1 /*
2 * Copyright (c) 1994, 2015, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import java.io.ObjectStreamField;
29 import java.io.UnsupportedEncodingException;
30 import java.nio.charset.Charset;
31 import java.util.ArrayList;
32 import java.util.Arrays;
33 import java.util.Comparator;
34 import java.util.Formatter;
35 import java.util.Locale;
36 import java.util.Objects;
37 import java.util.Spliterator;
38 import java.util.StringJoiner;
39 import java.util.function.IntConsumer;
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
47 /**
48 * The {@code String} class represents character strings. All
49 * string literals in Java programs, such as {@code "abc"}, are
50 * implemented as instances of this class.
51 * <p>
52 * Strings are constant; their values cannot be changed after they
53 * are created. String buffers support mutable strings.
54 * Because String objects are immutable they can be shared. For example:
55 * <blockquote><pre>
56 * String str = "abc";
57 * </pre></blockquote><p>
58 * is equivalent to:
59 * <blockquote><pre>
60 * char data[] = {'a', 'b', 'c'};
61 * String str = new String(data);
62 * </pre></blockquote><p>
63 * Here are some more examples of how strings can be used:
64 * <blockquote><pre>
65 * System.out.println("abc");
66 * String cde = "cde";
67 * System.out.println("abc" + cde);
68 * String c = "abc".substring(2,3);
69 * String d = cde.substring(1, 2);
70 * </pre></blockquote>
71 * <p>
72 * The class {@code String} includes methods for examining
73 * individual characters of the sequence, for comparing strings, for
74 * searching strings, for extracting substrings, and for creating a
75 * copy of a string with all characters translated to uppercase or to
76 * lowercase. Case mapping is based on the Unicode Standard version
77 * specified by the {@link java.lang.Character Character} class.
78 * <p>
79 * The Java language provides special support for the string
80 * concatenation operator ( + ), and for conversion of
81 * other objects to strings. String concatenation is implemented
82 * through the {@code StringBuilder}(or {@code StringBuffer})
83 * class and its {@code append} method.
84 * String conversions are implemented through the method
85 * {@code toString}, defined by {@code Object} and
86 * inherited by all classes in Java. For additional information on
87 * string concatenation and conversion, see Gosling, Joy, and Steele,
88 * <i>The Java Language Specification</i>.
89 *
90 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor
91 * or method in this class will cause a {@link NullPointerException} to be
92 * thrown.
93 *
94 * <p>A {@code String} represents a string in the UTF-16 format
95 * in which <em>supplementary characters</em> are represented by <em>surrogate
96 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
97 * Character Representations</a> in the {@code Character} class for
98 * more information).
99 * Index values refer to {@code char} code units, so a supplementary
100 * character uses two positions in a {@code String}.
101 * <p>The {@code String} class provides methods for dealing with
102 * Unicode code points (i.e., characters), in addition to those for
103 * dealing with Unicode code units (i.e., {@code char} values).
104 *
105 * @author Lee Boynton
106 * @author Arthur van Hoff
107 * @author Martin Buchholz
108 * @author Ulf Zibis
109 * @see java.lang.Object#toString()
110 * @see java.lang.StringBuffer
111 * @see java.lang.StringBuilder
112 * @see java.nio.charset.Charset
113 * @since 1.0
114 */
115
116 public final class String
117 implements java.io.Serializable, Comparable<String>, CharSequence {
118 /** The value is used for character storage. */
119 private final char value[];
120
121 /** Cache the hash code for the string */
122 private int hash; // Default to 0
123
124 /** use serialVersionUID from JDK 1.0.2 for interoperability */
125 private static final long serialVersionUID = -6849794470754667710L;
126
127 /**
128 * Class String is special cased within the Serialization Stream Protocol.
129 *
130 * A String instance is written into an ObjectOutputStream according to
131 * <a href="{@docRoot}/../platform/serialization/spec/output.html">
132 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
133 */
134 private static final ObjectStreamField[] serialPersistentFields =
135 new ObjectStreamField[0];
136
137 /**
138 * Initializes a newly created {@code String} object so that it represents
139 * an empty character sequence. Note that use of this constructor is
140 * unnecessary since Strings are immutable.
141 */
142 public String() {
143 this.value = "".value;
144 }
145
146 /**
147 * Initializes a newly created {@code String} object so that it represents
148 * the same sequence of characters as the argument; in other words, the
149 * newly created string is a copy of the argument string. Unless an
150 * explicit copy of {@code original} is needed, use of this constructor is
151 * unnecessary since Strings are immutable.
152 *
153 * @param original
154 * A {@code String}
155 */
156 @HotSpotIntrinsicCandidate
157 public String(String original) {
158 this.value = original.value;
159 this.hash = original.hash;
160 }
161
162 /**
163 * Allocates a new {@code String} so that it represents the sequence of
164 * characters currently contained in the character array argument. The
165 * contents of the character array are copied; subsequent modification of
166 * the character array does not affect the newly created string.
167 *
168 * @param value
169 * The initial value of the string
170 */
171 public String(char value[]) {
172 this.value = Arrays.copyOf(value, value.length);
173 }
174
175 /**
176 * Allocates a new {@code String} that contains characters from a subarray
177 * of the character array argument. The {@code offset} argument is the
178 * index of the first character of the subarray and the {@code count}
179 * argument specifies the length of the subarray. The contents of the
180 * subarray are copied; subsequent modification of the character array does
181 * not affect the newly created string.
182 *
183 * @param value
184 * Array that is the source of characters
185 *
186 * @param offset
187 * The initial offset
188 *
189 * @param count
190 * The length
191 *
192 * @throws IndexOutOfBoundsException
193 * If {@code offset} is negative, {@code count} is negative, or
194 * {@code offset} is greater than {@code value.length - count}
195 */
196 public String(char value[], int offset, int count) {
197 if (offset < 0) {
198 throw new StringIndexOutOfBoundsException(offset);
199 }
200 if (count <= 0) {
201 if (count < 0) {
202 throw new StringIndexOutOfBoundsException(count);
203 }
204 if (offset <= value.length) {
205 this.value = "".value;
206 return;
207 }
208 }
209 // Note: offset or count might be near -1>>>1.
210 if (offset > value.length - count) {
211 throw new StringIndexOutOfBoundsException(offset + count);
212 }
213 this.value = Arrays.copyOfRange(value, offset, offset + count);
214 }
215
216 /**
217 * Allocates a new {@code String} that contains characters from a subarray
218 * of the <a href="Character.html#unicode">Unicode code point</a> array
219 * argument. The {@code offset} argument is the index of the first code
220 * point of the subarray and the {@code count} argument specifies the
221 * length of the subarray. The contents of the subarray are converted to
222 * {@code char}s; subsequent modification of the {@code int} array does not
223 * affect the newly created string.
224 *
225 * @param codePoints
226 * Array that is the source of Unicode code points
227 *
228 * @param offset
229 * The initial offset
230 *
231 * @param count
232 * The length
233 *
234 * @throws IllegalArgumentException
235 * If any invalid Unicode code point is found in {@code
236 * codePoints}
237 *
238 * @throws IndexOutOfBoundsException
239 * If {@code offset} is negative, {@code count} is negative, or
240 * {@code offset} is greater than {@code codePoints.length - count}
241 *
242 * @since 1.5
243 */
244 public String(int[] codePoints, int offset, int count) {
245 if (offset < 0) {
246 throw new StringIndexOutOfBoundsException(offset);
247 }
248 if (count <= 0) {
249 if (count < 0) {
250 throw new StringIndexOutOfBoundsException(count);
251 }
252 if (offset <= codePoints.length) {
253 this.value = "".value;
254 return;
255 }
256 }
257 // Note: offset or count might be near -1>>>1.
258 if (offset > codePoints.length - count) {
259 throw new StringIndexOutOfBoundsException(offset + count);
260 }
261
262 final int end = offset + count;
263
264 // Pass 1: Compute precise size of char[]
265 int n = count;
266 for (int i = offset; i < end; i++) {
267 int c = codePoints[i];
268 if (Character.isBmpCodePoint(c))
269 continue;
270 else if (Character.isValidCodePoint(c))
271 n++;
272 else throw new IllegalArgumentException(Integer.toString(c));
273 }
274
275 // Pass 2: Allocate and fill in char[]
276 final char[] v = new char[n];
277
278 for (int i = offset, j = 0; i < end; i++, j++) {
279 int c = codePoints[i];
280 if (Character.isBmpCodePoint(c))
281 v[j] = (char)c;
282 else
283 Character.toSurrogates(c, v, j++);
284 }
285
286 this.value = v;
287 }
288
289 /**
290 * Allocates a new {@code String} constructed from a subarray of an array
291 * of 8-bit integer values.
292 *
293 * <p> The {@code offset} argument is the index of the first byte of the
294 * subarray, and the {@code count} argument specifies the length of the
295 * subarray.
296 *
297 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
298 * specified in the method above.
299 *
300 * @deprecated This method does not properly convert bytes into characters.
301 * As of JDK 1.1, the preferred way to do this is via the
302 * {@code String} constructors that take a {@link
303 * java.nio.charset.Charset}, charset name, or that use the platform's
304 * default charset.
305 *
306 * @param ascii
307 * The bytes to be converted to characters
308 *
309 * @param hibyte
310 * The top 8 bits of each 16-bit Unicode code unit
311 *
312 * @param offset
313 * The initial offset
314 * @param count
315 * The length
316 *
317 * @throws IndexOutOfBoundsException
318 * If {@code offset} is negative, {@code count} is negative, or
319 * {@code offset} is greater than {@code ascii.length - count}
320 *
321 * @see #String(byte[], int)
322 * @see #String(byte[], int, int, java.lang.String)
323 * @see #String(byte[], int, int, java.nio.charset.Charset)
324 * @see #String(byte[], int, int)
325 * @see #String(byte[], java.lang.String)
326 * @see #String(byte[], java.nio.charset.Charset)
327 * @see #String(byte[])
328 */
329 @Deprecated
330 public String(byte ascii[], int hibyte, int offset, int count) {
331 checkBounds(ascii, offset, count);
332 char[] value = new char[count];
333
334 if (hibyte == 0) {
335 for (int i = count; i-- > 0;) {
336 value[i] = (char)(ascii[i + offset] & 0xff);
337 }
338 } else {
339 hibyte <<= 8;
340 for (int i = count; i-- > 0;) {
341 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff));
342 }
343 }
344 this.value = value;
345 }
346
347 /**
348 * Allocates a new {@code String} containing characters constructed from
349 * an array of 8-bit integer values. Each character <i>c</i>in the
350 * resulting string is constructed from the corresponding component
351 * <i>b</i> in the byte array such that:
352 *
353 * <blockquote><pre>
354 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
355 * | (<b><i>b</i></b> & 0xff))
356 * </pre></blockquote>
357 *
358 * @deprecated This method does not properly convert bytes into
359 * characters. As of JDK 1.1, the preferred way to do this is via the
360 * {@code String} constructors that take a {@link
361 * java.nio.charset.Charset}, charset name, or that use the platform's
362 * default charset.
363 *
364 * @param ascii
365 * The bytes to be converted to characters
366 *
367 * @param hibyte
368 * The top 8 bits of each 16-bit Unicode code unit
369 *
370 * @see #String(byte[], int, int, java.lang.String)
371 * @see #String(byte[], int, int, java.nio.charset.Charset)
372 * @see #String(byte[], int, int)
373 * @see #String(byte[], java.lang.String)
374 * @see #String(byte[], java.nio.charset.Charset)
375 * @see #String(byte[])
376 */
377 @Deprecated
378 public String(byte ascii[], int hibyte) {
379 this(ascii, hibyte, 0, ascii.length);
380 }
381
382 /* Common private utility method used to bounds check the byte array
383 * and requested offset & length values used by the String(byte[],..)
384 * constructors.
385 */
386 private static void checkBounds(byte[] bytes, int offset, int length) {
387 if (length < 0)
388 throw new StringIndexOutOfBoundsException(length);
389 if (offset < 0)
390 throw new StringIndexOutOfBoundsException(offset);
391 if (offset > bytes.length - length)
392 throw new StringIndexOutOfBoundsException(offset + length);
393 }
394
395 /**
396 * Constructs a new {@code String} by decoding the specified subarray of
397 * bytes using the specified charset. The length of the new {@code String}
398 * is a function of the charset, and hence may not be equal to the length
399 * of the subarray.
400 *
401 * <p> The behavior of this constructor when the given bytes are not valid
402 * in the given charset is unspecified. The {@link
403 * java.nio.charset.CharsetDecoder} class should be used when more control
404 * over the decoding process is required.
405 *
406 * @param bytes
407 * The bytes to be decoded into characters
408 *
409 * @param offset
410 * The index of the first byte to decode
411 *
412 * @param length
413 * The number of bytes to decode
414
415 * @param charsetName
416 * The name of a supported {@linkplain java.nio.charset.Charset
417 * charset}
418 *
419 * @throws UnsupportedEncodingException
420 * If the named charset is not supported
421 *
422 * @throws IndexOutOfBoundsException
423 * If {@code offset} is negative, {@code length} is negative, or
424 * {@code offset} is greater than {@code bytes.length - length}
425 *
426 * @since 1.1
427 */
428 public String(byte bytes[], int offset, int length, String charsetName)
429 throws UnsupportedEncodingException {
430 if (charsetName == null)
431 throw new NullPointerException("charsetName");
432 checkBounds(bytes, offset, length);
433 this.value = StringCoding.decode(charsetName, bytes, offset, length);
434 }
435
436 /**
437 * Constructs a new {@code String} by decoding the specified subarray of
438 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
439 * The length of the new {@code String} is a function of the charset, and
440 * hence may not be equal to the length of the subarray.
441 *
442 * <p> This method always replaces malformed-input and unmappable-character
443 * sequences with this charset's default replacement string. The {@link
444 * java.nio.charset.CharsetDecoder} class should be used when more control
445 * over the decoding process is required.
446 *
447 * @param bytes
448 * The bytes to be decoded into characters
449 *
450 * @param offset
451 * The index of the first byte to decode
452 *
453 * @param length
454 * The number of bytes to decode
455 *
456 * @param charset
457 * The {@linkplain java.nio.charset.Charset charset} to be used to
458 * decode the {@code bytes}
459 *
460 * @throws IndexOutOfBoundsException
461 * If {@code offset} is negative, {@code length} is negative, or
462 * {@code offset} is greater than {@code bytes.length - length}
463 *
464 * @since 1.6
465 */
466 public String(byte bytes[], int offset, int length, Charset charset) {
467 if (charset == null)
468 throw new NullPointerException("charset");
469 checkBounds(bytes, offset, length);
470 this.value = StringCoding.decode(charset, bytes, offset, length);
471 }
472
473 /**
474 * Constructs a new {@code String} by decoding the specified array of bytes
475 * using the specified {@linkplain java.nio.charset.Charset charset}. The
476 * length of the new {@code String} is a function of the charset, and hence
477 * may not be equal to the length of the byte array.
478 *
479 * <p> The behavior of this constructor when the given bytes are not valid
480 * in the given charset is unspecified. The {@link
481 * java.nio.charset.CharsetDecoder} class should be used when more control
482 * over the decoding process is required.
483 *
484 * @param bytes
485 * The bytes to be decoded into characters
486 *
487 * @param charsetName
488 * The name of a supported {@linkplain java.nio.charset.Charset
489 * charset}
490 *
491 * @throws UnsupportedEncodingException
492 * If the named charset is not supported
493 *
494 * @since 1.1
495 */
496 public String(byte bytes[], String charsetName)
497 throws UnsupportedEncodingException {
498 this(bytes, 0, bytes.length, charsetName);
499 }
500
501 /**
502 * Constructs a new {@code String} by decoding the specified array of
503 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
504 * The length of the new {@code String} is a function of the charset, and
505 * hence may not be equal to the length of the byte array.
506 *
507 * <p> This method always replaces malformed-input and unmappable-character
508 * sequences with this charset's default replacement string. The {@link
509 * java.nio.charset.CharsetDecoder} class should be used when more control
510 * over the decoding process is required.
511 *
512 * @param bytes
513 * The bytes to be decoded into characters
514 *
515 * @param charset
516 * The {@linkplain java.nio.charset.Charset charset} to be used to
517 * decode the {@code bytes}
518 *
519 * @since 1.6
520 */
521 public String(byte bytes[], Charset charset) {
522 this(bytes, 0, bytes.length, charset);
523 }
524
525 /**
526 * Constructs a new {@code String} by decoding the specified subarray of
527 * bytes using the platform's default charset. The length of the new
528 * {@code String} is a function of the charset, and hence may not be equal
529 * to the length of the subarray.
530 *
531 * <p> The behavior of this constructor when the given bytes are not valid
532 * in the default charset is unspecified. The {@link
533 * java.nio.charset.CharsetDecoder} class should be used when more control
534 * over the decoding process is required.
535 *
536 * @param bytes
537 * The bytes to be decoded into characters
538 *
539 * @param offset
540 * The index of the first byte to decode
541 *
542 * @param length
543 * The number of bytes to decode
544 *
545 * @throws IndexOutOfBoundsException
546 * If {@code offset} is negative, {@code length} is negative, or
547 * {@code offset} is greater than {@code bytes.length - length}
548 *
549 * @since 1.1
550 */
551 public String(byte bytes[], int offset, int length) {
552 checkBounds(bytes, offset, length);
553 this.value = StringCoding.decode(bytes, offset, length);
554 }
555
556 /**
557 * Constructs a new {@code String} by decoding the specified array of bytes
558 * using the platform's default charset. The length of the new {@code
559 * String} is a function of the charset, and hence may not be equal to the
560 * length of the byte array.
561 *
562 * <p> The behavior of this constructor when the given bytes are not valid
563 * in the default charset is unspecified. The {@link
564 * java.nio.charset.CharsetDecoder} class should be used when more control
565 * over the decoding process is required.
566 *
567 * @param bytes
568 * The bytes to be decoded into characters
569 *
570 * @since 1.1
571 */
572 public String(byte[] bytes) {
573 this(bytes, 0, bytes.length);
574 }
575
576 /**
577 * Allocates a new string that contains the sequence of characters
578 * currently contained in the string buffer argument. The contents of the
579 * string buffer are copied; subsequent modification of the string buffer
580 * does not affect the newly created string.
581 *
582 * @param buffer
583 * A {@code StringBuffer}
584 */
585 public String(StringBuffer buffer) {
586 synchronized(buffer) {
587 this.value = Arrays.copyOf(buffer.getValue(), buffer.length());
588 }
589 }
590
591 /**
592 * Allocates a new string that contains the sequence of characters
593 * currently contained in the string builder argument. The contents of the
594 * string builder are copied; subsequent modification of the string builder
595 * does not affect the newly created string.
596 *
597 * <p> This constructor is provided to ease migration to {@code
598 * StringBuilder}. Obtaining a string from a string builder via the {@code
599 * toString} method is likely to run faster and is generally preferred.
600 *
601 * @param builder
602 * A {@code StringBuilder}
603 *
604 * @since 1.5
605 */
606 public String(StringBuilder builder) {
607 this.value = Arrays.copyOf(builder.getValue(), builder.length());
608 }
609
610 /*
611 * Package private constructor which shares value array for speed.
612 * this constructor is always expected to be called with share==true.
613 * a separate constructor is needed because we already have a public
614 * String(char[]) constructor that makes a copy of the given char[].
615 */
616 String(char[] value, boolean share) {
617 // assert share : "unshared not supported";
618 this.value = value;
619 }
620
621 /**
622 * Returns the length of this string.
623 * The length is equal to the number of <a href="Character.html#unicode">Unicode
624 * code units</a> in the string.
625 *
626 * @return the length of the sequence of characters represented by this
627 * object.
628 */
629 public int length() {
630 return value.length;
631 }
632
633 /**
634 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
635 *
636 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
637 * {@code false}
638 *
639 * @since 1.6
640 */
641 public boolean isEmpty() {
642 return value.length == 0;
643 }
644
645 /**
646 * Returns the {@code char} value at the
647 * specified index. An index ranges from {@code 0} to
648 * {@code length() - 1}. The first {@code char} value of the sequence
649 * is at index {@code 0}, the next at index {@code 1},
650 * and so on, as for array indexing.
651 *
652 * <p>If the {@code char} value specified by the index is a
653 * <a href="Character.html#unicode">surrogate</a>, the surrogate
654 * value is returned.
655 *
656 * @param index the index of the {@code char} value.
657 * @return the {@code char} value at the specified index of this string.
658 * The first {@code char} value is at index {@code 0}.
659 * @exception IndexOutOfBoundsException if the {@code index}
660 * argument is negative or not less than the length of this
661 * string.
662 */
663 public char charAt(int index) {
664 if ((index < 0) || (index >= value.length)) {
665 throw new StringIndexOutOfBoundsException(index);
666 }
667 return value[index];
668 }
669
670 /**
671 * Returns the character (Unicode code point) at the specified
672 * index. The index refers to {@code char} values
673 * (Unicode code units) and ranges from {@code 0} to
674 * {@link #length()}{@code - 1}.
675 *
676 * <p> If the {@code char} value specified at the given index
677 * is in the high-surrogate range, the following index is less
678 * than the length of this {@code String}, and the
679 * {@code char} value at the following index is in the
680 * low-surrogate range, then the supplementary code point
681 * corresponding to this surrogate pair is returned. Otherwise,
682 * the {@code char} value at the given index is returned.
683 *
684 * @param index the index to the {@code char} values
685 * @return the code point value of the character at the
686 * {@code index}
687 * @exception IndexOutOfBoundsException if the {@code index}
688 * argument is negative or not less than the length of this
689 * string.
690 * @since 1.5
691 */
692 public int codePointAt(int index) {
693 if ((index < 0) || (index >= value.length)) {
694 throw new StringIndexOutOfBoundsException(index);
695 }
696 return Character.codePointAtImpl(value, index, value.length);
697 }
698
699 /**
700 * Returns the character (Unicode code point) before the specified
701 * index. The index refers to {@code char} values
702 * (Unicode code units) and ranges from {@code 1} to {@link
703 * CharSequence#length() length}.
704 *
705 * <p> If the {@code char} value at {@code (index - 1)}
706 * is in the low-surrogate range, {@code (index - 2)} is not
707 * negative, and the {@code char} value at {@code (index -
708 * 2)} is in the high-surrogate range, then the
709 * supplementary code point value of the surrogate pair is
710 * returned. If the {@code char} value at {@code index -
711 * 1} is an unpaired low-surrogate or a high-surrogate, the
712 * surrogate value is returned.
713 *
714 * @param index the index following the code point that should be returned
715 * @return the Unicode code point value before the given index.
716 * @exception IndexOutOfBoundsException if the {@code index}
717 * argument is less than 1 or greater than the length
718 * of this string.
719 * @since 1.5
720 */
721 public int codePointBefore(int index) {
722 int i = index - 1;
723 if ((i < 0) || (i >= value.length)) {
724 throw new StringIndexOutOfBoundsException(index);
725 }
726 return Character.codePointBeforeImpl(value, index, 0);
727 }
728
729 /**
730 * Returns the number of Unicode code points in the specified text
731 * range of this {@code String}. The text range begins at the
732 * specified {@code beginIndex} and extends to the
733 * {@code char} at index {@code endIndex - 1}. Thus the
734 * length (in {@code char}s) of the text range is
735 * {@code endIndex-beginIndex}. Unpaired surrogates within
736 * the text range count as one code point each.
737 *
738 * @param beginIndex the index to the first {@code char} of
739 * the text range.
740 * @param endIndex the index after the last {@code char} of
741 * the text range.
742 * @return the number of Unicode code points in the specified text
743 * range
744 * @exception IndexOutOfBoundsException if the
745 * {@code beginIndex} is negative, or {@code endIndex}
746 * is larger than the length of this {@code String}, or
747 * {@code beginIndex} is larger than {@code endIndex}.
748 * @since 1.5
749 */
750 public int codePointCount(int beginIndex, int endIndex) {
751 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) {
752 throw new IndexOutOfBoundsException();
753 }
754 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex);
755 }
756
757 /**
758 * Returns the index within this {@code String} that is
759 * offset from the given {@code index} by
760 * {@code codePointOffset} code points. Unpaired surrogates
761 * within the text range given by {@code index} and
762 * {@code codePointOffset} count as one code point each.
763 *
764 * @param index the index to be offset
765 * @param codePointOffset the offset in code points
766 * @return the index within this {@code String}
767 * @exception IndexOutOfBoundsException if {@code index}
768 * is negative or larger then the length of this
769 * {@code String}, or if {@code codePointOffset} is positive
770 * and the substring starting with {@code index} has fewer
771 * than {@code codePointOffset} code points,
772 * or if {@code codePointOffset} is negative and the substring
773 * before {@code index} has fewer than the absolute value
774 * of {@code codePointOffset} code points.
775 * @since 1.5
776 */
777 public int offsetByCodePoints(int index, int codePointOffset) {
778 if (index < 0 || index > value.length) {
779 throw new IndexOutOfBoundsException();
780 }
781 return Character.offsetByCodePointsImpl(value, 0, value.length,
782 index, codePointOffset);
783 }
784
785 /**
786 * Copy characters from this string into dst starting at dstBegin.
787 * This method doesn't perform any range checking.
788 */
789 void getChars(char dst[], int dstBegin) {
790 System.arraycopy(value, 0, dst, dstBegin, value.length);
791 }
792
793 /**
794 * Copies characters from this string into the destination character
795 * array.
796 * <p>
797 * The first character to be copied is at index {@code srcBegin};
798 * the last character to be copied is at index {@code srcEnd-1}
799 * (thus the total number of characters to be copied is
800 * {@code srcEnd-srcBegin}). The characters are copied into the
801 * subarray of {@code dst} starting at index {@code dstBegin}
802 * and ending at index:
803 * <blockquote><pre>
804 * dstBegin + (srcEnd-srcBegin) - 1
805 * </pre></blockquote>
806 *
807 * @param srcBegin index of the first character in the string
808 * to copy.
809 * @param srcEnd index after the last character in the string
810 * to copy.
811 * @param dst the destination array.
812 * @param dstBegin the start offset in the destination array.
813 * @exception IndexOutOfBoundsException If any of the following
814 * is true:
815 * <ul><li>{@code srcBegin} is negative.
816 * <li>{@code srcBegin} is greater than {@code srcEnd}
817 * <li>{@code srcEnd} is greater than the length of this
818 * string
819 * <li>{@code dstBegin} is negative
820 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
821 * {@code dst.length}</ul>
822 */
823 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
824 if (srcBegin < 0) {
825 throw new StringIndexOutOfBoundsException(srcBegin);
826 }
827 if (srcEnd > value.length) {
828 throw new StringIndexOutOfBoundsException(srcEnd);
829 }
830 if (srcBegin > srcEnd) {
831 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
832 }
833 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin);
834 }
835
836 /**
837 * Copies characters from this string into the destination byte array. Each
838 * byte receives the 8 low-order bits of the corresponding character. The
839 * eight high-order bits of each character are not copied and do not
840 * participate in the transfer in any way.
841 *
842 * <p> The first character to be copied is at index {@code srcBegin}; the
843 * last character to be copied is at index {@code srcEnd-1}. The total
844 * number of characters to be copied is {@code srcEnd-srcBegin}. The
845 * characters, converted to bytes, are copied into the subarray of {@code
846 * dst} starting at index {@code dstBegin} and ending at index:
847 *
848 * <blockquote><pre>
849 * dstBegin + (srcEnd-srcBegin) - 1
850 * </pre></blockquote>
851 *
852 * @deprecated This method does not properly convert characters into
853 * bytes. As of JDK 1.1, the preferred way to do this is via the
854 * {@link #getBytes()} method, which uses the platform's default charset.
855 *
856 * @param srcBegin
857 * Index of the first character in the string to copy
858 *
859 * @param srcEnd
860 * Index after the last character in the string to copy
861 *
862 * @param dst
863 * The destination array
864 *
865 * @param dstBegin
866 * The start offset in the destination array
867 *
868 * @throws IndexOutOfBoundsException
869 * If any of the following is true:
870 * <ul>
871 * <li> {@code srcBegin} is negative
872 * <li> {@code srcBegin} is greater than {@code srcEnd}
873 * <li> {@code srcEnd} is greater than the length of this String
874 * <li> {@code dstBegin} is negative
875 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
876 * dst.length}
877 * </ul>
878 */
879 @Deprecated
880 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
881 if (srcBegin < 0) {
882 throw new StringIndexOutOfBoundsException(srcBegin);
883 }
884 if (srcEnd > value.length) {
885 throw new StringIndexOutOfBoundsException(srcEnd);
886 }
887 if (srcBegin > srcEnd) {
888 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
889 }
890 Objects.requireNonNull(dst);
891
892 int j = dstBegin;
893 int n = srcEnd;
894 int i = srcBegin;
895 char[] val = value; /* avoid getfield opcode */
896
897 while (i < n) {
898 dst[j++] = (byte)val[i++];
899 }
900 }
901
902 /**
903 * Encodes this {@code String} into a sequence of bytes using the named
904 * charset, storing the result into a new byte array.
905 *
906 * <p> The behavior of this method when this string cannot be encoded in
907 * the given charset is unspecified. The {@link
908 * java.nio.charset.CharsetEncoder} class should be used when more control
909 * over the encoding process is required.
910 *
911 * @param charsetName
912 * The name of a supported {@linkplain java.nio.charset.Charset
913 * charset}
914 *
915 * @return The resultant byte array
916 *
917 * @throws UnsupportedEncodingException
918 * If the named charset is not supported
919 *
920 * @since 1.1
921 */
922 public byte[] getBytes(String charsetName)
923 throws UnsupportedEncodingException {
924 if (charsetName == null) throw new NullPointerException();
925 return StringCoding.encode(charsetName, value, 0, value.length);
926 }
927
928 /**
929 * Encodes this {@code String} into a sequence of bytes using the given
930 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
931 * new byte array.
932 *
933 * <p> This method always replaces malformed-input and unmappable-character
934 * sequences with this charset's default replacement byte array. The
935 * {@link java.nio.charset.CharsetEncoder} class should be used when more
936 * control over the encoding process is required.
937 *
938 * @param charset
939 * The {@linkplain java.nio.charset.Charset} to be used to encode
940 * the {@code String}
941 *
942 * @return The resultant byte array
943 *
944 * @since 1.6
945 */
946 public byte[] getBytes(Charset charset) {
947 if (charset == null) throw new NullPointerException();
948 return StringCoding.encode(charset, value, 0, value.length);
949 }
950
951 /**
952 * Encodes this {@code String} into a sequence of bytes using the
953 * platform's default charset, storing the result into a new byte array.
954 *
955 * <p> The behavior of this method when this string cannot be encoded in
956 * the default charset is unspecified. The {@link
957 * java.nio.charset.CharsetEncoder} class should be used when more control
958 * over the encoding process is required.
959 *
960 * @return The resultant byte array
961 *
962 * @since 1.1
963 */
964 public byte[] getBytes() {
965 return StringCoding.encode(value, 0, value.length);
966 }
967
968 /**
969 * Compares this string to the specified object. The result is {@code
970 * true} if and only if the argument is not {@code null} and is a {@code
971 * String} object that represents the same sequence of characters as this
972 * object.
973 *
974 * @param anObject
975 * The object to compare this {@code String} against
976 *
977 * @return {@code true} if the given object represents a {@code String}
978 * equivalent to this string, {@code false} otherwise
979 *
980 * @see #compareTo(String)
981 * @see #equalsIgnoreCase(String)
982 */
983 @HotSpotIntrinsicCandidate
984 public boolean equals(Object anObject) {
985 if (this == anObject) {
986 return true;
987 }
988 if (anObject instanceof String) {
989 char[] v1 = value;
990 char[] v2 = ((String)anObject).value;
991 int n = v1.length;
992 if (n == v2.length) {
993 int i = 0;
994 while (n-- != 0) {
995 if (v1[i] != v2[i])
996 return false;
997 i++;
998 }
999 return true;
1000 }
1001 }
1002 return false;
1003 }
1004
1005 /**
1006 * Compares this string to the specified {@code StringBuffer}. The result
1007 * is {@code true} if and only if this {@code String} represents the same
1008 * sequence of characters as the specified {@code StringBuffer}. This method
1009 * synchronizes on the {@code StringBuffer}.
1010 *
1011 * @param sb
1012 * The {@code StringBuffer} to compare this {@code String} against
1013 *
1014 * @return {@code true} if this {@code String} represents the same
1015 * sequence of characters as the specified {@code StringBuffer},
1016 * {@code false} otherwise
1017 *
1018 * @since 1.4
1019 */
1020 public boolean contentEquals(StringBuffer sb) {
1021 return contentEquals((CharSequence)sb);
1022 }
1023
1024 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1025 char[] v1 = value;
1026 char[] v2 = sb.getValue();
1027 int n = v1.length;
1028 if (n != sb.length()) {
1029 return false;
1030 }
1031 for (int i = 0; i < n; i++) {
1032 if (v1[i] != v2[i]) {
1033 return false;
1034 }
1035 }
1036 return true;
1037 }
1038
1039 /**
1040 * Compares this string to the specified {@code CharSequence}. The
1041 * result is {@code true} if and only if this {@code String} represents the
1042 * same sequence of char values as the specified sequence. Note that if the
1043 * {@code CharSequence} is a {@code StringBuffer} then the method
1044 * synchronizes on it.
1045 *
1046 * @param cs
1047 * The sequence to compare this {@code String} against
1048 *
1049 * @return {@code true} if this {@code String} represents the same
1050 * sequence of char values as the specified sequence, {@code
1051 * false} otherwise
1052 *
1053 * @since 1.5
1054 */
1055 public boolean contentEquals(CharSequence cs) {
1056 // Argument is a StringBuffer, StringBuilder
1057 if (cs instanceof AbstractStringBuilder) {
1058 if (cs instanceof StringBuffer) {
1059 synchronized(cs) {
1060 return nonSyncContentEquals((AbstractStringBuilder)cs);
1061 }
1062 } else {
1063 return nonSyncContentEquals((AbstractStringBuilder)cs);
1064 }
1065 }
1066 // Argument is a String
1067 if (cs instanceof String) {
1068 return equals(cs);
1069 }
1070 // Argument is a generic CharSequence
1071 char[] v1 = value;
1072 int n = v1.length;
1073 if (n != cs.length()) {
1074 return false;
1075 }
1076 for (int i = 0; i < n; i++) {
1077 if (v1[i] != cs.charAt(i)) {
1078 return false;
1079 }
1080 }
1081 return true;
1082 }
1083
1084 /**
1085 * Compares this {@code String} to another {@code String}, ignoring case
1086 * considerations. Two strings are considered equal ignoring case if they
1087 * are of the same length and corresponding characters in the two strings
1088 * are equal ignoring case.
1089 *
1090 * <p> Two characters {@code c1} and {@code c2} are considered the same
1091 * ignoring case if at least one of the following is true:
1092 * <ul>
1093 * <li> The two characters are the same (as compared by the
1094 * {@code ==} operator)
1095 * <li> Applying the method {@link
1096 * java.lang.Character#toUpperCase(char)} to each character
1097 * produces the same result
1098 * <li> Applying the method {@link
1099 * java.lang.Character#toLowerCase(char)} to each character
1100 * produces the same result
1101 * </ul>
1102 *
1103 * @param anotherString
1104 * The {@code String} to compare this {@code String} against
1105 *
1106 * @return {@code true} if the argument is not {@code null} and it
1107 * represents an equivalent {@code String} ignoring case; {@code
1108 * false} otherwise
1109 *
1110 * @see #equals(Object)
1111 */
1112 public boolean equalsIgnoreCase(String anotherString) {
1113 return (this == anotherString) ? true
1114 : (anotherString != null)
1115 && (anotherString.value.length == value.length)
1116 && regionMatches(true, 0, anotherString, 0, value.length);
1117 }
1118
1119 /**
1120 * Compares two strings lexicographically.
1121 * The comparison is based on the Unicode value of each character in
1122 * the strings. The character sequence represented by this
1123 * {@code String} object is compared lexicographically to the
1124 * character sequence represented by the argument string. The result is
1125 * a negative integer if this {@code String} object
1126 * lexicographically precedes the argument string. The result is a
1127 * positive integer if this {@code String} object lexicographically
1128 * follows the argument string. The result is zero if the strings
1129 * are equal; {@code compareTo} returns {@code 0} exactly when
1130 * the {@link #equals(Object)} method would return {@code true}.
1131 * <p>
1132 * This is the definition of lexicographic ordering. If two strings are
1133 * different, then either they have different characters at some index
1134 * that is a valid index for both strings, or their lengths are different,
1135 * or both. If they have different characters at one or more index
1136 * positions, let <i>k</i> be the smallest such index; then the string
1137 * whose character at position <i>k</i> has the smaller value, as
1138 * determined by using the {@code <} operator, lexicographically precedes the
1139 * other string. In this case, {@code compareTo} returns the
1140 * difference of the two character values at position {@code k} in
1141 * the two string -- that is, the value:
1142 * <blockquote><pre>
1143 * this.charAt(k)-anotherString.charAt(k)
1144 * </pre></blockquote>
1145 * If there is no index position at which they differ, then the shorter
1146 * string lexicographically precedes the longer string. In this case,
1147 * {@code compareTo} returns the difference of the lengths of the
1148 * strings -- that is, the value:
1149 * <blockquote><pre>
1150 * this.length()-anotherString.length()
1151 * </pre></blockquote>
1152 *
1153 * @param anotherString the {@code String} to be compared.
1154 * @return the value {@code 0} if the argument string is equal to
1155 * this string; a value less than {@code 0} if this string
1156 * is lexicographically less than the string argument; and a
1157 * value greater than {@code 0} if this string is
1158 * lexicographically greater than the string argument.
1159 */
1160 @HotSpotIntrinsicCandidate
1161 public int compareTo(String anotherString) {
1162 char[] v1 = value;
1163 char[] v2 = anotherString.value;
1164 int len1 = v1.length;
1165 int len2 = v2.length;
1166 int lim = Math.min(len1, len2);
1167
1168 for (int k = 0; k < lim; k++) {
1169 char c1 = v1[k];
1170 char c2 = v2[k];
1171 if (c1 != c2) {
1172 return c1 - c2;
1173 }
1174 }
1175 return len1 - len2;
1176 }
1177
1178 /**
1179 * A Comparator that orders {@code String} objects as by
1180 * {@code compareToIgnoreCase}. This comparator is serializable.
1181 * <p>
1182 * Note that this Comparator does <em>not</em> take locale into account,
1183 * and will result in an unsatisfactory ordering for certain locales.
1184 * The java.text package provides <em>Collators</em> to allow
1185 * locale-sensitive ordering.
1186 *
1187 * @see java.text.Collator#compare(String, String)
1188 * @since 1.2
1189 */
1190 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1191 = new CaseInsensitiveComparator();
1192 private static class CaseInsensitiveComparator
1193 implements Comparator<String>, java.io.Serializable {
1194 // use serialVersionUID from JDK 1.2.2 for interoperability
1195 private static final long serialVersionUID = 8575799808933029326L;
1196
1197 public int compare(String s1, String s2) {
1198 int n1 = s1.length();
1199 int n2 = s2.length();
1200 int min = Math.min(n1, n2);
1201 for (int i = 0; i < min; i++) {
1202 char c1 = s1.charAt(i);
1203 char c2 = s2.charAt(i);
1204 if (c1 != c2) {
1205 c1 = Character.toUpperCase(c1);
1206 c2 = Character.toUpperCase(c2);
1207 if (c1 != c2) {
1208 c1 = Character.toLowerCase(c1);
1209 c2 = Character.toLowerCase(c2);
1210 if (c1 != c2) {
1211 // No overflow because of numeric promotion
1212 return c1 - c2;
1213 }
1214 }
1215 }
1216 }
1217 return n1 - n2;
1218 }
1219
1220 /** Replaces the de-serialized object. */
1221 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1222 }
1223
1224 /**
1225 * Compares two strings lexicographically, ignoring case
1226 * differences. This method returns an integer whose sign is that of
1227 * calling {@code compareTo} with normalized versions of the strings
1228 * where case differences have been eliminated by calling
1229 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1230 * each character.
1231 * <p>
1232 * Note that this method does <em>not</em> take locale into account,
1233 * and will result in an unsatisfactory ordering for certain locales.
1234 * The java.text package provides <em>collators</em> to allow
1235 * locale-sensitive ordering.
1236 *
1237 * @param str the {@code String} to be compared.
1238 * @return a negative integer, zero, or a positive integer as the
1239 * specified String is greater than, equal to, or less
1240 * than this String, ignoring case considerations.
1241 * @see java.text.Collator#compare(String, String)
1242 * @since 1.2
1243 */
1244 public int compareToIgnoreCase(String str) {
1245 return CASE_INSENSITIVE_ORDER.compare(this, str);
1246 }
1247
1248 /**
1249 * Tests if two string regions are equal.
1250 * <p>
1251 * A substring of this {@code String} object is compared to a substring
1252 * of the argument other. The result is true if these substrings
1253 * represent identical character sequences. The substring of this
1254 * {@code String} object to be compared begins at index {@code toffset}
1255 * and has length {@code len}. The substring of other to be compared
1256 * begins at index {@code ooffset} and has length {@code len}. The
1257 * result is {@code false} if and only if at least one of the following
1258 * is true:
1259 * <ul><li>{@code toffset} is negative.
1260 * <li>{@code ooffset} is negative.
1261 * <li>{@code toffset+len} is greater than the length of this
1262 * {@code String} object.
1263 * <li>{@code ooffset+len} is greater than the length of the other
1264 * argument.
1265 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1266 * such that:
1267 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1268 * <i>k</i>{@code )}
1269 * </ul>
1270 *
1271 * @param toffset the starting offset of the subregion in this string.
1272 * @param other the string argument.
1273 * @param ooffset the starting offset of the subregion in the string
1274 * argument.
1275 * @param len the number of characters to compare.
1276 * @return {@code true} if the specified subregion of this string
1277 * exactly matches the specified subregion of the string argument;
1278 * {@code false} otherwise.
1279 */
1280 public boolean regionMatches(int toffset, String other, int ooffset,
1281 int len) {
1282 char[] ta = value;
1283 int to = toffset;
1284 char[] pa = other.value;
1285 int po = ooffset;
1286 // Note: toffset, ooffset, or len might be near -1>>>1.
1287 if ((ooffset < 0) || (toffset < 0)
1288 || (toffset > (long)ta.length - len)
1289 || (ooffset > (long)pa.length - len)) {
1290 return false;
1291 }
1292 while (len-- > 0) {
1293 if (ta[to++] != pa[po++]) {
1294 return false;
1295 }
1296 }
1297 return true;
1298 }
1299
1300 /**
1301 * Tests if two string regions are equal.
1302 * <p>
1303 * A substring of this {@code String} object is compared to a substring
1304 * of the argument {@code other}. The result is {@code true} if these
1305 * substrings represent character sequences that are the same, ignoring
1306 * case if and only if {@code ignoreCase} is true. The substring of
1307 * this {@code String} object to be compared begins at index
1308 * {@code toffset} and has length {@code len}. The substring of
1309 * {@code other} to be compared begins at index {@code ooffset} and
1310 * has length {@code len}. The result is {@code false} if and only if
1311 * at least one of the following is true:
1312 * <ul><li>{@code toffset} is negative.
1313 * <li>{@code ooffset} is negative.
1314 * <li>{@code toffset+len} is greater than the length of this
1315 * {@code String} object.
1316 * <li>{@code ooffset+len} is greater than the length of the other
1317 * argument.
1318 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1319 * integer <i>k</i> less than {@code len} such that:
1320 * <blockquote><pre>
1321 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1322 * </pre></blockquote>
1323 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1324 * integer <i>k</i> less than {@code len} such that:
1325 * <blockquote><pre>
1326 * Character.toLowerCase(this.charAt(toffset+k)) !=
1327 Character.toLowerCase(other.charAt(ooffset+k))
1328 * </pre></blockquote>
1329 * and:
1330 * <blockquote><pre>
1331 * Character.toUpperCase(this.charAt(toffset+k)) !=
1332 * Character.toUpperCase(other.charAt(ooffset+k))
1333 * </pre></blockquote>
1334 * </ul>
1335 *
1336 * @param ignoreCase if {@code true}, ignore case when comparing
1337 * characters.
1338 * @param toffset the starting offset of the subregion in this
1339 * string.
1340 * @param other the string argument.
1341 * @param ooffset the starting offset of the subregion in the string
1342 * argument.
1343 * @param len the number of characters to compare.
1344 * @return {@code true} if the specified subregion of this string
1345 * matches the specified subregion of the string argument;
1346 * {@code false} otherwise. Whether the matching is exact
1347 * or case insensitive depends on the {@code ignoreCase}
1348 * argument.
1349 */
1350 public boolean regionMatches(boolean ignoreCase, int toffset,
1351 String other, int ooffset, int len) {
1352 char[] ta = value;
1353 int to = toffset;
1354 char[] pa = other.value;
1355 int po = ooffset;
1356 // Note: toffset, ooffset, or len might be near -1>>>1.
1357 if ((ooffset < 0) || (toffset < 0)
1358 || (toffset > (long)ta.length - len)
1359 || (ooffset > (long)pa.length - len)) {
1360 return false;
1361 }
1362 while (len-- > 0) {
1363 char c1 = ta[to++];
1364 char c2 = pa[po++];
1365 if (c1 == c2) {
1366 continue;
1367 }
1368 if (ignoreCase) {
1369 // If characters don't match but case may be ignored,
1370 // try converting both characters to uppercase.
1371 // If the results match, then the comparison scan should
1372 // continue.
1373 char u1 = Character.toUpperCase(c1);
1374 char u2 = Character.toUpperCase(c2);
1375 if (u1 == u2) {
1376 continue;
1377 }
1378 // Unfortunately, conversion to uppercase does not work properly
1379 // for the Georgian alphabet, which has strange rules about case
1380 // conversion. So we need to make one last check before
1381 // exiting.
1382 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1383 continue;
1384 }
1385 }
1386 return false;
1387 }
1388 return true;
1389 }
1390
1391 /**
1392 * Tests if the substring of this string beginning at the
1393 * specified index starts with the specified prefix.
1394 *
1395 * @param prefix the prefix.
1396 * @param toffset where to begin looking in this string.
1397 * @return {@code true} if the character sequence represented by the
1398 * argument is a prefix of the substring of this object starting
1399 * at index {@code toffset}; {@code false} otherwise.
1400 * The result is {@code false} if {@code toffset} is
1401 * negative or greater than the length of this
1402 * {@code String} object; otherwise the result is the same
1403 * as the result of the expression
1404 * <pre>
1405 * this.substring(toffset).startsWith(prefix)
1406 * </pre>
1407 */
1408 public boolean startsWith(String prefix, int toffset) {
1409 char[] ta = value;
1410 int to = toffset;
1411 char[] pa = prefix.value;
1412 int po = 0;
1413 int pc = pa.length;
1414 // Note: toffset might be near -1>>>1.
1415 if ((toffset < 0) || (toffset > ta.length - pc)) {
1416 return false;
1417 }
1418 while (--pc >= 0) {
1419 if (ta[to++] != pa[po++]) {
1420 return false;
1421 }
1422 }
1423 return true;
1424 }
1425
1426 /**
1427 * Tests if this string starts with the specified prefix.
1428 *
1429 * @param prefix the prefix.
1430 * @return {@code true} if the character sequence represented by the
1431 * argument is a prefix of the character sequence represented by
1432 * this string; {@code false} otherwise.
1433 * Note also that {@code true} will be returned if the
1434 * argument is an empty string or is equal to this
1435 * {@code String} object as determined by the
1436 * {@link #equals(Object)} method.
1437 * @since 1.0
1438 */
1439 public boolean startsWith(String prefix) {
1440 return startsWith(prefix, 0);
1441 }
1442
1443 /**
1444 * Tests if this string ends with the specified suffix.
1445 *
1446 * @param suffix the suffix.
1447 * @return {@code true} if the character sequence represented by the
1448 * argument is a suffix of the character sequence represented by
1449 * this object; {@code false} otherwise. Note that the
1450 * result will be {@code true} if the argument is the
1451 * empty string or is equal to this {@code String} object
1452 * as determined by the {@link #equals(Object)} method.
1453 */
1454 public boolean endsWith(String suffix) {
1455 return startsWith(suffix, value.length - suffix.value.length);
1456 }
1457
1458 /**
1459 * Returns a hash code for this string. The hash code for a
1460 * {@code String} object is computed as
1461 * <blockquote><pre>
1462 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1463 * </pre></blockquote>
1464 * using {@code int} arithmetic, where {@code s[i]} is the
1465 * <i>i</i>th character of the string, {@code n} is the length of
1466 * the string, and {@code ^} indicates exponentiation.
1467 * (The hash value of the empty string is zero.)
1468 *
1469 * @return a hash code value for this object.
1470 */
1471 public int hashCode() {
1472 int h = hash;
1473 if (h == 0) {
1474 for (char v : value) {
1475 h = 31 * h + v;
1476 }
1477 if (h != 0) {
1478 hash = h;
1479 }
1480 }
1481 return h;
1482 }
1483
1484 /**
1485 * Returns the index within this string of the first occurrence of
1486 * the specified character. If a character with value
1487 * {@code ch} occurs in the character sequence represented by
1488 * this {@code String} object, then the index (in Unicode
1489 * code units) of the first such occurrence is returned. For
1490 * values of {@code ch} in the range from 0 to 0xFFFF
1491 * (inclusive), this is the smallest value <i>k</i> such that:
1492 * <blockquote><pre>
1493 * this.charAt(<i>k</i>) == ch
1494 * </pre></blockquote>
1495 * is true. For other values of {@code ch}, it is the
1496 * smallest value <i>k</i> such that:
1497 * <blockquote><pre>
1498 * this.codePointAt(<i>k</i>) == ch
1499 * </pre></blockquote>
1500 * is true. In either case, if no such character occurs in this
1501 * string, then {@code -1} is returned.
1502 *
1503 * @param ch a character (Unicode code point).
1504 * @return the index of the first occurrence of the character in the
1505 * character sequence represented by this object, or
1506 * {@code -1} if the character does not occur.
1507 */
1508 public int indexOf(int ch) {
1509 return indexOf(ch, 0);
1510 }
1511
1512 /**
1513 * Returns the index within this string of the first occurrence of the
1514 * specified character, starting the search at the specified index.
1515 * <p>
1516 * If a character with value {@code ch} occurs in the
1517 * character sequence represented by this {@code String}
1518 * object at an index no smaller than {@code fromIndex}, then
1519 * the index of the first such occurrence is returned. For values
1520 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1521 * this is the smallest value <i>k</i> such that:
1522 * <blockquote><pre>
1523 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1524 * </pre></blockquote>
1525 * is true. For other values of {@code ch}, it is the
1526 * smallest value <i>k</i> such that:
1527 * <blockquote><pre>
1528 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1529 * </pre></blockquote>
1530 * is true. In either case, if no such character occurs in this
1531 * string at or after position {@code fromIndex}, then
1532 * {@code -1} is returned.
1533 *
1534 * <p>
1535 * There is no restriction on the value of {@code fromIndex}. If it
1536 * is negative, it has the same effect as if it were zero: this entire
1537 * string may be searched. If it is greater than the length of this
1538 * string, it has the same effect as if it were equal to the length of
1539 * this string: {@code -1} is returned.
1540 *
1541 * <p>All indices are specified in {@code char} values
1542 * (Unicode code units).
1543 *
1544 * @param ch a character (Unicode code point).
1545 * @param fromIndex the index to start the search from.
1546 * @return the index of the first occurrence of the character in the
1547 * character sequence represented by this object that is greater
1548 * than or equal to {@code fromIndex}, or {@code -1}
1549 * if the character does not occur.
1550 */
1551 public int indexOf(int ch, int fromIndex) {
1552 final int max = value.length;
1553 if (fromIndex < 0) {
1554 fromIndex = 0;
1555 } else if (fromIndex >= max) {
1556 // Note: fromIndex might be near -1>>>1.
1557 return -1;
1558 }
1559
1560 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1561 // handle most cases here (ch is a BMP code point or a
1562 // negative value (invalid code point))
1563 final char[] value = this.value;
1564 for (int i = fromIndex; i < max; i++) {
1565 if (value[i] == ch) {
1566 return i;
1567 }
1568 }
1569 return -1;
1570 } else {
1571 return indexOfSupplementary(ch, fromIndex);
1572 }
1573 }
1574
1575 /**
1576 * Handles (rare) calls of indexOf with a supplementary character.
1577 */
1578 private int indexOfSupplementary(int ch, int fromIndex) {
1579 if (Character.isValidCodePoint(ch)) {
1580 final char[] value = this.value;
1581 final char hi = Character.highSurrogate(ch);
1582 final char lo = Character.lowSurrogate(ch);
1583 final int max = value.length - 1;
1584 for (int i = fromIndex; i < max; i++) {
1585 if (value[i] == hi && value[i + 1] == lo) {
1586 return i;
1587 }
1588 }
1589 }
1590 return -1;
1591 }
1592
1593 /**
1594 * Returns the index within this string of the last occurrence of
1595 * the specified character. For values of {@code ch} in the
1596 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1597 * units) returned is the largest value <i>k</i> such that:
1598 * <blockquote><pre>
1599 * this.charAt(<i>k</i>) == ch
1600 * </pre></blockquote>
1601 * is true. For other values of {@code ch}, it is the
1602 * largest value <i>k</i> such that:
1603 * <blockquote><pre>
1604 * this.codePointAt(<i>k</i>) == ch
1605 * </pre></blockquote>
1606 * is true. In either case, if no such character occurs in this
1607 * string, then {@code -1} is returned. The
1608 * {@code String} is searched backwards starting at the last
1609 * character.
1610 *
1611 * @param ch a character (Unicode code point).
1612 * @return the index of the last occurrence of the character in the
1613 * character sequence represented by this object, or
1614 * {@code -1} if the character does not occur.
1615 */
1616 public int lastIndexOf(int ch) {
1617 return lastIndexOf(ch, value.length - 1);
1618 }
1619
1620 /**
1621 * Returns the index within this string of the last occurrence of
1622 * the specified character, searching backward starting at the
1623 * specified index. For values of {@code ch} in the range
1624 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1625 * value <i>k</i> such that:
1626 * <blockquote><pre>
1627 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1628 * </pre></blockquote>
1629 * is true. For other values of {@code ch}, it is the
1630 * largest value <i>k</i> such that:
1631 * <blockquote><pre>
1632 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1633 * </pre></blockquote>
1634 * is true. In either case, if no such character occurs in this
1635 * string at or before position {@code fromIndex}, then
1636 * {@code -1} is returned.
1637 *
1638 * <p>All indices are specified in {@code char} values
1639 * (Unicode code units).
1640 *
1641 * @param ch a character (Unicode code point).
1642 * @param fromIndex the index to start the search from. There is no
1643 * restriction on the value of {@code fromIndex}. If it is
1644 * greater than or equal to the length of this string, it has
1645 * the same effect as if it were equal to one less than the
1646 * length of this string: this entire string may be searched.
1647 * If it is negative, it has the same effect as if it were -1:
1648 * -1 is returned.
1649 * @return the index of the last occurrence of the character in the
1650 * character sequence represented by this object that is less
1651 * than or equal to {@code fromIndex}, or {@code -1}
1652 * if the character does not occur before that point.
1653 */
1654 public int lastIndexOf(int ch, int fromIndex) {
1655 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1656 // handle most cases here (ch is a BMP code point or a
1657 // negative value (invalid code point))
1658 final char[] value = this.value;
1659 int i = Math.min(fromIndex, value.length - 1);
1660 for (; i >= 0; i--) {
1661 if (value[i] == ch) {
1662 return i;
1663 }
1664 }
1665 return -1;
1666 } else {
1667 return lastIndexOfSupplementary(ch, fromIndex);
1668 }
1669 }
1670
1671 /**
1672 * Handles (rare) calls of lastIndexOf with a supplementary character.
1673 */
1674 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1675 if (Character.isValidCodePoint(ch)) {
1676 final char[] value = this.value;
1677 char hi = Character.highSurrogate(ch);
1678 char lo = Character.lowSurrogate(ch);
1679 int i = Math.min(fromIndex, value.length - 2);
1680 for (; i >= 0; i--) {
1681 if (value[i] == hi && value[i + 1] == lo) {
1682 return i;
1683 }
1684 }
1685 }
1686 return -1;
1687 }
1688
1689 /**
1690 * Returns the index within this string of the first occurrence of the
1691 * specified substring.
1692 *
1693 * <p>The returned index is the smallest value {@code k} for which:
1694 * <pre>{@code
1695 * this.startsWith(str, k)
1696 * }</pre>
1697 * If no such value of {@code k} exists, then {@code -1} is returned.
1698 *
1699 * @param str the substring to search for.
1700 * @return the index of the first occurrence of the specified substring,
1701 * or {@code -1} if there is no such occurrence.
1702 */
1703 @HotSpotIntrinsicCandidate
1704 public int indexOf(String str) {
1705 return indexOf(str, 0);
1706 }
1707
1708 /**
1709 * Returns the index within this string of the first occurrence of the
1710 * specified substring, starting at the specified index.
1711 *
1712 * <p>The returned index is the smallest value {@code k} for which:
1713 * <pre>{@code
1714 * k >= Math.min(fromIndex, this.length()) &&
1715 * this.startsWith(str, k)
1716 * }</pre>
1717 * If no such value of {@code k} exists, then {@code -1} is returned.
1718 *
1719 * @param str the substring to search for.
1720 * @param fromIndex the index from which to start the search.
1721 * @return the index of the first occurrence of the specified substring,
1722 * starting at the specified index,
1723 * or {@code -1} if there is no such occurrence.
1724 */
1725 public int indexOf(String str, int fromIndex) {
1726 return indexOf(value, 0, value.length,
1727 str.value, 0, str.value.length, fromIndex);
1728 }
1729
1730 /**
1731 * Code shared by String and AbstractStringBuilder to do searches. The
1732 * source is the character array being searched, and the target
1733 * is the string being searched for.
1734 *
1735 * @param source the characters being searched.
1736 * @param sourceOffset offset of the source string.
1737 * @param sourceCount count of the source string.
1738 * @param target the characters being searched for.
1739 * @param fromIndex the index to begin searching from.
1740 */
1741 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1742 String target, int fromIndex) {
1743 return indexOf(source, sourceOffset, sourceCount,
1744 target.value, 0, target.value.length,
1745 fromIndex);
1746 }
1747
1748 /**
1749 * Code shared by String and StringBuffer to do searches. The
1750 * source is the character array being searched, and the target
1751 * is the string being searched for.
1752 *
1753 * @param source the characters being searched.
1754 * @param sourceOffset offset of the source string.
1755 * @param sourceCount count of the source string.
1756 * @param target the characters being searched for.
1757 * @param targetOffset offset of the target string.
1758 * @param targetCount count of the target string.
1759 * @param fromIndex the index to begin searching from.
1760 */
1761 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1762 char[] target, int targetOffset, int targetCount,
1763 int fromIndex) {
1764 if (fromIndex >= sourceCount) {
1765 return (targetCount == 0 ? sourceCount : -1);
1766 }
1767 if (fromIndex < 0) {
1768 fromIndex = 0;
1769 }
1770 if (targetCount == 0) {
1771 return fromIndex;
1772 }
1773
1774 char first = target[targetOffset];
1775 int max = sourceOffset + (sourceCount - targetCount);
1776
1777 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1778 /* Look for first character. */
1779 if (source[i] != first) {
1780 while (++i <= max && source[i] != first);
1781 }
1782
1783 /* Found first character, now look at the rest of v2 */
1784 if (i <= max) {
1785 int j = i + 1;
1786 int end = j + targetCount - 1;
1787 for (int k = targetOffset + 1; j < end && source[j]
1788 == target[k]; j++, k++);
1789
1790 if (j == end) {
1791 /* Found whole string. */
1792 return i - sourceOffset;
1793 }
1794 }
1795 }
1796 return -1;
1797 }
1798
1799 /**
1800 * Returns the index within this string of the last occurrence of the
1801 * specified substring. The last occurrence of the empty string ""
1802 * is considered to occur at the index value {@code this.length()}.
1803 *
1804 * <p>The returned index is the largest value {@code k} for which:
1805 * <pre>{@code
1806 * this.startsWith(str, k)
1807 * }</pre>
1808 * If no such value of {@code k} exists, then {@code -1} is returned.
1809 *
1810 * @param str the substring to search for.
1811 * @return the index of the last occurrence of the specified substring,
1812 * or {@code -1} if there is no such occurrence.
1813 */
1814 public int lastIndexOf(String str) {
1815 return lastIndexOf(str, value.length);
1816 }
1817
1818 /**
1819 * Returns the index within this string of the last occurrence of the
1820 * specified substring, searching backward starting at the specified index.
1821 *
1822 * <p>The returned index is the largest value {@code k} for which:
1823 * <pre>{@code
1824 * k <= Math.min(fromIndex, this.length()) &&
1825 * this.startsWith(str, k)
1826 * }</pre>
1827 * If no such value of {@code k} exists, then {@code -1} is returned.
1828 *
1829 * @param str the substring to search for.
1830 * @param fromIndex the index to start the search from.
1831 * @return the index of the last occurrence of the specified substring,
1832 * searching backward from the specified index,
1833 * or {@code -1} if there is no such occurrence.
1834 */
1835 public int lastIndexOf(String str, int fromIndex) {
1836 return lastIndexOf(value, 0, value.length,
1837 str.value, 0, str.value.length, fromIndex);
1838 }
1839
1840 /**
1841 * Code shared by String and AbstractStringBuilder to do searches. The
1842 * source is the character array being searched, and the target
1843 * is the string being searched for.
1844 *
1845 * @param source the characters being searched.
1846 * @param sourceOffset offset of the source string.
1847 * @param sourceCount count of the source string.
1848 * @param target the characters being searched for.
1849 * @param fromIndex the index to begin searching from.
1850 */
1851 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1852 String target, int fromIndex) {
1853 return lastIndexOf(source, sourceOffset, sourceCount,
1854 target.value, 0, target.value.length,
1855 fromIndex);
1856 }
1857
1858 /**
1859 * Code shared by String and StringBuffer to do searches. The
1860 * source is the character array being searched, and the target
1861 * is the string being searched for.
1862 *
1863 * @param source the characters being searched.
1864 * @param sourceOffset offset of the source string.
1865 * @param sourceCount count of the source string.
1866 * @param target the characters being searched for.
1867 * @param targetOffset offset of the target string.
1868 * @param targetCount count of the target string.
1869 * @param fromIndex the index to begin searching from.
1870 */
1871 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1872 char[] target, int targetOffset, int targetCount,
1873 int fromIndex) {
1874 /*
1875 * Check arguments; return immediately where possible. For
1876 * consistency, don't check for null str.
1877 */
1878 int rightIndex = sourceCount - targetCount;
1879 if (fromIndex < 0) {
1880 return -1;
1881 }
1882 if (fromIndex > rightIndex) {
1883 fromIndex = rightIndex;
1884 }
1885 /* Empty string always matches. */
1886 if (targetCount == 0) {
1887 return fromIndex;
1888 }
1889
1890 int strLastIndex = targetOffset + targetCount - 1;
1891 char strLastChar = target[strLastIndex];
1892 int min = sourceOffset + targetCount - 1;
1893 int i = min + fromIndex;
1894
1895 startSearchForLastChar:
1896 while (true) {
1897 while (i >= min && source[i] != strLastChar) {
1898 i--;
1899 }
1900 if (i < min) {
1901 return -1;
1902 }
1903 int j = i - 1;
1904 int start = j - (targetCount - 1);
1905 int k = strLastIndex - 1;
1906
1907 while (j > start) {
1908 if (source[j--] != target[k--]) {
1909 i--;
1910 continue startSearchForLastChar;
1911 }
1912 }
1913 return start - sourceOffset + 1;
1914 }
1915 }
1916
1917 /**
1918 * Returns a string that is a substring of this string. The
1919 * substring begins with the character at the specified index and
1920 * extends to the end of this string. <p>
1921 * Examples:
1922 * <blockquote><pre>
1923 * "unhappy".substring(2) returns "happy"
1924 * "Harbison".substring(3) returns "bison"
1925 * "emptiness".substring(9) returns "" (an empty string)
1926 * </pre></blockquote>
1927 *
1928 * @param beginIndex the beginning index, inclusive.
1929 * @return the specified substring.
1930 * @exception IndexOutOfBoundsException if
1931 * {@code beginIndex} is negative or larger than the
1932 * length of this {@code String} object.
1933 */
1934 public String substring(int beginIndex) {
1935 if (beginIndex <= 0) {
1936 if (beginIndex < 0) {
1937 throw new StringIndexOutOfBoundsException(beginIndex);
1938 }
1939 return this;
1940 }
1941 int subLen = value.length - beginIndex;
1942 if (subLen < 0) {
1943 throw new StringIndexOutOfBoundsException(subLen);
1944 }
1945 return new String(value, beginIndex, subLen);
1946 }
1947
1948 /**
1949 * Returns a string that is a substring of this string. The
1950 * substring begins at the specified {@code beginIndex} and
1951 * extends to the character at index {@code endIndex - 1}.
1952 * Thus the length of the substring is {@code endIndex-beginIndex}.
1953 * <p>
1954 * Examples:
1955 * <blockquote><pre>
1956 * "hamburger".substring(4, 8) returns "urge"
1957 * "smiles".substring(1, 5) returns "mile"
1958 * </pre></blockquote>
1959 *
1960 * @param beginIndex the beginning index, inclusive.
1961 * @param endIndex the ending index, exclusive.
1962 * @return the specified substring.
1963 * @exception IndexOutOfBoundsException if the
1964 * {@code beginIndex} is negative, or
1965 * {@code endIndex} is larger than the length of
1966 * this {@code String} object, or
1967 * {@code beginIndex} is larger than
1968 * {@code endIndex}.
1969 */
1970 public String substring(int beginIndex, int endIndex) {
1971 if (beginIndex <= 0) {
1972 if (beginIndex < 0) {
1973 throw new StringIndexOutOfBoundsException(beginIndex);
1974 }
1975 if (endIndex == value.length) {
1976 return this;
1977 }
1978 }
1979 if (endIndex > value.length) {
1980 throw new StringIndexOutOfBoundsException(endIndex);
1981 }
1982 int subLen = endIndex - beginIndex;
1983 if (subLen < 0) {
1984 throw new StringIndexOutOfBoundsException(subLen);
1985 }
1986 return new String(value, beginIndex, subLen);
1987 }
1988
1989 /**
1990 * Returns a character sequence that is a subsequence of this sequence.
1991 *
1992 * <p> An invocation of this method of the form
1993 *
1994 * <blockquote><pre>
1995 * str.subSequence(begin, end)</pre></blockquote>
1996 *
1997 * behaves in exactly the same way as the invocation
1998 *
1999 * <blockquote><pre>
2000 * str.substring(begin, end)</pre></blockquote>
2001 *
2002 * @apiNote
2003 * This method is defined so that the {@code String} class can implement
2004 * the {@link CharSequence} interface.
2005 *
2006 * @param beginIndex the begin index, inclusive.
2007 * @param endIndex the end index, exclusive.
2008 * @return the specified subsequence.
2009 *
2010 * @throws IndexOutOfBoundsException
2011 * if {@code beginIndex} or {@code endIndex} is negative,
2012 * if {@code endIndex} is greater than {@code length()},
2013 * or if {@code beginIndex} is greater than {@code endIndex}
2014 *
2015 * @since 1.4
2016 * @spec JSR-51
2017 */
2018 public CharSequence subSequence(int beginIndex, int endIndex) {
2019 return this.substring(beginIndex, endIndex);
2020 }
2021
2022 /**
2023 * Concatenates the specified string to the end of this string.
2024 * <p>
2025 * If the length of the argument string is {@code 0}, then this
2026 * {@code String} object is returned. Otherwise, a
2027 * {@code String} object is returned that represents a character
2028 * sequence that is the concatenation of the character sequence
2029 * represented by this {@code String} object and the character
2030 * sequence represented by the argument string.<p>
2031 * Examples:
2032 * <blockquote><pre>
2033 * "cares".concat("s") returns "caress"
2034 * "to".concat("get").concat("her") returns "together"
2035 * </pre></blockquote>
2036 *
2037 * @param str the {@code String} that is concatenated to the end
2038 * of this {@code String}.
2039 * @return a string that represents the concatenation of this object's
2040 * characters followed by the string argument's characters.
2041 */
2042 public String concat(String str) {
2043 int otherLen = str.length();
2044 if (otherLen == 0) {
2045 return this;
2046 }
2047 int len = value.length;
2048 char[] buf = Arrays.copyOf(value, len + otherLen);
2049 str.getChars(buf, len);
2050 return new String(buf, true);
2051 }
2052
2053 /**
2054 * Returns a string resulting from replacing all occurrences of
2055 * {@code oldChar} in this string with {@code newChar}.
2056 * <p>
2057 * If the character {@code oldChar} does not occur in the
2058 * character sequence represented by this {@code String} object,
2059 * then a reference to this {@code String} object is returned.
2060 * Otherwise, a {@code String} object is returned that
2061 * represents a character sequence identical to the character sequence
2062 * represented by this {@code String} object, except that every
2063 * occurrence of {@code oldChar} is replaced by an occurrence
2064 * of {@code newChar}.
2065 * <p>
2066 * Examples:
2067 * <blockquote><pre>
2068 * "mesquite in your cellar".replace('e', 'o')
2069 * returns "mosquito in your collar"
2070 * "the war of baronets".replace('r', 'y')
2071 * returns "the way of bayonets"
2072 * "sparring with a purple porpoise".replace('p', 't')
2073 * returns "starring with a turtle tortoise"
2074 * "JonL".replace('q', 'x') returns "JonL" (no change)
2075 * </pre></blockquote>
2076 *
2077 * @param oldChar the old character.
2078 * @param newChar the new character.
2079 * @return a string derived from this string by replacing every
2080 * occurrence of {@code oldChar} with {@code newChar}.
2081 */
2082 public String replace(char oldChar, char newChar) {
2083 if (oldChar != newChar) {
2084 char[] val = value; /* avoid getfield opcode */
2085 int len = val.length;
2086 int i = -1;
2087
2088 while (++i < len) {
2089 if (val[i] == oldChar) {
2090 break;
2091 }
2092 }
2093 if (i < len) {
2094 char[] buf = new char[len];
2095 for (int j = 0; j < i; j++) {
2096 buf[j] = val[j];
2097 }
2098 while (i < len) {
2099 char c = val[i];
2100 buf[i] = (c == oldChar) ? newChar : c;
2101 i++;
2102 }
2103 return new String(buf, true);
2104 }
2105 }
2106 return this;
2107 }
2108
2109 /**
2110 * Tells whether or not this string matches the given <a
2111 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2112 *
2113 * <p> An invocation of this method of the form
2114 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2115 * same result as the expression
2116 *
2117 * <blockquote>
2118 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2119 * matches(<i>regex</i>, <i>str</i>)}
2120 * </blockquote>
2121 *
2122 * @param regex
2123 * the regular expression to which this string is to be matched
2124 *
2125 * @return {@code true} if, and only if, this string matches the
2126 * given regular expression
2127 *
2128 * @throws PatternSyntaxException
2129 * if the regular expression's syntax is invalid
2130 *
2131 * @see java.util.regex.Pattern
2132 *
2133 * @since 1.4
2134 * @spec JSR-51
2135 */
2136 public boolean matches(String regex) {
2137 return Pattern.matches(regex, this);
2138 }
2139
2140 /**
2141 * Returns true if and only if this string contains the specified
2142 * sequence of char values.
2143 *
2144 * @param s the sequence to search for
2145 * @return true if this string contains {@code s}, false otherwise
2146 * @since 1.5
2147 */
2148 public boolean contains(CharSequence s) {
2149 return indexOf(s.toString()) >= 0;
2150 }
2151
2152 /**
2153 * Replaces the first substring of this string that matches the given <a
2154 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2155 * given replacement.
2156 *
2157 * <p> An invocation of this method of the form
2158 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2159 * yields exactly the same result as the expression
2160 *
2161 * <blockquote>
2162 * <code>
2163 * {@link java.util.regex.Pattern}.{@link
2164 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2165 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2166 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2167 * </code>
2168 * </blockquote>
2169 *
2170 *<p>
2171 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2172 * replacement string may cause the results to be different than if it were
2173 * being treated as a literal replacement string; see
2174 * {@link java.util.regex.Matcher#replaceFirst}.
2175 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2176 * meaning of these characters, if desired.
2177 *
2178 * @param regex
2179 * the regular expression to which this string is to be matched
2180 * @param replacement
2181 * the string to be substituted for the first match
2182 *
2183 * @return The resulting {@code String}
2184 *
2185 * @throws PatternSyntaxException
2186 * if the regular expression's syntax is invalid
2187 *
2188 * @see java.util.regex.Pattern
2189 *
2190 * @since 1.4
2191 * @spec JSR-51
2192 */
2193 public String replaceFirst(String regex, String replacement) {
2194 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2195 }
2196
2197 /**
2198 * Replaces each substring of this string that matches the given <a
2199 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2200 * given replacement.
2201 *
2202 * <p> An invocation of this method of the form
2203 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2204 * yields exactly the same result as the expression
2205 *
2206 * <blockquote>
2207 * <code>
2208 * {@link java.util.regex.Pattern}.{@link
2209 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2210 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2211 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2212 * </code>
2213 * </blockquote>
2214 *
2215 *<p>
2216 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2217 * replacement string may cause the results to be different than if it were
2218 * being treated as a literal replacement string; see
2219 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2220 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2221 * meaning of these characters, if desired.
2222 *
2223 * @param regex
2224 * the regular expression to which this string is to be matched
2225 * @param replacement
2226 * the string to be substituted for each match
2227 *
2228 * @return The resulting {@code String}
2229 *
2230 * @throws PatternSyntaxException
2231 * if the regular expression's syntax is invalid
2232 *
2233 * @see java.util.regex.Pattern
2234 *
2235 * @since 1.4
2236 * @spec JSR-51
2237 */
2238 public String replaceAll(String regex, String replacement) {
2239 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2240 }
2241
2242 /**
2243 * Replaces each substring of this string that matches the literal target
2244 * sequence with the specified literal replacement sequence. The
2245 * replacement proceeds from the beginning of the string to the end, for
2246 * example, replacing "aa" with "b" in the string "aaa" will result in
2247 * "ba" rather than "ab".
2248 *
2249 * @param target The sequence of char values to be replaced
2250 * @param replacement The replacement sequence of char values
2251 * @return The resulting string
2252 * @since 1.5
2253 */
2254 public String replace(CharSequence target, CharSequence replacement) {
2255 String starget = target.toString();
2256 String srepl = replacement.toString();
2257 int j = indexOf(starget);
2258 if (j < 0) {
2259 return this;
2260 }
2261 int targLen = starget.length();
2262 int targLen1 = Math.max(targLen, 1);
2263 final char[] value = this.value;
2264 final char[] replValue = srepl.value;
2265 int newLenHint = value.length - targLen + replValue.length;
2266 if (newLenHint < 0) {
2267 throw new OutOfMemoryError();
2268 }
2269 StringBuilder sb = new StringBuilder(newLenHint);
2270 int i = 0;
2271 do {
2272 sb.append(value, i, j - i)
2273 .append(replValue);
2274 i = j + targLen;
2275 } while (j < value.length && (j = indexOf(starget, j + targLen1)) > 0);
2276
2277 return sb.append(value, i, value.length - i).toString();
2278 }
2279
2280 /**
2281 * Splits this string around matches of the given
2282 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2283 *
2284 * <p> The array returned by this method contains each substring of this
2285 * string that is terminated by another substring that matches the given
2286 * expression or is terminated by the end of the string. The substrings in
2287 * the array are in the order in which they occur in this string. If the
2288 * expression does not match any part of the input then the resulting array
2289 * has just one element, namely this string.
2290 *
2291 * <p> When there is a positive-width match at the beginning of this
2292 * string then an empty leading substring is included at the beginning
2293 * of the resulting array. A zero-width match at the beginning however
2294 * never produces such empty leading substring.
2295 *
2296 * <p> The {@code limit} parameter controls the number of times the
2297 * pattern is applied and therefore affects the length of the resulting
2298 * array. If the limit <i>n</i> is greater than zero then the pattern
2299 * will be applied at most <i>n</i> - 1 times, the array's
2300 * length will be no greater than <i>n</i>, and the array's last entry
2301 * will contain all input beyond the last matched delimiter. If <i>n</i>
2302 * is non-positive then the pattern will be applied as many times as
2303 * possible and the array can have any length. If <i>n</i> is zero then
2304 * the pattern will be applied as many times as possible, the array can
2305 * have any length, and trailing empty strings will be discarded.
2306 *
2307 * <p> The string {@code "boo:and:foo"}, for example, yields the
2308 * following results with these parameters:
2309 *
2310 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2311 * <tr>
2312 * <th>Regex</th>
2313 * <th>Limit</th>
2314 * <th>Result</th>
2315 * </tr>
2316 * <tr><td align=center>:</td>
2317 * <td align=center>2</td>
2318 * <td>{@code { "boo", "and:foo" }}</td></tr>
2319 * <tr><td align=center>:</td>
2320 * <td align=center>5</td>
2321 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2322 * <tr><td align=center>:</td>
2323 * <td align=center>-2</td>
2324 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2325 * <tr><td align=center>o</td>
2326 * <td align=center>5</td>
2327 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2328 * <tr><td align=center>o</td>
2329 * <td align=center>-2</td>
2330 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2331 * <tr><td align=center>o</td>
2332 * <td align=center>0</td>
2333 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2334 * </table></blockquote>
2335 *
2336 * <p> An invocation of this method of the form
2337 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2338 * yields the same result as the expression
2339 *
2340 * <blockquote>
2341 * <code>
2342 * {@link java.util.regex.Pattern}.{@link
2343 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2344 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2345 * </code>
2346 * </blockquote>
2347 *
2348 *
2349 * @param regex
2350 * the delimiting regular expression
2351 *
2352 * @param limit
2353 * the result threshold, as described above
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, int limit) {
2367 /* fastpath if the regex is a
2368 (1)one-char String and this character is not one of the
2369 RegEx's meta characters ".$|()[{^?*+\\", or
2370 (2)two-char String and the first char is the backslash and
2371 the second is not the ascii digit or ascii letter.
2372 */
2373 char ch = 0;
2374 if (((regex.value.length == 1 &&
2375 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2376 (regex.length() == 2 &&
2377 regex.charAt(0) == '\\' &&
2378 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2379 ((ch-'a')|('z'-ch)) < 0 &&
2380 ((ch-'A')|('Z'-ch)) < 0)) &&
2381 (ch < Character.MIN_HIGH_SURROGATE ||
2382 ch > Character.MAX_LOW_SURROGATE))
2383 {
2384 int off = 0;
2385 int next = 0;
2386 boolean limited = limit > 0;
2387 ArrayList<String> list = new ArrayList<>();
2388 while ((next = indexOf(ch, off)) != -1) {
2389 if (!limited || list.size() < limit - 1) {
2390 list.add(substring(off, next));
2391 off = next + 1;
2392 } else { // last one
2393 //assert (list.size() == limit - 1);
2394 list.add(substring(off, value.length));
2395 off = value.length;
2396 break;
2397 }
2398 }
2399 // If no match was found, return this
2400 if (off == 0)
2401 return new String[]{this};
2402
2403 // Add remaining segment
2404 if (!limited || list.size() < limit)
2405 list.add(substring(off, value.length));
2406
2407 // Construct result
2408 int resultSize = list.size();
2409 if (limit == 0) {
2410 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2411 resultSize--;
2412 }
2413 }
2414 String[] result = new String[resultSize];
2415 return list.subList(0, resultSize).toArray(result);
2416 }
2417 return Pattern.compile(regex).split(this, limit);
2418 }
2419
2420 /**
2421 * Splits this string around matches of the given <a
2422 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2423 *
2424 * <p> This method works as if by invoking the two-argument {@link
2425 * #split(String, int) split} method with the given expression and a limit
2426 * argument of zero. Trailing empty strings are therefore not included in
2427 * the resulting array.
2428 *
2429 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2430 * results with these expressions:
2431 *
2432 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2433 * <tr>
2434 * <th>Regex</th>
2435 * <th>Result</th>
2436 * </tr>
2437 * <tr><td align=center>:</td>
2438 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2439 * <tr><td align=center>o</td>
2440 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2441 * </table></blockquote>
2442 *
2443 *
2444 * @param regex
2445 * the delimiting regular expression
2446 *
2447 * @return the array of strings computed by splitting this string
2448 * around matches of the given regular expression
2449 *
2450 * @throws PatternSyntaxException
2451 * if the regular expression's syntax is invalid
2452 *
2453 * @see java.util.regex.Pattern
2454 *
2455 * @since 1.4
2456 * @spec JSR-51
2457 */
2458 public String[] split(String regex) {
2459 return split(regex, 0);
2460 }
2461
2462 /**
2463 * Returns a new String composed of copies of the
2464 * {@code CharSequence elements} joined together with a copy of
2465 * the specified {@code delimiter}.
2466 *
2467 * <blockquote>For example,
2468 * <pre>{@code
2469 * String message = String.join("-", "Java", "is", "cool");
2470 * // message returned is: "Java-is-cool"
2471 * }</pre></blockquote>
2472 *
2473 * Note that if an element is null, then {@code "null"} is added.
2474 *
2475 * @param delimiter the delimiter that separates each element
2476 * @param elements the elements to join together.
2477 *
2478 * @return a new {@code String} that is composed of the {@code elements}
2479 * separated by the {@code delimiter}
2480 *
2481 * @throws NullPointerException If {@code delimiter} or {@code elements}
2482 * is {@code null}
2483 *
2484 * @see java.util.StringJoiner
2485 * @since 1.8
2486 */
2487 public static String join(CharSequence delimiter, CharSequence... elements) {
2488 Objects.requireNonNull(delimiter);
2489 Objects.requireNonNull(elements);
2490 // Number of elements not likely worth Arrays.stream overhead.
2491 StringJoiner joiner = new StringJoiner(delimiter);
2492 for (CharSequence cs: elements) {
2493 joiner.add(cs);
2494 }
2495 return joiner.toString();
2496 }
2497
2498 /**
2499 * Returns a new {@code String} composed of copies of the
2500 * {@code CharSequence elements} joined together with a copy of the
2501 * specified {@code delimiter}.
2502 *
2503 * <blockquote>For example,
2504 * <pre>{@code
2505 * List<String> strings = new LinkedList<>();
2506 * strings.add("Java");strings.add("is");
2507 * strings.add("cool");
2508 * String message = String.join(" ", strings);
2509 * //message returned is: "Java is cool"
2510 *
2511 * Set<String> strings = new LinkedHashSet<>();
2512 * strings.add("Java"); strings.add("is");
2513 * strings.add("very"); strings.add("cool");
2514 * String message = String.join("-", strings);
2515 * //message returned is: "Java-is-very-cool"
2516 * }</pre></blockquote>
2517 *
2518 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2519 *
2520 * @param delimiter a sequence of characters that is used to separate each
2521 * of the {@code elements} in the resulting {@code String}
2522 * @param elements an {@code Iterable} that will have its {@code elements}
2523 * joined together.
2524 *
2525 * @return a new {@code String} that is composed from the {@code elements}
2526 * argument
2527 *
2528 * @throws NullPointerException If {@code delimiter} or {@code elements}
2529 * is {@code null}
2530 *
2531 * @see #join(CharSequence,CharSequence...)
2532 * @see java.util.StringJoiner
2533 * @since 1.8
2534 */
2535 public static String join(CharSequence delimiter,
2536 Iterable<? extends CharSequence> elements) {
2537 Objects.requireNonNull(delimiter);
2538 Objects.requireNonNull(elements);
2539 StringJoiner joiner = new StringJoiner(delimiter);
2540 for (CharSequence cs: elements) {
2541 joiner.add(cs);
2542 }
2543 return joiner.toString();
2544 }
2545
2546 /**
2547 * Converts all of the characters in this {@code String} to lower
2548 * case using the rules of the given {@code Locale}. Case mapping is based
2549 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2550 * class. Since case mappings are not always 1:1 char mappings, the resulting
2551 * {@code String} may be a different length than the original {@code String}.
2552 * <p>
2553 * Examples of lowercase mappings are in the following table:
2554 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2555 * <tr>
2556 * <th>Language Code of Locale</th>
2557 * <th>Upper Case</th>
2558 * <th>Lower Case</th>
2559 * <th>Description</th>
2560 * </tr>
2561 * <tr>
2562 * <td>tr (Turkish)</td>
2563 * <td>\u0130</td>
2564 * <td>\u0069</td>
2565 * <td>capital letter I with dot above -> small letter i</td>
2566 * </tr>
2567 * <tr>
2568 * <td>tr (Turkish)</td>
2569 * <td>\u0049</td>
2570 * <td>\u0131</td>
2571 * <td>capital letter I -> small letter dotless i </td>
2572 * </tr>
2573 * <tr>
2574 * <td>(all)</td>
2575 * <td>French Fries</td>
2576 * <td>french fries</td>
2577 * <td>lowercased all chars in String</td>
2578 * </tr>
2579 * <tr>
2580 * <td>(all)</td>
2581 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2582 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2583 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2584 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2585 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2586 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2587 * <td>lowercased all chars in String</td>
2588 * </tr>
2589 * </table>
2590 *
2591 * @param locale use the case transformation rules for this locale
2592 * @return the {@code String}, converted to lowercase.
2593 * @see java.lang.String#toLowerCase()
2594 * @see java.lang.String#toUpperCase()
2595 * @see java.lang.String#toUpperCase(Locale)
2596 * @since 1.1
2597 */
2598 public String toLowerCase(Locale locale) {
2599 if (locale == null) {
2600 throw new NullPointerException();
2601 }
2602 int first;
2603 boolean hasSurr = false;
2604 final int len = value.length;
2605
2606 // Now check if there are any characters that need to be changed, or are surrogate
2607 for (first = 0 ; first < len; first++) {
2608 int cp = (int)value[first];
2609 if (Character.isSurrogate((char)cp)) {
2610 hasSurr = true;
2611 break;
2612 }
2613 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR
2614 break;
2615 }
2616 }
2617 if (first == len)
2618 return this;
2619 char[] result = new char[len];
2620 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2621 // lowerCase characters.
2622 String lang = locale.getLanguage();
2623 if (lang == "tr" || lang == "az" || lang == "lt") {
2624 return toLowerCaseEx(result, first, locale, true);
2625 }
2626 if (hasSurr) {
2627 return toLowerCaseEx(result, first, locale, false);
2628 }
2629 for (int i = first; i < len; i++) {
2630 int cp = (int)value[i];
2631 if (cp == '\u03A3' || // GREEK CAPITAL LETTER SIGMA
2632 Character.isSurrogate((char)cp)) {
2633 return toLowerCaseEx(result, i, locale, false);
2634 }
2635 if (cp == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE
2636 return toLowerCaseEx(result, i, locale, true);
2637 }
2638 cp = Character.toLowerCase(cp);
2639 if (!Character.isBmpCodePoint(cp)) {
2640 return toLowerCaseEx(result, i, locale, false);
2641 }
2642 result[i] = (char)cp;
2643 }
2644 return new String(result, true);
2645 }
2646
2647 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) {
2648 int resultOffset = first;
2649 int srcCount;
2650 for (int i = first; i < value.length; i += srcCount) {
2651 int srcChar = (int)value[i];
2652 int lowerChar;
2653 char[] lowerCharArray;
2654 srcCount = 1;
2655 if (Character.isSurrogate((char)srcChar)) {
2656 srcChar = codePointAt(i);
2657 srcCount = Character.charCount(srcChar);
2658 }
2659 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2660 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2661 } else {
2662 lowerChar = Character.toLowerCase(srcChar);
2663 }
2664 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp
2665 result[resultOffset++] = (char)lowerChar;
2666 } else {
2667 if (lowerChar == Character.ERROR) {
2668 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2669 } else if (srcCount == 2) {
2670 resultOffset += Character.toChars(lowerChar, result, resultOffset);
2671 continue;
2672 } else {
2673 lowerCharArray = Character.toChars(lowerChar);
2674 }
2675 /* Grow result if needed */
2676 int mapLen = lowerCharArray.length;
2677 if (mapLen > srcCount) {
2678 char[] result2 = new char[result.length + mapLen - srcCount];
2679 System.arraycopy(result, 0, result2, 0, resultOffset);
2680 result = result2;
2681 }
2682 for (int x = 0; x < mapLen; ++x) {
2683 result[resultOffset++] = lowerCharArray[x];
2684 }
2685 }
2686 }
2687 return new String(result, 0, resultOffset);
2688 }
2689
2690 /**
2691 * Converts all of the characters in this {@code String} to lower
2692 * case using the rules of the default locale. This is equivalent to calling
2693 * {@code toLowerCase(Locale.getDefault())}.
2694 * <p>
2695 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2696 * results if used for strings that are intended to be interpreted locale
2697 * independently.
2698 * Examples are programming language identifiers, protocol keys, and HTML
2699 * tags.
2700 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2701 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2702 * LATIN SMALL LETTER DOTLESS I character.
2703 * To obtain correct results for locale insensitive strings, use
2704 * {@code toLowerCase(Locale.ROOT)}.
2705 *
2706 * @return the {@code String}, converted to lowercase.
2707 * @see java.lang.String#toLowerCase(Locale)
2708 */
2709 public String toLowerCase() {
2710 return toLowerCase(Locale.getDefault());
2711 }
2712
2713 /**
2714 * Converts all of the characters in this {@code String} to upper
2715 * case using the rules of the given {@code Locale}. Case mapping is based
2716 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2717 * class. Since case mappings are not always 1:1 char mappings, the resulting
2718 * {@code String} may be a different length than the original {@code String}.
2719 * <p>
2720 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2721 *
2722 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2723 * <tr>
2724 * <th>Language Code of Locale</th>
2725 * <th>Lower Case</th>
2726 * <th>Upper Case</th>
2727 * <th>Description</th>
2728 * </tr>
2729 * <tr>
2730 * <td>tr (Turkish)</td>
2731 * <td>\u0069</td>
2732 * <td>\u0130</td>
2733 * <td>small letter i -> capital letter I with dot above</td>
2734 * </tr>
2735 * <tr>
2736 * <td>tr (Turkish)</td>
2737 * <td>\u0131</td>
2738 * <td>\u0049</td>
2739 * <td>small letter dotless i -> capital letter I</td>
2740 * </tr>
2741 * <tr>
2742 * <td>(all)</td>
2743 * <td>\u00df</td>
2744 * <td>\u0053 \u0053</td>
2745 * <td>small letter sharp s -> two letters: SS</td>
2746 * </tr>
2747 * <tr>
2748 * <td>(all)</td>
2749 * <td>Fahrvergnügen</td>
2750 * <td>FAHRVERGNÜGEN</td>
2751 * <td></td>
2752 * </tr>
2753 * </table>
2754 * @param locale use the case transformation rules for this locale
2755 * @return the {@code String}, converted to uppercase.
2756 * @see java.lang.String#toUpperCase()
2757 * @see java.lang.String#toLowerCase()
2758 * @see java.lang.String#toLowerCase(Locale)
2759 * @since 1.1
2760 */
2761 public String toUpperCase(Locale locale) {
2762 if (locale == null) {
2763 throw new NullPointerException();
2764 }
2765 int first;
2766 boolean hasSurr = false;
2767 final int len = value.length;
2768
2769 // Now check if there are any characters that need to be changed, or are surrogate
2770 for (first = 0 ; first < len; first++ ) {
2771 int cp = (int)value[first];
2772 if (Character.isSurrogate((char)cp)) {
2773 hasSurr = true;
2774 break;
2775 }
2776 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR
2777 break;
2778 }
2779 }
2780 if (first == len) {
2781 return this;
2782 }
2783 char[] result = new char[len];
2784 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2785 // upperCase characters.
2786 String lang = locale.getLanguage();
2787 if (lang == "tr" || lang == "az" || lang == "lt") {
2788 return toUpperCaseEx(result, first, locale, true);
2789 }
2790 if (hasSurr) {
2791 return toUpperCaseEx(result, first, locale, false);
2792 }
2793 for (int i = first; i < len; i++) {
2794 int cp = (int)value[i];
2795 if (Character.isSurrogate((char)cp)) {
2796 return toUpperCaseEx(result, i, locale, false);
2797 }
2798 cp = Character.toUpperCaseEx(cp);
2799 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp
2800 return toUpperCaseEx(result, i, locale, false);
2801 }
2802 result[i] = (char)cp;
2803 }
2804 return new String(result, true);
2805 }
2806
2807 private String toUpperCaseEx(char[] result, int first, Locale locale,
2808 boolean localeDependent) {
2809 int resultOffset = first;
2810 int srcCount;
2811 for (int i = first; i < value.length; i += srcCount) {
2812 int srcChar = (int)value[i];
2813 int upperChar;
2814 char[] upperCharArray;
2815 srcCount = 1;
2816 if (Character.isSurrogate((char)srcChar)) {
2817 srcChar = codePointAt(i);
2818 srcCount = Character.charCount(srcChar);
2819 }
2820 if (localeDependent) {
2821 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2822 } else {
2823 upperChar = Character.toUpperCaseEx(srcChar);
2824 }
2825 if (Character.isBmpCodePoint(upperChar)) {
2826 result[resultOffset++] = (char)upperChar;
2827 } else {
2828 if (upperChar == Character.ERROR) {
2829 if (localeDependent) {
2830 upperCharArray =
2831 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
2832 } else {
2833 upperCharArray = Character.toUpperCaseCharArray(srcChar);
2834 }
2835 } else if (srcCount == 2) {
2836 resultOffset += Character.toChars(upperChar, result, resultOffset);
2837 continue;
2838 } else {
2839 upperCharArray = Character.toChars(upperChar);
2840 }
2841 /* Grow result if needed */
2842 int mapLen = upperCharArray.length;
2843 if (mapLen > srcCount) {
2844 char[] result2 = new char[result.length + mapLen - srcCount];
2845 System.arraycopy(result, 0, result2, 0, resultOffset);
2846 result = result2;
2847 }
2848 for (int x = 0; x < mapLen; ++x) {
2849 result[resultOffset++] = upperCharArray[x];
2850 }
2851 }
2852 }
2853 return new String(result, 0, resultOffset);
2854 }
2855
2856 /**
2857 * Converts all of the characters in this {@code String} to upper
2858 * case using the rules of the default locale. This method is equivalent to
2859 * {@code toUpperCase(Locale.getDefault())}.
2860 * <p>
2861 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2862 * results if used for strings that are intended to be interpreted locale
2863 * independently.
2864 * Examples are programming language identifiers, protocol keys, and HTML
2865 * tags.
2866 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2867 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2868 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2869 * To obtain correct results for locale insensitive strings, use
2870 * {@code toUpperCase(Locale.ROOT)}.
2871 *
2872 * @return the {@code String}, converted to uppercase.
2873 * @see java.lang.String#toUpperCase(Locale)
2874 */
2875 public String toUpperCase() {
2876 return toUpperCase(Locale.getDefault());
2877 }
2878
2879 /**
2880 * Returns a string whose value is this string, with any leading and trailing
2881 * whitespace removed.
2882 * <p>
2883 * If this {@code String} object represents an empty character
2884 * sequence, or the first and last characters of character sequence
2885 * represented by this {@code String} object both have codes
2886 * greater than {@code '\u005Cu0020'} (the space character), then a
2887 * reference to this {@code String} object is returned.
2888 * <p>
2889 * Otherwise, if there is no character with a code greater than
2890 * {@code '\u005Cu0020'} in the string, then a
2891 * {@code String} object representing an empty string is
2892 * returned.
2893 * <p>
2894 * Otherwise, let <i>k</i> be the index of the first character in the
2895 * string whose code is greater than {@code '\u005Cu0020'}, and let
2896 * <i>m</i> be the index of the last character in the string whose code
2897 * is greater than {@code '\u005Cu0020'}. A {@code String}
2898 * object is returned, representing the substring of this string that
2899 * begins with the character at index <i>k</i> and ends with the
2900 * character at index <i>m</i>-that is, the result of
2901 * {@code this.substring(k, m + 1)}.
2902 * <p>
2903 * This method may be used to trim whitespace (as defined above) from
2904 * the beginning and end of a string.
2905 *
2906 * @return A string whose value is this string, with any leading and trailing white
2907 * space removed, or this string if it has no leading or
2908 * trailing white space.
2909 */
2910 public String trim() {
2911 char[] val = value; /* avoid getfield opcode */
2912 int end = val.length;
2913 int beg = 0;
2914
2915 while ((beg < end) && (val[beg] <= ' ')) {
2916 beg++;
2917 }
2918 while ((beg < end) && (val[end - 1] <= ' ')) {
2919 end--;
2920 }
2921 return substring(beg, end);
2922 }
2923
2924 /**
2925 * This object (which is already a string!) is itself returned.
2926 *
2927 * @return the string itself.
2928 */
2929 public String toString() {
2930 return this;
2931 }
2932
2933 static class IntCharArraySpliterator implements Spliterator.OfInt {
2934 private final char[] array;
2935 private int index; // current index, modified on advance/split
2936 private final int fence; // one past last index
2937 private final int cs;
2938
2939 IntCharArraySpliterator(char[] array, int acs) {
2940 this(array, 0, array.length, acs);
2941 }
2942
2943 IntCharArraySpliterator(char[] array, int origin, int fence, int acs) {
2944 this.array = array;
2945 this.index = origin;
2946 this.fence = fence;
2947 this.cs = acs | Spliterator.ORDERED | Spliterator.SIZED
2948 | Spliterator.SUBSIZED;
2949 }
2950
2951 @Override
2952 public OfInt trySplit() {
2953 int lo = index, mid = (lo + fence) >>> 1;
2954 return (lo >= mid)
2955 ? null
2956 : new IntCharArraySpliterator(array, lo, index = mid, cs);
2957 }
2958
2959 @Override
2960 public void forEachRemaining(IntConsumer action) {
2961 char[] a; int i, hi; // hoist accesses and checks from loop
2962 if (action == null)
2963 throw new NullPointerException();
2964 if ((a = array).length >= (hi = fence) &&
2965 (i = index) >= 0 && i < (index = hi)) {
2966 do { action.accept(a[i]); } while (++i < hi);
2967 }
2968 }
2969
2970 @Override
2971 public boolean tryAdvance(IntConsumer action) {
2972 if (action == null)
2973 throw new NullPointerException();
2974 if (index >= 0 && index < fence) {
2975 action.accept(array[index++]);
2976 return true;
2977 }
2978 return false;
2979 }
2980
2981 @Override
2982 public long estimateSize() { return (long)(fence - index); }
2983
2984 @Override
2985 public int characteristics() {
2986 return cs;
2987 }
2988 }
2989
2990 /**
2991 * Returns a stream of {@code int} zero-extending the {@code char} values
2992 * from this sequence. Any char which maps to a <a
2993 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code
2994 * point</a> is passed through uninterpreted.
2995 *
2996 * @return an IntStream of char values from this sequence
2997 * @since 1.9
2998 */
2999 @Override
3000 public IntStream chars() {
3001 return StreamSupport.intStream(
3002 new IntCharArraySpliterator(value, Spliterator.IMMUTABLE), false);
3003 }
3004
3005 static class CodePointsSpliterator implements Spliterator.OfInt {
3006 private final char[] array;
3007 private int index; // current index, modified on advance/split
3008 private final int fence; // one past last index
3009 private final int cs;
3010
3011 CodePointsSpliterator(char[] array, int acs) {
3012 this(array, 0, array.length, acs);
3013 }
3014
3015 CodePointsSpliterator(char[] array, int origin, int fence, int acs) {
3016 this.array = array;
3017 this.index = origin;
3018 this.fence = fence;
3019 this.cs = acs | Spliterator.ORDERED;
3020 }
3021
3022 @Override
3023 public OfInt trySplit() {
3024 int lo = index, mid = (lo + fence) >>> 1;
3025 if (lo >= mid)
3026 return null;
3027
3028 int midOneLess;
3029 // If the mid-point intersects a surrogate pair
3030 if (Character.isLowSurrogate(array[mid]) &&
3031 Character.isHighSurrogate(array[midOneLess = (mid -1)])) {
3032 // If there is only one pair it cannot be split
3033 if (lo >= midOneLess)
3034 return null;
3035 // Shift the mid-point to align with the surrogate pair
3036 return new CodePointsSpliterator(array, lo, index = midOneLess, cs);
3037 }
3038 return new CodePointsSpliterator(array, lo, index = mid, cs);
3039 }
3040
3041 @Override
3042 public void forEachRemaining(IntConsumer action) {
3043 char[] a; int i, hi; // hoist accesses and checks from loop
3044 if (action == null)
3045 throw new NullPointerException();
3046 if ((a = array).length >= (hi = fence) &&
3047 (i = index) >= 0 && i < (index = hi)) {
3048 do {
3049 i = advance(a, i, hi, action);
3050 } while (i < hi);
3051 }
3052 }
3053
3054 @Override
3055 public boolean tryAdvance(IntConsumer action) {
3056 if (action == null)
3057 throw new NullPointerException();
3058 if (index >= 0 && index < fence) {
3059 index = advance(array, index, fence, action);
3060 return true;
3061 }
3062 return false;
3063 }
3064
3065 // Advance one code point from the index, i, and return the next
3066 // index to advance from
3067 private static int advance(char[] a, int i, int hi, IntConsumer action) {
3068 char c1 = a[i++];
3069 int cp = c1;
3070 if (Character.isHighSurrogate(c1) && i < hi) {
3071 char c2 = a[i];
3072 if (Character.isLowSurrogate(c2)) {
3073 i++;
3074 cp = Character.toCodePoint(c1, c2);
3075 }
3076 }
3077 action.accept(cp);
3078 return i;
3079 }
3080
3081 @Override
3082 public long estimateSize() { return (long)(fence - index); }
3083
3084 @Override
3085 public int characteristics() {
3086 return cs;
3087 }
3088 }
3089
3090 /**
3091 * Returns a stream of code point values from this sequence. Any surrogate
3092 * pairs encountered in the sequence are combined as if by {@linkplain
3093 * Character#toCodePoint Character.toCodePoint} and the result is passed
3094 * to the stream. Any other code units, including ordinary BMP characters,
3095 * unpaired surrogates, and undefined code units, are zero-extended to
3096 * {@code int} values which are then passed to the stream.
3097 *
3098 * @return an IntStream of Unicode code points from this sequence
3099 * @since 1.9
3100 */
3101 @Override
3102 public IntStream codePoints() {
3103 return StreamSupport.intStream(
3104 new CodePointsSpliterator(value, Spliterator.IMMUTABLE), false);
3105 }
3106
3107 /**
3108 * Converts this string to a new character array.
3109 *
3110 * @return a newly allocated character array whose length is the length
3111 * of this string and whose contents are initialized to contain
3112 * the character sequence represented by this string.
3113 */
3114 public char[] toCharArray() {
3115 // Cannot use Arrays.copyOf because of class initialization order issues
3116 char[] result = new char[value.length];
3117 System.arraycopy(value, 0, result, 0, value.length);
3118 return result;
3119 }
3120
3121 /**
3122 * Returns a formatted string using the specified format string and
3123 * arguments.
3124 *
3125 * <p> The locale always used is the one returned by {@link
3126 * java.util.Locale#getDefault() Locale.getDefault()}.
3127 *
3128 * @param format
3129 * A <a href="../util/Formatter.html#syntax">format string</a>
3130 *
3131 * @param args
3132 * Arguments referenced by the format specifiers in the format
3133 * string. If there are more arguments than format specifiers, the
3134 * extra arguments are ignored. The number of arguments is
3135 * variable and may be zero. The maximum number of arguments is
3136 * limited by the maximum dimension of a Java array as defined by
3137 * <cite>The Java™ Virtual Machine Specification</cite>.
3138 * The behaviour on a
3139 * {@code null} argument depends on the <a
3140 * href="../util/Formatter.html#syntax">conversion</a>.
3141 *
3142 * @throws java.util.IllegalFormatException
3143 * If a format string contains an illegal syntax, a format
3144 * specifier that is incompatible with the given arguments,
3145 * insufficient arguments given the format string, or other
3146 * illegal conditions. For specification of all possible
3147 * formatting errors, see the <a
3148 * href="../util/Formatter.html#detail">Details</a> section of the
3149 * formatter class specification.
3150 *
3151 * @return A formatted string
3152 *
3153 * @see java.util.Formatter
3154 * @since 1.5
3155 */
3156 public static String format(String format, Object... args) {
3157 return new Formatter().format(format, args).toString();
3158 }
3159
3160 /**
3161 * Returns a formatted string using the specified locale, format string,
3162 * and arguments.
3163 *
3164 * @param l
3165 * The {@linkplain java.util.Locale locale} to apply during
3166 * formatting. If {@code l} is {@code null} then no localization
3167 * is applied.
3168 *
3169 * @param format
3170 * A <a href="../util/Formatter.html#syntax">format string</a>
3171 *
3172 * @param args
3173 * Arguments referenced by the format specifiers in the format
3174 * string. If there are more arguments than format specifiers, the
3175 * extra arguments are ignored. The number of arguments is
3176 * variable and may be zero. The maximum number of arguments is
3177 * limited by the maximum dimension of a Java array as defined by
3178 * <cite>The Java™ Virtual Machine Specification</cite>.
3179 * The behaviour on a
3180 * {@code null} argument depends on the
3181 * <a href="../util/Formatter.html#syntax">conversion</a>.
3182 *
3183 * @throws java.util.IllegalFormatException
3184 * If a format string contains an illegal syntax, a format
3185 * specifier that is incompatible with the given arguments,
3186 * insufficient arguments given the format string, or other
3187 * illegal conditions. For specification of all possible
3188 * formatting errors, see the <a
3189 * href="../util/Formatter.html#detail">Details</a> section of the
3190 * formatter class specification
3191 *
3192 * @return A formatted string
3193 *
3194 * @see java.util.Formatter
3195 * @since 1.5
3196 */
3197 public static String format(Locale l, String format, Object... args) {
3198 return new Formatter(l).format(format, args).toString();
3199 }
3200
3201 /**
3202 * Returns the string representation of the {@code Object} argument.
3203 *
3204 * @param obj an {@code Object}.
3205 * @return if the argument is {@code null}, then a string equal to
3206 * {@code "null"}; otherwise, the value of
3207 * {@code obj.toString()} is returned.
3208 * @see java.lang.Object#toString()
3209 */
3210 public static String valueOf(Object obj) {
3211 return (obj == null) ? "null" : obj.toString();
3212 }
3213
3214 /**
3215 * Returns the string representation of the {@code char} array
3216 * argument. The contents of the character array are copied; subsequent
3217 * modification of the character array does not affect the returned
3218 * string.
3219 *
3220 * @param data the character array.
3221 * @return a {@code String} that contains the characters of the
3222 * character array.
3223 */
3224 public static String valueOf(char data[]) {
3225 return new String(data);
3226 }
3227
3228 /**
3229 * Returns the string representation of a specific subarray of the
3230 * {@code char} array argument.
3231 * <p>
3232 * The {@code offset} argument is the index of the first
3233 * character of the subarray. The {@code count} argument
3234 * specifies the length of the subarray. The contents of the subarray
3235 * are copied; subsequent modification of the character array does not
3236 * affect the returned string.
3237 *
3238 * @param data the character array.
3239 * @param offset initial offset of the subarray.
3240 * @param count length of the subarray.
3241 * @return a {@code String} that contains the characters of the
3242 * specified subarray of the character array.
3243 * @exception IndexOutOfBoundsException if {@code offset} is
3244 * negative, or {@code count} is negative, or
3245 * {@code offset+count} is larger than
3246 * {@code data.length}.
3247 */
3248 public static String valueOf(char data[], int offset, int count) {
3249 return new String(data, offset, count);
3250 }
3251
3252 /**
3253 * Equivalent to {@link #valueOf(char[], int, int)}.
3254 *
3255 * @param data the character array.
3256 * @param offset initial offset of the subarray.
3257 * @param count length of the subarray.
3258 * @return a {@code String} that contains the characters of the
3259 * specified subarray of the character array.
3260 * @exception IndexOutOfBoundsException if {@code offset} is
3261 * negative, or {@code count} is negative, or
3262 * {@code offset+count} is larger than
3263 * {@code data.length}.
3264 */
3265 public static String copyValueOf(char data[], int offset, int count) {
3266 return new String(data, offset, count);
3267 }
3268
3269 /**
3270 * Equivalent to {@link #valueOf(char[])}.
3271 *
3272 * @param data the character array.
3273 * @return a {@code String} that contains the characters of the
3274 * character array.
3275 */
3276 public static String copyValueOf(char data[]) {
3277 return new String(data);
3278 }
3279
3280 /**
3281 * Returns the string representation of the {@code boolean} argument.
3282 *
3283 * @param b a {@code boolean}.
3284 * @return if the argument is {@code true}, a string equal to
3285 * {@code "true"} is returned; otherwise, a string equal to
3286 * {@code "false"} is returned.
3287 */
3288 public static String valueOf(boolean b) {
3289 return b ? "true" : "false";
3290 }
3291
3292 /**
3293 * Returns the string representation of the {@code char}
3294 * argument.
3295 *
3296 * @param c a {@code char}.
3297 * @return a string of length {@code 1} containing
3298 * as its single character the argument {@code c}.
3299 */
3300 public static String valueOf(char c) {
3301 return new String(new char[]{c}, true);
3302 }
3303
3304 /**
3305 * Returns the string representation of the {@code int} argument.
3306 * <p>
3307 * The representation is exactly the one returned by the
3308 * {@code Integer.toString} method of one argument.
3309 *
3310 * @param i an {@code int}.
3311 * @return a string representation of the {@code int} argument.
3312 * @see java.lang.Integer#toString(int, int)
3313 */
3314 public static String valueOf(int i) {
3315 return Integer.toString(i);
3316 }
3317
3318 /**
3319 * Returns the string representation of the {@code long} argument.
3320 * <p>
3321 * The representation is exactly the one returned by the
3322 * {@code Long.toString} method of one argument.
3323 *
3324 * @param l a {@code long}.
3325 * @return a string representation of the {@code long} argument.
3326 * @see java.lang.Long#toString(long)
3327 */
3328 public static String valueOf(long l) {
3329 return Long.toString(l);
3330 }
3331
3332 /**
3333 * Returns the string representation of the {@code float} argument.
3334 * <p>
3335 * The representation is exactly the one returned by the
3336 * {@code Float.toString} method of one argument.
3337 *
3338 * @param f a {@code float}.
3339 * @return a string representation of the {@code float} argument.
3340 * @see java.lang.Float#toString(float)
3341 */
3342 public static String valueOf(float f) {
3343 return Float.toString(f);
3344 }
3345
3346 /**
3347 * Returns the string representation of the {@code double} argument.
3348 * <p>
3349 * The representation is exactly the one returned by the
3350 * {@code Double.toString} method of one argument.
3351 *
3352 * @param d a {@code double}.
3353 * @return a string representation of the {@code double} argument.
3354 * @see java.lang.Double#toString(double)
3355 */
3356 public static String valueOf(double d) {
3357 return Double.toString(d);
3358 }
3359
3360 /**
3361 * Returns a canonical representation for the string object.
3362 * <p>
3363 * A pool of strings, initially empty, is maintained privately by the
3364 * class {@code String}.
3365 * <p>
3366 * When the intern method is invoked, if the pool already contains a
3367 * string equal to this {@code String} object as determined by
3368 * the {@link #equals(Object)} method, then the string from the pool is
3369 * returned. Otherwise, this {@code String} object is added to the
3370 * pool and a reference to this {@code String} object is returned.
3371 * <p>
3372 * It follows that for any two strings {@code s} and {@code t},
3373 * {@code s.intern() == t.intern()} is {@code true}
3374 * if and only if {@code s.equals(t)} is {@code true}.
3375 * <p>
3376 * All literal strings and string-valued constant expressions are
3377 * interned. String literals are defined in section 3.10.5 of the
3378 * <cite>The Java™ Language Specification</cite>.
3379 *
3380 * @return a string that has the same contents as this string, but is
3381 * guaranteed to be from a pool of unique strings.
3382 */
3383 public native String intern();
3384 }