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
46 /**
47 * The {@code String} class represents character strings. All
48 * string literals in Java programs, such as {@code "abc"}, are
49 * implemented as instances of this class.
50 * <p>
51 * Strings are constant; their values cannot be changed after they
52 * are created. String buffers support mutable strings.
53 * Because String objects are immutable they can be shared. For example:
54 * <blockquote><pre>
55 * String str = "abc";
56 * </pre></blockquote><p>
57 * is equivalent to:
58 * <blockquote><pre>
59 * char data[] = {'a', 'b', 'c'};
60 * String str = new String(data);
61 * </pre></blockquote><p>
62 * Here are some more examples of how strings can be used:
63 * <blockquote><pre>
64 * System.out.println("abc");
65 * String cde = "cde";
66 * System.out.println("abc" + cde);
67 * String c = "abc".substring(2,3);
68 * String d = cde.substring(1, 2);
69 * </pre></blockquote>
70 * <p>
71 * The class {@code String} includes methods for examining
72 * individual characters of the sequence, for comparing strings, for
73 * searching strings, for extracting substrings, and for creating a
74 * copy of a string with all characters translated to uppercase or to
75 * lowercase. Case mapping is based on the Unicode Standard version
76 * specified by the {@link java.lang.Character Character} class.
77 * <p>
78 * The Java language provides special support for the string
79 * concatenation operator ( + ), and for conversion of
80 * other objects to strings. String concatenation is implemented
81 * through the {@code StringBuilder}(or {@code StringBuffer})
82 * class and its {@code append} method.
83 * String conversions are implemented through the method
84 * {@code toString}, defined by {@code Object} and
85 * inherited by all classes in Java. For additional information on
86 * string concatenation and conversion, see Gosling, Joy, and Steele,
87 * <i>The Java Language Specification</i>.
88 *
89 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
90 * or method in this class will cause a {@link NullPointerException} to be
91 * thrown.
92 *
93 * <p>A {@code String} represents a string in the UTF-16 format
94 * in which <em>supplementary characters</em> are represented by <em>surrogate
95 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
96 * Character Representations</a> in the {@code Character} class for
97 * more information).
98 * Index values refer to {@code char} code units, so a supplementary
99 * character uses two positions in a {@code String}.
100 * <p>The {@code String} class provides methods for dealing with
101 * Unicode code points (i.e., characters), in addition to those for
102 * dealing with Unicode code units (i.e., {@code char} values).
103 *
104 * @author Lee Boynton
105 * @author Arthur van Hoff
106 * @author Martin Buchholz
107 * @author Ulf Zibis
108 * @see java.lang.Object#toString()
109 * @see java.lang.StringBuffer
110 * @see java.lang.StringBuilder
111 * @see java.nio.charset.Charset
112 * @since 1.0
113 */
114
115 public final class String
116 implements java.io.Serializable, Comparable<String>, CharSequence {
117 /** The value is used for character storage. */
118 private final char value[];
119
120 /** Cache the hash code for the string */
121 private int hash; // Default to 0
122
123 /** use serialVersionUID from JDK 1.0.2 for interoperability */
124 private static final long serialVersionUID = -6849794470754667710L;
125
126 /**
127 * Class String is special cased within the Serialization Stream Protocol.
128 *
129 * A String instance is written into an ObjectOutputStream according to
130 * <a href="{@docRoot}/../platform/serialization/spec/output.html">
131 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
132 */
133 private static final ObjectStreamField[] serialPersistentFields =
134 new ObjectStreamField[0];
135
136 /**
137 * Initializes a newly created {@code String} object so that it represents
138 * an empty character sequence. Note that use of this constructor is
139 * unnecessary since Strings are immutable.
140 */
141 public String() {
142 this.value = "".value;
143 }
144
145 /**
146 * Initializes a newly created {@code String} object so that it represents
147 * the same sequence of characters as the argument; in other words, the
148 * newly created string is a copy of the argument string. Unless an
149 * explicit copy of {@code original} is needed, use of this constructor is
150 * unnecessary since Strings are immutable.
151 *
152 * @param original
153 * A {@code String}
154 */
155 public String(String original) {
156 this.value = original.value;
157 this.hash = original.hash;
158 }
159
160 /**
161 * Allocates a new {@code String} so that it represents the sequence of
162 * characters currently contained in the character array argument. The
163 * contents of the character array are copied; subsequent modification of
164 * the character array does not affect the newly created string.
165 *
166 * @param value
167 * The initial value of the string
168 */
169 public String(char value[]) {
170 this.value = Arrays.copyOf(value, value.length);
171 }
172
173 /**
174 * Allocates a new {@code String} that contains characters from a subarray
175 * of the character array argument. The {@code offset} argument is the
176 * index of the first character of the subarray and the {@code count}
177 * argument specifies the length of the subarray. The contents of the
178 * subarray are copied; subsequent modification of the character array does
179 * not affect the newly created string.
180 *
181 * @param value
182 * Array that is the source of characters
183 *
184 * @param offset
185 * The initial offset
186 *
187 * @param count
188 * The length
189 *
190 * @throws IndexOutOfBoundsException
191 * If {@code offset} is negative, {@code count} is negative, or
192 * {@code offset} is greater than {@code value.length - count}
193 */
194 public String(char value[], int offset, int count) {
195 if (offset < 0) {
196 throw new StringIndexOutOfBoundsException(offset);
197 }
198 if (count <= 0) {
199 if (count < 0) {
200 throw new StringIndexOutOfBoundsException(count);
201 }
202 if (offset <= value.length) {
203 this.value = "".value;
204 return;
205 }
206 }
207 // Note: offset or count might be near -1>>>1.
208 if (offset > value.length - count) {
209 throw new StringIndexOutOfBoundsException(offset + count);
210 }
211 this.value = Arrays.copyOfRange(value, offset, offset+count);
212 }
213
214 /**
215 * Allocates a new {@code String} that contains characters from a subarray
216 * of the <a href="Character.html#unicode">Unicode code point</a> array
217 * argument. The {@code offset} argument is the index of the first code
218 * point of the subarray and the {@code count} argument specifies the
219 * length of the subarray. The contents of the subarray are converted to
220 * {@code char}s; subsequent modification of the {@code int} array does not
221 * affect the newly created string.
222 *
223 * @param codePoints
224 * Array that is the source of Unicode code points
225 *
226 * @param offset
227 * The initial offset
228 *
229 * @param count
230 * The length
231 *
232 * @throws IllegalArgumentException
233 * If any invalid Unicode code point is found in {@code
234 * codePoints}
235 *
236 * @throws IndexOutOfBoundsException
237 * If {@code offset} is negative, {@code count} is negative, or
238 * {@code offset} is greater than {@code codePoints.length - count}
239 *
240 * @since 1.5
241 */
242 public String(int[] codePoints, int offset, int count) {
243 if (offset < 0) {
244 throw new StringIndexOutOfBoundsException(offset);
245 }
246 if (count <= 0) {
247 if (count < 0) {
248 throw new StringIndexOutOfBoundsException(count);
249 }
250 if (offset <= codePoints.length) {
251 this.value = "".value;
252 return;
253 }
254 }
255 // Note: offset or count might be near -1>>>1.
256 if (offset > codePoints.length - count) {
257 throw new StringIndexOutOfBoundsException(offset + count);
258 }
259
260 final int end = offset + count;
261
262 // Pass 1: Compute precise size of char[]
263 int n = count;
264 for (int i = offset; i < end; i++) {
265 int c = codePoints[i];
266 if (Character.isBmpCodePoint(c))
267 continue;
268 else if (Character.isValidCodePoint(c))
269 n++;
270 else throw new IllegalArgumentException(Integer.toString(c));
271 }
272
273 // Pass 2: Allocate and fill in char[]
274 final char[] v = new char[n];
275
276 for (int i = offset, j = 0; i < end; i++, j++) {
277 int c = codePoints[i];
278 if (Character.isBmpCodePoint(c))
279 v[j] = (char)c;
280 else
281 Character.toSurrogates(c, v, j++);
282 }
283
284 this.value = v;
285 }
286
287 /**
288 * Allocates a new {@code String} constructed from a subarray of an array
289 * of 8-bit integer values.
290 *
291 * <p> The {@code offset} argument is the index of the first byte of the
292 * subarray, and the {@code count} argument specifies the length of the
293 * subarray.
294 *
295 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
296 * specified in the method above.
297 *
298 * @deprecated This method does not properly convert bytes into characters.
299 * As of JDK 1.1, the preferred way to do this is via the
300 * {@code String} constructors that take a {@link
301 * java.nio.charset.Charset}, charset name, or that use the platform's
302 * default charset.
303 *
304 * @param ascii
305 * The bytes to be converted to characters
306 *
307 * @param hibyte
308 * The top 8 bits of each 16-bit Unicode code unit
309 *
310 * @param offset
311 * The initial offset
312 * @param count
313 * The length
314 *
315 * @throws IndexOutOfBoundsException
316 * If {@code offset} is negative, {@code count} is negative, or
317 * {@code offset} is greater than {@code ascii.length - count}
318 *
319 * @see #String(byte[], int)
320 * @see #String(byte[], int, int, java.lang.String)
321 * @see #String(byte[], int, int, java.nio.charset.Charset)
322 * @see #String(byte[], int, int)
323 * @see #String(byte[], java.lang.String)
324 * @see #String(byte[], java.nio.charset.Charset)
325 * @see #String(byte[])
326 */
327 @Deprecated
328 public String(byte ascii[], int hibyte, int offset, int count) {
329 checkBounds(ascii, offset, count);
330 char[] value = new char[count];
331
332 if (hibyte == 0) {
333 for (int i = count; i-- > 0;) {
334 value[i] = (char)(ascii[i + offset] & 0xff);
335 }
336 } else {
337 hibyte <<= 8;
338 for (int i = count; i-- > 0;) {
339 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff));
340 }
341 }
342 this.value = value;
343 }
344
345 /**
346 * Allocates a new {@code String} containing characters constructed from
347 * an array of 8-bit integer values. Each character <i>c</i>in the
348 * resulting string is constructed from the corresponding component
349 * <i>b</i> in the byte array such that:
350 *
351 * <blockquote><pre>
352 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
353 * | (<b><i>b</i></b> & 0xff))
354 * </pre></blockquote>
355 *
356 * @deprecated This method does not properly convert bytes into
357 * characters. As of JDK 1.1, the preferred way to do this is via the
358 * {@code String} constructors that take a {@link
359 * java.nio.charset.Charset}, charset name, or that use the platform's
360 * default charset.
361 *
362 * @param ascii
363 * The bytes to be converted to characters
364 *
365 * @param hibyte
366 * The top 8 bits of each 16-bit Unicode code unit
367 *
368 * @see #String(byte[], int, int, java.lang.String)
369 * @see #String(byte[], int, int, java.nio.charset.Charset)
370 * @see #String(byte[], int, int)
371 * @see #String(byte[], java.lang.String)
372 * @see #String(byte[], java.nio.charset.Charset)
373 * @see #String(byte[])
374 */
375 @Deprecated
376 public String(byte ascii[], int hibyte) {
377 this(ascii, hibyte, 0, ascii.length);
378 }
379
380 /* Common private utility method used to bounds check the byte array
381 * and requested offset & length values used by the String(byte[],..)
382 * constructors.
383 */
384 private static void checkBounds(byte[] bytes, int offset, int length) {
385 if (length < 0)
386 throw new StringIndexOutOfBoundsException(length);
387 if (offset < 0)
388 throw new StringIndexOutOfBoundsException(offset);
389 if (offset > bytes.length - length)
390 throw new StringIndexOutOfBoundsException(offset + length);
391 }
392
393 /**
394 * Constructs a new {@code String} by decoding the specified subarray of
395 * bytes using the specified charset. The length of the new {@code String}
396 * is a function of the charset, and hence may not be equal to the length
397 * of the subarray.
398 *
399 * <p> The behavior of this constructor when the given bytes are not valid
400 * in the given charset is unspecified. The {@link
401 * java.nio.charset.CharsetDecoder} class should be used when more control
402 * over the decoding process is required.
403 *
404 * @param bytes
405 * The bytes to be decoded into characters
406 *
407 * @param offset
408 * The index of the first byte to decode
409 *
410 * @param length
411 * The number of bytes to decode
412
413 * @param charsetName
414 * The name of a supported {@linkplain java.nio.charset.Charset
415 * charset}
416 *
417 * @throws UnsupportedEncodingException
418 * If the named charset is not supported
419 *
420 * @throws IndexOutOfBoundsException
421 * If {@code offset} is negative, {@code length} is negative, or
422 * {@code offset} is greater than {@code bytes.length - length}
423 *
424 * @since 1.1
425 */
426 public String(byte bytes[], int offset, int length, String charsetName)
427 throws UnsupportedEncodingException {
428 if (charsetName == null)
429 throw new NullPointerException("charsetName");
430 checkBounds(bytes, offset, length);
431 this.value = StringCoding.decode(charsetName, bytes, offset, length);
432 }
433
434 /**
435 * Constructs a new {@code String} by decoding the specified subarray of
436 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
437 * The length of the new {@code String} is a function of the charset, and
438 * hence may not be equal to the length of the subarray.
439 *
440 * <p> This method always replaces malformed-input and unmappable-character
441 * sequences with this charset's default replacement string. The {@link
442 * java.nio.charset.CharsetDecoder} class should be used when more control
443 * over the decoding process is required.
444 *
445 * @param bytes
446 * The bytes to be decoded into characters
447 *
448 * @param offset
449 * The index of the first byte to decode
450 *
451 * @param length
452 * The number of bytes to decode
453 *
454 * @param charset
455 * The {@linkplain java.nio.charset.Charset charset} to be used to
456 * decode the {@code bytes}
457 *
458 * @throws IndexOutOfBoundsException
459 * If {@code offset} is negative, {@code length} is negative, or
460 * {@code offset} is greater than {@code bytes.length - length}
461 *
462 * @since 1.6
463 */
464 public String(byte bytes[], int offset, int length, Charset charset) {
465 if (charset == null)
466 throw new NullPointerException("charset");
467 checkBounds(bytes, offset, length);
468 this.value = StringCoding.decode(charset, bytes, offset, length);
469 }
470
471 /**
472 * Constructs a new {@code String} by decoding the specified array of bytes
473 * using the specified {@linkplain java.nio.charset.Charset charset}. The
474 * length of the new {@code String} is a function of the charset, and hence
475 * may not be equal to the length of the byte array.
476 *
477 * <p> The behavior of this constructor when the given bytes are not valid
478 * in the given charset is unspecified. The {@link
479 * java.nio.charset.CharsetDecoder} class should be used when more control
480 * over the decoding process is required.
481 *
482 * @param bytes
483 * The bytes to be decoded into characters
484 *
485 * @param charsetName
486 * The name of a supported {@linkplain java.nio.charset.Charset
487 * charset}
488 *
489 * @throws UnsupportedEncodingException
490 * If the named charset is not supported
491 *
492 * @since 1.1
493 */
494 public String(byte bytes[], String charsetName)
495 throws UnsupportedEncodingException {
496 this(bytes, 0, bytes.length, charsetName);
497 }
498
499 /**
500 * Constructs a new {@code String} by decoding the specified array of
501 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
502 * The length of the new {@code String} is a function of the charset, and
503 * hence may not be equal to the length of the byte array.
504 *
505 * <p> This method always replaces malformed-input and unmappable-character
506 * sequences with this charset's default replacement string. The {@link
507 * java.nio.charset.CharsetDecoder} class should be used when more control
508 * over the decoding process is required.
509 *
510 * @param bytes
511 * The bytes to be decoded into characters
512 *
513 * @param charset
514 * The {@linkplain java.nio.charset.Charset charset} to be used to
515 * decode the {@code bytes}
516 *
517 * @since 1.6
518 */
519 public String(byte bytes[], Charset charset) {
520 this(bytes, 0, bytes.length, charset);
521 }
522
523 /**
524 * Constructs a new {@code String} by decoding the specified subarray of
525 * bytes using the platform's default charset. The length of the new
526 * {@code String} is a function of the charset, and hence may not be equal
527 * to the length of the subarray.
528 *
529 * <p> The behavior of this constructor when the given bytes are not valid
530 * in the default charset is unspecified. The {@link
531 * java.nio.charset.CharsetDecoder} class should be used when more control
532 * over the decoding process is required.
533 *
534 * @param bytes
535 * The bytes to be decoded into characters
536 *
537 * @param offset
538 * The index of the first byte to decode
539 *
540 * @param length
541 * The number of bytes to decode
542 *
543 * @throws IndexOutOfBoundsException
544 * If {@code offset} is negative, {@code length} is negative, or
545 * {@code offset} is greater than {@code bytes.length - length}
546 *
547 * @since 1.1
548 */
549 public String(byte bytes[], int offset, int length) {
550 checkBounds(bytes, offset, length);
551 this.value = StringCoding.decode(bytes, offset, length);
552 }
553
554 /**
555 * Constructs a new {@code String} by decoding the specified array of bytes
556 * using the platform's default charset. The length of the new {@code
557 * String} is a function of the charset, and hence may not be equal to the
558 * length of the byte array.
559 *
560 * <p> The behavior of this constructor when the given bytes are not valid
561 * in the default charset is unspecified. The {@link
562 * java.nio.charset.CharsetDecoder} class should be used when more control
563 * over the decoding process is required.
564 *
565 * @param bytes
566 * The bytes to be decoded into characters
567 *
568 * @since 1.1
569 */
570 public String(byte bytes[]) {
571 this(bytes, 0, bytes.length);
572 }
573
574 /**
575 * Allocates a new string that contains the sequence of characters
576 * currently contained in the string buffer argument. The contents of the
577 * string buffer are copied; subsequent modification of the string buffer
578 * does not affect the newly created string.
579 *
580 * @param buffer
581 * A {@code StringBuffer}
582 */
583 public String(StringBuffer buffer) {
584 synchronized(buffer) {
585 this.value = Arrays.copyOf(buffer.getValue(), buffer.length());
586 }
587 }
588
589 /**
590 * Allocates a new string that contains the sequence of characters
591 * currently contained in the string builder argument. The contents of the
592 * string builder are copied; subsequent modification of the string builder
593 * does not affect the newly created string.
594 *
595 * <p> This constructor is provided to ease migration to {@code
596 * StringBuilder}. Obtaining a string from a string builder via the {@code
597 * toString} method is likely to run faster and is generally preferred.
598 *
599 * @param builder
600 * A {@code StringBuilder}
601 *
602 * @since 1.5
603 */
604 public String(StringBuilder builder) {
605 this.value = Arrays.copyOf(builder.getValue(), builder.length());
606 }
607
608 /*
609 * Package private constructor which shares value array for speed.
610 * this constructor is always expected to be called with share==true.
611 * a separate constructor is needed because we already have a public
612 * String(char[]) constructor that makes a copy of the given char[].
613 */
614 String(char[] value, boolean share) {
615 // assert share : "unshared not supported";
616 this.value = value;
617 }
618
619 /**
620 * Returns the length of this string.
621 * The length is equal to the number of <a href="Character.html#unicode">Unicode
622 * code units</a> in the string.
623 *
624 * @return the length of the sequence of characters represented by this
625 * object.
626 */
627 public int length() {
628 return value.length;
629 }
630
631 /**
632 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
633 *
634 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
635 * {@code false}
636 *
637 * @since 1.6
638 */
639 public boolean isEmpty() {
640 return value.length == 0;
641 }
642
643 /**
644 * Returns the {@code char} value at the
645 * specified index. An index ranges from {@code 0} to
646 * {@code length() - 1}. The first {@code char} value of the sequence
647 * is at index {@code 0}, the next at index {@code 1},
648 * and so on, as for array indexing.
649 *
650 * <p>If the {@code char} value specified by the index is a
651 * <a href="Character.html#unicode">surrogate</a>, the surrogate
652 * value is returned.
653 *
654 * @param index the index of the {@code char} value.
655 * @return the {@code char} value at the specified index of this string.
656 * The first {@code char} value is at index {@code 0}.
657 * @exception IndexOutOfBoundsException if the {@code index}
658 * argument is negative or not less than the length of this
659 * string.
660 */
661 public char charAt(int index) {
662 if ((index < 0) || (index >= value.length)) {
663 throw new StringIndexOutOfBoundsException(index);
664 }
665 return value[index];
666 }
667
668 /**
669 * Returns the character (Unicode code point) at the specified
670 * index. The index refers to {@code char} values
671 * (Unicode code units) and ranges from {@code 0} to
672 * {@link #length()}{@code - 1}.
673 *
674 * <p> If the {@code char} value specified at the given index
675 * is in the high-surrogate range, the following index is less
676 * than the length of this {@code String}, and the
677 * {@code char} value at the following index is in the
678 * low-surrogate range, then the supplementary code point
679 * corresponding to this surrogate pair is returned. Otherwise,
680 * the {@code char} value at the given index is returned.
681 *
682 * @param index the index to the {@code char} values
683 * @return the code point value of the character at the
684 * {@code index}
685 * @exception IndexOutOfBoundsException if the {@code index}
686 * argument is negative or not less than the length of this
687 * string.
688 * @since 1.5
689 */
690 public int codePointAt(int index) {
691 if ((index < 0) || (index >= value.length)) {
692 throw new StringIndexOutOfBoundsException(index);
693 }
694 return Character.codePointAtImpl(value, index, value.length);
695 }
696
697 /**
698 * Returns the character (Unicode code point) before the specified
699 * index. The index refers to {@code char} values
700 * (Unicode code units) and ranges from {@code 1} to {@link
701 * CharSequence#length() length}.
702 *
703 * <p> If the {@code char} value at {@code (index - 1)}
704 * is in the low-surrogate range, {@code (index - 2)} is not
705 * negative, and the {@code char} value at {@code (index -
706 * 2)} is in the high-surrogate range, then the
707 * supplementary code point value of the surrogate pair is
708 * returned. If the {@code char} value at {@code index -
709 * 1} is an unpaired low-surrogate or a high-surrogate, the
710 * surrogate value is returned.
711 *
712 * @param index the index following the code point that should be returned
713 * @return the Unicode code point value before the given index.
714 * @exception IndexOutOfBoundsException if the {@code index}
715 * argument is less than 1 or greater than the length
716 * of this string.
717 * @since 1.5
718 */
719 public int codePointBefore(int index) {
720 int i = index - 1;
721 if ((i < 0) || (i >= value.length)) {
722 throw new StringIndexOutOfBoundsException(index);
723 }
724 return Character.codePointBeforeImpl(value, index, 0);
725 }
726
727 /**
728 * Returns the number of Unicode code points in the specified text
729 * range of this {@code String}. The text range begins at the
730 * specified {@code beginIndex} and extends to the
731 * {@code char} at index {@code endIndex - 1}. Thus the
732 * length (in {@code char}s) of the text range is
733 * {@code endIndex-beginIndex}. Unpaired surrogates within
734 * the text range count as one code point each.
735 *
736 * @param beginIndex the index to the first {@code char} of
737 * the text range.
738 * @param endIndex the index after the last {@code char} of
739 * the text range.
740 * @return the number of Unicode code points in the specified text
741 * range
742 * @exception IndexOutOfBoundsException if the
743 * {@code beginIndex} is negative, or {@code endIndex}
744 * is larger than the length of this {@code String}, or
745 * {@code beginIndex} is larger than {@code endIndex}.
746 * @since 1.5
747 */
748 public int codePointCount(int beginIndex, int endIndex) {
749 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) {
750 throw new IndexOutOfBoundsException();
751 }
752 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex);
753 }
754
755 /**
756 * Returns the index within this {@code String} that is
757 * offset from the given {@code index} by
758 * {@code codePointOffset} code points. Unpaired surrogates
759 * within the text range given by {@code index} and
760 * {@code codePointOffset} count as one code point each.
761 *
762 * @param index the index to be offset
763 * @param codePointOffset the offset in code points
764 * @return the index within this {@code String}
765 * @exception IndexOutOfBoundsException if {@code index}
766 * is negative or larger then the length of this
767 * {@code String}, or if {@code codePointOffset} is positive
768 * and the substring starting with {@code index} has fewer
769 * than {@code codePointOffset} code points,
770 * or if {@code codePointOffset} is negative and the substring
771 * before {@code index} has fewer than the absolute value
772 * of {@code codePointOffset} code points.
773 * @since 1.5
774 */
775 public int offsetByCodePoints(int index, int codePointOffset) {
776 if (index < 0 || index > value.length) {
777 throw new IndexOutOfBoundsException();
778 }
779 return Character.offsetByCodePointsImpl(value, 0, value.length,
780 index, codePointOffset);
781 }
782
783 /**
784 * Copy characters from this string into dst starting at dstBegin.
785 * This method doesn't perform any range checking.
786 */
787 void getChars(char dst[], int dstBegin) {
788 System.arraycopy(value, 0, dst, dstBegin, value.length);
789 }
790
791 /**
792 * Copies characters from this string into the destination character
793 * array.
794 * <p>
795 * The first character to be copied is at index {@code srcBegin};
796 * the last character to be copied is at index {@code srcEnd-1}
797 * (thus the total number of characters to be copied is
798 * {@code srcEnd-srcBegin}). The characters are copied into the
799 * subarray of {@code dst} starting at index {@code dstBegin}
800 * and ending at index:
801 * <blockquote><pre>
802 * dstBegin + (srcEnd-srcBegin) - 1
803 * </pre></blockquote>
804 *
805 * @param srcBegin index of the first character in the string
806 * to copy.
807 * @param srcEnd index after the last character in the string
808 * to copy.
809 * @param dst the destination array.
810 * @param dstBegin the start offset in the destination array.
811 * @exception IndexOutOfBoundsException If any of the following
812 * is true:
813 * <ul><li>{@code srcBegin} is negative.
814 * <li>{@code srcBegin} is greater than {@code srcEnd}
815 * <li>{@code srcEnd} is greater than the length of this
816 * string
817 * <li>{@code dstBegin} is negative
818 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
819 * {@code dst.length}</ul>
820 */
821 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
822 if (srcBegin < 0) {
823 throw new StringIndexOutOfBoundsException(srcBegin);
824 }
825 if (srcEnd > value.length) {
826 throw new StringIndexOutOfBoundsException(srcEnd);
827 }
828 if (srcBegin > srcEnd) {
829 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
830 }
831 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin);
832 }
833
834 /**
835 * Copies characters from this string into the destination byte array. Each
836 * byte receives the 8 low-order bits of the corresponding character. The
837 * eight high-order bits of each character are not copied and do not
838 * participate in the transfer in any way.
839 *
840 * <p> The first character to be copied is at index {@code srcBegin}; the
841 * last character to be copied is at index {@code srcEnd-1}. The total
842 * number of characters to be copied is {@code srcEnd-srcBegin}. The
843 * characters, converted to bytes, are copied into the subarray of {@code
844 * dst} starting at index {@code dstBegin} and ending at index:
845 *
846 * <blockquote><pre>
847 * dstBegin + (srcEnd-srcBegin) - 1
848 * </pre></blockquote>
849 *
850 * @deprecated This method does not properly convert characters into
851 * bytes. As of JDK 1.1, the preferred way to do this is via the
852 * {@link #getBytes()} method, which uses the platform's default charset.
853 *
854 * @param srcBegin
855 * Index of the first character in the string to copy
856 *
857 * @param srcEnd
858 * Index after the last character in the string to copy
859 *
860 * @param dst
861 * The destination array
862 *
863 * @param dstBegin
864 * The start offset in the destination array
865 *
866 * @throws IndexOutOfBoundsException
867 * If any of the following is true:
868 * <ul>
869 * <li> {@code srcBegin} is negative
870 * <li> {@code srcBegin} is greater than {@code srcEnd}
871 * <li> {@code srcEnd} is greater than the length of this String
872 * <li> {@code dstBegin} is negative
873 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
874 * dst.length}
875 * </ul>
876 */
877 @Deprecated
878 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
879 if (srcBegin < 0) {
880 throw new StringIndexOutOfBoundsException(srcBegin);
881 }
882 if (srcEnd > value.length) {
883 throw new StringIndexOutOfBoundsException(srcEnd);
884 }
885 if (srcBegin > srcEnd) {
886 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
887 }
888 Objects.requireNonNull(dst);
889
890 int j = dstBegin;
891 int n = srcEnd;
892 int i = srcBegin;
893 char[] val = value; /* avoid getfield opcode */
894
895 while (i < n) {
896 dst[j++] = (byte)val[i++];
897 }
898 }
899
900 /**
901 * Encodes this {@code String} into a sequence of bytes using the named
902 * charset, storing the result into a new byte array.
903 *
904 * <p> The behavior of this method when this string cannot be encoded in
905 * the given charset is unspecified. The {@link
906 * java.nio.charset.CharsetEncoder} class should be used when more control
907 * over the encoding process is required.
908 *
909 * @param charsetName
910 * The name of a supported {@linkplain java.nio.charset.Charset
911 * charset}
912 *
913 * @return The resultant byte array
914 *
915 * @throws UnsupportedEncodingException
916 * If the named charset is not supported
917 *
918 * @since 1.1
919 */
920 public byte[] getBytes(String charsetName)
921 throws UnsupportedEncodingException {
922 if (charsetName == null) throw new NullPointerException();
923 return StringCoding.encode(charsetName, value, 0, value.length);
924 }
925
926 /**
927 * Encodes this {@code String} into a sequence of bytes using the given
928 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
929 * new byte array.
930 *
931 * <p> This method always replaces malformed-input and unmappable-character
932 * sequences with this charset's default replacement byte array. The
933 * {@link java.nio.charset.CharsetEncoder} class should be used when more
934 * control over the encoding process is required.
935 *
936 * @param charset
937 * The {@linkplain java.nio.charset.Charset} to be used to encode
938 * the {@code String}
939 *
940 * @return The resultant byte array
941 *
942 * @since 1.6
943 */
944 public byte[] getBytes(Charset charset) {
945 if (charset == null) throw new NullPointerException();
946 return StringCoding.encode(charset, value, 0, value.length);
947 }
948
949 /**
950 * Encodes this {@code String} into a sequence of bytes using the
951 * platform's default charset, storing the result into a new byte array.
952 *
953 * <p> The behavior of this method when this string cannot be encoded in
954 * the default charset is unspecified. The {@link
955 * java.nio.charset.CharsetEncoder} class should be used when more control
956 * over the encoding process is required.
957 *
958 * @return The resultant byte array
959 *
960 * @since 1.1
961 */
962 public byte[] getBytes() {
963 return StringCoding.encode(value, 0, value.length);
964 }
965
966 /**
967 * Compares this string to the specified object. The result is {@code
968 * true} if and only if the argument is not {@code null} and is a {@code
969 * String} object that represents the same sequence of characters as this
970 * object.
971 *
972 * @param anObject
973 * The object to compare this {@code String} against
974 *
975 * @return {@code true} if the given object represents a {@code String}
976 * equivalent to this string, {@code false} otherwise
977 *
978 * @see #compareTo(String)
979 * @see #equalsIgnoreCase(String)
980 */
981 public boolean equals(Object anObject) {
982 if (this == anObject) {
983 return true;
984 }
985 if (anObject instanceof String) {
986 char[] v1 = value;
987 char[] v2 = ((String)anObject).value;
988 int n = v1.length;
989 if (n == v2.length) {
990 int i = 0;
991 while (n-- != 0) {
992 if (v1[i] != v2[i])
993 return false;
994 i++;
995 }
996 return true;
997 }
998 }
999 return false;
1000 }
1001
1002 /**
1003 * Compares this string to the specified {@code StringBuffer}. The result
1004 * is {@code true} if and only if this {@code String} represents the same
1005 * sequence of characters as the specified {@code StringBuffer}. This method
1006 * synchronizes on the {@code StringBuffer}.
1007 *
1008 * @param sb
1009 * The {@code StringBuffer} to compare this {@code String} against
1010 *
1011 * @return {@code true} if this {@code String} represents the same
1012 * sequence of characters as the specified {@code StringBuffer},
1013 * {@code false} otherwise
1014 *
1015 * @since 1.4
1016 */
1017 public boolean contentEquals(StringBuffer sb) {
1018 return contentEquals((CharSequence)sb);
1019 }
1020
1021 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1022 char[] v1 = value;
1023 char[] v2 = sb.getValue();
1024 int n = v1.length;
1025 if (n != v2.length) {
1026 return false;
1027 }
1028 for (int i = 0; i < n; i++) {
1029 if (v1[i] != v2[i]) {
1030 return false;
1031 }
1032 }
1033 return true;
1034 }
1035
1036 /**
1037 * Compares this string to the specified {@code CharSequence}. The
1038 * result is {@code true} if and only if this {@code String} represents the
1039 * same sequence of char values as the specified sequence. Note that if the
1040 * {@code CharSequence} is a {@code StringBuffer} then the method
1041 * synchronizes on it.
1042 *
1043 * @param cs
1044 * The sequence to compare this {@code String} against
1045 *
1046 * @return {@code true} if this {@code String} represents the same
1047 * sequence of char values as the specified sequence, {@code
1048 * false} otherwise
1049 *
1050 * @since 1.5
1051 */
1052 public boolean contentEquals(CharSequence cs) {
1053 // Argument is a StringBuffer, StringBuilder
1054 if (cs instanceof AbstractStringBuilder) {
1055 if (cs instanceof StringBuffer) {
1056 synchronized(cs) {
1057 return nonSyncContentEquals((AbstractStringBuilder)cs);
1058 }
1059 } else {
1060 return nonSyncContentEquals((AbstractStringBuilder)cs);
1061 }
1062 }
1063 // Argument is a String
1064 if (cs instanceof String) {
1065 return equals(cs);
1066 }
1067 // Argument is a generic CharSequence
1068 char[] v1 = value;
1069 int n = v1.length;
1070 if (n != cs.length()) {
1071 return false;
1072 }
1073 for (int i = 0; i < n; i++) {
1074 if (v1[i] != cs.charAt(i)) {
1075 return false;
1076 }
1077 }
1078 return true;
1079 }
1080
1081 /**
1082 * Compares this {@code String} to another {@code String}, ignoring case
1083 * considerations. Two strings are considered equal ignoring case if they
1084 * are of the same length and corresponding characters in the two strings
1085 * are equal ignoring case.
1086 *
1087 * <p> Two characters {@code c1} and {@code c2} are considered the same
1088 * ignoring case if at least one of the following is true:
1089 * <ul>
1090 * <li> The two characters are the same (as compared by the
1091 * {@code ==} operator)
1092 * <li> Applying the method {@link
1093 * java.lang.Character#toUpperCase(char)} to each character
1094 * produces the same result
1095 * <li> Applying the method {@link
1096 * java.lang.Character#toLowerCase(char)} to each character
1097 * produces the same result
1098 * </ul>
1099 *
1100 * @param anotherString
1101 * The {@code String} to compare this {@code String} against
1102 *
1103 * @return {@code true} if the argument is not {@code null} and it
1104 * represents an equivalent {@code String} ignoring case; {@code
1105 * false} otherwise
1106 *
1107 * @see #equals(Object)
1108 */
1109 public boolean equalsIgnoreCase(String anotherString) {
1110 return (this == anotherString) ? true
1111 : (anotherString != null)
1112 && (anotherString.value.length == value.length)
1113 && regionMatches(true, 0, anotherString, 0, value.length);
1114 }
1115
1116 /**
1117 * Compares two strings lexicographically.
1118 * The comparison is based on the Unicode value of each character in
1119 * the strings. The character sequence represented by this
1120 * {@code String} object is compared lexicographically to the
1121 * character sequence represented by the argument string. The result is
1122 * a negative integer if this {@code String} object
1123 * lexicographically precedes the argument string. The result is a
1124 * positive integer if this {@code String} object lexicographically
1125 * follows the argument string. The result is zero if the strings
1126 * are equal; {@code compareTo} returns {@code 0} exactly when
1127 * the {@link #equals(Object)} method would return {@code true}.
1128 * <p>
1129 * This is the definition of lexicographic ordering. If two strings are
1130 * different, then either they have different characters at some index
1131 * that is a valid index for both strings, or their lengths are different,
1132 * or both. If they have different characters at one or more index
1133 * positions, let <i>k</i> be the smallest such index; then the string
1134 * whose character at position <i>k</i> has the smaller value, as
1135 * determined by using the < operator, lexicographically precedes the
1136 * other string. In this case, {@code compareTo} returns the
1137 * difference of the two character values at position {@code k} in
1138 * the two string -- that is, the value:
1139 * <blockquote><pre>
1140 * this.charAt(k)-anotherString.charAt(k)
1141 * </pre></blockquote>
1142 * If there is no index position at which they differ, then the shorter
1143 * string lexicographically precedes the longer string. In this case,
1144 * {@code compareTo} returns the difference of the lengths of the
1145 * strings -- that is, the value:
1146 * <blockquote><pre>
1147 * this.length()-anotherString.length()
1148 * </pre></blockquote>
1149 *
1150 * @param anotherString the {@code String} to be compared.
1151 * @return the value {@code 0} if the argument string is equal to
1152 * this string; a value less than {@code 0} if this string
1153 * is lexicographically less than the string argument; and a
1154 * value greater than {@code 0} if this string is
1155 * lexicographically greater than the string argument.
1156 */
1157 public int compareTo(String anotherString) {
1158 char[] v1 = value;
1159 char[] v2 = anotherString.value;
1160 int len1 = v1.length;
1161 int len2 = v2.length;
1162 int lim = Math.min(len1, len2);
1163
1164 for (int k = 0; k < lim; k++) {
1165 char c1 = v1[k];
1166 char c2 = v2[k];
1167 if (c1 != c2) {
1168 return c1 - c2;
1169 }
1170 }
1171 return len1 - len2;
1172 }
1173
1174 /**
1175 * A Comparator that orders {@code String} objects as by
1176 * {@code compareToIgnoreCase}. This comparator is serializable.
1177 * <p>
1178 * Note that this Comparator does <em>not</em> take locale into account,
1179 * and will result in an unsatisfactory ordering for certain locales.
1180 * The java.text package provides <em>Collators</em> to allow
1181 * locale-sensitive ordering.
1182 *
1183 * @see java.text.Collator#compare(String, String)
1184 * @since 1.2
1185 */
1186 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1187 = new CaseInsensitiveComparator();
1188 private static class CaseInsensitiveComparator
1189 implements Comparator<String>, java.io.Serializable {
1190 // use serialVersionUID from JDK 1.2.2 for interoperability
1191 private static final long serialVersionUID = 8575799808933029326L;
1192
1193 public int compare(String s1, String s2) {
1194 int n1 = s1.length();
1195 int n2 = s2.length();
1196 int min = Math.min(n1, n2);
1197 for (int i = 0; i < min; i++) {
1198 char c1 = s1.charAt(i);
1199 char c2 = s2.charAt(i);
1200 if (c1 != c2) {
1201 c1 = Character.toUpperCase(c1);
1202 c2 = Character.toUpperCase(c2);
1203 if (c1 != c2) {
1204 c1 = Character.toLowerCase(c1);
1205 c2 = Character.toLowerCase(c2);
1206 if (c1 != c2) {
1207 // No overflow because of numeric promotion
1208 return c1 - c2;
1209 }
1210 }
1211 }
1212 }
1213 return n1 - n2;
1214 }
1215
1216 /** Replaces the de-serialized object. */
1217 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1218 }
1219
1220 /**
1221 * Compares two strings lexicographically, ignoring case
1222 * differences. This method returns an integer whose sign is that of
1223 * calling {@code compareTo} with normalized versions of the strings
1224 * where case differences have been eliminated by calling
1225 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1226 * each character.
1227 * <p>
1228 * Note that this method does <em>not</em> take locale into account,
1229 * and will result in an unsatisfactory ordering for certain locales.
1230 * The java.text package provides <em>collators</em> to allow
1231 * locale-sensitive ordering.
1232 *
1233 * @param str the {@code String} to be compared.
1234 * @return a negative integer, zero, or a positive integer as the
1235 * specified String is greater than, equal to, or less
1236 * than this String, ignoring case considerations.
1237 * @see java.text.Collator#compare(String, String)
1238 * @since 1.2
1239 */
1240 public int compareToIgnoreCase(String str) {
1241 return CASE_INSENSITIVE_ORDER.compare(this, str);
1242 }
1243
1244 /**
1245 * Tests if two string regions are equal.
1246 * <p>
1247 * A substring of this {@code String} object is compared to a substring
1248 * of the argument other. The result is true if these substrings
1249 * represent identical character sequences. The substring of this
1250 * {@code String} object to be compared begins at index {@code toffset}
1251 * and has length {@code len}. The substring of other to be compared
1252 * begins at index {@code ooffset} and has length {@code len}. The
1253 * result is {@code false} if and only if at least one of the following
1254 * is true:
1255 * <ul><li>{@code toffset} is negative.
1256 * <li>{@code ooffset} is negative.
1257 * <li>{@code toffset+len} is greater than the length of this
1258 * {@code String} object.
1259 * <li>{@code ooffset+len} is greater than the length of the other
1260 * argument.
1261 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1262 * such that:
1263 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1264 * <i>k</i>{@code )}
1265 * </ul>
1266 *
1267 * @param toffset the starting offset of the subregion in this string.
1268 * @param other the string argument.
1269 * @param ooffset the starting offset of the subregion in the string
1270 * argument.
1271 * @param len the number of characters to compare.
1272 * @return {@code true} if the specified subregion of this string
1273 * exactly matches the specified subregion of the string argument;
1274 * {@code false} otherwise.
1275 */
1276 public boolean regionMatches(int toffset, String other, int ooffset,
1277 int len) {
1278 char[] ta = value;
1279 int to = toffset;
1280 char[] pa = other.value;
1281 int po = ooffset;
1282 // Note: toffset, ooffset, or len might be near -1>>>1.
1283 if ((ooffset < 0) || (toffset < 0)
1284 || (toffset > (long)ta.length - len)
1285 || (ooffset > (long)pa.length - len)) {
1286 return false;
1287 }
1288 while (len-- > 0) {
1289 if (ta[to++] != pa[po++]) {
1290 return false;
1291 }
1292 }
1293 return true;
1294 }
1295
1296 /**
1297 * Tests if two string regions are equal.
1298 * <p>
1299 * A substring of this {@code String} object is compared to a substring
1300 * of the argument {@code other}. The result is {@code true} if these
1301 * substrings represent character sequences that are the same, ignoring
1302 * case if and only if {@code ignoreCase} is true. The substring of
1303 * this {@code String} object to be compared begins at index
1304 * {@code toffset} and has length {@code len}. The substring of
1305 * {@code other} to be compared begins at index {@code ooffset} and
1306 * has length {@code len}. The result is {@code false} if and only if
1307 * at least one of the following is true:
1308 * <ul><li>{@code toffset} is negative.
1309 * <li>{@code ooffset} is negative.
1310 * <li>{@code toffset+len} is greater than the length of this
1311 * {@code String} object.
1312 * <li>{@code ooffset+len} is greater than the length of the other
1313 * argument.
1314 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1315 * integer <i>k</i> less than {@code len} such that:
1316 * <blockquote><pre>
1317 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1318 * </pre></blockquote>
1319 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1320 * integer <i>k</i> less than {@code len} such that:
1321 * <blockquote><pre>
1322 * Character.toLowerCase(this.charAt(toffset+k)) !=
1323 Character.toLowerCase(other.charAt(ooffset+k))
1324 * </pre></blockquote>
1325 * and:
1326 * <blockquote><pre>
1327 * Character.toUpperCase(this.charAt(toffset+k)) !=
1328 * Character.toUpperCase(other.charAt(ooffset+k))
1329 * </pre></blockquote>
1330 * </ul>
1331 *
1332 * @param ignoreCase if {@code true}, ignore case when comparing
1333 * characters.
1334 * @param toffset the starting offset of the subregion in this
1335 * string.
1336 * @param other the string argument.
1337 * @param ooffset the starting offset of the subregion in the string
1338 * argument.
1339 * @param len the number of characters to compare.
1340 * @return {@code true} if the specified subregion of this string
1341 * matches the specified subregion of the string argument;
1342 * {@code false} otherwise. Whether the matching is exact
1343 * or case insensitive depends on the {@code ignoreCase}
1344 * argument.
1345 */
1346 public boolean regionMatches(boolean ignoreCase, int toffset,
1347 String other, int ooffset, int len) {
1348 char[] ta = value;
1349 int to = toffset;
1350 char[] pa = other.value;
1351 int po = ooffset;
1352 // Note: toffset, ooffset, or len might be near -1>>>1.
1353 if ((ooffset < 0) || (toffset < 0)
1354 || (toffset > (long)ta.length - len)
1355 || (ooffset > (long)pa.length - len)) {
1356 return false;
1357 }
1358 while (len-- > 0) {
1359 char c1 = ta[to++];
1360 char c2 = pa[po++];
1361 if (c1 == c2) {
1362 continue;
1363 }
1364 if (ignoreCase) {
1365 // If characters don't match but case may be ignored,
1366 // try converting both characters to uppercase.
1367 // If the results match, then the comparison scan should
1368 // continue.
1369 char u1 = Character.toUpperCase(c1);
1370 char u2 = Character.toUpperCase(c2);
1371 if (u1 == u2) {
1372 continue;
1373 }
1374 // Unfortunately, conversion to uppercase does not work properly
1375 // for the Georgian alphabet, which has strange rules about case
1376 // conversion. So we need to make one last check before
1377 // exiting.
1378 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1379 continue;
1380 }
1381 }
1382 return false;
1383 }
1384 return true;
1385 }
1386
1387 /**
1388 * Tests if the substring of this string beginning at the
1389 * specified index starts with the specified prefix.
1390 *
1391 * @param prefix the prefix.
1392 * @param toffset where to begin looking in this string.
1393 * @return {@code true} if the character sequence represented by the
1394 * argument is a prefix of the substring of this object starting
1395 * at index {@code toffset}; {@code false} otherwise.
1396 * The result is {@code false} if {@code toffset} is
1397 * negative or greater than the length of this
1398 * {@code String} object; otherwise the result is the same
1399 * as the result of the expression
1400 * <pre>
1401 * this.substring(toffset).startsWith(prefix)
1402 * </pre>
1403 */
1404 public boolean startsWith(String prefix, int toffset) {
1405 char[] ta = value;
1406 int to = toffset;
1407 char[] pa = prefix.value;
1408 int po = 0;
1409 int pc = pa.length;
1410 // Note: toffset might be near -1>>>1.
1411 if ((toffset < 0) || (toffset > ta.length - pc)) {
1412 return false;
1413 }
1414 while (--pc >= 0) {
1415 if (ta[to++] != pa[po++]) {
1416 return false;
1417 }
1418 }
1419 return true;
1420 }
1421
1422 /**
1423 * Tests if this string starts with the specified prefix.
1424 *
1425 * @param prefix the prefix.
1426 * @return {@code true} if the character sequence represented by the
1427 * argument is a prefix of the character sequence represented by
1428 * this string; {@code false} otherwise.
1429 * Note also that {@code true} will be returned if the
1430 * argument is an empty string or is equal to this
1431 * {@code String} object as determined by the
1432 * {@link #equals(Object)} method.
1433 * @since 1.0
1434 */
1435 public boolean startsWith(String prefix) {
1436 return startsWith(prefix, 0);
1437 }
1438
1439 /**
1440 * Tests if this string ends with the specified suffix.
1441 *
1442 * @param suffix the suffix.
1443 * @return {@code true} if the character sequence represented by the
1444 * argument is a suffix of the character sequence represented by
1445 * this object; {@code false} otherwise. Note that the
1446 * result will be {@code true} if the argument is the
1447 * empty string or is equal to this {@code String} object
1448 * as determined by the {@link #equals(Object)} method.
1449 */
1450 public boolean endsWith(String suffix) {
1451 return startsWith(suffix, value.length - suffix.value.length);
1452 }
1453
1454 /**
1455 * Returns a hash code for this string. The hash code for a
1456 * {@code String} object is computed as
1457 * <blockquote><pre>
1458 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1459 * </pre></blockquote>
1460 * using {@code int} arithmetic, where {@code s[i]} is the
1461 * <i>i</i>th character of the string, {@code n} is the length of
1462 * the string, and {@code ^} indicates exponentiation.
1463 * (The hash value of the empty string is zero.)
1464 *
1465 * @return a hash code value for this object.
1466 */
1467 public int hashCode() {
1468 int h = hash;
1469 if (h == 0) {
1470 for (char v : value) {
1471 h = 31 * h + v;
1472 }
1473 hash = h;
1474 }
1475 return h;
1476 }
1477
1478 /**
1479 * Returns the index within this string of the first occurrence of
1480 * the specified character. If a character with value
1481 * {@code ch} occurs in the character sequence represented by
1482 * this {@code String} object, then the index (in Unicode
1483 * code units) of the first such occurrence is returned. For
1484 * values of {@code ch} in the range from 0 to 0xFFFF
1485 * (inclusive), this is the smallest value <i>k</i> such that:
1486 * <blockquote><pre>
1487 * this.charAt(<i>k</i>) == ch
1488 * </pre></blockquote>
1489 * is true. For other values of {@code ch}, it is the
1490 * smallest value <i>k</i> such that:
1491 * <blockquote><pre>
1492 * this.codePointAt(<i>k</i>) == ch
1493 * </pre></blockquote>
1494 * is true. In either case, if no such character occurs in this
1495 * string, then {@code -1} is returned.
1496 *
1497 * @param ch a character (Unicode code point).
1498 * @return the index of the first occurrence of the character in the
1499 * character sequence represented by this object, or
1500 * {@code -1} if the character does not occur.
1501 */
1502 public int indexOf(int ch) {
1503 return indexOf(ch, 0);
1504 }
1505
1506 /**
1507 * Returns the index within this string of the first occurrence of the
1508 * specified character, starting the search at the specified index.
1509 * <p>
1510 * If a character with value {@code ch} occurs in the
1511 * character sequence represented by this {@code String}
1512 * object at an index no smaller than {@code fromIndex}, then
1513 * the index of the first such occurrence is returned. For values
1514 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1515 * this is the smallest value <i>k</i> such that:
1516 * <blockquote><pre>
1517 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1518 * </pre></blockquote>
1519 * is true. For other values of {@code ch}, it is the
1520 * smallest value <i>k</i> such that:
1521 * <blockquote><pre>
1522 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1523 * </pre></blockquote>
1524 * is true. In either case, if no such character occurs in this
1525 * string at or after position {@code fromIndex}, then
1526 * {@code -1} is returned.
1527 *
1528 * <p>
1529 * There is no restriction on the value of {@code fromIndex}. If it
1530 * is negative, it has the same effect as if it were zero: this entire
1531 * string may be searched. If it is greater than the length of this
1532 * string, it has the same effect as if it were equal to the length of
1533 * this string: {@code -1} is returned.
1534 *
1535 * <p>All indices are specified in {@code char} values
1536 * (Unicode code units).
1537 *
1538 * @param ch a character (Unicode code point).
1539 * @param fromIndex the index to start the search from.
1540 * @return the index of the first occurrence of the character in the
1541 * character sequence represented by this object that is greater
1542 * than or equal to {@code fromIndex}, or {@code -1}
1543 * if the character does not occur.
1544 */
1545 public int indexOf(int ch, int fromIndex) {
1546 final int max = value.length;
1547 if (fromIndex < 0) {
1548 fromIndex = 0;
1549 } else if (fromIndex >= max) {
1550 // Note: fromIndex might be near -1>>>1.
1551 return -1;
1552 }
1553
1554 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1555 // handle most cases here (ch is a BMP code point or a
1556 // negative value (invalid code point))
1557 final char[] value = this.value;
1558 for (int i = fromIndex; i < max; i++) {
1559 if (value[i] == ch) {
1560 return i;
1561 }
1562 }
1563 return -1;
1564 } else {
1565 return indexOfSupplementary(ch, fromIndex);
1566 }
1567 }
1568
1569 /**
1570 * Handles (rare) calls of indexOf with a supplementary character.
1571 */
1572 private int indexOfSupplementary(int ch, int fromIndex) {
1573 if (Character.isValidCodePoint(ch)) {
1574 final char[] value = this.value;
1575 final char hi = Character.highSurrogate(ch);
1576 final char lo = Character.lowSurrogate(ch);
1577 final int max = value.length - 1;
1578 for (int i = fromIndex; i < max; i++) {
1579 if (value[i] == hi && value[i + 1] == lo) {
1580 return i;
1581 }
1582 }
1583 }
1584 return -1;
1585 }
1586
1587 /**
1588 * Returns the index within this string of the last occurrence of
1589 * the specified character. For values of {@code ch} in the
1590 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1591 * units) returned is the largest value <i>k</i> such that:
1592 * <blockquote><pre>
1593 * this.charAt(<i>k</i>) == ch
1594 * </pre></blockquote>
1595 * is true. For other values of {@code ch}, it is the
1596 * largest value <i>k</i> such that:
1597 * <blockquote><pre>
1598 * this.codePointAt(<i>k</i>) == ch
1599 * </pre></blockquote>
1600 * is true. In either case, if no such character occurs in this
1601 * string, then {@code -1} is returned. The
1602 * {@code String} is searched backwards starting at the last
1603 * character.
1604 *
1605 * @param ch a character (Unicode code point).
1606 * @return the index of the last occurrence of the character in the
1607 * character sequence represented by this object, or
1608 * {@code -1} if the character does not occur.
1609 */
1610 public int lastIndexOf(int ch) {
1611 return lastIndexOf(ch, value.length - 1);
1612 }
1613
1614 /**
1615 * Returns the index within this string of the last occurrence of
1616 * the specified character, searching backward starting at the
1617 * specified index. For values of {@code ch} in the range
1618 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1619 * value <i>k</i> such that:
1620 * <blockquote><pre>
1621 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1622 * </pre></blockquote>
1623 * is true. For other values of {@code ch}, it is the
1624 * largest value <i>k</i> such that:
1625 * <blockquote><pre>
1626 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1627 * </pre></blockquote>
1628 * is true. In either case, if no such character occurs in this
1629 * string at or before position {@code fromIndex}, then
1630 * {@code -1} is returned.
1631 *
1632 * <p>All indices are specified in {@code char} values
1633 * (Unicode code units).
1634 *
1635 * @param ch a character (Unicode code point).
1636 * @param fromIndex the index to start the search from. There is no
1637 * restriction on the value of {@code fromIndex}. If it is
1638 * greater than or equal to the length of this string, it has
1639 * the same effect as if it were equal to one less than the
1640 * length of this string: this entire string may be searched.
1641 * If it is negative, it has the same effect as if it were -1:
1642 * -1 is returned.
1643 * @return the index of the last occurrence of the character in the
1644 * character sequence represented by this object that is less
1645 * than or equal to {@code fromIndex}, or {@code -1}
1646 * if the character does not occur before that point.
1647 */
1648 public int lastIndexOf(int ch, int fromIndex) {
1649 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1650 // handle most cases here (ch is a BMP code point or a
1651 // negative value (invalid code point))
1652 final char[] value = this.value;
1653 int i = Math.min(fromIndex, value.length - 1);
1654 for (; i >= 0; i--) {
1655 if (value[i] == ch) {
1656 return i;
1657 }
1658 }
1659 return -1;
1660 } else {
1661 return lastIndexOfSupplementary(ch, fromIndex);
1662 }
1663 }
1664
1665 /**
1666 * Handles (rare) calls of lastIndexOf with a supplementary character.
1667 */
1668 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1669 if (Character.isValidCodePoint(ch)) {
1670 final char[] value = this.value;
1671 char hi = Character.highSurrogate(ch);
1672 char lo = Character.lowSurrogate(ch);
1673 int i = Math.min(fromIndex, value.length - 2);
1674 for (; i >= 0; i--) {
1675 if (value[i] == hi && value[i + 1] == lo) {
1676 return i;
1677 }
1678 }
1679 }
1680 return -1;
1681 }
1682
1683 /**
1684 * Returns the index within this string of the first occurrence of the
1685 * specified substring.
1686 *
1687 * <p>The returned index is the smallest value {@code k} for which:
1688 * <pre>{@code
1689 * this.startsWith(str, k)
1690 * }</pre>
1691 * If no such value of {@code k} exists, then {@code -1} is returned.
1692 *
1693 * @param str the substring to search for.
1694 * @return the index of the first occurrence of the specified substring,
1695 * or {@code -1} if there is no such occurrence.
1696 */
1697 public int indexOf(String str) {
1698 return indexOf(str, 0);
1699 }
1700
1701 /**
1702 * Returns the index within this string of the first occurrence of the
1703 * specified substring, starting at the specified index.
1704 *
1705 * <p>The returned index is the smallest value {@code k} for which:
1706 * <pre>{@code
1707 * k >= Math.min(fromIndex, this.length()) &&
1708 * this.startsWith(str, k)
1709 * }</pre>
1710 * If no such value of {@code k} exists, then {@code -1} is returned.
1711 *
1712 * @param str the substring to search for.
1713 * @param fromIndex the index from which to start the search.
1714 * @return the index of the first occurrence of the specified substring,
1715 * starting at the specified index,
1716 * or {@code -1} if there is no such occurrence.
1717 */
1718 public int indexOf(String str, int fromIndex) {
1719 return indexOf(value, 0, value.length,
1720 str.value, 0, str.value.length, fromIndex);
1721 }
1722
1723 /**
1724 * Code shared by String and AbstractStringBuilder to do searches. The
1725 * source is the character array being searched, and the target
1726 * is the string being searched for.
1727 *
1728 * @param source the characters being searched.
1729 * @param sourceOffset offset of the source string.
1730 * @param sourceCount count of the source string.
1731 * @param target the characters being searched for.
1732 * @param fromIndex the index to begin searching from.
1733 */
1734 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1735 String target, int fromIndex) {
1736 return indexOf(source, sourceOffset, sourceCount,
1737 target.value, 0, target.value.length,
1738 fromIndex);
1739 }
1740
1741 /**
1742 * Code shared by String and StringBuffer to do searches. The
1743 * source is the character array being searched, and the target
1744 * is the string being searched for.
1745 *
1746 * @param source the characters being searched.
1747 * @param sourceOffset offset of the source string.
1748 * @param sourceCount count of the source string.
1749 * @param target the characters being searched for.
1750 * @param targetOffset offset of the target string.
1751 * @param targetCount count of the target string.
1752 * @param fromIndex the index to begin searching from.
1753 */
1754 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1755 char[] target, int targetOffset, int targetCount,
1756 int fromIndex) {
1757 if (fromIndex >= sourceCount) {
1758 return (targetCount == 0 ? sourceCount : -1);
1759 }
1760 if (fromIndex < 0) {
1761 fromIndex = 0;
1762 }
1763 if (targetCount == 0) {
1764 return fromIndex;
1765 }
1766
1767 char first = target[targetOffset];
1768 int max = sourceOffset + (sourceCount - targetCount);
1769
1770 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1771 /* Look for first character. */
1772 if (source[i] != first) {
1773 while (++i <= max && source[i] != first);
1774 }
1775
1776 /* Found first character, now look at the rest of v2 */
1777 if (i <= max) {
1778 int j = i + 1;
1779 int end = j + targetCount - 1;
1780 for (int k = targetOffset + 1; j < end && source[j]
1781 == target[k]; j++, k++);
1782
1783 if (j == end) {
1784 /* Found whole string. */
1785 return i - sourceOffset;
1786 }
1787 }
1788 }
1789 return -1;
1790 }
1791
1792 /**
1793 * Returns the index within this string of the last occurrence of the
1794 * specified substring. The last occurrence of the empty string ""
1795 * is considered to occur at the index value {@code this.length()}.
1796 *
1797 * <p>The returned index is the largest value {@code k} for which:
1798 * <pre>{@code
1799 * this.startsWith(str, k)
1800 * }</pre>
1801 * If no such value of {@code k} exists, then {@code -1} is returned.
1802 *
1803 * @param str the substring to search for.
1804 * @return the index of the last occurrence of the specified substring,
1805 * or {@code -1} if there is no such occurrence.
1806 */
1807 public int lastIndexOf(String str) {
1808 return lastIndexOf(str, value.length);
1809 }
1810
1811 /**
1812 * Returns the index within this string of the last occurrence of the
1813 * specified substring, searching backward starting at the specified index.
1814 *
1815 * <p>The returned index is the largest value {@code k} for which:
1816 * <pre>{@code
1817 * k <= Math.min(fromIndex, this.length()) &&
1818 * this.startsWith(str, k)
1819 * }</pre>
1820 * If no such value of {@code k} exists, then {@code -1} is returned.
1821 *
1822 * @param str the substring to search for.
1823 * @param fromIndex the index to start the search from.
1824 * @return the index of the last occurrence of the specified substring,
1825 * searching backward from the specified index,
1826 * or {@code -1} if there is no such occurrence.
1827 */
1828 public int lastIndexOf(String str, int fromIndex) {
1829 return lastIndexOf(value, 0, value.length,
1830 str.value, 0, str.value.length, fromIndex);
1831 }
1832
1833 /**
1834 * Code shared by String and AbstractStringBuilder to do searches. The
1835 * source is the character array being searched, and the target
1836 * is the string being searched for.
1837 *
1838 * @param source the characters being searched.
1839 * @param sourceOffset offset of the source string.
1840 * @param sourceCount count of the source string.
1841 * @param target the characters being searched for.
1842 * @param fromIndex the index to begin searching from.
1843 */
1844 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1845 String target, int fromIndex) {
1846 return lastIndexOf(source, sourceOffset, sourceCount,
1847 target.value, 0, target.value.length,
1848 fromIndex);
1849 }
1850
1851 /**
1852 * Code shared by String and StringBuffer to do searches. The
1853 * source is the character array being searched, and the target
1854 * is the string being searched for.
1855 *
1856 * @param source the characters being searched.
1857 * @param sourceOffset offset of the source string.
1858 * @param sourceCount count of the source string.
1859 * @param target the characters being searched for.
1860 * @param targetOffset offset of the target string.
1861 * @param targetCount count of the target string.
1862 * @param fromIndex the index to begin searching from.
1863 */
1864 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1865 char[] target, int targetOffset, int targetCount,
1866 int fromIndex) {
1867 /*
1868 * Check arguments; return immediately where possible. For
1869 * consistency, don't check for null str.
1870 */
1871 int rightIndex = sourceCount - targetCount;
1872 if (fromIndex < 0) {
1873 return -1;
1874 }
1875 if (fromIndex > rightIndex) {
1876 fromIndex = rightIndex;
1877 }
1878 /* Empty string always matches. */
1879 if (targetCount == 0) {
1880 return fromIndex;
1881 }
1882
1883 int strLastIndex = targetOffset + targetCount - 1;
1884 char strLastChar = target[strLastIndex];
1885 int min = sourceOffset + targetCount - 1;
1886 int i = min + fromIndex;
1887
1888 startSearchForLastChar:
1889 while (true) {
1890 while (i >= min && source[i] != strLastChar) {
1891 i--;
1892 }
1893 if (i < min) {
1894 return -1;
1895 }
1896 int j = i - 1;
1897 int start = j - (targetCount - 1);
1898 int k = strLastIndex - 1;
1899
1900 while (j > start) {
1901 if (source[j--] != target[k--]) {
1902 i--;
1903 continue startSearchForLastChar;
1904 }
1905 }
1906 return start - sourceOffset + 1;
1907 }
1908 }
1909
1910 /**
1911 * Returns a string that is a substring of this string. The
1912 * substring begins with the character at the specified index and
1913 * extends to the end of this string. <p>
1914 * Examples:
1915 * <blockquote><pre>
1916 * "unhappy".substring(2) returns "happy"
1917 * "Harbison".substring(3) returns "bison"
1918 * "emptiness".substring(9) returns "" (an empty string)
1919 * </pre></blockquote>
1920 *
1921 * @param beginIndex the beginning index, inclusive.
1922 * @return the specified substring.
1923 * @exception IndexOutOfBoundsException if
1924 * {@code beginIndex} is negative or larger than the
1925 * length of this {@code String} object.
1926 */
1927 public String substring(int beginIndex) {
1928 if (beginIndex <= 0) {
1929 if (beginIndex < 0) {
1930 throw new StringIndexOutOfBoundsException(beginIndex);
1931 }
1932 return this;
1933 }
1934 int subLen = value.length - beginIndex;
1935 if (subLen < 0) {
1936 throw new StringIndexOutOfBoundsException(subLen);
1937 }
1938 return new String(value, beginIndex, subLen);
1939 }
1940
1941 /**
1942 * Returns a string that is a substring of this string. The
1943 * substring begins at the specified {@code beginIndex} and
1944 * extends to the character at index {@code endIndex - 1}.
1945 * Thus the length of the substring is {@code endIndex-beginIndex}.
1946 * <p>
1947 * Examples:
1948 * <blockquote><pre>
1949 * "hamburger".substring(4, 8) returns "urge"
1950 * "smiles".substring(1, 5) returns "mile"
1951 * </pre></blockquote>
1952 *
1953 * @param beginIndex the beginning index, inclusive.
1954 * @param endIndex the ending index, exclusive.
1955 * @return the specified substring.
1956 * @exception IndexOutOfBoundsException if the
1957 * {@code beginIndex} is negative, or
1958 * {@code endIndex} is larger than the length of
1959 * this {@code String} object, or
1960 * {@code beginIndex} is larger than
1961 * {@code endIndex}.
1962 */
1963 public String substring(int beginIndex, int endIndex) {
1964 if (beginIndex <= 0) {
1965 if (beginIndex < 0) {
1966 throw new StringIndexOutOfBoundsException(beginIndex);
1967 }
1968 if (endIndex == value.length) {
1969 return this;
1970 }
1971 }
1972 if (endIndex > value.length) {
1973 throw new StringIndexOutOfBoundsException(endIndex);
1974 }
1975 int subLen = endIndex - beginIndex;
1976 if (subLen < 0) {
1977 throw new StringIndexOutOfBoundsException(subLen);
1978 }
1979 return new String(value, beginIndex, subLen);
1980 }
1981
1982 /**
1983 * Returns a character sequence that is a subsequence of this sequence.
1984 *
1985 * <p> An invocation of this method of the form
1986 *
1987 * <blockquote><pre>
1988 * str.subSequence(begin, end)</pre></blockquote>
1989 *
1990 * behaves in exactly the same way as the invocation
1991 *
1992 * <blockquote><pre>
1993 * str.substring(begin, end)</pre></blockquote>
1994 *
1995 * @apiNote
1996 * This method is defined so that the {@code String} class can implement
1997 * the {@link CharSequence} interface.
1998 *
1999 * @param beginIndex the begin index, inclusive.
2000 * @param endIndex the end index, exclusive.
2001 * @return the specified subsequence.
2002 *
2003 * @throws IndexOutOfBoundsException
2004 * if {@code beginIndex} or {@code endIndex} is negative,
2005 * if {@code endIndex} is greater than {@code length()},
2006 * or if {@code beginIndex} is greater than {@code endIndex}
2007 *
2008 * @since 1.4
2009 * @spec JSR-51
2010 */
2011 public CharSequence subSequence(int beginIndex, int endIndex) {
2012 return this.substring(beginIndex, endIndex);
2013 }
2014
2015 /**
2016 * Concatenates the specified string to the end of this string.
2017 * <p>
2018 * If the length of the argument string is {@code 0}, then this
2019 * {@code String} object is returned. Otherwise, a
2020 * {@code String} object is returned that represents a character
2021 * sequence that is the concatenation of the character sequence
2022 * represented by this {@code String} object and the character
2023 * sequence represented by the argument string.<p>
2024 * Examples:
2025 * <blockquote><pre>
2026 * "cares".concat("s") returns "caress"
2027 * "to".concat("get").concat("her") returns "together"
2028 * </pre></blockquote>
2029 *
2030 * @param str the {@code String} that is concatenated to the end
2031 * of this {@code String}.
2032 * @return a string that represents the concatenation of this object's
2033 * characters followed by the string argument's characters.
2034 */
2035 public String concat(String str) {
2036 int otherLen = str.length();
2037 if (otherLen == 0) {
2038 return this;
2039 }
2040 int len = value.length;
2041 char[] buf = Arrays.copyOf(value, len + otherLen);
2042 str.getChars(buf, len);
2043 return new String(buf, true);
2044 }
2045
2046 /**
2047 * Returns a string resulting from replacing all occurrences of
2048 * {@code oldChar} in this string with {@code newChar}.
2049 * <p>
2050 * If the character {@code oldChar} does not occur in the
2051 * character sequence represented by this {@code String} object,
2052 * then a reference to this {@code String} object is returned.
2053 * Otherwise, a {@code String} object is returned that
2054 * represents a character sequence identical to the character sequence
2055 * represented by this {@code String} object, except that every
2056 * occurrence of {@code oldChar} is replaced by an occurrence
2057 * of {@code newChar}.
2058 * <p>
2059 * Examples:
2060 * <blockquote><pre>
2061 * "mesquite in your cellar".replace('e', 'o')
2062 * returns "mosquito in your collar"
2063 * "the war of baronets".replace('r', 'y')
2064 * returns "the way of bayonets"
2065 * "sparring with a purple porpoise".replace('p', 't')
2066 * returns "starring with a turtle tortoise"
2067 * "JonL".replace('q', 'x') returns "JonL" (no change)
2068 * </pre></blockquote>
2069 *
2070 * @param oldChar the old character.
2071 * @param newChar the new character.
2072 * @return a string derived from this string by replacing every
2073 * occurrence of {@code oldChar} with {@code newChar}.
2074 */
2075 public String replace(char oldChar, char newChar) {
2076 if (oldChar != newChar) {
2077 char[] val = value; /* avoid getfield opcode */
2078 int len = val.length;
2079 int i = -1;
2080
2081 while (++i < len) {
2082 if (val[i] == oldChar) {
2083 break;
2084 }
2085 }
2086 if (i < len) {
2087 char[] buf = new char[len];
2088 for (int j = 0; j < i; j++) {
2089 buf[j] = val[j];
2090 }
2091 while (i < len) {
2092 char c = val[i];
2093 buf[i] = (c == oldChar) ? newChar : c;
2094 i++;
2095 }
2096 return new String(buf, true);
2097 }
2098 }
2099 return this;
2100 }
2101
2102 /**
2103 * Tells whether or not this string matches the given <a
2104 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2105 *
2106 * <p> An invocation of this method of the form
2107 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2108 * same result as the expression
2109 *
2110 * <blockquote>
2111 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2112 * matches(<i>regex</i>, <i>str</i>)}
2113 * </blockquote>
2114 *
2115 * @param regex
2116 * the regular expression to which this string is to be matched
2117 *
2118 * @return {@code true} if, and only if, this string matches the
2119 * given regular expression
2120 *
2121 * @throws PatternSyntaxException
2122 * if the regular expression's syntax is invalid
2123 *
2124 * @see java.util.regex.Pattern
2125 *
2126 * @since 1.4
2127 * @spec JSR-51
2128 */
2129 public boolean matches(String regex) {
2130 return Pattern.matches(regex, this);
2131 }
2132
2133 /**
2134 * Returns true if and only if this string contains the specified
2135 * sequence of char values.
2136 *
2137 * @param s the sequence to search for
2138 * @return true if this string contains {@code s}, false otherwise
2139 * @since 1.5
2140 */
2141 public boolean contains(CharSequence s) {
2142 return indexOf(s.toString()) >= 0;
2143 }
2144
2145 /**
2146 * Replaces the first substring of this string that matches the given <a
2147 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2148 * given replacement.
2149 *
2150 * <p> An invocation of this method of the form
2151 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2152 * yields exactly the same result as the expression
2153 *
2154 * <blockquote>
2155 * <code>
2156 * {@link java.util.regex.Pattern}.{@link
2157 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2158 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2159 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2160 * </code>
2161 * </blockquote>
2162 *
2163 *<p>
2164 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2165 * replacement string may cause the results to be different than if it were
2166 * being treated as a literal replacement string; see
2167 * {@link java.util.regex.Matcher#replaceFirst}.
2168 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2169 * meaning of these characters, if desired.
2170 *
2171 * @param regex
2172 * the regular expression to which this string is to be matched
2173 * @param replacement
2174 * the string to be substituted for the first match
2175 *
2176 * @return The resulting {@code String}
2177 *
2178 * @throws PatternSyntaxException
2179 * if the regular expression's syntax is invalid
2180 *
2181 * @see java.util.regex.Pattern
2182 *
2183 * @since 1.4
2184 * @spec JSR-51
2185 */
2186 public String replaceFirst(String regex, String replacement) {
2187 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2188 }
2189
2190 /**
2191 * Replaces each substring of this string that matches the given <a
2192 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2193 * given replacement.
2194 *
2195 * <p> An invocation of this method of the form
2196 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2197 * yields exactly the same result as the expression
2198 *
2199 * <blockquote>
2200 * <code>
2201 * {@link java.util.regex.Pattern}.{@link
2202 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2203 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2204 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2205 * </code>
2206 * </blockquote>
2207 *
2208 *<p>
2209 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2210 * replacement string may cause the results to be different than if it were
2211 * being treated as a literal replacement string; see
2212 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2213 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2214 * meaning of these characters, if desired.
2215 *
2216 * @param regex
2217 * the regular expression to which this string is to be matched
2218 * @param replacement
2219 * the string to be substituted for each match
2220 *
2221 * @return The resulting {@code String}
2222 *
2223 * @throws PatternSyntaxException
2224 * if the regular expression's syntax is invalid
2225 *
2226 * @see java.util.regex.Pattern
2227 *
2228 * @since 1.4
2229 * @spec JSR-51
2230 */
2231 public String replaceAll(String regex, String replacement) {
2232 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2233 }
2234
2235 /**
2236 * Replaces each substring of this string that matches the literal target
2237 * sequence with the specified literal replacement sequence. The
2238 * replacement proceeds from the beginning of the string to the end, for
2239 * example, replacing "aa" with "b" in the string "aaa" will result in
2240 * "ba" rather than "ab".
2241 *
2242 * @param target The sequence of char values to be replaced
2243 * @param replacement The replacement sequence of char values
2244 * @return The resulting string
2245 * @since 1.5
2246 */
2247 public String replace(CharSequence target, CharSequence replacement) {
2248 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
2249 this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
2250 }
2251
2252 /**
2253 * Splits this string around matches of the given
2254 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2255 *
2256 * <p> The array returned by this method contains each substring of this
2257 * string that is terminated by another substring that matches the given
2258 * expression or is terminated by the end of the string. The substrings in
2259 * the array are in the order in which they occur in this string. If the
2260 * expression does not match any part of the input then the resulting array
2261 * has just one element, namely this string.
2262 *
2263 * <p> When there is a positive-width match at the beginning of this
2264 * string then an empty leading substring is included at the beginning
2265 * of the resulting array. A zero-width match at the beginning however
2266 * never produces such empty leading substring.
2267 *
2268 * <p> The {@code limit} parameter controls the number of times the
2269 * pattern is applied and therefore affects the length of the resulting
2270 * array. If the limit <i>n</i> is greater than zero then the pattern
2271 * will be applied at most <i>n</i> - 1 times, the array's
2272 * length will be no greater than <i>n</i>, and the array's last entry
2273 * will contain all input beyond the last matched delimiter. If <i>n</i>
2274 * is non-positive then the pattern will be applied as many times as
2275 * possible and the array can have any length. If <i>n</i> is zero then
2276 * the pattern will be applied as many times as possible, the array can
2277 * have any length, and trailing empty strings will be discarded.
2278 *
2279 * <p> The string {@code "boo:and:foo"}, for example, yields the
2280 * following results with these parameters:
2281 *
2282 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2283 * <tr>
2284 * <th>Regex</th>
2285 * <th>Limit</th>
2286 * <th>Result</th>
2287 * </tr>
2288 * <tr><td align=center>:</td>
2289 * <td align=center>2</td>
2290 * <td>{@code { "boo", "and:foo" }}</td></tr>
2291 * <tr><td align=center>:</td>
2292 * <td align=center>5</td>
2293 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2294 * <tr><td align=center>:</td>
2295 * <td align=center>-2</td>
2296 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2297 * <tr><td align=center>o</td>
2298 * <td align=center>5</td>
2299 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2300 * <tr><td align=center>o</td>
2301 * <td align=center>-2</td>
2302 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2303 * <tr><td align=center>o</td>
2304 * <td align=center>0</td>
2305 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2306 * </table></blockquote>
2307 *
2308 * <p> An invocation of this method of the form
2309 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2310 * yields the same result as the expression
2311 *
2312 * <blockquote>
2313 * <code>
2314 * {@link java.util.regex.Pattern}.{@link
2315 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2316 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2317 * </code>
2318 * </blockquote>
2319 *
2320 *
2321 * @param regex
2322 * the delimiting regular expression
2323 *
2324 * @param limit
2325 * the result threshold, as described above
2326 *
2327 * @return the array of strings computed by splitting this string
2328 * around matches of the given regular expression
2329 *
2330 * @throws PatternSyntaxException
2331 * if the regular expression's syntax is invalid
2332 *
2333 * @see java.util.regex.Pattern
2334 *
2335 * @since 1.4
2336 * @spec JSR-51
2337 */
2338 public String[] split(String regex, int limit) {
2339 /* fastpath if the regex is a
2340 (1)one-char String and this character is not one of the
2341 RegEx's meta characters ".$|()[{^?*+\\", or
2342 (2)two-char String and the first char is the backslash and
2343 the second is not the ascii digit or ascii letter.
2344 */
2345 char ch = 0;
2346 if (((regex.value.length == 1 &&
2347 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2348 (regex.length() == 2 &&
2349 regex.charAt(0) == '\\' &&
2350 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2351 ((ch-'a')|('z'-ch)) < 0 &&
2352 ((ch-'A')|('Z'-ch)) < 0)) &&
2353 (ch < Character.MIN_HIGH_SURROGATE ||
2354 ch > Character.MAX_LOW_SURROGATE))
2355 {
2356 int off = 0;
2357 int next = 0;
2358 boolean limited = limit > 0;
2359 ArrayList<String> list = new ArrayList<>();
2360 while ((next = indexOf(ch, off)) != -1) {
2361 if (!limited || list.size() < limit - 1) {
2362 list.add(substring(off, next));
2363 off = next + 1;
2364 } else { // last one
2365 //assert (list.size() == limit - 1);
2366 list.add(substring(off, value.length));
2367 off = value.length;
2368 break;
2369 }
2370 }
2371 // If no match was found, return this
2372 if (off == 0)
2373 return new String[]{this};
2374
2375 // Add remaining segment
2376 if (!limited || list.size() < limit)
2377 list.add(substring(off, value.length));
2378
2379 // Construct result
2380 int resultSize = list.size();
2381 if (limit == 0) {
2382 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2383 resultSize--;
2384 }
2385 }
2386 String[] result = new String[resultSize];
2387 return list.subList(0, resultSize).toArray(result);
2388 }
2389 return Pattern.compile(regex).split(this, limit);
2390 }
2391
2392 /**
2393 * Splits this string around matches of the given <a
2394 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2395 *
2396 * <p> This method works as if by invoking the two-argument {@link
2397 * #split(String, int) split} method with the given expression and a limit
2398 * argument of zero. Trailing empty strings are therefore not included in
2399 * the resulting array.
2400 *
2401 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2402 * results with these expressions:
2403 *
2404 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2405 * <tr>
2406 * <th>Regex</th>
2407 * <th>Result</th>
2408 * </tr>
2409 * <tr><td align=center>:</td>
2410 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2411 * <tr><td align=center>o</td>
2412 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2413 * </table></blockquote>
2414 *
2415 *
2416 * @param regex
2417 * the delimiting regular expression
2418 *
2419 * @return the array of strings computed by splitting this string
2420 * around matches of the given regular expression
2421 *
2422 * @throws PatternSyntaxException
2423 * if the regular expression's syntax is invalid
2424 *
2425 * @see java.util.regex.Pattern
2426 *
2427 * @since 1.4
2428 * @spec JSR-51
2429 */
2430 public String[] split(String regex) {
2431 return split(regex, 0);
2432 }
2433
2434 /**
2435 * Returns a new String composed of copies of the
2436 * {@code CharSequence elements} joined together with a copy of
2437 * the specified {@code delimiter}.
2438 *
2439 * <blockquote>For example,
2440 * <pre>{@code
2441 * String message = String.join("-", "Java", "is", "cool");
2442 * // message returned is: "Java-is-cool"
2443 * }</pre></blockquote>
2444 *
2445 * Note that if an element is null, then {@code "null"} is added.
2446 *
2447 * @param delimiter the delimiter that separates each element
2448 * @param elements the elements to join together.
2449 *
2450 * @return a new {@code String} that is composed of the {@code elements}
2451 * separated by the {@code delimiter}
2452 *
2453 * @throws NullPointerException If {@code delimiter} or {@code elements}
2454 * is {@code null}
2455 *
2456 * @see java.util.StringJoiner
2457 * @since 1.8
2458 */
2459 public static String join(CharSequence delimiter, CharSequence... elements) {
2460 Objects.requireNonNull(delimiter);
2461 Objects.requireNonNull(elements);
2462 // Number of elements not likely worth Arrays.stream overhead.
2463 StringJoiner joiner = new StringJoiner(delimiter);
2464 for (CharSequence cs: elements) {
2465 joiner.add(cs);
2466 }
2467 return joiner.toString();
2468 }
2469
2470 /**
2471 * Returns a new {@code String} composed of copies of the
2472 * {@code CharSequence elements} joined together with a copy of the
2473 * specified {@code delimiter}.
2474 *
2475 * <blockquote>For example,
2476 * <pre>{@code
2477 * List<String> strings = new LinkedList<>();
2478 * strings.add("Java");strings.add("is");
2479 * strings.add("cool");
2480 * String message = String.join(" ", strings);
2481 * //message returned is: "Java is cool"
2482 *
2483 * Set<String> strings = new LinkedHashSet<>();
2484 * strings.add("Java"); strings.add("is");
2485 * strings.add("very"); strings.add("cool");
2486 * String message = String.join("-", strings);
2487 * //message returned is: "Java-is-very-cool"
2488 * }</pre></blockquote>
2489 *
2490 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2491 *
2492 * @param delimiter a sequence of characters that is used to separate each
2493 * of the {@code elements} in the resulting {@code String}
2494 * @param elements an {@code Iterable} that will have its {@code elements}
2495 * joined together.
2496 *
2497 * @return a new {@code String} that is composed from the {@code elements}
2498 * argument
2499 *
2500 * @throws NullPointerException If {@code delimiter} or {@code elements}
2501 * is {@code null}
2502 *
2503 * @see #join(CharSequence,CharSequence...)
2504 * @see java.util.StringJoiner
2505 * @since 1.8
2506 */
2507 public static String join(CharSequence delimiter,
2508 Iterable<? extends CharSequence> elements) {
2509 Objects.requireNonNull(delimiter);
2510 Objects.requireNonNull(elements);
2511 StringJoiner joiner = new StringJoiner(delimiter);
2512 for (CharSequence cs: elements) {
2513 joiner.add(cs);
2514 }
2515 return joiner.toString();
2516 }
2517
2518 /**
2519 * Converts all of the characters in this {@code String} to lower
2520 * case using the rules of the given {@code Locale}. Case mapping is based
2521 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2522 * class. Since case mappings are not always 1:1 char mappings, the resulting
2523 * {@code String} may be a different length than the original {@code String}.
2524 * <p>
2525 * Examples of lowercase mappings are in the following table:
2526 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2527 * <tr>
2528 * <th>Language Code of Locale</th>
2529 * <th>Upper Case</th>
2530 * <th>Lower Case</th>
2531 * <th>Description</th>
2532 * </tr>
2533 * <tr>
2534 * <td>tr (Turkish)</td>
2535 * <td>\u0130</td>
2536 * <td>\u0069</td>
2537 * <td>capital letter I with dot above -> small letter i</td>
2538 * </tr>
2539 * <tr>
2540 * <td>tr (Turkish)</td>
2541 * <td>\u0049</td>
2542 * <td>\u0131</td>
2543 * <td>capital letter I -> small letter dotless i </td>
2544 * </tr>
2545 * <tr>
2546 * <td>(all)</td>
2547 * <td>French Fries</td>
2548 * <td>french fries</td>
2549 * <td>lowercased all chars in String</td>
2550 * </tr>
2551 * <tr>
2552 * <td>(all)</td>
2553 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2554 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2555 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2556 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2557 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2558 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2559 * <td>lowercased all chars in String</td>
2560 * </tr>
2561 * </table>
2562 *
2563 * @param locale use the case transformation rules for this locale
2564 * @return the {@code String}, converted to lowercase.
2565 * @see java.lang.String#toLowerCase()
2566 * @see java.lang.String#toUpperCase()
2567 * @see java.lang.String#toUpperCase(Locale)
2568 * @since 1.1
2569 */
2570 public String toLowerCase(Locale locale) {
2571 if (locale == null) {
2572 throw new NullPointerException();
2573 }
2574 int first;
2575 boolean hasSurr = false;
2576 final int len = value.length;
2577
2578 // Now check if there are any characters that need to be changed, or are surrogate
2579 for (first = 0 ; first < len; first++) {
2580 int cp = (int)value[first];
2581 if (Character.isSurrogate((char)cp)) {
2582 hasSurr = true;
2583 break;
2584 }
2585 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR
2586 break;
2587 }
2588 }
2589 if (first == len)
2590 return this;
2591 char[] result = new char[len];
2592 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2593 // lowerCase characters.
2594 String lang = locale.getLanguage();
2595 if (lang == "tr" || lang == "az" || lang == "lt") {
2596 return toLowerCaseEx(result, first, locale, true);
2597 }
2598 if (hasSurr) {
2599 return toLowerCaseEx(result, first, locale, false);
2600 }
2601 for (int i = first; i < len; i++) {
2602 int cp = (int)value[i];
2603 if (cp == '\u03A3' || // GREEK CAPITAL LETTER SIGMA
2604 Character.isSurrogate((char)cp)) {
2605 return toLowerCaseEx(result, i, locale, false);
2606 }
2607 if (cp == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE
2608 return toLowerCaseEx(result, i, locale, true);
2609 }
2610 cp = Character.toLowerCase(cp);
2611 if (!Character.isBmpCodePoint(cp)) {
2612 return toLowerCaseEx(result, i, locale, false);
2613 }
2614 result[i] = (char)cp;
2615 }
2616 return new String(result, true);
2617 }
2618
2619 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) {
2620 int resultOffset = first;
2621 int srcCount;
2622 for (int i = first; i < value.length; i += srcCount) {
2623 int srcChar = (int)value[i];
2624 int lowerChar;
2625 char[] lowerCharArray;
2626 srcCount = 1;
2627 if (Character.isSurrogate((char)srcChar)) {
2628 srcChar = codePointAt(i);
2629 srcCount = Character.charCount(srcChar);
2630 }
2631 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2632 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2633 } else {
2634 lowerChar = Character.toLowerCase(srcChar);
2635 }
2636 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp
2637 result[resultOffset++] = (char)lowerChar;
2638 } else {
2639 if (lowerChar == Character.ERROR) {
2640 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2641 } else if (srcCount == 2) {
2642 resultOffset += Character.toChars(lowerChar, result, resultOffset);
2643 continue;
2644 } else {
2645 lowerCharArray = Character.toChars(lowerChar);
2646 }
2647 /* Grow result if needed */
2648 int mapLen = lowerCharArray.length;
2649 if (mapLen > srcCount) {
2650 char[] result2 = new char[result.length + mapLen - srcCount];
2651 System.arraycopy(result, 0, result2, 0, resultOffset);
2652 result = result2;
2653 }
2654 for (int x = 0; x < mapLen; ++x) {
2655 result[resultOffset++] = lowerCharArray[x];
2656 }
2657 }
2658 }
2659 return new String(result, 0, resultOffset);
2660 }
2661
2662 /**
2663 * Converts all of the characters in this {@code String} to lower
2664 * case using the rules of the default locale. This is equivalent to calling
2665 * {@code toLowerCase(Locale.getDefault())}.
2666 * <p>
2667 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2668 * results if used for strings that are intended to be interpreted locale
2669 * independently.
2670 * Examples are programming language identifiers, protocol keys, and HTML
2671 * tags.
2672 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2673 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2674 * LATIN SMALL LETTER DOTLESS I character.
2675 * To obtain correct results for locale insensitive strings, use
2676 * {@code toLowerCase(Locale.ROOT)}.
2677 *
2678 * @return the {@code String}, converted to lowercase.
2679 * @see java.lang.String#toLowerCase(Locale)
2680 */
2681 public String toLowerCase() {
2682 return toLowerCase(Locale.getDefault());
2683 }
2684
2685 /**
2686 * Converts all of the characters in this {@code String} to upper
2687 * case using the rules of the given {@code Locale}. Case mapping is based
2688 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2689 * class. Since case mappings are not always 1:1 char mappings, the resulting
2690 * {@code String} may be a different length than the original {@code String}.
2691 * <p>
2692 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2693 *
2694 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2695 * <tr>
2696 * <th>Language Code of Locale</th>
2697 * <th>Lower Case</th>
2698 * <th>Upper Case</th>
2699 * <th>Description</th>
2700 * </tr>
2701 * <tr>
2702 * <td>tr (Turkish)</td>
2703 * <td>\u0069</td>
2704 * <td>\u0130</td>
2705 * <td>small letter i -> capital letter I with dot above</td>
2706 * </tr>
2707 * <tr>
2708 * <td>tr (Turkish)</td>
2709 * <td>\u0131</td>
2710 * <td>\u0049</td>
2711 * <td>small letter dotless i -> capital letter I</td>
2712 * </tr>
2713 * <tr>
2714 * <td>(all)</td>
2715 * <td>\u00df</td>
2716 * <td>\u0053 \u0053</td>
2717 * <td>small letter sharp s -> two letters: SS</td>
2718 * </tr>
2719 * <tr>
2720 * <td>(all)</td>
2721 * <td>Fahrvergnügen</td>
2722 * <td>FAHRVERGNÜGEN</td>
2723 * <td></td>
2724 * </tr>
2725 * </table>
2726 * @param locale use the case transformation rules for this locale
2727 * @return the {@code String}, converted to uppercase.
2728 * @see java.lang.String#toUpperCase()
2729 * @see java.lang.String#toLowerCase()
2730 * @see java.lang.String#toLowerCase(Locale)
2731 * @since 1.1
2732 */
2733 public String toUpperCase(Locale locale) {
2734 if (locale == null) {
2735 throw new NullPointerException();
2736 }
2737 int first;
2738 boolean hasSurr = false;
2739 final int len = value.length;
2740
2741 // Now check if there are any characters that need to be changed, or are surrogate
2742 for (first = 0 ; first < len; first++ ) {
2743 int cp = (int)value[first];
2744 if (Character.isSurrogate((char)cp)) {
2745 hasSurr = true;
2746 break;
2747 }
2748 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR
2749 break;
2750 }
2751 }
2752 if (first == len) {
2753 return this;
2754 }
2755 char[] result = new char[len];
2756 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2757 // upperCase characters.
2758 String lang = locale.getLanguage();
2759 if (lang == "tr" || lang == "az" || lang == "lt") {
2760 return toUpperCaseEx(result, first, locale, true);
2761 }
2762 if (hasSurr) {
2763 return toUpperCaseEx(result, first, locale, false);
2764 }
2765 for (int i = first; i < len; i++) {
2766 int cp = (int)value[i];
2767 if (Character.isSurrogate((char)cp)) {
2768 return toUpperCaseEx(result, i, locale, false);
2769 }
2770 cp = Character.toUpperCaseEx(cp);
2771 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp
2772 return toUpperCaseEx(result, i, locale, false);
2773 }
2774 result[i] = (char)cp;
2775 }
2776 return new String(result, true);
2777 }
2778
2779 private String toUpperCaseEx(char[] result, int first, Locale locale,
2780 boolean localeDependent) {
2781 int resultOffset = first;
2782 int srcCount;
2783 for (int i = first; i < value.length; i += srcCount) {
2784 int srcChar = (int)value[i];
2785 int upperChar;
2786 char[] upperCharArray;
2787 srcCount = 1;
2788 if (Character.isSurrogate((char)srcChar)) {
2789 srcChar = codePointAt(i);
2790 srcCount = Character.charCount(srcChar);
2791 }
2792 if (localeDependent) {
2793 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2794 } else {
2795 upperChar = Character.toUpperCaseEx(srcChar);
2796 }
2797 if (Character.isBmpCodePoint(upperChar)) {
2798 result[resultOffset++] = (char)upperChar;
2799 } else {
2800 if (upperChar == Character.ERROR) {
2801 if (localeDependent) {
2802 upperCharArray =
2803 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
2804 } else {
2805 upperCharArray = Character.toUpperCaseCharArray(srcChar);
2806 }
2807 } else if (srcCount == 2) {
2808 resultOffset += Character.toChars(upperChar, result, resultOffset);
2809 continue;
2810 } else {
2811 upperCharArray = Character.toChars(upperChar);
2812 }
2813 /* Grow result if needed */
2814 int mapLen = upperCharArray.length;
2815 if (mapLen > srcCount) {
2816 char[] result2 = new char[result.length + mapLen - srcCount];
2817 System.arraycopy(result, 0, result2, 0, resultOffset);
2818 result = result2;
2819 }
2820 for (int x = 0; x < mapLen; ++x) {
2821 result[resultOffset++] = upperCharArray[x];
2822 }
2823 }
2824 }
2825 return new String(result, 0, resultOffset);
2826 }
2827
2828 /**
2829 * Converts all of the characters in this {@code String} to upper
2830 * case using the rules of the default locale. This method is equivalent to
2831 * {@code toUpperCase(Locale.getDefault())}.
2832 * <p>
2833 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2834 * results if used for strings that are intended to be interpreted locale
2835 * independently.
2836 * Examples are programming language identifiers, protocol keys, and HTML
2837 * tags.
2838 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2839 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2840 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2841 * To obtain correct results for locale insensitive strings, use
2842 * {@code toUpperCase(Locale.ROOT)}.
2843 *
2844 * @return the {@code String}, converted to uppercase.
2845 * @see java.lang.String#toUpperCase(Locale)
2846 */
2847 public String toUpperCase() {
2848 return toUpperCase(Locale.getDefault());
2849 }
2850
2851 /**
2852 * Returns a string whose value is this string, with any leading and trailing
2853 * whitespace removed.
2854 * <p>
2855 * If this {@code String} object represents an empty character
2856 * sequence, or the first and last characters of character sequence
2857 * represented by this {@code String} object both have codes
2858 * greater than {@code '\u005Cu0020'} (the space character), then a
2859 * reference to this {@code String} object is returned.
2860 * <p>
2861 * Otherwise, if there is no character with a code greater than
2862 * {@code '\u005Cu0020'} in the string, then a
2863 * {@code String} object representing an empty string is
2864 * returned.
2865 * <p>
2866 * Otherwise, let <i>k</i> be the index of the first character in the
2867 * string whose code is greater than {@code '\u005Cu0020'}, and let
2868 * <i>m</i> be the index of the last character in the string whose code
2869 * is greater than {@code '\u005Cu0020'}. A {@code String}
2870 * object is returned, representing the substring of this string that
2871 * begins with the character at index <i>k</i> and ends with the
2872 * character at index <i>m</i>-that is, the result of
2873 * {@code this.substring(k, m + 1)}.
2874 * <p>
2875 * This method may be used to trim whitespace (as defined above) from
2876 * the beginning and end of a string.
2877 *
2878 * @return A string whose value is this string, with any leading and trailing white
2879 * space removed, or this string if it has no leading or
2880 * trailing white space.
2881 */
2882 public String trim() {
2883 char[] val = value; /* avoid getfield opcode */
2884 int end = val.length;
2885 int beg = 0;
2886
2887 while ((beg < end) && (val[beg] <= ' ')) {
2888 beg++;
2889 }
2890 while ((beg < end) && (val[end - 1] <= ' ')) {
2891 end--;
2892 }
2893 return substring(beg, end);
2894 }
2895
2896 /**
2897 * This object (which is already a string!) is itself returned.
2898 *
2899 * @return the string itself.
2900 */
2901 public String toString() {
2902 return this;
2903 }
2904
2905 static class IntCharArraySpliterator implements Spliterator.OfInt {
2906 private final char[] array;
2907 private int index; // current index, modified on advance/split
2908 private final int fence; // one past last index
2909 private final int cs;
2910
2911 IntCharArraySpliterator(char[] array, int acs) {
2912 this(array, 0, array.length, acs);
2913 }
2914
2915 IntCharArraySpliterator(char[] array, int origin, int fence, int acs) {
2916 this.array = array;
2917 this.index = origin;
2918 this.fence = fence;
2919 this.cs = acs | Spliterator.ORDERED | Spliterator.SIZED
2920 | Spliterator.SUBSIZED;
2921 }
2922
2923 @Override
2924 public OfInt trySplit() {
2925 int lo = index, mid = (lo + fence) >>> 1;
2926 return (lo >= mid)
2927 ? null
2928 : new IntCharArraySpliterator(array, lo, index = mid, cs);
2929 }
2930
2931 @Override
2932 public void forEachRemaining(IntConsumer action) {
2933 char[] a; int i, hi; // hoist accesses and checks from loop
2934 if (action == null)
2935 throw new NullPointerException();
2936 if ((a = array).length >= (hi = fence) &&
2937 (i = index) >= 0 && i < (index = hi)) {
2938 do { action.accept(a[i]); } while (++i < hi);
2939 }
2940 }
2941
2942 @Override
2943 public boolean tryAdvance(IntConsumer action) {
2944 if (action == null)
2945 throw new NullPointerException();
2946 if (index >= 0 && index < fence) {
2947 action.accept(array[index++]);
2948 return true;
2949 }
2950 return false;
2951 }
2952
2953 @Override
2954 public long estimateSize() { return (long)(fence - index); }
2955
2956 @Override
2957 public int characteristics() {
2958 return cs;
2959 }
2960 }
2961
2962 /**
2963 * Returns a stream of {@code int} zero-extending the {@code char} values
2964 * from this sequence. Any char which maps to a <a
2965 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code
2966 * point</a> is passed through uninterpreted.
2967 *
2968 * @return an IntStream of char values from this sequence
2969 * @since 1.9
2970 */
2971 @Override
2972 public IntStream chars() {
2973 return StreamSupport.intStream(
2974 new IntCharArraySpliterator(value, Spliterator.IMMUTABLE), false);
2975 }
2976
2977 static class CodePointsSpliterator implements Spliterator.OfInt {
2978 private final char[] array;
2979 private int index; // current index, modified on advance/split
2980 private final int fence; // one past last index
2981 private final int cs;
2982
2983 CodePointsSpliterator(char[] array, int acs) {
2984 this(array, 0, array.length, acs);
2985 }
2986
2987 CodePointsSpliterator(char[] array, int origin, int fence, int acs) {
2988 this.array = array;
2989 this.index = origin;
2990 this.fence = fence;
2991 this.cs = acs | Spliterator.ORDERED;
2992 }
2993
2994 @Override
2995 public OfInt trySplit() {
2996 int lo = index, mid = (lo + fence) >>> 1;
2997 if (lo >= mid)
2998 return null;
2999
3000 int midOneLess;
3001 // If the mid-point intersects a surrogate pair
3002 if (Character.isLowSurrogate(array[mid]) &&
3003 Character.isHighSurrogate(array[midOneLess = (mid -1)])) {
3004 // If there is only one pair it cannot be split
3005 if (lo >= midOneLess)
3006 return null;
3007 // Shift the mid-point to align with the surrogate pair
3008 return new CodePointsSpliterator(array, lo, index = midOneLess, cs);
3009 }
3010 return new CodePointsSpliterator(array, lo, index = mid, cs);
3011 }
3012
3013 @Override
3014 public void forEachRemaining(IntConsumer action) {
3015 char[] a; int i, hi; // hoist accesses and checks from loop
3016 if (action == null)
3017 throw new NullPointerException();
3018 if ((a = array).length >= (hi = fence) &&
3019 (i = index) >= 0 && i < (index = hi)) {
3020 do {
3021 i = advance(a, i, hi, action);
3022 } while (i < hi);
3023 }
3024 }
3025
3026 @Override
3027 public boolean tryAdvance(IntConsumer action) {
3028 if (action == null)
3029 throw new NullPointerException();
3030 if (index >= 0 && index < fence) {
3031 index = advance(array, index, fence, action);
3032 return true;
3033 }
3034 return false;
3035 }
3036
3037 // Advance one code point from the index, i, and return the next
3038 // index to advance from
3039 private static int advance(char[] a, int i, int hi, IntConsumer action) {
3040 char c1 = a[i++];
3041 int cp = c1;
3042 if (Character.isHighSurrogate(c1) && i < hi) {
3043 char c2 = a[i];
3044 if (Character.isLowSurrogate(c2)) {
3045 i++;
3046 cp = Character.toCodePoint(c1, c2);
3047 }
3048 }
3049 action.accept(cp);
3050 return i;
3051 }
3052
3053 @Override
3054 public long estimateSize() { return (long)(fence - index); }
3055
3056 @Override
3057 public int characteristics() {
3058 return cs;
3059 }
3060 }
3061
3062 /**
3063 * Returns a stream of code point values from this sequence. Any surrogate
3064 * pairs encountered in the sequence are combined as if by {@linkplain
3065 * Character#toCodePoint Character.toCodePoint} and the result is passed
3066 * to the stream. Any other code units, including ordinary BMP characters,
3067 * unpaired surrogates, and undefined code units, are zero-extended to
3068 * {@code int} values which are then passed to the stream.
3069 *
3070 * @return an IntStream of Unicode code points from this sequence
3071 * @since 1.9
3072 */
3073 @Override
3074 public IntStream codePoints() {
3075 return StreamSupport.intStream(
3076 new CodePointsSpliterator(value, Spliterator.IMMUTABLE), false);
3077 }
3078
3079 /**
3080 * Converts this string to a new character array.
3081 *
3082 * @return a newly allocated character array whose length is the length
3083 * of this string and whose contents are initialized to contain
3084 * the character sequence represented by this string.
3085 */
3086 public char[] toCharArray() {
3087 // Cannot use Arrays.copyOf because of class initialization order issues
3088 char[] result = new char[value.length];
3089 System.arraycopy(value, 0, result, 0, value.length);
3090 return result;
3091 }
3092
3093 /**
3094 * Returns a formatted string using the specified format string and
3095 * arguments.
3096 *
3097 * <p> The locale always used is the one returned by {@link
3098 * java.util.Locale#getDefault() Locale.getDefault()}.
3099 *
3100 * @param format
3101 * A <a href="../util/Formatter.html#syntax">format string</a>
3102 *
3103 * @param args
3104 * Arguments referenced by the format specifiers in the format
3105 * string. If there are more arguments than format specifiers, the
3106 * extra arguments are ignored. The number of arguments is
3107 * variable and may be zero. The maximum number of arguments is
3108 * limited by the maximum dimension of a Java array as defined by
3109 * <cite>The Java™ Virtual Machine Specification</cite>.
3110 * The behaviour on a
3111 * {@code null} argument depends on the <a
3112 * href="../util/Formatter.html#syntax">conversion</a>.
3113 *
3114 * @throws java.util.IllegalFormatException
3115 * If a format string contains an illegal syntax, a format
3116 * specifier that is incompatible with the given arguments,
3117 * insufficient arguments given the format string, or other
3118 * illegal conditions. For specification of all possible
3119 * formatting errors, see the <a
3120 * href="../util/Formatter.html#detail">Details</a> section of the
3121 * formatter class specification.
3122 *
3123 * @return A formatted string
3124 *
3125 * @see java.util.Formatter
3126 * @since 1.5
3127 */
3128 public static String format(String format, Object... args) {
3129 return new Formatter().format(format, args).toString();
3130 }
3131
3132 /**
3133 * Returns a formatted string using the specified locale, format string,
3134 * and arguments.
3135 *
3136 * @param l
3137 * The {@linkplain java.util.Locale locale} to apply during
3138 * formatting. If {@code l} is {@code null} then no localization
3139 * is applied.
3140 *
3141 * @param format
3142 * A <a href="../util/Formatter.html#syntax">format string</a>
3143 *
3144 * @param args
3145 * Arguments referenced by the format specifiers in the format
3146 * string. If there are more arguments than format specifiers, the
3147 * extra arguments are ignored. The number of arguments is
3148 * variable and may be zero. The maximum number of arguments is
3149 * limited by the maximum dimension of a Java array as defined by
3150 * <cite>The Java™ Virtual Machine Specification</cite>.
3151 * The behaviour on a
3152 * {@code null} argument depends on the
3153 * <a href="../util/Formatter.html#syntax">conversion</a>.
3154 *
3155 * @throws java.util.IllegalFormatException
3156 * If a format string contains an illegal syntax, a format
3157 * specifier that is incompatible with the given arguments,
3158 * insufficient arguments given the format string, or other
3159 * illegal conditions. For specification of all possible
3160 * formatting errors, see the <a
3161 * href="../util/Formatter.html#detail">Details</a> section of the
3162 * formatter class specification
3163 *
3164 * @return A formatted string
3165 *
3166 * @see java.util.Formatter
3167 * @since 1.5
3168 */
3169 public static String format(Locale l, String format, Object... args) {
3170 return new Formatter(l).format(format, args).toString();
3171 }
3172
3173 /**
3174 * Returns the string representation of the {@code Object} argument.
3175 *
3176 * @param obj an {@code Object}.
3177 * @return if the argument is {@code null}, then a string equal to
3178 * {@code "null"}; otherwise, the value of
3179 * {@code obj.toString()} is returned.
3180 * @see java.lang.Object#toString()
3181 */
3182 public static String valueOf(Object obj) {
3183 return (obj == null) ? "null" : obj.toString();
3184 }
3185
3186 /**
3187 * Returns the string representation of the {@code char} array
3188 * argument. The contents of the character array are copied; subsequent
3189 * modification of the character array does not affect the returned
3190 * string.
3191 *
3192 * @param data the character array.
3193 * @return a {@code String} that contains the characters of the
3194 * character array.
3195 */
3196 public static String valueOf(char data[]) {
3197 return new String(data);
3198 }
3199
3200 /**
3201 * Returns the string representation of a specific subarray of the
3202 * {@code char} array argument.
3203 * <p>
3204 * The {@code offset} argument is the index of the first
3205 * character of the subarray. The {@code count} argument
3206 * specifies the length of the subarray. The contents of the subarray
3207 * are copied; subsequent modification of the character array does not
3208 * affect the returned string.
3209 *
3210 * @param data the character array.
3211 * @param offset initial offset of the subarray.
3212 * @param count length of the subarray.
3213 * @return a {@code String} that contains the characters of the
3214 * specified subarray of the character array.
3215 * @exception IndexOutOfBoundsException if {@code offset} is
3216 * negative, or {@code count} is negative, or
3217 * {@code offset+count} is larger than
3218 * {@code data.length}.
3219 */
3220 public static String valueOf(char data[], int offset, int count) {
3221 return new String(data, offset, count);
3222 }
3223
3224 /**
3225 * Equivalent to {@link #valueOf(char[], int, int)}.
3226 *
3227 * @param data the character array.
3228 * @param offset initial offset of the subarray.
3229 * @param count length of the subarray.
3230 * @return a {@code String} that contains the characters of the
3231 * specified subarray of the character array.
3232 * @exception IndexOutOfBoundsException if {@code offset} is
3233 * negative, or {@code count} is negative, or
3234 * {@code offset+count} is larger than
3235 * {@code data.length}.
3236 */
3237 public static String copyValueOf(char data[], int offset, int count) {
3238 return new String(data, offset, count);
3239 }
3240
3241 /**
3242 * Equivalent to {@link #valueOf(char[])}.
3243 *
3244 * @param data the character array.
3245 * @return a {@code String} that contains the characters of the
3246 * character array.
3247 */
3248 public static String copyValueOf(char data[]) {
3249 return new String(data);
3250 }
3251
3252 /**
3253 * Returns the string representation of the {@code boolean} argument.
3254 *
3255 * @param b a {@code boolean}.
3256 * @return if the argument is {@code true}, a string equal to
3257 * {@code "true"} is returned; otherwise, a string equal to
3258 * {@code "false"} is returned.
3259 */
3260 public static String valueOf(boolean b) {
3261 return b ? "true" : "false";
3262 }
3263
3264 /**
3265 * Returns the string representation of the {@code char}
3266 * argument.
3267 *
3268 * @param c a {@code char}.
3269 * @return a string of length {@code 1} containing
3270 * as its single character the argument {@code c}.
3271 */
3272 public static String valueOf(char c) {
3273 return new String(new char[]{c}, true);
3274 }
3275
3276 /**
3277 * Returns the string representation of the {@code int} argument.
3278 * <p>
3279 * The representation is exactly the one returned by the
3280 * {@code Integer.toString} method of one argument.
3281 *
3282 * @param i an {@code int}.
3283 * @return a string representation of the {@code int} argument.
3284 * @see java.lang.Integer#toString(int, int)
3285 */
3286 public static String valueOf(int i) {
3287 return Integer.toString(i);
3288 }
3289
3290 /**
3291 * Returns the string representation of the {@code long} argument.
3292 * <p>
3293 * The representation is exactly the one returned by the
3294 * {@code Long.toString} method of one argument.
3295 *
3296 * @param l a {@code long}.
3297 * @return a string representation of the {@code long} argument.
3298 * @see java.lang.Long#toString(long)
3299 */
3300 public static String valueOf(long l) {
3301 return Long.toString(l);
3302 }
3303
3304 /**
3305 * Returns the string representation of the {@code float} argument.
3306 * <p>
3307 * The representation is exactly the one returned by the
3308 * {@code Float.toString} method of one argument.
3309 *
3310 * @param f a {@code float}.
3311 * @return a string representation of the {@code float} argument.
3312 * @see java.lang.Float#toString(float)
3313 */
3314 public static String valueOf(float f) {
3315 return Float.toString(f);
3316 }
3317
3318 /**
3319 * Returns the string representation of the {@code double} argument.
3320 * <p>
3321 * The representation is exactly the one returned by the
3322 * {@code Double.toString} method of one argument.
3323 *
3324 * @param d a {@code double}.
3325 * @return a string representation of the {@code double} argument.
3326 * @see java.lang.Double#toString(double)
3327 */
3328 public static String valueOf(double d) {
3329 return Double.toString(d);
3330 }
3331
3332 /**
3333 * Returns a canonical representation for the string object.
3334 * <p>
3335 * A pool of strings, initially empty, is maintained privately by the
3336 * class {@code String}.
3337 * <p>
3338 * When the intern method is invoked, if the pool already contains a
3339 * string equal to this {@code String} object as determined by
3340 * the {@link #equals(Object)} method, then the string from the pool is
3341 * returned. Otherwise, this {@code String} object is added to the
3342 * pool and a reference to this {@code String} object is returned.
3343 * <p>
3344 * It follows that for any two strings {@code s} and {@code t},
3345 * {@code s.intern() == t.intern()} is {@code true}
3346 * if and only if {@code s.equals(t)} is {@code true}.
3347 * <p>
3348 * All literal strings and string-valued constant expressions are
3349 * interned. String literals are defined in section 3.10.5 of the
3350 * <cite>The Java™ Language Specification</cite>.
3351 *
3352 * @return a string that has the same contents as this string, but is
3353 * guaranteed to be from a pool of unique strings.
3354 */
3355 public native String intern();
3356 }