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 String anotherString = (String)anObject;
987 int n = value.length;
988 if (n == anotherString.value.length) {
989 char v1[] = value;
990 char v2[] = anotherString.value;
991 int i = 0;
992 while (n-- != 0) {
993 if (v1[i] != v2[i])
994 return false;
995 i++;
996 }
997 return true;
998 }
999 }
1000 return false;
1001 }
1002
1003 /**
1004 * Compares this string to the specified {@code StringBuffer}. The result
1005 * is {@code true} if and only if this {@code String} represents the same
1006 * sequence of characters as the specified {@code StringBuffer}. This method
1007 * synchronizes on the {@code StringBuffer}.
1008 *
1009 * @param sb
1010 * The {@code StringBuffer} to compare this {@code String} against
1011 *
1012 * @return {@code true} if this {@code String} represents the same
1013 * sequence of characters as the specified {@code StringBuffer},
1014 * {@code false} otherwise
1015 *
1016 * @since 1.4
1017 */
1018 public boolean contentEquals(StringBuffer sb) {
1019 return contentEquals((CharSequence)sb);
1020 }
1021
1022 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1023 char v1[] = value;
1024 char v2[] = sb.getValue();
1025 int n = v1.length;
1026 if (n != sb.length()) {
1027 return false;
1028 }
1029 for (int i = 0; i < n; i++) {
1030 if (v1[i] != v2[i]) {
1031 return false;
1032 }
1033 }
1034 return true;
1035 }
1036
1037 /**
1038 * Compares this string to the specified {@code CharSequence}. The
1039 * result is {@code true} if and only if this {@code String} represents the
1040 * same sequence of char values as the specified sequence. Note that if the
1041 * {@code CharSequence} is a {@code StringBuffer} then the method
1042 * synchronizes on it.
1043 *
1044 * @param cs
1045 * The sequence to compare this {@code String} against
1046 *
1047 * @return {@code true} if this {@code String} represents the same
1048 * sequence of char values as the specified sequence, {@code
1049 * false} otherwise
1050 *
1051 * @since 1.5
1052 */
1053 public boolean contentEquals(CharSequence cs) {
1054 // Argument is a StringBuffer, StringBuilder
1055 if (cs instanceof AbstractStringBuilder) {
1056 if (cs instanceof StringBuffer) {
1057 synchronized(cs) {
1058 return nonSyncContentEquals((AbstractStringBuilder)cs);
1059 }
1060 } else {
1061 return nonSyncContentEquals((AbstractStringBuilder)cs);
1062 }
1063 }
1064 // Argument is a String
1065 if (cs instanceof String) {
1066 return equals(cs);
1067 }
1068 // Argument is a generic CharSequence
1069 char v1[] = value;
1070 int n = v1.length;
1071 if (n != cs.length()) {
1072 return false;
1073 }
1074 for (int i = 0; i < n; i++) {
1075 if (v1[i] != cs.charAt(i)) {
1076 return false;
1077 }
1078 }
1079 return true;
1080 }
1081
1082 /**
1083 * Compares this {@code String} to another {@code String}, ignoring case
1084 * considerations. Two strings are considered equal ignoring case if they
1085 * are of the same length and corresponding characters in the two strings
1086 * are equal ignoring case.
1087 *
1088 * <p> Two characters {@code c1} and {@code c2} are considered the same
1089 * ignoring case if at least one of the following is true:
1090 * <ul>
1091 * <li> The two characters are the same (as compared by the
1092 * {@code ==} operator)
1093 * <li> Applying the method {@link
1094 * java.lang.Character#toUpperCase(char)} to each character
1095 * produces the same result
1096 * <li> Applying the method {@link
1097 * java.lang.Character#toLowerCase(char)} to each character
1098 * produces the same result
1099 * </ul>
1100 *
1101 * @param anotherString
1102 * The {@code String} to compare this {@code String} against
1103 *
1104 * @return {@code true} if the argument is not {@code null} and it
1105 * represents an equivalent {@code String} ignoring case; {@code
1106 * false} otherwise
1107 *
1108 * @see #equals(Object)
1109 */
1110 public boolean equalsIgnoreCase(String anotherString) {
1111 return (this == anotherString) ? true
1112 : (anotherString != null)
1113 && (anotherString.value.length == value.length)
1114 && regionMatches(true, 0, anotherString, 0, value.length);
1115 }
1116
1117 /**
1118 * Compares two strings lexicographically.
1119 * The comparison is based on the Unicode value of each character in
1120 * the strings. The character sequence represented by this
1121 * {@code String} object is compared lexicographically to the
1122 * character sequence represented by the argument string. The result is
1123 * a negative integer if this {@code String} object
1124 * lexicographically precedes the argument string. The result is a
1125 * positive integer if this {@code String} object lexicographically
1126 * follows the argument string. The result is zero if the strings
1127 * are equal; {@code compareTo} returns {@code 0} exactly when
1128 * the {@link #equals(Object)} method would return {@code true}.
1129 * <p>
1130 * This is the definition of lexicographic ordering. If two strings are
1131 * different, then either they have different characters at some index
1132 * that is a valid index for both strings, or their lengths are different,
1133 * or both. If they have different characters at one or more index
1134 * positions, let <i>k</i> be the smallest such index; then the string
1135 * whose character at position <i>k</i> has the smaller value, as
1136 * determined by using the < operator, lexicographically precedes the
1137 * other string. In this case, {@code compareTo} returns the
1138 * difference of the two character values at position {@code k} in
1139 * the two string -- that is, the value:
1140 * <blockquote><pre>
1141 * this.charAt(k)-anotherString.charAt(k)
1142 * </pre></blockquote>
1143 * If there is no index position at which they differ, then the shorter
1144 * string lexicographically precedes the longer string. In this case,
1145 * {@code compareTo} returns the difference of the lengths of the
1146 * strings -- that is, the value:
1147 * <blockquote><pre>
1148 * this.length()-anotherString.length()
1149 * </pre></blockquote>
1150 *
1151 * @param anotherString the {@code String} to be compared.
1152 * @return the value {@code 0} if the argument string is equal to
1153 * this string; a value less than {@code 0} if this string
1154 * is lexicographically less than the string argument; and a
1155 * value greater than {@code 0} if this string is
1156 * lexicographically greater than the string argument.
1157 */
1158 public int compareTo(String anotherString) {
1159 int len1 = value.length;
1160 int len2 = anotherString.value.length;
1161 int lim = Math.min(len1, len2);
1162 char v1[] = value;
1163 char v2[] = anotherString.value;
1164
1165 int k = 0;
1166 while (k < lim) {
1167 char c1 = v1[k];
1168 char c2 = v2[k];
1169 if (c1 != c2) {
1170 return c1 - c2;
1171 }
1172 k++;
1173 }
1174 return len1 - len2;
1175 }
1176
1177 /**
1178 * A Comparator that orders {@code String} objects as by
1179 * {@code compareToIgnoreCase}. This comparator is serializable.
1180 * <p>
1181 * Note that this Comparator does <em>not</em> take locale into account,
1182 * and will result in an unsatisfactory ordering for certain locales.
1183 * The java.text package provides <em>Collators</em> to allow
1184 * locale-sensitive ordering.
1185 *
1186 * @see java.text.Collator#compare(String, String)
1187 * @since 1.2
1188 */
1189 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1190 = new CaseInsensitiveComparator();
1191 private static class CaseInsensitiveComparator
1192 implements Comparator<String>, java.io.Serializable {
1193 // use serialVersionUID from JDK 1.2.2 for interoperability
1194 private static final long serialVersionUID = 8575799808933029326L;
1195
1196 public int compare(String s1, String s2) {
1197 int n1 = s1.length();
1198 int n2 = s2.length();
1199 int min = Math.min(n1, n2);
1200 for (int i = 0; i < min; i++) {
1201 char c1 = s1.charAt(i);
1202 char c2 = s2.charAt(i);
1203 if (c1 != c2) {
1204 c1 = Character.toUpperCase(c1);
1205 c2 = Character.toUpperCase(c2);
1206 if (c1 != c2) {
1207 c1 = Character.toLowerCase(c1);
1208 c2 = Character.toLowerCase(c2);
1209 if (c1 != c2) {
1210 // No overflow because of numeric promotion
1211 return c1 - c2;
1212 }
1213 }
1214 }
1215 }
1216 return n1 - n2;
1217 }
1218
1219 /** Replaces the de-serialized object. */
1220 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1221 }
1222
1223 /**
1224 * Compares two strings lexicographically, ignoring case
1225 * differences. This method returns an integer whose sign is that of
1226 * calling {@code compareTo} with normalized versions of the strings
1227 * where case differences have been eliminated by calling
1228 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1229 * each character.
1230 * <p>
1231 * Note that this method does <em>not</em> take locale into account,
1232 * and will result in an unsatisfactory ordering for certain locales.
1233 * The java.text package provides <em>collators</em> to allow
1234 * locale-sensitive ordering.
1235 *
1236 * @param str the {@code String} to be compared.
1237 * @return a negative integer, zero, or a positive integer as the
1238 * specified String is greater than, equal to, or less
1239 * than this String, ignoring case considerations.
1240 * @see java.text.Collator#compare(String, String)
1241 * @since 1.2
1242 */
1243 public int compareToIgnoreCase(String str) {
1244 return CASE_INSENSITIVE_ORDER.compare(this, str);
1245 }
1246
1247 /**
1248 * Tests if two string regions are equal.
1249 * <p>
1250 * A substring of this {@code String} object is compared to a substring
1251 * of the argument other. The result is true if these substrings
1252 * represent identical character sequences. The substring of this
1253 * {@code String} object to be compared begins at index {@code toffset}
1254 * and has length {@code len}. The substring of other to be compared
1255 * begins at index {@code ooffset} and has length {@code len}. The
1256 * result is {@code false} if and only if at least one of the following
1257 * is true:
1258 * <ul><li>{@code toffset} is negative.
1259 * <li>{@code ooffset} is negative.
1260 * <li>{@code toffset+len} is greater than the length of this
1261 * {@code String} object.
1262 * <li>{@code ooffset+len} is greater than the length of the other
1263 * argument.
1264 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1265 * such that:
1266 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1267 * <i>k</i>{@code )}
1268 * </ul>
1269 *
1270 * @param toffset the starting offset of the subregion in this string.
1271 * @param other the string argument.
1272 * @param ooffset the starting offset of the subregion in the string
1273 * argument.
1274 * @param len the number of characters to compare.
1275 * @return {@code true} if the specified subregion of this string
1276 * exactly matches the specified subregion of the string argument;
1277 * {@code false} otherwise.
1278 */
1279 public boolean regionMatches(int toffset, String other, int ooffset,
1280 int len) {
1281 char ta[] = value;
1282 int to = toffset;
1283 char pa[] = other.value;
1284 int po = ooffset;
1285 // Note: toffset, ooffset, or len might be near -1>>>1.
1286 if ((ooffset < 0) || (toffset < 0)
1287 || (toffset > (long)value.length - len)
1288 || (ooffset > (long)other.value.length - len)) {
1289 return false;
1290 }
1291 while (len-- > 0) {
1292 if (ta[to++] != pa[po++]) {
1293 return false;
1294 }
1295 }
1296 return true;
1297 }
1298
1299 /**
1300 * Tests if two string regions are equal.
1301 * <p>
1302 * A substring of this {@code String} object is compared to a substring
1303 * of the argument {@code other}. The result is {@code true} if these
1304 * substrings represent character sequences that are the same, ignoring
1305 * case if and only if {@code ignoreCase} is true. The substring of
1306 * this {@code String} object to be compared begins at index
1307 * {@code toffset} and has length {@code len}. The substring of
1308 * {@code other} to be compared begins at index {@code ooffset} and
1309 * has length {@code len}. The result is {@code false} if and only if
1310 * at least one of the following is true:
1311 * <ul><li>{@code toffset} is negative.
1312 * <li>{@code ooffset} is negative.
1313 * <li>{@code toffset+len} is greater than the length of this
1314 * {@code String} object.
1315 * <li>{@code ooffset+len} is greater than the length of the other
1316 * argument.
1317 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1318 * integer <i>k</i> less than {@code len} such that:
1319 * <blockquote><pre>
1320 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1321 * </pre></blockquote>
1322 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1323 * integer <i>k</i> less than {@code len} such that:
1324 * <blockquote><pre>
1325 * Character.toLowerCase(this.charAt(toffset+k)) !=
1326 Character.toLowerCase(other.charAt(ooffset+k))
1327 * </pre></blockquote>
1328 * and:
1329 * <blockquote><pre>
1330 * Character.toUpperCase(this.charAt(toffset+k)) !=
1331 * Character.toUpperCase(other.charAt(ooffset+k))
1332 * </pre></blockquote>
1333 * </ul>
1334 *
1335 * @param ignoreCase if {@code true}, ignore case when comparing
1336 * characters.
1337 * @param toffset the starting offset of the subregion in this
1338 * string.
1339 * @param other the string argument.
1340 * @param ooffset the starting offset of the subregion in the string
1341 * argument.
1342 * @param len the number of characters to compare.
1343 * @return {@code true} if the specified subregion of this string
1344 * matches the specified subregion of the string argument;
1345 * {@code false} otherwise. Whether the matching is exact
1346 * or case insensitive depends on the {@code ignoreCase}
1347 * argument.
1348 */
1349 public boolean regionMatches(boolean ignoreCase, int toffset,
1350 String other, int ooffset, int len) {
1351 char ta[] = value;
1352 int to = toffset;
1353 char pa[] = other.value;
1354 int po = ooffset;
1355 // Note: toffset, ooffset, or len might be near -1>>>1.
1356 if ((ooffset < 0) || (toffset < 0)
1357 || (toffset > (long)value.length - len)
1358 || (ooffset > (long)other.value.length - len)) {
1359 return false;
1360 }
1361 while (len-- > 0) {
1362 char c1 = ta[to++];
1363 char c2 = pa[po++];
1364 if (c1 == c2) {
1365 continue;
1366 }
1367 if (ignoreCase) {
1368 // If characters don't match but case may be ignored,
1369 // try converting both characters to uppercase.
1370 // If the results match, then the comparison scan should
1371 // continue.
1372 char u1 = Character.toUpperCase(c1);
1373 char u2 = Character.toUpperCase(c2);
1374 if (u1 == u2) {
1375 continue;
1376 }
1377 // Unfortunately, conversion to uppercase does not work properly
1378 // for the Georgian alphabet, which has strange rules about case
1379 // conversion. So we need to make one last check before
1380 // exiting.
1381 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1382 continue;
1383 }
1384 }
1385 return false;
1386 }
1387 return true;
1388 }
1389
1390 /**
1391 * Tests if the substring of this string beginning at the
1392 * specified index starts with the specified prefix.
1393 *
1394 * @param prefix the prefix.
1395 * @param toffset where to begin looking in this string.
1396 * @return {@code true} if the character sequence represented by the
1397 * argument is a prefix of the substring of this object starting
1398 * at index {@code toffset}; {@code false} otherwise.
1399 * The result is {@code false} if {@code toffset} is
1400 * negative or greater than the length of this
1401 * {@code String} object; otherwise the result is the same
1402 * as the result of the expression
1403 * <pre>
1404 * this.substring(toffset).startsWith(prefix)
1405 * </pre>
1406 */
1407 public boolean startsWith(String prefix, int toffset) {
1408 char ta[] = value;
1409 int to = toffset;
1410 char pa[] = prefix.value;
1411 int po = 0;
1412 int pc = prefix.value.length;
1413 // Note: toffset might be near -1>>>1.
1414 if ((toffset < 0) || (toffset > value.length - pc)) {
1415 return false;
1416 }
1417 while (--pc >= 0) {
1418 if (ta[to++] != pa[po++]) {
1419 return false;
1420 }
1421 }
1422 return true;
1423 }
1424
1425 /**
1426 * Tests if this string starts with the specified prefix.
1427 *
1428 * @param prefix the prefix.
1429 * @return {@code true} if the character sequence represented by the
1430 * argument is a prefix of the character sequence represented by
1431 * this string; {@code false} otherwise.
1432 * Note also that {@code true} will be returned if the
1433 * argument is an empty string or is equal to this
1434 * {@code String} object as determined by the
1435 * {@link #equals(Object)} method.
1436 * @since 1.0
1437 */
1438 public boolean startsWith(String prefix) {
1439 return startsWith(prefix, 0);
1440 }
1441
1442 /**
1443 * Tests if this string ends with the specified suffix.
1444 *
1445 * @param suffix the suffix.
1446 * @return {@code true} if the character sequence represented by the
1447 * argument is a suffix of the character sequence represented by
1448 * this object; {@code false} otherwise. Note that the
1449 * result will be {@code true} if the argument is the
1450 * empty string or is equal to this {@code String} object
1451 * as determined by the {@link #equals(Object)} method.
1452 */
1453 public boolean endsWith(String suffix) {
1454 return startsWith(suffix, value.length - suffix.value.length);
1455 }
1456
1457 /**
1458 * Returns a hash code for this string. The hash code for a
1459 * {@code String} object is computed as
1460 * <blockquote><pre>
1461 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1462 * </pre></blockquote>
1463 * using {@code int} arithmetic, where {@code s[i]} is the
1464 * <i>i</i>th character of the string, {@code n} is the length of
1465 * the string, and {@code ^} indicates exponentiation.
1466 * (The hash value of the empty string is zero.)
1467 *
1468 * @return a hash code value for this object.
1469 */
1470 public int hashCode() {
1471 int h = hash;
1472 if (h == 0) {
1473 for (char v : value) {
1474 h = 31 * h + v;
1475 }
1476 hash = h;
1477 }
1478 return h;
1479 }
1480
1481 /**
1482 * Returns the index within this string of the first occurrence of
1483 * the specified character. If a character with value
1484 * {@code ch} occurs in the character sequence represented by
1485 * this {@code String} object, then the index (in Unicode
1486 * code units) of the first such occurrence is returned. For
1487 * values of {@code ch} in the range from 0 to 0xFFFF
1488 * (inclusive), this is the smallest value <i>k</i> such that:
1489 * <blockquote><pre>
1490 * this.charAt(<i>k</i>) == ch
1491 * </pre></blockquote>
1492 * is true. For other values of {@code ch}, it is the
1493 * smallest value <i>k</i> such that:
1494 * <blockquote><pre>
1495 * this.codePointAt(<i>k</i>) == ch
1496 * </pre></blockquote>
1497 * is true. In either case, if no such character occurs in this
1498 * string, then {@code -1} is returned.
1499 *
1500 * @param ch a character (Unicode code point).
1501 * @return the index of the first occurrence of the character in the
1502 * character sequence represented by this object, or
1503 * {@code -1} if the character does not occur.
1504 */
1505 public int indexOf(int ch) {
1506 return indexOf(ch, 0);
1507 }
1508
1509 /**
1510 * Returns the index within this string of the first occurrence of the
1511 * specified character, starting the search at the specified index.
1512 * <p>
1513 * If a character with value {@code ch} occurs in the
1514 * character sequence represented by this {@code String}
1515 * object at an index no smaller than {@code fromIndex}, then
1516 * the index of the first such occurrence is returned. For values
1517 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1518 * this is the smallest value <i>k</i> such that:
1519 * <blockquote><pre>
1520 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1521 * </pre></blockquote>
1522 * is true. For other values of {@code ch}, it is the
1523 * smallest value <i>k</i> such that:
1524 * <blockquote><pre>
1525 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1526 * </pre></blockquote>
1527 * is true. In either case, if no such character occurs in this
1528 * string at or after position {@code fromIndex}, then
1529 * {@code -1} is returned.
1530 *
1531 * <p>
1532 * There is no restriction on the value of {@code fromIndex}. If it
1533 * is negative, it has the same effect as if it were zero: this entire
1534 * string may be searched. If it is greater than the length of this
1535 * string, it has the same effect as if it were equal to the length of
1536 * this string: {@code -1} is returned.
1537 *
1538 * <p>All indices are specified in {@code char} values
1539 * (Unicode code units).
1540 *
1541 * @param ch a character (Unicode code point).
1542 * @param fromIndex the index to start the search from.
1543 * @return the index of the first occurrence of the character in the
1544 * character sequence represented by this object that is greater
1545 * than or equal to {@code fromIndex}, or {@code -1}
1546 * if the character does not occur.
1547 */
1548 public int indexOf(int ch, int fromIndex) {
1549 final int max = value.length;
1550 if (fromIndex < 0) {
1551 fromIndex = 0;
1552 } else if (fromIndex >= max) {
1553 // Note: fromIndex might be near -1>>>1.
1554 return -1;
1555 }
1556
1557 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1558 // handle most cases here (ch is a BMP code point or a
1559 // negative value (invalid code point))
1560 final char[] value = this.value;
1561 for (int i = fromIndex; i < max; i++) {
1562 if (value[i] == ch) {
1563 return i;
1564 }
1565 }
1566 return -1;
1567 } else {
1568 return indexOfSupplementary(ch, fromIndex);
1569 }
1570 }
1571
1572 /**
1573 * Handles (rare) calls of indexOf with a supplementary character.
1574 */
1575 private int indexOfSupplementary(int ch, int fromIndex) {
1576 if (Character.isValidCodePoint(ch)) {
1577 final char[] value = this.value;
1578 final char hi = Character.highSurrogate(ch);
1579 final char lo = Character.lowSurrogate(ch);
1580 final int max = value.length - 1;
1581 for (int i = fromIndex; i < max; i++) {
1582 if (value[i] == hi && value[i + 1] == lo) {
1583 return i;
1584 }
1585 }
1586 }
1587 return -1;
1588 }
1589
1590 /**
1591 * Returns the index within this string of the last occurrence of
1592 * the specified character. For values of {@code ch} in the
1593 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1594 * units) returned is the largest value <i>k</i> such that:
1595 * <blockquote><pre>
1596 * this.charAt(<i>k</i>) == ch
1597 * </pre></blockquote>
1598 * is true. For other values of {@code ch}, it is the
1599 * largest value <i>k</i> such that:
1600 * <blockquote><pre>
1601 * this.codePointAt(<i>k</i>) == ch
1602 * </pre></blockquote>
1603 * is true. In either case, if no such character occurs in this
1604 * string, then {@code -1} is returned. The
1605 * {@code String} is searched backwards starting at the last
1606 * character.
1607 *
1608 * @param ch a character (Unicode code point).
1609 * @return the index of the last occurrence of the character in the
1610 * character sequence represented by this object, or
1611 * {@code -1} if the character does not occur.
1612 */
1613 public int lastIndexOf(int ch) {
1614 return lastIndexOf(ch, value.length - 1);
1615 }
1616
1617 /**
1618 * Returns the index within this string of the last occurrence of
1619 * the specified character, searching backward starting at the
1620 * specified index. For values of {@code ch} in the range
1621 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1622 * value <i>k</i> such that:
1623 * <blockquote><pre>
1624 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1625 * </pre></blockquote>
1626 * is true. For other values of {@code ch}, it is the
1627 * largest value <i>k</i> such that:
1628 * <blockquote><pre>
1629 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1630 * </pre></blockquote>
1631 * is true. In either case, if no such character occurs in this
1632 * string at or before position {@code fromIndex}, then
1633 * {@code -1} is returned.
1634 *
1635 * <p>All indices are specified in {@code char} values
1636 * (Unicode code units).
1637 *
1638 * @param ch a character (Unicode code point).
1639 * @param fromIndex the index to start the search from. There is no
1640 * restriction on the value of {@code fromIndex}. If it is
1641 * greater than or equal to the length of this string, it has
1642 * the same effect as if it were equal to one less than the
1643 * length of this string: this entire string may be searched.
1644 * If it is negative, it has the same effect as if it were -1:
1645 * -1 is returned.
1646 * @return the index of the last occurrence of the character in the
1647 * character sequence represented by this object that is less
1648 * than or equal to {@code fromIndex}, or {@code -1}
1649 * if the character does not occur before that point.
1650 */
1651 public int lastIndexOf(int ch, int fromIndex) {
1652 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1653 // handle most cases here (ch is a BMP code point or a
1654 // negative value (invalid code point))
1655 final char[] value = this.value;
1656 int i = Math.min(fromIndex, value.length - 1);
1657 for (; i >= 0; i--) {
1658 if (value[i] == ch) {
1659 return i;
1660 }
1661 }
1662 return -1;
1663 } else {
1664 return lastIndexOfSupplementary(ch, fromIndex);
1665 }
1666 }
1667
1668 /**
1669 * Handles (rare) calls of lastIndexOf with a supplementary character.
1670 */
1671 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1672 if (Character.isValidCodePoint(ch)) {
1673 final char[] value = this.value;
1674 char hi = Character.highSurrogate(ch);
1675 char lo = Character.lowSurrogate(ch);
1676 int i = Math.min(fromIndex, value.length - 2);
1677 for (; i >= 0; i--) {
1678 if (value[i] == hi && value[i + 1] == lo) {
1679 return i;
1680 }
1681 }
1682 }
1683 return -1;
1684 }
1685
1686 /**
1687 * Returns the index within this string of the first occurrence of the
1688 * specified substring.
1689 *
1690 * <p>The returned index is the smallest value {@code k} for which:
1691 * <pre>{@code
1692 * this.startsWith(str, k)
1693 * }</pre>
1694 * If no such value of {@code k} exists, then {@code -1} is returned.
1695 *
1696 * @param str the substring to search for.
1697 * @return the index of the first occurrence of the specified substring,
1698 * or {@code -1} if there is no such occurrence.
1699 */
1700 public int indexOf(String str) {
1701 return indexOf(str, 0);
1702 }
1703
1704 /**
1705 * Returns the index within this string of the first occurrence of the
1706 * specified substring, starting at the specified index.
1707 *
1708 * <p>The returned index is the smallest value {@code k} for which:
1709 * <pre>{@code
1710 * k >= Math.min(fromIndex, this.length()) &&
1711 * this.startsWith(str, k)
1712 * }</pre>
1713 * If no such value of {@code k} exists, then {@code -1} is returned.
1714 *
1715 * @param str the substring to search for.
1716 * @param fromIndex the index from which to start the search.
1717 * @return the index of the first occurrence of the specified substring,
1718 * starting at the specified index,
1719 * or {@code -1} if there is no such occurrence.
1720 */
1721 public int indexOf(String str, int fromIndex) {
1722 return indexOf(value, 0, value.length,
1723 str.value, 0, str.value.length, fromIndex);
1724 }
1725
1726 /**
1727 * Code shared by String and AbstractStringBuilder to do searches. The
1728 * source is the character array being searched, and the target
1729 * is the string being searched for.
1730 *
1731 * @param source the characters being searched.
1732 * @param sourceOffset offset of the source string.
1733 * @param sourceCount count of the source string.
1734 * @param target the characters being searched for.
1735 * @param fromIndex the index to begin searching from.
1736 */
1737 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1738 String target, int fromIndex) {
1739 return indexOf(source, sourceOffset, sourceCount,
1740 target.value, 0, target.value.length,
1741 fromIndex);
1742 }
1743
1744 /**
1745 * Code shared by String and StringBuffer to do searches. The
1746 * source is the character array being searched, and the target
1747 * is the string being searched for.
1748 *
1749 * @param source the characters being searched.
1750 * @param sourceOffset offset of the source string.
1751 * @param sourceCount count of the source string.
1752 * @param target the characters being searched for.
1753 * @param targetOffset offset of the target string.
1754 * @param targetCount count of the target string.
1755 * @param fromIndex the index to begin searching from.
1756 */
1757 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1758 char[] target, int targetOffset, int targetCount,
1759 int fromIndex) {
1760 if (fromIndex >= sourceCount) {
1761 return (targetCount == 0 ? sourceCount : -1);
1762 }
1763 if (fromIndex < 0) {
1764 fromIndex = 0;
1765 }
1766 if (targetCount == 0) {
1767 return fromIndex;
1768 }
1769
1770 char first = target[targetOffset];
1771 int max = sourceOffset + (sourceCount - targetCount);
1772
1773 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1774 /* Look for first character. */
1775 if (source[i] != first) {
1776 while (++i <= max && source[i] != first);
1777 }
1778
1779 /* Found first character, now look at the rest of v2 */
1780 if (i <= max) {
1781 int j = i + 1;
1782 int end = j + targetCount - 1;
1783 for (int k = targetOffset + 1; j < end && source[j]
1784 == target[k]; j++, k++);
1785
1786 if (j == end) {
1787 /* Found whole string. */
1788 return i - sourceOffset;
1789 }
1790 }
1791 }
1792 return -1;
1793 }
1794
1795 /**
1796 * Returns the index within this string of the last occurrence of the
1797 * specified substring. The last occurrence of the empty string ""
1798 * is considered to occur at the index value {@code this.length()}.
1799 *
1800 * <p>The returned index is the largest value {@code k} for which:
1801 * <pre>{@code
1802 * this.startsWith(str, k)
1803 * }</pre>
1804 * If no such value of {@code k} exists, then {@code -1} is returned.
1805 *
1806 * @param str the substring to search for.
1807 * @return the index of the last occurrence of the specified substring,
1808 * or {@code -1} if there is no such occurrence.
1809 */
1810 public int lastIndexOf(String str) {
1811 return lastIndexOf(str, value.length);
1812 }
1813
1814 /**
1815 * Returns the index within this string of the last occurrence of the
1816 * specified substring, searching backward starting at the specified index.
1817 *
1818 * <p>The returned index is the largest value {@code k} for which:
1819 * <pre>{@code
1820 * k <= Math.min(fromIndex, this.length()) &&
1821 * this.startsWith(str, k)
1822 * }</pre>
1823 * If no such value of {@code k} exists, then {@code -1} is returned.
1824 *
1825 * @param str the substring to search for.
1826 * @param fromIndex the index to start the search from.
1827 * @return the index of the last occurrence of the specified substring,
1828 * searching backward from the specified index,
1829 * or {@code -1} if there is no such occurrence.
1830 */
1831 public int lastIndexOf(String str, int fromIndex) {
1832 return lastIndexOf(value, 0, value.length,
1833 str.value, 0, str.value.length, fromIndex);
1834 }
1835
1836 /**
1837 * Code shared by String and AbstractStringBuilder to do searches. The
1838 * source is the character array being searched, and the target
1839 * is the string being searched for.
1840 *
1841 * @param source the characters being searched.
1842 * @param sourceOffset offset of the source string.
1843 * @param sourceCount count of the source string.
1844 * @param target the characters being searched for.
1845 * @param fromIndex the index to begin searching from.
1846 */
1847 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1848 String target, int fromIndex) {
1849 return lastIndexOf(source, sourceOffset, sourceCount,
1850 target.value, 0, target.value.length,
1851 fromIndex);
1852 }
1853
1854 /**
1855 * Code shared by String and StringBuffer to do searches. The
1856 * source is the character array being searched, and the target
1857 * is the string being searched for.
1858 *
1859 * @param source the characters being searched.
1860 * @param sourceOffset offset of the source string.
1861 * @param sourceCount count of the source string.
1862 * @param target the characters being searched for.
1863 * @param targetOffset offset of the target string.
1864 * @param targetCount count of the target string.
1865 * @param fromIndex the index to begin searching from.
1866 */
1867 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1868 char[] target, int targetOffset, int targetCount,
1869 int fromIndex) {
1870 /*
1871 * Check arguments; return immediately where possible. For
1872 * consistency, don't check for null str.
1873 */
1874 int rightIndex = sourceCount - targetCount;
1875 if (fromIndex < 0) {
1876 return -1;
1877 }
1878 if (fromIndex > rightIndex) {
1879 fromIndex = rightIndex;
1880 }
1881 /* Empty string always matches. */
1882 if (targetCount == 0) {
1883 return fromIndex;
1884 }
1885
1886 int strLastIndex = targetOffset + targetCount - 1;
1887 char strLastChar = target[strLastIndex];
1888 int min = sourceOffset + targetCount - 1;
1889 int i = min + fromIndex;
1890
1891 startSearchForLastChar:
1892 while (true) {
1893 while (i >= min && source[i] != strLastChar) {
1894 i--;
1895 }
1896 if (i < min) {
1897 return -1;
1898 }
1899 int j = i - 1;
1900 int start = j - (targetCount - 1);
1901 int k = strLastIndex - 1;
1902
1903 while (j > start) {
1904 if (source[j--] != target[k--]) {
1905 i--;
1906 continue startSearchForLastChar;
1907 }
1908 }
1909 return start - sourceOffset + 1;
1910 }
1911 }
1912
1913 /**
1914 * Returns a string that is a substring of this string. The
1915 * substring begins with the character at the specified index and
1916 * extends to the end of this string. <p>
1917 * Examples:
1918 * <blockquote><pre>
1919 * "unhappy".substring(2) returns "happy"
1920 * "Harbison".substring(3) returns "bison"
1921 * "emptiness".substring(9) returns "" (an empty string)
1922 * </pre></blockquote>
1923 *
1924 * @param beginIndex the beginning index, inclusive.
1925 * @return the specified substring.
1926 * @exception IndexOutOfBoundsException if
1927 * {@code beginIndex} is negative or larger than the
1928 * length of this {@code String} object.
1929 */
1930 public String substring(int beginIndex) {
1931 if (beginIndex < 0) {
1932 throw new StringIndexOutOfBoundsException(beginIndex);
1933 }
1934 int subLen = value.length - beginIndex;
1935 if (subLen < 0) {
1936 throw new StringIndexOutOfBoundsException(subLen);
1937 }
1938 return (beginIndex == 0) ? this : 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 throw new StringIndexOutOfBoundsException(beginIndex);
1966 }
1967 if (endIndex > value.length) {
1968 throw new StringIndexOutOfBoundsException(endIndex);
1969 }
1970 int subLen = endIndex - beginIndex;
1971 if (subLen < 0) {
1972 throw new StringIndexOutOfBoundsException(subLen);
1973 }
1974 return ((beginIndex == 0) && (endIndex == value.length)) ? this
1975 : new String(value, beginIndex, subLen);
1976 }
1977
1978 /**
1979 * Returns a character sequence that is a subsequence of this sequence.
1980 *
1981 * <p> An invocation of this method of the form
1982 *
1983 * <blockquote><pre>
1984 * str.subSequence(begin, end)</pre></blockquote>
1985 *
1986 * behaves in exactly the same way as the invocation
1987 *
1988 * <blockquote><pre>
1989 * str.substring(begin, end)</pre></blockquote>
1990 *
1991 * @apiNote
1992 * This method is defined so that the {@code String} class can implement
1993 * the {@link CharSequence} interface.
1994 *
1995 * @param beginIndex the begin index, inclusive.
1996 * @param endIndex the end index, exclusive.
1997 * @return the specified subsequence.
1998 *
1999 * @throws IndexOutOfBoundsException
2000 * if {@code beginIndex} or {@code endIndex} is negative,
2001 * if {@code endIndex} is greater than {@code length()},
2002 * or if {@code beginIndex} is greater than {@code endIndex}
2003 *
2004 * @since 1.4
2005 * @spec JSR-51
2006 */
2007 public CharSequence subSequence(int beginIndex, int endIndex) {
2008 return this.substring(beginIndex, endIndex);
2009 }
2010
2011 /**
2012 * Concatenates the specified string to the end of this string.
2013 * <p>
2014 * If the length of the argument string is {@code 0}, then this
2015 * {@code String} object is returned. Otherwise, a
2016 * {@code String} object is returned that represents a character
2017 * sequence that is the concatenation of the character sequence
2018 * represented by this {@code String} object and the character
2019 * sequence represented by the argument string.<p>
2020 * Examples:
2021 * <blockquote><pre>
2022 * "cares".concat("s") returns "caress"
2023 * "to".concat("get").concat("her") returns "together"
2024 * </pre></blockquote>
2025 *
2026 * @param str the {@code String} that is concatenated to the end
2027 * of this {@code String}.
2028 * @return a string that represents the concatenation of this object's
2029 * characters followed by the string argument's characters.
2030 */
2031 public String concat(String str) {
2032 int otherLen = str.length();
2033 if (otherLen == 0) {
2034 return this;
2035 }
2036 int len = value.length;
2037 char buf[] = Arrays.copyOf(value, len + otherLen);
2038 str.getChars(buf, len);
2039 return new String(buf, true);
2040 }
2041
2042 /**
2043 * Returns a string resulting from replacing all occurrences of
2044 * {@code oldChar} in this string with {@code newChar}.
2045 * <p>
2046 * If the character {@code oldChar} does not occur in the
2047 * character sequence represented by this {@code String} object,
2048 * then a reference to this {@code String} object is returned.
2049 * Otherwise, a {@code String} object is returned that
2050 * represents a character sequence identical to the character sequence
2051 * represented by this {@code String} object, except that every
2052 * occurrence of {@code oldChar} is replaced by an occurrence
2053 * of {@code newChar}.
2054 * <p>
2055 * Examples:
2056 * <blockquote><pre>
2057 * "mesquite in your cellar".replace('e', 'o')
2058 * returns "mosquito in your collar"
2059 * "the war of baronets".replace('r', 'y')
2060 * returns "the way of bayonets"
2061 * "sparring with a purple porpoise".replace('p', 't')
2062 * returns "starring with a turtle tortoise"
2063 * "JonL".replace('q', 'x') returns "JonL" (no change)
2064 * </pre></blockquote>
2065 *
2066 * @param oldChar the old character.
2067 * @param newChar the new character.
2068 * @return a string derived from this string by replacing every
2069 * occurrence of {@code oldChar} with {@code newChar}.
2070 */
2071 public String replace(char oldChar, char newChar) {
2072 if (oldChar != newChar) {
2073 int len = value.length;
2074 int i = -1;
2075 char[] val = value; /* avoid getfield opcode */
2076
2077 while (++i < len) {
2078 if (val[i] == oldChar) {
2079 break;
2080 }
2081 }
2082 if (i < len) {
2083 char buf[] = new char[len];
2084 for (int j = 0; j < i; j++) {
2085 buf[j] = val[j];
2086 }
2087 while (i < len) {
2088 char c = val[i];
2089 buf[i] = (c == oldChar) ? newChar : c;
2090 i++;
2091 }
2092 return new String(buf, true);
2093 }
2094 }
2095 return this;
2096 }
2097
2098 /**
2099 * Tells whether or not this string matches the given <a
2100 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2101 *
2102 * <p> An invocation of this method of the form
2103 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2104 * same result as the expression
2105 *
2106 * <blockquote>
2107 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2108 * matches(<i>regex</i>, <i>str</i>)}
2109 * </blockquote>
2110 *
2111 * @param regex
2112 * the regular expression to which this string is to be matched
2113 *
2114 * @return {@code true} if, and only if, this string matches the
2115 * given regular expression
2116 *
2117 * @throws PatternSyntaxException
2118 * if the regular expression's syntax is invalid
2119 *
2120 * @see java.util.regex.Pattern
2121 *
2122 * @since 1.4
2123 * @spec JSR-51
2124 */
2125 public boolean matches(String regex) {
2126 return Pattern.matches(regex, this);
2127 }
2128
2129 /**
2130 * Returns true if and only if this string contains the specified
2131 * sequence of char values.
2132 *
2133 * @param s the sequence to search for
2134 * @return true if this string contains {@code s}, false otherwise
2135 * @since 1.5
2136 */
2137 public boolean contains(CharSequence s) {
2138 return indexOf(s.toString()) >= 0;
2139 }
2140
2141 /**
2142 * Replaces the first substring of this string that matches the given <a
2143 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2144 * given replacement.
2145 *
2146 * <p> An invocation of this method of the form
2147 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2148 * yields exactly the same result as the expression
2149 *
2150 * <blockquote>
2151 * <code>
2152 * {@link java.util.regex.Pattern}.{@link
2153 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2154 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2155 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2156 * </code>
2157 * </blockquote>
2158 *
2159 *<p>
2160 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2161 * replacement string may cause the results to be different than if it were
2162 * being treated as a literal replacement string; see
2163 * {@link java.util.regex.Matcher#replaceFirst}.
2164 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2165 * meaning of these characters, if desired.
2166 *
2167 * @param regex
2168 * the regular expression to which this string is to be matched
2169 * @param replacement
2170 * the string to be substituted for the first match
2171 *
2172 * @return The resulting {@code String}
2173 *
2174 * @throws PatternSyntaxException
2175 * if the regular expression's syntax is invalid
2176 *
2177 * @see java.util.regex.Pattern
2178 *
2179 * @since 1.4
2180 * @spec JSR-51
2181 */
2182 public String replaceFirst(String regex, String replacement) {
2183 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2184 }
2185
2186 /**
2187 * Replaces each substring of this string that matches the given <a
2188 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2189 * given replacement.
2190 *
2191 * <p> An invocation of this method of the form
2192 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2193 * yields exactly the same result as the expression
2194 *
2195 * <blockquote>
2196 * <code>
2197 * {@link java.util.regex.Pattern}.{@link
2198 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2199 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2200 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2201 * </code>
2202 * </blockquote>
2203 *
2204 *<p>
2205 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2206 * replacement string may cause the results to be different than if it were
2207 * being treated as a literal replacement string; see
2208 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2209 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2210 * meaning of these characters, if desired.
2211 *
2212 * @param regex
2213 * the regular expression to which this string is to be matched
2214 * @param replacement
2215 * the string to be substituted for each match
2216 *
2217 * @return The resulting {@code String}
2218 *
2219 * @throws PatternSyntaxException
2220 * if the regular expression's syntax is invalid
2221 *
2222 * @see java.util.regex.Pattern
2223 *
2224 * @since 1.4
2225 * @spec JSR-51
2226 */
2227 public String replaceAll(String regex, String replacement) {
2228 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2229 }
2230
2231 /**
2232 * Replaces each substring of this string that matches the literal target
2233 * sequence with the specified literal replacement sequence. The
2234 * replacement proceeds from the beginning of the string to the end, for
2235 * example, replacing "aa" with "b" in the string "aaa" will result in
2236 * "ba" rather than "ab".
2237 *
2238 * @param target The sequence of char values to be replaced
2239 * @param replacement The replacement sequence of char values
2240 * @return The resulting string
2241 * @since 1.5
2242 */
2243 public String replace(CharSequence target, CharSequence replacement) {
2244 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
2245 this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
2246 }
2247
2248 /**
2249 * Splits this string around matches of the given
2250 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2251 *
2252 * <p> The array returned by this method contains each substring of this
2253 * string that is terminated by another substring that matches the given
2254 * expression or is terminated by the end of the string. The substrings in
2255 * the array are in the order in which they occur in this string. If the
2256 * expression does not match any part of the input then the resulting array
2257 * has just one element, namely this string.
2258 *
2259 * <p> When there is a positive-width match at the beginning of this
2260 * string then an empty leading substring is included at the beginning
2261 * of the resulting array. A zero-width match at the beginning however
2262 * never produces such empty leading substring.
2263 *
2264 * <p> The {@code limit} parameter controls the number of times the
2265 * pattern is applied and therefore affects the length of the resulting
2266 * array. If the limit <i>n</i> is greater than zero then the pattern
2267 * will be applied at most <i>n</i> - 1 times, the array's
2268 * length will be no greater than <i>n</i>, and the array's last entry
2269 * will contain all input beyond the last matched delimiter. If <i>n</i>
2270 * is non-positive then the pattern will be applied as many times as
2271 * possible and the array can have any length. If <i>n</i> is zero then
2272 * the pattern will be applied as many times as possible, the array can
2273 * have any length, and trailing empty strings will be discarded.
2274 *
2275 * <p> The string {@code "boo:and:foo"}, for example, yields the
2276 * following results with these parameters:
2277 *
2278 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2279 * <tr>
2280 * <th>Regex</th>
2281 * <th>Limit</th>
2282 * <th>Result</th>
2283 * </tr>
2284 * <tr><td align=center>:</td>
2285 * <td align=center>2</td>
2286 * <td>{@code { "boo", "and:foo" }}</td></tr>
2287 * <tr><td align=center>:</td>
2288 * <td align=center>5</td>
2289 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2290 * <tr><td align=center>:</td>
2291 * <td align=center>-2</td>
2292 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2293 * <tr><td align=center>o</td>
2294 * <td align=center>5</td>
2295 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2296 * <tr><td align=center>o</td>
2297 * <td align=center>-2</td>
2298 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2299 * <tr><td align=center>o</td>
2300 * <td align=center>0</td>
2301 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2302 * </table></blockquote>
2303 *
2304 * <p> An invocation of this method of the form
2305 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2306 * yields the same result as the expression
2307 *
2308 * <blockquote>
2309 * <code>
2310 * {@link java.util.regex.Pattern}.{@link
2311 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2312 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2313 * </code>
2314 * </blockquote>
2315 *
2316 *
2317 * @param regex
2318 * the delimiting regular expression
2319 *
2320 * @param limit
2321 * the result threshold, as described above
2322 *
2323 * @return the array of strings computed by splitting this string
2324 * around matches of the given regular expression
2325 *
2326 * @throws PatternSyntaxException
2327 * if the regular expression's syntax is invalid
2328 *
2329 * @see java.util.regex.Pattern
2330 *
2331 * @since 1.4
2332 * @spec JSR-51
2333 */
2334 public String[] split(String regex, int limit) {
2335 /* fastpath if the regex is a
2336 (1)one-char String and this character is not one of the
2337 RegEx's meta characters ".$|()[{^?*+\\", or
2338 (2)two-char String and the first char is the backslash and
2339 the second is not the ascii digit or ascii letter.
2340 */
2341 char ch = 0;
2342 if (((regex.value.length == 1 &&
2343 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2344 (regex.length() == 2 &&
2345 regex.charAt(0) == '\\' &&
2346 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2347 ((ch-'a')|('z'-ch)) < 0 &&
2348 ((ch-'A')|('Z'-ch)) < 0)) &&
2349 (ch < Character.MIN_HIGH_SURROGATE ||
2350 ch > Character.MAX_LOW_SURROGATE))
2351 {
2352 int off = 0;
2353 int next = 0;
2354 boolean limited = limit > 0;
2355 ArrayList<String> list = new ArrayList<>();
2356 while ((next = indexOf(ch, off)) != -1) {
2357 if (!limited || list.size() < limit - 1) {
2358 list.add(substring(off, next));
2359 off = next + 1;
2360 } else { // last one
2361 //assert (list.size() == limit - 1);
2362 list.add(substring(off, value.length));
2363 off = value.length;
2364 break;
2365 }
2366 }
2367 // If no match was found, return this
2368 if (off == 0)
2369 return new String[]{this};
2370
2371 // Add remaining segment
2372 if (!limited || list.size() < limit)
2373 list.add(substring(off, value.length));
2374
2375 // Construct result
2376 int resultSize = list.size();
2377 if (limit == 0) {
2378 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2379 resultSize--;
2380 }
2381 }
2382 String[] result = new String[resultSize];
2383 return list.subList(0, resultSize).toArray(result);
2384 }
2385 return Pattern.compile(regex).split(this, limit);
2386 }
2387
2388 /**
2389 * Splits this string around matches of the given <a
2390 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2391 *
2392 * <p> This method works as if by invoking the two-argument {@link
2393 * #split(String, int) split} method with the given expression and a limit
2394 * argument of zero. Trailing empty strings are therefore not included in
2395 * the resulting array.
2396 *
2397 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2398 * results with these expressions:
2399 *
2400 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2401 * <tr>
2402 * <th>Regex</th>
2403 * <th>Result</th>
2404 * </tr>
2405 * <tr><td align=center>:</td>
2406 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2407 * <tr><td align=center>o</td>
2408 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2409 * </table></blockquote>
2410 *
2411 *
2412 * @param regex
2413 * the delimiting regular expression
2414 *
2415 * @return the array of strings computed by splitting this string
2416 * around matches of the given regular expression
2417 *
2418 * @throws PatternSyntaxException
2419 * if the regular expression's syntax is invalid
2420 *
2421 * @see java.util.regex.Pattern
2422 *
2423 * @since 1.4
2424 * @spec JSR-51
2425 */
2426 public String[] split(String regex) {
2427 return split(regex, 0);
2428 }
2429
2430 /**
2431 * Returns a new String composed of copies of the
2432 * {@code CharSequence elements} joined together with a copy of
2433 * the specified {@code delimiter}.
2434 *
2435 * <blockquote>For example,
2436 * <pre>{@code
2437 * String message = String.join("-", "Java", "is", "cool");
2438 * // message returned is: "Java-is-cool"
2439 * }</pre></blockquote>
2440 *
2441 * Note that if an element is null, then {@code "null"} is added.
2442 *
2443 * @param delimiter the delimiter that separates each element
2444 * @param elements the elements to join together.
2445 *
2446 * @return a new {@code String} that is composed of the {@code elements}
2447 * separated by the {@code delimiter}
2448 *
2449 * @throws NullPointerException If {@code delimiter} or {@code elements}
2450 * is {@code null}
2451 *
2452 * @see java.util.StringJoiner
2453 * @since 1.8
2454 */
2455 public static String join(CharSequence delimiter, CharSequence... elements) {
2456 Objects.requireNonNull(delimiter);
2457 Objects.requireNonNull(elements);
2458 // Number of elements not likely worth Arrays.stream overhead.
2459 StringJoiner joiner = new StringJoiner(delimiter);
2460 for (CharSequence cs: elements) {
2461 joiner.add(cs);
2462 }
2463 return joiner.toString();
2464 }
2465
2466 /**
2467 * Returns a new {@code String} composed of copies of the
2468 * {@code CharSequence elements} joined together with a copy of the
2469 * specified {@code delimiter}.
2470 *
2471 * <blockquote>For example,
2472 * <pre>{@code
2473 * List<String> strings = new LinkedList<>();
2474 * strings.add("Java");strings.add("is");
2475 * strings.add("cool");
2476 * String message = String.join(" ", strings);
2477 * //message returned is: "Java is cool"
2478 *
2479 * Set<String> strings = new LinkedHashSet<>();
2480 * strings.add("Java"); strings.add("is");
2481 * strings.add("very"); strings.add("cool");
2482 * String message = String.join("-", strings);
2483 * //message returned is: "Java-is-very-cool"
2484 * }</pre></blockquote>
2485 *
2486 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2487 *
2488 * @param delimiter a sequence of characters that is used to separate each
2489 * of the {@code elements} in the resulting {@code String}
2490 * @param elements an {@code Iterable} that will have its {@code elements}
2491 * joined together.
2492 *
2493 * @return a new {@code String} that is composed from the {@code elements}
2494 * argument
2495 *
2496 * @throws NullPointerException If {@code delimiter} or {@code elements}
2497 * is {@code null}
2498 *
2499 * @see #join(CharSequence,CharSequence...)
2500 * @see java.util.StringJoiner
2501 * @since 1.8
2502 */
2503 public static String join(CharSequence delimiter,
2504 Iterable<? extends CharSequence> elements) {
2505 Objects.requireNonNull(delimiter);
2506 Objects.requireNonNull(elements);
2507 StringJoiner joiner = new StringJoiner(delimiter);
2508 for (CharSequence cs: elements) {
2509 joiner.add(cs);
2510 }
2511 return joiner.toString();
2512 }
2513
2514 /**
2515 * Converts all of the characters in this {@code String} to lower
2516 * case using the rules of the given {@code Locale}. Case mapping is based
2517 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2518 * class. Since case mappings are not always 1:1 char mappings, the resulting
2519 * {@code String} may be a different length than the original {@code String}.
2520 * <p>
2521 * Examples of lowercase mappings are in the following table:
2522 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2523 * <tr>
2524 * <th>Language Code of Locale</th>
2525 * <th>Upper Case</th>
2526 * <th>Lower Case</th>
2527 * <th>Description</th>
2528 * </tr>
2529 * <tr>
2530 * <td>tr (Turkish)</td>
2531 * <td>\u0130</td>
2532 * <td>\u0069</td>
2533 * <td>capital letter I with dot above -> small letter i</td>
2534 * </tr>
2535 * <tr>
2536 * <td>tr (Turkish)</td>
2537 * <td>\u0049</td>
2538 * <td>\u0131</td>
2539 * <td>capital letter I -> small letter dotless i </td>
2540 * </tr>
2541 * <tr>
2542 * <td>(all)</td>
2543 * <td>French Fries</td>
2544 * <td>french fries</td>
2545 * <td>lowercased all chars in String</td>
2546 * </tr>
2547 * <tr>
2548 * <td>(all)</td>
2549 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2550 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2551 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2552 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2553 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2554 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2555 * <td>lowercased all chars in String</td>
2556 * </tr>
2557 * </table>
2558 *
2559 * @param locale use the case transformation rules for this locale
2560 * @return the {@code String}, converted to lowercase.
2561 * @see java.lang.String#toLowerCase()
2562 * @see java.lang.String#toUpperCase()
2563 * @see java.lang.String#toUpperCase(Locale)
2564 * @since 1.1
2565 */
2566 public String toLowerCase(Locale locale) {
2567 if (locale == null) {
2568 throw new NullPointerException();
2569 }
2570 int first;
2571 boolean hasSurr = false;
2572 final int len = value.length;
2573
2574 // Now check if there are any characters that need to be changed, or are surrogate
2575 for (first = 0 ; first < len; first++) {
2576 int cp = (int)value[first];
2577 if (Character.isSurrogate((char)cp)) {
2578 hasSurr = true;
2579 break;
2580 }
2581 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR
2582 break;
2583 }
2584 }
2585 if (first == len)
2586 return this;
2587 char[] result = new char[len];
2588 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2589 // lowerCase characters.
2590 String lang = locale.getLanguage();
2591 if (lang == "tr" || lang == "az" || lang == "lt") {
2592 return toLowerCaseEx(result, first, locale, true);
2593 }
2594 if (hasSurr) {
2595 return toLowerCaseEx(result, first, locale, false);
2596 }
2597 for (int i = first; i < len; i++) {
2598 int cp = (int)value[i];
2599 if (cp == '\u03A3' || // GREEK CAPITAL LETTER SIGMA
2600 Character.isSurrogate((char)cp)) {
2601 return toLowerCaseEx(result, i, locale, false);
2602 }
2603 if (cp == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE
2604 return toLowerCaseEx(result, i, locale, true);
2605 }
2606 cp = Character.toLowerCase(cp);
2607 if (!Character.isBmpCodePoint(cp)) {
2608 return toLowerCaseEx(result, i, locale, false);
2609 }
2610 result[i] = (char)cp;
2611 }
2612 return new String(result, true);
2613 }
2614
2615 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) {
2616 int resultOffset = first;
2617 int srcCount;
2618 for (int i = first; i < value.length; i += srcCount) {
2619 int srcChar = (int)value[i];
2620 int lowerChar;
2621 char[] lowerCharArray;
2622 srcCount = 1;
2623 if (Character.isSurrogate((char)srcChar)) {
2624 srcChar = codePointAt(i);
2625 srcCount = Character.charCount(srcChar);
2626 }
2627 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2628 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2629 } else {
2630 lowerChar = Character.toLowerCase(srcChar);
2631 }
2632 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp
2633 result[resultOffset++] = (char)lowerChar;
2634 } else {
2635 if (lowerChar == Character.ERROR) {
2636 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2637 } else if (srcCount == 2) {
2638 resultOffset += Character.toChars(lowerChar, result, resultOffset);
2639 continue;
2640 } else {
2641 lowerCharArray = Character.toChars(lowerChar);
2642 }
2643 /* Grow result if needed */
2644 int mapLen = lowerCharArray.length;
2645 if (mapLen > srcCount) {
2646 char[] result2 = new char[result.length + mapLen - srcCount];
2647 System.arraycopy(result, 0, result2, 0, resultOffset);
2648 result = result2;
2649 }
2650 for (int x = 0; x < mapLen; ++x) {
2651 result[resultOffset++] = lowerCharArray[x];
2652 }
2653 }
2654 }
2655 return new String(result, 0, resultOffset);
2656 }
2657
2658 /**
2659 * Converts all of the characters in this {@code String} to lower
2660 * case using the rules of the default locale. This is equivalent to calling
2661 * {@code toLowerCase(Locale.getDefault())}.
2662 * <p>
2663 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2664 * results if used for strings that are intended to be interpreted locale
2665 * independently.
2666 * Examples are programming language identifiers, protocol keys, and HTML
2667 * tags.
2668 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2669 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2670 * LATIN SMALL LETTER DOTLESS I character.
2671 * To obtain correct results for locale insensitive strings, use
2672 * {@code toLowerCase(Locale.ROOT)}.
2673 *
2674 * @return the {@code String}, converted to lowercase.
2675 * @see java.lang.String#toLowerCase(Locale)
2676 */
2677 public String toLowerCase() {
2678 return toLowerCase(Locale.getDefault());
2679 }
2680
2681 /**
2682 * Converts all of the characters in this {@code String} to upper
2683 * case using the rules of the given {@code Locale}. Case mapping is based
2684 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2685 * class. Since case mappings are not always 1:1 char mappings, the resulting
2686 * {@code String} may be a different length than the original {@code String}.
2687 * <p>
2688 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2689 *
2690 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2691 * <tr>
2692 * <th>Language Code of Locale</th>
2693 * <th>Lower Case</th>
2694 * <th>Upper Case</th>
2695 * <th>Description</th>
2696 * </tr>
2697 * <tr>
2698 * <td>tr (Turkish)</td>
2699 * <td>\u0069</td>
2700 * <td>\u0130</td>
2701 * <td>small letter i -> capital letter I with dot above</td>
2702 * </tr>
2703 * <tr>
2704 * <td>tr (Turkish)</td>
2705 * <td>\u0131</td>
2706 * <td>\u0049</td>
2707 * <td>small letter dotless i -> capital letter I</td>
2708 * </tr>
2709 * <tr>
2710 * <td>(all)</td>
2711 * <td>\u00df</td>
2712 * <td>\u0053 \u0053</td>
2713 * <td>small letter sharp s -> two letters: SS</td>
2714 * </tr>
2715 * <tr>
2716 * <td>(all)</td>
2717 * <td>Fahrvergnügen</td>
2718 * <td>FAHRVERGNÜGEN</td>
2719 * <td></td>
2720 * </tr>
2721 * </table>
2722 * @param locale use the case transformation rules for this locale
2723 * @return the {@code String}, converted to uppercase.
2724 * @see java.lang.String#toUpperCase()
2725 * @see java.lang.String#toLowerCase()
2726 * @see java.lang.String#toLowerCase(Locale)
2727 * @since 1.1
2728 */
2729 public String toUpperCase(Locale locale) {
2730 if (locale == null) {
2731 throw new NullPointerException();
2732 }
2733 int first;
2734 boolean hasSurr = false;
2735 final int len = value.length;
2736
2737 // Now check if there are any characters that need to be changed, or are surrogate
2738 for (first = 0 ; first < len; first++ ) {
2739 int cp = (int)value[first];
2740 if (Character.isSurrogate((char)cp)) {
2741 hasSurr = true;
2742 break;
2743 }
2744 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR
2745 break;
2746 }
2747 }
2748 if (first == len) {
2749 return this;
2750 }
2751 char[] result = new char[len];
2752 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2753 // upperCase characters.
2754 String lang = locale.getLanguage();
2755 if (lang == "tr" || lang == "az" || lang == "lt") {
2756 return toUpperCaseEx(result, first, locale, true);
2757 }
2758 if (hasSurr) {
2759 return toUpperCaseEx(result, first, locale, false);
2760 }
2761 for (int i = first; i < len; i++) {
2762 int cp = (int)value[i];
2763 if (Character.isSurrogate((char)cp)) {
2764 return toUpperCaseEx(result, i, locale, false);
2765 }
2766 cp = Character.toUpperCaseEx(cp);
2767 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp
2768 return toUpperCaseEx(result, i, locale, false);
2769 }
2770 result[i] = (char)cp;
2771 }
2772 return new String(result, true);
2773 }
2774
2775 private String toUpperCaseEx(char[] result, int first, Locale locale,
2776 boolean localeDependent) {
2777 int resultOffset = first;
2778 int srcCount;
2779 for (int i = first; i < value.length; i += srcCount) {
2780 int srcChar = (int)value[i];
2781 int upperChar;
2782 char[] upperCharArray;
2783 srcCount = 1;
2784 if (Character.isSurrogate((char)srcChar)) {
2785 srcChar = codePointAt(i);
2786 srcCount = Character.charCount(srcChar);
2787 }
2788 if (localeDependent) {
2789 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2790 } else {
2791 upperChar = Character.toUpperCaseEx(srcChar);
2792 }
2793 if (Character.isBmpCodePoint(upperChar)) {
2794 result[resultOffset++] = (char)upperChar;
2795 } else {
2796 if (upperChar == Character.ERROR) {
2797 if (localeDependent) {
2798 upperCharArray =
2799 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
2800 } else {
2801 upperCharArray = Character.toUpperCaseCharArray(srcChar);
2802 }
2803 } else if (srcCount == 2) {
2804 resultOffset += Character.toChars(upperChar, result, resultOffset);
2805 continue;
2806 } else {
2807 upperCharArray = Character.toChars(upperChar);
2808 }
2809 /* Grow result if needed */
2810 int mapLen = upperCharArray.length;
2811 if (mapLen > srcCount) {
2812 char[] result2 = new char[result.length + mapLen - srcCount];
2813 System.arraycopy(result, 0, result2, 0, resultOffset);
2814 result = result2;
2815 }
2816 for (int x = 0; x < mapLen; ++x) {
2817 result[resultOffset++] = upperCharArray[x];
2818 }
2819 }
2820 }
2821 return new String(result, 0, resultOffset);
2822 }
2823
2824 /**
2825 * Converts all of the characters in this {@code String} to upper
2826 * case using the rules of the default locale. This method is equivalent to
2827 * {@code toUpperCase(Locale.getDefault())}.
2828 * <p>
2829 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2830 * results if used for strings that are intended to be interpreted locale
2831 * independently.
2832 * Examples are programming language identifiers, protocol keys, and HTML
2833 * tags.
2834 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2835 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2836 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2837 * To obtain correct results for locale insensitive strings, use
2838 * {@code toUpperCase(Locale.ROOT)}.
2839 *
2840 * @return the {@code String}, converted to uppercase.
2841 * @see java.lang.String#toUpperCase(Locale)
2842 */
2843 public String toUpperCase() {
2844 return toUpperCase(Locale.getDefault());
2845 }
2846
2847 /**
2848 * Returns a string whose value is this string, with any leading and trailing
2849 * whitespace removed.
2850 * <p>
2851 * If this {@code String} object represents an empty character
2852 * sequence, or the first and last characters of character sequence
2853 * represented by this {@code String} object both have codes
2854 * greater than {@code '\u005Cu0020'} (the space character), then a
2855 * reference to this {@code String} object is returned.
2856 * <p>
2857 * Otherwise, if there is no character with a code greater than
2858 * {@code '\u005Cu0020'} in the string, then a
2859 * {@code String} object representing an empty string is
2860 * returned.
2861 * <p>
2862 * Otherwise, let <i>k</i> be the index of the first character in the
2863 * string whose code is greater than {@code '\u005Cu0020'}, and let
2864 * <i>m</i> be the index of the last character in the string whose code
2865 * is greater than {@code '\u005Cu0020'}. A {@code String}
2866 * object is returned, representing the substring of this string that
2867 * begins with the character at index <i>k</i> and ends with the
2868 * character at index <i>m</i>-that is, the result of
2869 * {@code this.substring(k, m + 1)}.
2870 * <p>
2871 * This method may be used to trim whitespace (as defined above) from
2872 * the beginning and end of a string.
2873 *
2874 * @return A string whose value is this string, with any leading and trailing white
2875 * space removed, or this string if it has no leading or
2876 * trailing white space.
2877 */
2878 public String trim() {
2879 int len = value.length;
2880 int st = 0;
2881 char[] val = value; /* avoid getfield opcode */
2882
2883 while ((st < len) && (val[st] <= ' ')) {
2884 st++;
2885 }
2886 while ((st < len) && (val[len - 1] <= ' ')) {
2887 len--;
2888 }
2889 return ((st > 0) || (len < value.length)) ? substring(st, len) : this;
2890 }
2891
2892 /**
2893 * This object (which is already a string!) is itself returned.
2894 *
2895 * @return the string itself.
2896 */
2897 public String toString() {
2898 return this;
2899 }
2900
2901 static class IntCharArraySpliterator implements Spliterator.OfInt {
2902 private final char[] array;
2903 private int index; // current index, modified on advance/split
2904 private final int fence; // one past last index
2905 private final int cs;
2906
2907 IntCharArraySpliterator(char[] array, int acs) {
2908 this(array, 0, array.length, acs);
2909 }
2910
2911 IntCharArraySpliterator(char[] array, int origin, int fence, int acs) {
2912 this.array = array;
2913 this.index = origin;
2914 this.fence = fence;
2915 this.cs = acs | Spliterator.ORDERED | Spliterator.SIZED
2916 | Spliterator.SUBSIZED;
2917 }
2918
2919 @Override
2920 public OfInt trySplit() {
2921 int lo = index, mid = (lo + fence) >>> 1;
2922 return (lo >= mid)
2923 ? null
2924 : new IntCharArraySpliterator(array, lo, index = mid, cs);
2925 }
2926
2927 @Override
2928 public void forEachRemaining(IntConsumer action) {
2929 char[] a; int i, hi; // hoist accesses and checks from loop
2930 if (action == null)
2931 throw new NullPointerException();
2932 if ((a = array).length >= (hi = fence) &&
2933 (i = index) >= 0 && i < (index = hi)) {
2934 do { action.accept(a[i]); } while (++i < hi);
2935 }
2936 }
2937
2938 @Override
2939 public boolean tryAdvance(IntConsumer action) {
2940 if (action == null)
2941 throw new NullPointerException();
2942 if (index >= 0 && index < fence) {
2943 action.accept(array[index++]);
2944 return true;
2945 }
2946 return false;
2947 }
2948
2949 @Override
2950 public long estimateSize() { return (long)(fence - index); }
2951
2952 @Override
2953 public int characteristics() {
2954 return cs;
2955 }
2956 }
2957
2958 /**
2959 * Returns a stream of {@code int} zero-extending the {@code char} values
2960 * from this sequence. Any char which maps to a <a
2961 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code
2962 * point</a> is passed through uninterpreted.
2963 *
2964 * @return an IntStream of char values from this sequence
2965 * @since 1.9
2966 */
2967 @Override
2968 public IntStream chars() {
2969 return StreamSupport.intStream(
2970 new IntCharArraySpliterator(value, Spliterator.IMMUTABLE), false);
2971 }
2972
2973 static class CodePointsSpliterator implements Spliterator.OfInt {
2974 private final char[] array;
2975 private int index; // current index, modified on advance/split
2976 private final int fence; // one past last index
2977 private final int cs;
2978
2979 CodePointsSpliterator(char[] array, int acs) {
2980 this(array, 0, array.length, acs);
2981 }
2982
2983 CodePointsSpliterator(char[] array, int origin, int fence, int acs) {
2984 this.array = array;
2985 this.index = origin;
2986 this.fence = fence;
2987 this.cs = acs | Spliterator.ORDERED;
2988 }
2989
2990 @Override
2991 public OfInt trySplit() {
2992 int lo = index, mid = (lo + fence) >>> 1;
2993 if (lo >= mid)
2994 return null;
2995
2996 int midOneLess;
2997 // If the mid-point intersects a surrogate pair
2998 if (Character.isLowSurrogate(array[mid]) &&
2999 Character.isHighSurrogate(array[midOneLess = (mid -1)])) {
3000 // If there is only one pair it cannot be split
3001 if (lo >= midOneLess)
3002 return null;
3003 // Shift the mid-point to align with the surrogate pair
3004 return new CodePointsSpliterator(array, lo, index = midOneLess, cs);
3005 }
3006 return new CodePointsSpliterator(array, lo, index = mid, cs);
3007 }
3008
3009 @Override
3010 public void forEachRemaining(IntConsumer action) {
3011 char[] a; int i, hi; // hoist accesses and checks from loop
3012 if (action == null)
3013 throw new NullPointerException();
3014 if ((a = array).length >= (hi = fence) &&
3015 (i = index) >= 0 && i < (index = hi)) {
3016 do {
3017 i = advance(a, i, hi, action);
3018 } while (i < hi);
3019 }
3020 }
3021
3022 @Override
3023 public boolean tryAdvance(IntConsumer action) {
3024 if (action == null)
3025 throw new NullPointerException();
3026 if (index >= 0 && index < fence) {
3027 index = advance(array, index, fence, action);
3028 return true;
3029 }
3030 return false;
3031 }
3032
3033 // Advance one code point from the index, i, and return the next
3034 // index to advance from
3035 private static int advance(char[] a, int i, int hi, IntConsumer action) {
3036 char c1 = a[i++];
3037 int cp = c1;
3038 if (Character.isHighSurrogate(c1) && i < hi) {
3039 char c2 = a[i];
3040 if (Character.isLowSurrogate(c2)) {
3041 i++;
3042 cp = Character.toCodePoint(c1, c2);
3043 }
3044 }
3045 action.accept(cp);
3046 return i;
3047 }
3048
3049 @Override
3050 public long estimateSize() { return (long)(fence - index); }
3051
3052 @Override
3053 public int characteristics() {
3054 return cs;
3055 }
3056 }
3057
3058 /**
3059 * Returns a stream of code point values from this sequence. Any surrogate
3060 * pairs encountered in the sequence are combined as if by {@linkplain
3061 * Character#toCodePoint Character.toCodePoint} and the result is passed
3062 * to the stream. Any other code units, including ordinary BMP characters,
3063 * unpaired surrogates, and undefined code units, are zero-extended to
3064 * {@code int} values which are then passed to the stream.
3065 *
3066 * @return an IntStream of Unicode code points from this sequence
3067 * @since 1.9
3068 */
3069 @Override
3070 public IntStream codePoints() {
3071 return StreamSupport.intStream(
3072 new CodePointsSpliterator(value, Spliterator.IMMUTABLE), false);
3073 }
3074
3075 /**
3076 * Converts this string to a new character array.
3077 *
3078 * @return a newly allocated character array whose length is the length
3079 * of this string and whose contents are initialized to contain
3080 * the character sequence represented by this string.
3081 */
3082 public char[] toCharArray() {
3083 // Cannot use Arrays.copyOf because of class initialization order issues
3084 char result[] = new char[value.length];
3085 System.arraycopy(value, 0, result, 0, value.length);
3086 return result;
3087 }
3088
3089 /**
3090 * Returns a formatted string using the specified format string and
3091 * arguments.
3092 *
3093 * <p> The locale always used is the one returned by {@link
3094 * java.util.Locale#getDefault() Locale.getDefault()}.
3095 *
3096 * @param format
3097 * A <a href="../util/Formatter.html#syntax">format string</a>
3098 *
3099 * @param args
3100 * Arguments referenced by the format specifiers in the format
3101 * string. If there are more arguments than format specifiers, the
3102 * extra arguments are ignored. The number of arguments is
3103 * variable and may be zero. The maximum number of arguments is
3104 * limited by the maximum dimension of a Java array as defined by
3105 * <cite>The Java™ Virtual Machine Specification</cite>.
3106 * The behaviour on a
3107 * {@code null} argument depends on the <a
3108 * href="../util/Formatter.html#syntax">conversion</a>.
3109 *
3110 * @throws java.util.IllegalFormatException
3111 * If a format string contains an illegal syntax, a format
3112 * specifier that is incompatible with the given arguments,
3113 * insufficient arguments given the format string, or other
3114 * illegal conditions. For specification of all possible
3115 * formatting errors, see the <a
3116 * href="../util/Formatter.html#detail">Details</a> section of the
3117 * formatter class specification.
3118 *
3119 * @return A formatted string
3120 *
3121 * @see java.util.Formatter
3122 * @since 1.5
3123 */
3124 public static String format(String format, Object... args) {
3125 return new Formatter().format(format, args).toString();
3126 }
3127
3128 /**
3129 * Returns a formatted string using the specified locale, format string,
3130 * and arguments.
3131 *
3132 * @param l
3133 * The {@linkplain java.util.Locale locale} to apply during
3134 * formatting. If {@code l} is {@code null} then no localization
3135 * is applied.
3136 *
3137 * @param format
3138 * A <a href="../util/Formatter.html#syntax">format string</a>
3139 *
3140 * @param args
3141 * Arguments referenced by the format specifiers in the format
3142 * string. If there are more arguments than format specifiers, the
3143 * extra arguments are ignored. The number of arguments is
3144 * variable and may be zero. The maximum number of arguments is
3145 * limited by the maximum dimension of a Java array as defined by
3146 * <cite>The Java™ Virtual Machine Specification</cite>.
3147 * The behaviour on a
3148 * {@code null} argument depends on the
3149 * <a href="../util/Formatter.html#syntax">conversion</a>.
3150 *
3151 * @throws java.util.IllegalFormatException
3152 * If a format string contains an illegal syntax, a format
3153 * specifier that is incompatible with the given arguments,
3154 * insufficient arguments given the format string, or other
3155 * illegal conditions. For specification of all possible
3156 * formatting errors, see the <a
3157 * href="../util/Formatter.html#detail">Details</a> section of the
3158 * formatter class specification
3159 *
3160 * @return A formatted string
3161 *
3162 * @see java.util.Formatter
3163 * @since 1.5
3164 */
3165 public static String format(Locale l, String format, Object... args) {
3166 return new Formatter(l).format(format, args).toString();
3167 }
3168
3169 /**
3170 * Returns the string representation of the {@code Object} argument.
3171 *
3172 * @param obj an {@code Object}.
3173 * @return if the argument is {@code null}, then a string equal to
3174 * {@code "null"}; otherwise, the value of
3175 * {@code obj.toString()} is returned.
3176 * @see java.lang.Object#toString()
3177 */
3178 public static String valueOf(Object obj) {
3179 return (obj == null) ? "null" : obj.toString();
3180 }
3181
3182 /**
3183 * Returns the string representation of the {@code char} array
3184 * argument. The contents of the character array are copied; subsequent
3185 * modification of the character array does not affect the returned
3186 * string.
3187 *
3188 * @param data the character array.
3189 * @return a {@code String} that contains the characters of the
3190 * character array.
3191 */
3192 public static String valueOf(char data[]) {
3193 return new String(data);
3194 }
3195
3196 /**
3197 * Returns the string representation of a specific subarray of the
3198 * {@code char} array argument.
3199 * <p>
3200 * The {@code offset} argument is the index of the first
3201 * character of the subarray. The {@code count} argument
3202 * specifies the length of the subarray. The contents of the subarray
3203 * are copied; subsequent modification of the character array does not
3204 * affect the returned string.
3205 *
3206 * @param data the character array.
3207 * @param offset initial offset of the subarray.
3208 * @param count length of the subarray.
3209 * @return a {@code String} that contains the characters of the
3210 * specified subarray of the character array.
3211 * @exception IndexOutOfBoundsException if {@code offset} is
3212 * negative, or {@code count} is negative, or
3213 * {@code offset+count} is larger than
3214 * {@code data.length}.
3215 */
3216 public static String valueOf(char data[], int offset, int count) {
3217 return new String(data, offset, count);
3218 }
3219
3220 /**
3221 * Equivalent to {@link #valueOf(char[], int, int)}.
3222 *
3223 * @param data the character array.
3224 * @param offset initial offset of the subarray.
3225 * @param count length of the subarray.
3226 * @return a {@code String} that contains the characters of the
3227 * specified subarray of the character array.
3228 * @exception IndexOutOfBoundsException if {@code offset} is
3229 * negative, or {@code count} is negative, or
3230 * {@code offset+count} is larger than
3231 * {@code data.length}.
3232 */
3233 public static String copyValueOf(char data[], int offset, int count) {
3234 return new String(data, offset, count);
3235 }
3236
3237 /**
3238 * Equivalent to {@link #valueOf(char[])}.
3239 *
3240 * @param data the character array.
3241 * @return a {@code String} that contains the characters of the
3242 * character array.
3243 */
3244 public static String copyValueOf(char data[]) {
3245 return new String(data);
3246 }
3247
3248 /**
3249 * Returns the string representation of the {@code boolean} argument.
3250 *
3251 * @param b a {@code boolean}.
3252 * @return if the argument is {@code true}, a string equal to
3253 * {@code "true"} is returned; otherwise, a string equal to
3254 * {@code "false"} is returned.
3255 */
3256 public static String valueOf(boolean b) {
3257 return b ? "true" : "false";
3258 }
3259
3260 /**
3261 * Returns the string representation of the {@code char}
3262 * argument.
3263 *
3264 * @param c a {@code char}.
3265 * @return a string of length {@code 1} containing
3266 * as its single character the argument {@code c}.
3267 */
3268 public static String valueOf(char c) {
3269 char data[] = {c};
3270 return new String(data, true);
3271 }
3272
3273 /**
3274 * Returns the string representation of the {@code int} argument.
3275 * <p>
3276 * The representation is exactly the one returned by the
3277 * {@code Integer.toString} method of one argument.
3278 *
3279 * @param i an {@code int}.
3280 * @return a string representation of the {@code int} argument.
3281 * @see java.lang.Integer#toString(int, int)
3282 */
3283 public static String valueOf(int i) {
3284 return Integer.toString(i);
3285 }
3286
3287 /**
3288 * Returns the string representation of the {@code long} argument.
3289 * <p>
3290 * The representation is exactly the one returned by the
3291 * {@code Long.toString} method of one argument.
3292 *
3293 * @param l a {@code long}.
3294 * @return a string representation of the {@code long} argument.
3295 * @see java.lang.Long#toString(long)
3296 */
3297 public static String valueOf(long l) {
3298 return Long.toString(l);
3299 }
3300
3301 /**
3302 * Returns the string representation of the {@code float} argument.
3303 * <p>
3304 * The representation is exactly the one returned by the
3305 * {@code Float.toString} method of one argument.
3306 *
3307 * @param f a {@code float}.
3308 * @return a string representation of the {@code float} argument.
3309 * @see java.lang.Float#toString(float)
3310 */
3311 public static String valueOf(float f) {
3312 return Float.toString(f);
3313 }
3314
3315 /**
3316 * Returns the string representation of the {@code double} argument.
3317 * <p>
3318 * The representation is exactly the one returned by the
3319 * {@code Double.toString} method of one argument.
3320 *
3321 * @param d a {@code double}.
3322 * @return a string representation of the {@code double} argument.
3323 * @see java.lang.Double#toString(double)
3324 */
3325 public static String valueOf(double d) {
3326 return Double.toString(d);
3327 }
3328
3329 /**
3330 * Returns a canonical representation for the string object.
3331 * <p>
3332 * A pool of strings, initially empty, is maintained privately by the
3333 * class {@code String}.
3334 * <p>
3335 * When the intern method is invoked, if the pool already contains a
3336 * string equal to this {@code String} object as determined by
3337 * the {@link #equals(Object)} method, then the string from the pool is
3338 * returned. Otherwise, this {@code String} object is added to the
3339 * pool and a reference to this {@code String} object is returned.
3340 * <p>
3341 * It follows that for any two strings {@code s} and {@code t},
3342 * {@code s.intern() == t.intern()} is {@code true}
3343 * if and only if {@code s.equals(t)} is {@code true}.
3344 * <p>
3345 * All literal strings and string-valued constant expressions are
3346 * interned. String literals are defined in section 3.10.5 of the
3347 * <cite>The Java™ Language Specification</cite>.
3348 *
3349 * @return a string that has the same contents as this string, but is
3350 * guaranteed to be from a pool of unique strings.
3351 */
3352 public native String intern();
3353 }