 : StringUTF16.toUpperCase(this, value, locale);
2574 }
2575
2576 /**
2577 * Converts all of the characters in this {@code String} to upper
2578 * case using the rules of the default locale. This method is equivalent to
2579 * {@code toUpperCase(Locale.getDefault())}.
2580 * <p>
2581 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2582 * results if used for strings that are intended to be interpreted locale
2583 * independently.
2584 * Examples are programming language identifiers, protocol keys, and HTML
2585 * tags.
2586 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2587 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2588 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2589 * To obtain correct results for locale insensitive strings, use
2590 * {@code toUpperCase(Locale.ROOT)}.
2591 *
2592 * @return the {@code String}, converted to uppercase.
2593 * @see java.lang.String#toUpperCase(Locale)
2594 */
2595 public String toUpperCase() {
2596 return toUpperCase(Locale.getDefault());
2597 }
2598
2599 /**
2600 * Returns a string whose value is this string, with any leading and trailing
2601 * whitespace removed.
2602 * <p>
2603 * If this {@code String} object represents an empty character
2604 * sequence, or the first and last characters of character sequence
2605 * represented by this {@code String} object both have codes
2606 * greater than {@code '\u005Cu0020'} (the space character), then a
2607 * reference to this {@code String} object is returned.
2608 * <p>
2609 * Otherwise, if there is no character with a code greater than
2610 * {@code '\u005Cu0020'} in the string, then a
2611 * {@code String} object representing an empty string is
2612 * returned.
2613 * <p>
2614 * Otherwise, let <i>k</i> be the index of the first character in the
2615 * string whose code is greater than {@code '\u005Cu0020'}, and let
2616 * <i>m</i> be the index of the last character in the string whose code
2617 * is greater than {@code '\u005Cu0020'}. A {@code String}
2618 * object is returned, representing the substring of this string that
2619 * begins with the character at index <i>k</i> and ends with the
2620 * character at index <i>m</i>-that is, the result of
2621 * {@code this.substring(k, m + 1)}.
2622 * <p>
2623 * This method may be used to trim whitespace (as defined above) from
2624 * the beginning and end of a string.
2625 *
2626 * @return A string whose value is this string, with any leading and trailing white
2627 * space removed, or this string if it has no leading or
2628 * trailing white space.
2629 */
2630 public String trim() {
2631 String ret = isLatin1() ? StringLatin1.trim(value)
2632 : StringUTF16.trim(value);
2633 return ret == null ? this : ret;
2634 }
2635
2636 /**
2637 * This object (which is already a string!) is itself returned.
2638 *
2639 * @return the string itself.
2640 */
2641 public String toString() {
2642 return this;
2643 }
2644
2645 /**
2646 * Returns a stream of {@code int} zero-extending the {@code char} values
2647 * from this sequence. Any char which maps to a <a
2648 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code
2649 * point</a> is passed through uninterpreted.
2650 *
2651 * @return an IntStream of char values from this sequence
2652 * @since 9
2653 */
2654 @Override
2655 public IntStream chars() {
2656 return StreamSupport.intStream(
2657 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
2658 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE),
2659 false);
2660 }
2661
2662
2663 /**
2664 * Returns a stream of code point values from this sequence. Any surrogate
2665 * pairs encountered in the sequence are combined as if by {@linkplain
2666 * Character#toCodePoint Character.toCodePoint} and the result is passed
2667 * to the stream. Any other code units, including ordinary BMP characters,
2668 * unpaired surrogates, and undefined code units, are zero-extended to
2669 * {@code int} values which are then passed to the stream.
2670 *
2671 * @return an IntStream of Unicode code points from this sequence
2672 * @since 9
2673 */
2674 @Override
2675 public IntStream codePoints() {
2676 return StreamSupport.intStream(
2677 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
2678 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE),
2679 false);
2680 }
2681
2682 /**
2683 * Converts this string to a new character array.
2684 *
2685 * @return a newly allocated character array whose length is the length
2686 * of this string and whose contents are initialized to contain
2687 * the character sequence represented by this string.
2688 */
2689 public char[] toCharArray() {
2690 return isLatin1() ? StringLatin1.toChars(value)
2691 : StringUTF16.toChars(value);
2692 }
2693
2694 /**
2695 * Returns a formatted string using the specified format string and
2696 * arguments.
2697 *
2698 * <p> The locale always used is the one returned by {@link
2699 * java.util.Locale#getDefault(java.util.Locale.Category)
2700 * Locale.getDefault(Locale.Category)} with
2701 * {@link java.util.Locale.Category#FORMAT FORMAT} category specified.
2702 *
2703 * @param format
2704 * A <a href="../util/Formatter.html#syntax">format string</a>
2705 *
2706 * @param args
2707 * Arguments referenced by the format specifiers in the format
2708 * string. If there are more arguments than format specifiers, the
2709 * extra arguments are ignored. The number of arguments is
2710 * variable and may be zero. The maximum number of arguments is
2711 * limited by the maximum dimension of a Java array as defined by
2712 * <cite>The Java™ Virtual Machine Specification</cite>.
2713 * The behaviour on a
2714 * {@code null} argument depends on the <a
2715 * href="../util/Formatter.html#syntax">conversion</a>.
2716 *
2717 * @throws java.util.IllegalFormatException
2718 * If a format string contains an illegal syntax, a format
2719 * specifier that is incompatible with the given arguments,
2720 * insufficient arguments given the format string, or other
2721 * illegal conditions. For specification of all possible
2722 * formatting errors, see the <a
2723 * href="../util/Formatter.html#detail">Details</a> section of the
2724 * formatter class specification.
2725 *
2726 * @return A formatted string
2727 *
2728 * @see java.util.Formatter
2729 * @since 1.5
2730 */
2731 public static String format(String format, Object... args) {
2732 return new Formatter().format(format, args).toString();
2733 }
2734
2735 /**
2736 * Returns a formatted string using the specified locale, format string,
2737 * and arguments.
2738 *
2739 * @param l
2740 * The {@linkplain java.util.Locale locale} to apply during
2741 * formatting. If {@code l} is {@code null} then no localization
2742 * is applied.
2743 *
2744 * @param format
2745 * A <a href="../util/Formatter.html#syntax">format string</a>
2746 *
2747 * @param args
2748 * Arguments referenced by the format specifiers in the format
2749 * string. If there are more arguments than format specifiers, the
2750 * extra arguments are ignored. The number of arguments is
2751 * variable and may be zero. The maximum number of arguments is
2752 * limited by the maximum dimension of a Java array as defined by
2753 * <cite>The Java™ Virtual Machine Specification</cite>.
2754 * The behaviour on a
2755 * {@code null} argument depends on the
2756 * <a href="../util/Formatter.html#syntax">conversion</a>.
2757 *
2758 * @throws java.util.IllegalFormatException
2759 * If a format string contains an illegal syntax, a format
2760 * specifier that is incompatible with the given arguments,
2761 * insufficient arguments given the format string, or other
2762 * illegal conditions. For specification of all possible
2763 * formatting errors, see the <a
2764 * href="../util/Formatter.html#detail">Details</a> section of the
2765 * formatter class specification
2766 *
2767 * @return A formatted string
2768 *
2769 * @see java.util.Formatter
2770 * @since 1.5
2771 */
2772 public static String format(Locale l, String format, Object... args) {
2773 return new Formatter(l).format(format, args).toString();
2774 }
2775
2776 /**
2777 * Returns the string representation of the {@code Object} argument.
2778 *
2779 * @param obj an {@code Object}.
2780 * @return if the argument is {@code null}, then a string equal to
2781 * {@code "null"}; otherwise, the value of
2782 * {@code obj.toString()} is returned.
2783 * @see java.lang.Object#toString()
2784 */
2785 public static String valueOf(Object obj) {
2786 return (obj == null) ? "null" : obj.toString();
2787 }
2788
2789 /**
2790 * Returns the string representation of the {@code char} array
2791 * argument. The contents of the character array are copied; subsequent
2792 * modification of the character array does not affect the returned
2793 * string.
2794 *
2795 * @param data the character array.
2796 * @return a {@code String} that contains the characters of the
2797 * character array.
2798 */
2799 public static String valueOf(char data[]) {
2800 return new String(data);
2801 }
2802
2803 /**
2804 * Returns the string representation of a specific subarray of the
2805 * {@code char} array argument.
2806 * <p>
2807 * The {@code offset} argument is the index of the first
2808 * character of the subarray. The {@code count} argument
2809 * specifies the length of the subarray. The contents of the subarray
2810 * are copied; subsequent modification of the character array does not
2811 * affect the returned string.
2812 *
2813 * @param data the character array.
2814 * @param offset initial offset of the subarray.
2815 * @param count length of the subarray.
2816 * @return a {@code String} that contains the characters of the
2817 * specified subarray of the character array.
2818 * @exception IndexOutOfBoundsException if {@code offset} is
2819 * negative, or {@code count} is negative, or
2820 * {@code offset+count} is larger than
2821 * {@code data.length}.
2822 */
2823 public static String valueOf(char data[], int offset, int count) {
2824 return new String(data, offset, count);
2825 }
2826
2827 /**
2828 * Equivalent to {@link #valueOf(char[], int, int)}.
2829 *
2830 * @param data the character array.
2831 * @param offset initial offset of the subarray.
2832 * @param count length of the subarray.
2833 * @return a {@code String} that contains the characters of the
2834 * specified subarray of the character array.
2835 * @exception IndexOutOfBoundsException if {@code offset} is
2836 * negative, or {@code count} is negative, or
2837 * {@code offset+count} is larger than
2838 * {@code data.length}.
2839 */
2840 public static String copyValueOf(char data[], int offset, int count) {
2841 return new String(data, offset, count);
2842 }
2843
2844 /**
2845 * Equivalent to {@link #valueOf(char[])}.
2846 *
2847 * @param data the character array.
2848 * @return a {@code String} that contains the characters of the
2849 * character array.
2850 */
2851 public static String copyValueOf(char data[]) {
2852 return new String(data);
2853 }
2854
2855 /**
2856 * Returns the string representation of the {@code boolean} argument.
2857 *
2858 * @param b a {@code boolean}.
2859 * @return if the argument is {@code true}, a string equal to
2860 * {@code "true"} is returned; otherwise, a string equal to
2861 * {@code "false"} is returned.
2862 */
2863 public static String valueOf(boolean b) {
2864 return b ? "true" : "false";
2865 }
2866
2867 /**
2868 * Returns the string representation of the {@code char}
2869 * argument.
2870 *
2871 * @param c a {@code char}.
2872 * @return a string of length {@code 1} containing
2873 * as its single character the argument {@code c}.
2874 */
2875 public static String valueOf(char c) {
2876 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) {
2877 return new String(StringLatin1.toBytes(c), LATIN1);
2878 }
2879 return new String(StringUTF16.toBytes(c), UTF16);
2880 }
2881
2882 /**
2883 * Returns the string representation of the {@code int} argument.
2884 * <p>
2885 * The representation is exactly the one returned by the
2886 * {@code Integer.toString} method of one argument.
2887 *
2888 * @param i an {@code int}.
2889 * @return a string representation of the {@code int} argument.
2890 * @see java.lang.Integer#toString(int, int)
2891 */
2892 public static String valueOf(int i) {
2893 return Integer.toString(i);
2894 }
2895
2896 /**
2897 * Returns the string representation of the {@code long} argument.
2898 * <p>
2899 * The representation is exactly the one returned by the
2900 * {@code Long.toString} method of one argument.
2901 *
2902 * @param l a {@code long}.
2903 * @return a string representation of the {@code long} argument.
2904 * @see java.lang.Long#toString(long)
2905 */
2906 public static String valueOf(long l) {
2907 return Long.toString(l);
2908 }
2909
2910 /**
2911 * Returns the string representation of the {@code float} argument.
2912 * <p>
2913 * The representation is exactly the one returned by the
2914 * {@code Float.toString} method of one argument.
2915 *
2916 * @param f a {@code float}.
2917 * @return a string representation of the {@code float} argument.
2918 * @see java.lang.Float#toString(float)
2919 */
2920 public static String valueOf(float f) {
2921 return Float.toString(f);
2922 }
2923
2924 /**
2925 * Returns the string representation of the {@code double} argument.
2926 * <p>
2927 * The representation is exactly the one returned by the
2928 * {@code Double.toString} method of one argument.
2929 *
2930 * @param d a {@code double}.
2931 * @return a string representation of the {@code double} argument.
2932 * @see java.lang.Double#toString(double)
2933 */
2934 public static String valueOf(double d) {
2935 return Double.toString(d);
2936 }
2937
2938 /**
2939 * Returns a canonical representation for the string object.
2940 * <p>
2941 * A pool of strings, initially empty, is maintained privately by the
2942 * class {@code String}.
2943 * <p>
2944 * When the intern method is invoked, if the pool already contains a
2945 * string equal to this {@code String} object as determined by
2946 * the {@link #equals(Object)} method, then the string from the pool is
2947 * returned. Otherwise, this {@code String} object is added to the
2948 * pool and a reference to this {@code String} object is returned.
2949 * <p>
2950 * It follows that for any two strings {@code s} and {@code t},
2951 * {@code s.intern() == t.intern()} is {@code true}
2952 * if and only if {@code s.equals(t)} is {@code true}.
2953 * <p>
2954 * All literal strings and string-valued constant expressions are
2955 * interned. String literals are defined in section 3.10.5 of the
2956 * <cite>The Java™ Language Specification</cite>.
2957 *
2958 * @return a string that has the same contents as this string, but is
2959 * guaranteed to be from a pool of unique strings.
2960 * @jls 3.10.5 String Literals
2961 */
2962 public native String intern();
2963
2964 ////////////////////////////////////////////////////////////////
2965
2966 /**
2967 * Copy character bytes from this string into dst starting at dstBegin.
2968 * This method doesn't perform any range checking.
2969 *
2970 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two
2971 * coders are different, and dst is big enough (range check)
2972 *
2973 * @param dstBegin the char index, not offset of byte[]
2974 * @param coder the coder of dst[]
2975 */
2976 void getBytes(byte dst[], int dstBegin, byte coder) {
2977 if (coder() == coder) {
2978 System.arraycopy(value, 0, dst, dstBegin << coder, value.length);
2979 } else { // this.coder == LATIN && coder == UTF16
2980 StringLatin1.inflate(value, 0, dst, dstBegin, value.length);
2981 }
2982 }
2983
2984 /*
2985 * Package private constructor. Trailing Void argument is there for
2986 * disambiguating it against other (public) constructors.
2987 *
2988 * Stores the char[] value into a byte[] that each byte represents
2989 * the8 low-order bits of the corresponding character, if the char[]
2990 * contains only latin1 character. Or a byte[] that stores all
2991 * characters in their byte sequences defined by the {@code StringUTF16}.
2992 */
2993 String(char[] value, int off, int len, Void sig) {
2994 if (len == 0) {
2995 this.value = "".value;
2996 this.coder = "".coder;
2997 return;
2998 }
2999 if (COMPACT_STRINGS) {
3000 byte[] val = StringUTF16.compress(value, off, len);
3001 if (val != null) {
3002 this.value = val;
3003 this.coder = LATIN1;
3004 return;
3005 }
3006 }
3007 this.coder = UTF16;
3008 this.value = StringUTF16.toBytes(value, off, len);
3009 }
3010
3011 /*
3012 * Package private constructor. Trailing Void argument is there for
3013 * disambiguating it against other (public) constructors.
3014 */
3015 String(AbstractStringBuilder asb, Void sig) {
3016 byte[] val = asb.getValue();
3017 int length = asb.length();
3018 if (asb.isLatin1()) {
3019 this.coder = LATIN1;
3020 this.value = Arrays.copyOfRange(val, 0, length);
3021 } else {
3022 if (COMPACT_STRINGS) {
3023 byte[] buf = StringUTF16.compress(val, 0, length);
3024 if (buf != null) {
3025 this.coder = LATIN1;
3026 this.value = buf;
3027 return;
3028 }
3029 }
3030 this.coder = UTF16;
3031 this.value = Arrays.copyOfRange(val, 0, length << 1);
3032 }
3033 }
3034
3035 /*
3036 * Package private constructor which shares value array for speed.
3037 */
3038 String(byte[] value, byte coder) {
3039 this.value = value;
3040 this.coder = coder;
3041 }
3042
3043 byte coder() {
3044 return COMPACT_STRINGS ? coder : UTF16;
3045 }
3046
3047 private boolean isLatin1() {
3048 return COMPACT_STRINGS && coder == LATIN1;
3049 }
3050
3051 static final byte LATIN1 = 0;
3052 static final byte UTF16 = 1;
3053
3054 /*
3055 * StringIndexOutOfBoundsException if {@code index} is
3056 * negative or greater than or equal to {@code length}.
3057 */
3058 static void checkIndex(int index, int length) {
3059 if (index < 0 || index >= length) {
3060 throw new StringIndexOutOfBoundsException("index " + index +
3061 ",length " + length);
3062 }
3063 }
3064
3065 /*
3066 * StringIndexOutOfBoundsException if {@code offset}
3067 * is negative or greater than {@code length}.
3068 */
3069 static void checkOffset(int offset, int length) {
3070 if (offset < 0 || offset > length) {
3071 throw new StringIndexOutOfBoundsException("offset " + offset +
3072 ",length " + length);
3073 }
3074 }
3075
3076 /*
3077 * Check {@code offset}, {@code count} against {@code 0} and {@code length}
3078 * bounds.
3079 *
3080 * @throws StringIndexOutOfBoundsException
3081 * If {@code offset} is negative, {@code count} is negative,
3082 * or {@code offset} is greater than {@code length - count}
3083 */
3084 static void checkBoundsOffCount(int offset, int count, int length) {
3085 if (offset < 0 || count < 0 || offset > length - count) {
3086 throw new StringIndexOutOfBoundsException(
3087 "offset " + offset + ", count " + count + ", length " + length);
3088 }
3089 }
3090
3091 /*
3092 * Check {@code begin}, {@code end} against {@code 0} and {@code length}
3093 * bounds.
3094 *
3095 * @throws StringIndexOutOfBoundsException
3096 * If {@code begin} is negative, {@code begin} is greater than
3097 * {@code end}, or {@code end} is greater than {@code length}.
3098 */
3099 static void checkBoundsBeginEnd(int begin, int end, int length) {
3100 if (begin < 0 || begin > end || end > length) {
3101 throw new StringIndexOutOfBoundsException(
3102 "begin " + begin + ", end " + end + ", length " + length);
3103 }
3104 }
3105 }