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