1 /*
2 * Copyright (c) 1994, 2014, 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.StringJoiner;
38 import java.util.regex.Matcher;
39 import java.util.regex.Pattern;
40 import java.util.regex.PatternSyntaxException;
41
42 /**
43 * The {@code String} class represents character strings. All
44 * string literals in Java programs, such as {@code "abc"}, are
45 * implemented as instances of this class.
46 * <p>
47 * Strings are constant; their values cannot be changed after they
48 * are created. String buffers support mutable strings.
49 * Because String objects are immutable they can be shared. For example:
50 * <blockquote><pre>
51 * String str = "abc";
52 * </pre></blockquote><p>
53 * is equivalent to:
54 * <blockquote><pre>
55 * char data[] = {'a', 'b', 'c'};
56 * String str = new String(data);
57 * </pre></blockquote><p>
58 * Here are some more examples of how strings can be used:
59 * <blockquote><pre>
60 * System.out.println("abc");
61 * String cde = "cde";
62 * System.out.println("abc" + cde);
63 * String c = "abc".substring(2,3);
64 * String d = cde.substring(1, 2);
65 * </pre></blockquote>
66 * <p>
67 * The class {@code String} includes methods for examining
68 * individual characters of the sequence, for comparing strings, for
69 * searching strings, for extracting substrings, and for creating a
70 * copy of a string with all characters translated to uppercase or to
71 * lowercase. Case mapping is based on the Unicode Standard version
72 * specified by the {@link java.lang.Character Character} class.
73 * <p>
74 * The Java language provides special support for the string
75 * concatenation operator ( + ), and for conversion of
76 * other objects to strings. String concatenation is implemented
77 * through the {@code StringBuilder}(or {@code StringBuffer})
78 * class and its {@code append} method.
79 * String conversions are implemented through the method
80 * {@code toString}, defined by {@code Object} and
81 * inherited by all classes in Java. For additional information on
82 * string concatenation and conversion, see Gosling, Joy, and Steele,
83 * <i>The Java Language Specification</i>.
84 *
85 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
86 * or method in this class will cause a {@link NullPointerException} to be
87 * thrown.
88 *
89 * <p>A {@code String} represents a string in the UTF-16 format
90 * in which <em>supplementary characters</em> are represented by <em>surrogate
91 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
92 * Character Representations</a> in the {@code Character} class for
93 * more information).
94 * Index values refer to {@code char} code units, so a supplementary
95 * character uses two positions in a {@code String}.
96 * <p>The {@code String} class provides methods for dealing with
97 * Unicode code points (i.e., characters), in addition to those for
98 * dealing with Unicode code units (i.e., {@code char} values).
99 *
100 * @author Lee Boynton
101 * @author Arthur van Hoff
102 * @author Martin Buchholz
103 * @author Ulf Zibis
104 * @see java.lang.Object#toString()
105 * @see java.lang.StringBuffer
106 * @see java.lang.StringBuilder
107 * @see java.nio.charset.Charset
108 * @since 1.0
109 */
110
111 public final class String
112 implements java.io.Serializable, Comparable<String>, CharSequence {
113 /** The value is used for character storage. */
114 private final char value[];
115
116 /** Cache the hash code for the string */
117 private int hash; // Default to 0
118
119 /** use serialVersionUID from JDK 1.0.2 for interoperability */
120 private static final long serialVersionUID = -6849794470754667710L;
121
122 /**
123 * Class String is special cased within the Serialization Stream Protocol.
124 *
125 * A String instance is written into an ObjectOutputStream according to
126 * <a href="{@docRoot}/../platform/serialization/spec/output.html">
127 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
128 */
129 private static final ObjectStreamField[] serialPersistentFields =
130 new ObjectStreamField[0];
131
132 /**
133 * Initializes a newly created {@code String} object so that it represents
134 * an empty character sequence. Note that use of this constructor is
135 * unnecessary since Strings are immutable.
136 */
137 public String() {
138 this.value = new char[0];
139 }
140
141 /**
142 * Initializes a newly created {@code String} object so that it represents
143 * the same sequence of characters as the argument; in other words, the
144 * newly created string is a copy of the argument string. Unless an
145 * explicit copy of {@code original} is needed, use of this constructor is
146 * unnecessary since Strings are immutable.
147 *
148 * @param original
149 * A {@code String}
150 */
151 public String(String original) {
152 this.value = original.value;
153 this.hash = original.hash;
154 }
155
156 /**
157 * Allocates a new {@code String} so that it represents the sequence of
158 * characters currently contained in the character array argument. The
159 * contents of the character array are copied; subsequent modification of
160 * the character array does not affect the newly created string.
161 *
162 * @param value
163 * The initial value of the string
164 */
165 public String(char value[]) {
166 this.value = Arrays.copyOf(value, value.length);
167 }
168
169 /**
170 * Allocates a new {@code String} that contains characters from a subarray
171 * of the character array argument. The {@code offset} argument is the
172 * index of the first character of the subarray and the {@code count}
173 * argument specifies the length of the subarray. The contents of the
174 * subarray are copied; subsequent modification of the character array does
175 * not affect the newly created string.
176 *
177 * @param value
178 * Array that is the source of characters
179 *
180 * @param offset
181 * The initial offset
182 *
183 * @param count
184 * The length
185 *
186 * @throws IndexOutOfBoundsException
187 * If the {@code offset} and {@code count} arguments index
188 * characters outside the bounds of the {@code value} array
189 */
190 public String(char value[], int offset, int count) {
191 if (offset < 0) {
192 throw new StringIndexOutOfBoundsException(offset);
193 }
194 if (count < 0) {
195 throw new StringIndexOutOfBoundsException(count);
196 }
197 // Note: offset or count might be near -1>>>1.
198 if (offset > value.length - count) {
199 throw new StringIndexOutOfBoundsException(offset + count);
200 }
201 this.value = Arrays.copyOfRange(value, offset, offset+count);
202 }
203
204 /**
205 * Allocates a new {@code String} that contains characters from a subarray
206 * of the <a href="Character.html#unicode">Unicode code point</a> array
207 * argument. The {@code offset} argument is the index of the first code
208 * point of the subarray and the {@code count} argument specifies the
209 * length of the subarray. The contents of the subarray are converted to
210 * {@code char}s; subsequent modification of the {@code int} array does not
211 * affect the newly created string.
212 *
213 * @param codePoints
214 * Array that is the source of Unicode code points
215 *
216 * @param offset
217 * The initial offset
218 *
219 * @param count
220 * The length
221 *
222 * @throws IllegalArgumentException
223 * If any invalid Unicode code point is found in {@code
224 * codePoints}
225 *
226 * @throws IndexOutOfBoundsException
227 * If the {@code offset} and {@code count} arguments index
228 * characters outside the bounds of the {@code codePoints} array
229 *
230 * @since 1.5
231 */
232 public String(int[] codePoints, int offset, int count) {
233 if (offset < 0) {
234 throw new StringIndexOutOfBoundsException(offset);
235 }
236 if (count < 0) {
237 throw new StringIndexOutOfBoundsException(count);
238 }
239 // Note: offset or count might be near -1>>>1.
240 if (offset > codePoints.length - count) {
241 throw new StringIndexOutOfBoundsException(offset + count);
242 }
243
244 final int end = offset + count;
245
246 // Pass 1: Compute precise size of char[]
247 int n = count;
248 for (int i = offset; i < end; i++) {
249 int c = codePoints[i];
250 if (Character.isBmpCodePoint(c))
251 continue;
252 else if (Character.isValidCodePoint(c))
253 n++;
254 else throw new IllegalArgumentException(Integer.toString(c));
255 }
256
257 // Pass 2: Allocate and fill in char[]
258 final char[] v = new char[n];
259
260 for (int i = offset, j = 0; i < end; i++, j++) {
261 int c = codePoints[i];
262 if (Character.isBmpCodePoint(c))
263 v[j] = (char)c;
264 else
265 Character.toSurrogates(c, v, j++);
266 }
267
268 this.value = v;
269 }
270
271 /**
272 * Allocates a new {@code String} constructed from a subarray of an array
273 * of 8-bit integer values.
274 *
275 * <p> The {@code offset} argument is the index of the first byte of the
276 * subarray, and the {@code count} argument specifies the length of the
277 * subarray.
278 *
279 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
280 * specified in the method above.
281 *
282 * @deprecated This method does not properly convert bytes into characters.
283 * As of JDK 1.1, the preferred way to do this is via the
284 * {@code String} constructors that take a {@link
285 * java.nio.charset.Charset}, charset name, or that use the platform's
286 * default charset.
287 *
288 * @param ascii
289 * The bytes to be converted to characters
290 *
291 * @param hibyte
292 * The top 8 bits of each 16-bit Unicode code unit
293 *
294 * @param offset
295 * The initial offset
296 * @param count
297 * The length
298 *
299 * @throws IndexOutOfBoundsException
300 * If the {@code offset} or {@code count} argument is invalid
301 *
302 * @see #String(byte[], int)
303 * @see #String(byte[], int, int, java.lang.String)
304 * @see #String(byte[], int, int, java.nio.charset.Charset)
305 * @see #String(byte[], int, int)
306 * @see #String(byte[], java.lang.String)
307 * @see #String(byte[], java.nio.charset.Charset)
308 * @see #String(byte[])
309 */
310 @Deprecated
311 public String(byte ascii[], int hibyte, int offset, int count) {
312 checkBounds(ascii, offset, count);
313 char value[] = new char[count];
314
315 if (hibyte == 0) {
316 for (int i = count; i-- > 0;) {
317 value[i] = (char)(ascii[i + offset] & 0xff);
318 }
319 } else {
320 hibyte <<= 8;
321 for (int i = count; i-- > 0;) {
322 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff));
323 }
324 }
325 this.value = value;
326 }
327
328 /**
329 * Allocates a new {@code String} containing characters constructed from
330 * an array of 8-bit integer values. Each character <i>c</i>in the
331 * resulting string is constructed from the corresponding component
332 * <i>b</i> in the byte array such that:
333 *
334 * <blockquote><pre>
335 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
336 * | (<b><i>b</i></b> & 0xff))
337 * </pre></blockquote>
338 *
339 * @deprecated This method does not properly convert bytes into
340 * characters. As of JDK 1.1, the preferred way to do this is via the
341 * {@code String} constructors that take a {@link
342 * java.nio.charset.Charset}, charset name, or that use the platform's
343 * default charset.
344 *
345 * @param ascii
346 * The bytes to be converted to characters
347 *
348 * @param hibyte
349 * The top 8 bits of each 16-bit Unicode code unit
350 *
351 * @see #String(byte[], int, int, java.lang.String)
352 * @see #String(byte[], int, int, java.nio.charset.Charset)
353 * @see #String(byte[], int, int)
354 * @see #String(byte[], java.lang.String)
355 * @see #String(byte[], java.nio.charset.Charset)
356 * @see #String(byte[])
357 */
358 @Deprecated
359 public String(byte ascii[], int hibyte) {
360 this(ascii, hibyte, 0, ascii.length);
361 }
362
363 /* Common private utility method used to bounds check the byte array
364 * and requested offset & length values used by the String(byte[],..)
365 * constructors.
366 */
367 private static void checkBounds(byte[] bytes, int offset, int length) {
368 if (length < 0)
369 throw new StringIndexOutOfBoundsException(length);
370 if (offset < 0)
371 throw new StringIndexOutOfBoundsException(offset);
372 if (offset > bytes.length - length)
373 throw new StringIndexOutOfBoundsException(offset + length);
374 }
375
376 /**
377 * Constructs a new {@code String} by decoding the specified subarray of
378 * bytes using the specified charset. The length of the new {@code String}
379 * is a function of the charset, and hence may not be equal to the length
380 * of the subarray.
381 *
382 * <p> The behavior of this constructor when the given bytes are not valid
383 * in the given charset is unspecified. The {@link
384 * java.nio.charset.CharsetDecoder} class should be used when more control
385 * over the decoding process is required.
386 *
387 * @param bytes
388 * The bytes to be decoded into characters
389 *
390 * @param offset
391 * The index of the first byte to decode
392 *
393 * @param length
394 * The number of bytes to decode
395
396 * @param charsetName
397 * The name of a supported {@linkplain java.nio.charset.Charset
398 * charset}
399 *
400 * @throws UnsupportedEncodingException
401 * If the named charset is not supported
402 *
403 * @throws IndexOutOfBoundsException
404 * If the {@code offset} and {@code length} arguments index
405 * characters outside the bounds of the {@code bytes} array
406 *
407 * @since 1.1
408 */
409 public String(byte bytes[], int offset, int length, String charsetName)
410 throws UnsupportedEncodingException {
411 if (charsetName == null)
412 throw new NullPointerException("charsetName");
413 checkBounds(bytes, offset, length);
414 this.value = StringCoding.decode(charsetName, bytes, offset, length);
415 }
416
417 /**
418 * Constructs a new {@code String} by decoding the specified subarray of
419 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
420 * The length of the new {@code String} is a function of the charset, and
421 * hence may not be equal to the length of the subarray.
422 *
423 * <p> This method always replaces malformed-input and unmappable-character
424 * sequences with this charset's default replacement string. The {@link
425 * java.nio.charset.CharsetDecoder} class should be used when more control
426 * over the decoding process is required.
427 *
428 * @param bytes
429 * The bytes to be decoded into characters
430 *
431 * @param offset
432 * The index of the first byte to decode
433 *
434 * @param length
435 * The number of bytes to decode
436 *
437 * @param charset
438 * The {@linkplain java.nio.charset.Charset charset} to be used to
439 * decode the {@code bytes}
440 *
441 * @throws IndexOutOfBoundsException
442 * If the {@code offset} and {@code length} arguments index
443 * characters outside the bounds of the {@code bytes} array
444 *
445 * @since 1.6
446 */
447 public String(byte bytes[], int offset, int length, Charset charset) {
448 if (charset == null)
449 throw new NullPointerException("charset");
450 checkBounds(bytes, offset, length);
451 this.value = StringCoding.decode(charset, bytes, offset, length);
452 }
453
454 /**
455 * Constructs a new {@code String} by decoding the specified array of bytes
456 * using the specified {@linkplain java.nio.charset.Charset charset}. The
457 * length of the new {@code String} is a function of the charset, and hence
458 * may not be equal to the length of the byte array.
459 *
460 * <p> The behavior of this constructor when the given bytes are not valid
461 * in the given charset is unspecified. The {@link
462 * java.nio.charset.CharsetDecoder} class should be used when more control
463 * over the decoding process is required.
464 *
465 * @param bytes
466 * The bytes to be decoded into characters
467 *
468 * @param charsetName
469 * The name of a supported {@linkplain java.nio.charset.Charset
470 * charset}
471 *
472 * @throws UnsupportedEncodingException
473 * If the named charset is not supported
474 *
475 * @since 1.1
476 */
477 public String(byte bytes[], String charsetName)
478 throws UnsupportedEncodingException {
479 this(bytes, 0, bytes.length, charsetName);
480 }
481
482 /**
483 * Constructs a new {@code String} by decoding the specified array of
484 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
485 * The length of the new {@code String} is a function of the charset, and
486 * hence may not be equal to the length of the byte array.
487 *
488 * <p> This method always replaces malformed-input and unmappable-character
489 * sequences with this charset's default replacement string. The {@link
490 * java.nio.charset.CharsetDecoder} class should be used when more control
491 * over the decoding process is required.
492 *
493 * @param bytes
494 * The bytes to be decoded into characters
495 *
496 * @param charset
497 * The {@linkplain java.nio.charset.Charset charset} to be used to
498 * decode the {@code bytes}
499 *
500 * @since 1.6
501 */
502 public String(byte bytes[], Charset charset) {
503 this(bytes, 0, bytes.length, charset);
504 }
505
506 /**
507 * Constructs a new {@code String} by decoding the specified subarray of
508 * bytes using the platform's default charset. The length of the new
509 * {@code String} is a function of the charset, and hence may not be equal
510 * to the length of the subarray.
511 *
512 * <p> The behavior of this constructor when the given bytes are not valid
513 * in the default charset is unspecified. The {@link
514 * java.nio.charset.CharsetDecoder} class should be used when more control
515 * over the decoding process is required.
516 *
517 * @param bytes
518 * The bytes to be decoded into characters
519 *
520 * @param offset
521 * The index of the first byte to decode
522 *
523 * @param length
524 * The number of bytes to decode
525 *
526 * @throws IndexOutOfBoundsException
527 * If the {@code offset} and the {@code length} arguments index
528 * characters outside the bounds of the {@code bytes} array
529 *
530 * @since 1.1
531 */
532 public String(byte bytes[], int offset, int length) {
533 checkBounds(bytes, offset, length);
534 this.value = StringCoding.decode(bytes, offset, length);
535 }
536
537 /**
538 * Constructs a new {@code String} by decoding the specified array of bytes
539 * using the platform's default charset. The length of the new {@code
540 * String} is a function of the charset, and hence may not be equal to the
541 * length of the byte array.
542 *
543 * <p> The behavior of this constructor when the given bytes are not valid
544 * in the default charset is unspecified. The {@link
545 * java.nio.charset.CharsetDecoder} class should be used when more control
546 * over the decoding process is required.
547 *
548 * @param bytes
549 * The bytes to be decoded into characters
550 *
551 * @since 1.1
552 */
553 public String(byte bytes[]) {
554 this(bytes, 0, bytes.length);
555 }
556
557 /**
558 * Allocates a new string that contains the sequence of characters
559 * currently contained in the string buffer argument. The contents of the
560 * string buffer are copied; subsequent modification of the string buffer
561 * does not affect the newly created string.
562 *
563 * @param buffer
564 * A {@code StringBuffer}
565 */
566 public String(StringBuffer buffer) {
567 synchronized(buffer) {
568 this.value = Arrays.copyOf(buffer.getValue(), buffer.length());
569 }
570 }
571
572 /**
573 * Allocates a new string that contains the sequence of characters
574 * currently contained in the string builder argument. The contents of the
575 * string builder are copied; subsequent modification of the string builder
576 * does not affect the newly created string.
577 *
578 * <p> This constructor is provided to ease migration to {@code
579 * StringBuilder}. Obtaining a string from a string builder via the {@code
580 * toString} method is likely to run faster and is generally preferred.
581 *
582 * @param builder
583 * A {@code StringBuilder}
584 *
585 * @since 1.5
586 */
587 public String(StringBuilder builder) {
588 this.value = Arrays.copyOf(builder.getValue(), builder.length());
589 }
590
591 /*
592 * Package private constructor which shares value array for speed.
593 * this constructor is always expected to be called with share==true.
594 * a separate constructor is needed because we already have a public
595 * String(char[]) constructor that makes a copy of the given char[].
596 */
597 String(char[] value, boolean share) {
598 // assert share : "unshared not supported";
599 this.value = value;
600 }
601
602 /**
603 * Returns the length of this string.
604 * The length is equal to the number of <a href="Character.html#unicode">Unicode
605 * code units</a> in the string.
606 *
607 * @return the length of the sequence of characters represented by this
608 * object.
609 */
610 public int length() {
611 return value.length;
612 }
613
614 /**
615 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
616 *
617 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
618 * {@code false}
619 *
620 * @since 1.6
621 */
622 public boolean isEmpty() {
623 return value.length == 0;
624 }
625
626 /**
627 * Returns the {@code char} value at the
628 * specified index. An index ranges from {@code 0} to
629 * {@code length() - 1}. The first {@code char} value of the sequence
630 * is at index {@code 0}, the next at index {@code 1},
631 * and so on, as for array indexing.
632 *
633 * <p>If the {@code char} value specified by the index is a
634 * <a href="Character.html#unicode">surrogate</a>, the surrogate
635 * value is returned.
636 *
637 * @param index the index of the {@code char} value.
638 * @return the {@code char} value at the specified index of this string.
639 * The first {@code char} value is at index {@code 0}.
640 * @exception IndexOutOfBoundsException if the {@code index}
641 * argument is negative or not less than the length of this
642 * string.
643 */
644 public char charAt(int index) {
645 if ((index < 0) || (index >= value.length)) {
646 throw new StringIndexOutOfBoundsException(index);
647 }
648 return value[index];
649 }
650
651 /**
652 * Returns the character (Unicode code point) at the specified
653 * index. The index refers to {@code char} values
654 * (Unicode code units) and ranges from {@code 0} to
655 * {@link #length()}{@code - 1}.
656 *
657 * <p> If the {@code char} value specified at the given index
658 * is in the high-surrogate range, the following index is less
659 * than the length of this {@code String}, and the
660 * {@code char} value at the following index is in the
661 * low-surrogate range, then the supplementary code point
662 * corresponding to this surrogate pair is returned. Otherwise,
663 * the {@code char} value at the given index is returned.
664 *
665 * @param index the index to the {@code char} values
666 * @return the code point value of the character at the
667 * {@code index}
668 * @exception IndexOutOfBoundsException if the {@code index}
669 * argument is negative or not less than the length of this
670 * string.
671 * @since 1.5
672 */
673 public int codePointAt(int index) {
674 if ((index < 0) || (index >= value.length)) {
675 throw new StringIndexOutOfBoundsException(index);
676 }
677 return Character.codePointAtImpl(value, index, value.length);
678 }
679
680 /**
681 * Returns the character (Unicode code point) before the specified
682 * index. The index refers to {@code char} values
683 * (Unicode code units) and ranges from {@code 1} to {@link
684 * CharSequence#length() length}.
685 *
686 * <p> If the {@code char} value at {@code (index - 1)}
687 * is in the low-surrogate range, {@code (index - 2)} is not
688 * negative, and the {@code char} value at {@code (index -
689 * 2)} is in the high-surrogate range, then the
690 * supplementary code point value of the surrogate pair is
691 * returned. If the {@code char} value at {@code index -
692 * 1} is an unpaired low-surrogate or a high-surrogate, the
693 * surrogate value is returned.
694 *
695 * @param index the index following the code point that should be returned
696 * @return the Unicode code point value before the given index.
697 * @exception IndexOutOfBoundsException if the {@code index}
698 * argument is less than 1 or greater than the length
699 * of this string.
700 * @since 1.5
701 */
702 public int codePointBefore(int index) {
703 int i = index - 1;
704 if ((i < 0) || (i >= value.length)) {
705 throw new StringIndexOutOfBoundsException(index);
706 }
707 return Character.codePointBeforeImpl(value, index, 0);
708 }
709
710 /**
711 * Returns the number of Unicode code points in the specified text
712 * range of this {@code String}. The text range begins at the
713 * specified {@code beginIndex} and extends to the
714 * {@code char} at index {@code endIndex - 1}. Thus the
715 * length (in {@code char}s) of the text range is
716 * {@code endIndex-beginIndex}. Unpaired surrogates within
717 * the text range count as one code point each.
718 *
719 * @param beginIndex the index to the first {@code char} of
720 * the text range.
721 * @param endIndex the index after the last {@code char} of
722 * the text range.
723 * @return the number of Unicode code points in the specified text
724 * range
725 * @exception IndexOutOfBoundsException if the
726 * {@code beginIndex} is negative, or {@code endIndex}
727 * is larger than the length of this {@code String}, or
728 * {@code beginIndex} is larger than {@code endIndex}.
729 * @since 1.5
730 */
731 public int codePointCount(int beginIndex, int endIndex) {
732 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) {
733 throw new IndexOutOfBoundsException();
734 }
735 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex);
736 }
737
738 /**
739 * Returns the index within this {@code String} that is
740 * offset from the given {@code index} by
741 * {@code codePointOffset} code points. Unpaired surrogates
742 * within the text range given by {@code index} and
743 * {@code codePointOffset} count as one code point each.
744 *
745 * @param index the index to be offset
746 * @param codePointOffset the offset in code points
747 * @return the index within this {@code String}
748 * @exception IndexOutOfBoundsException if {@code index}
749 * is negative or larger then the length of this
750 * {@code String}, or if {@code codePointOffset} is positive
751 * and the substring starting with {@code index} has fewer
752 * than {@code codePointOffset} code points,
753 * or if {@code codePointOffset} is negative and the substring
754 * before {@code index} has fewer than the absolute value
755 * of {@code codePointOffset} code points.
756 * @since 1.5
757 */
758 public int offsetByCodePoints(int index, int codePointOffset) {
759 if (index < 0 || index > value.length) {
760 throw new IndexOutOfBoundsException();
761 }
762 return Character.offsetByCodePointsImpl(value, 0, value.length,
763 index, codePointOffset);
764 }
765
766 /**
767 * Copy characters from this string into dst starting at dstBegin.
768 * This method doesn't perform any range checking.
769 */
770 void getChars(char dst[], int dstBegin) {
771 System.arraycopy(value, 0, dst, dstBegin, value.length);
772 }
773
774 /**
775 * Copies characters from this string into the destination character
776 * array.
777 * <p>
778 * The first character to be copied is at index {@code srcBegin};
779 * the last character to be copied is at index {@code srcEnd-1}
780 * (thus the total number of characters to be copied is
781 * {@code srcEnd-srcBegin}). The characters are copied into the
782 * subarray of {@code dst} starting at index {@code dstBegin}
783 * and ending at index:
784 * <blockquote><pre>
785 * dstbegin + (srcEnd-srcBegin) - 1
786 * </pre></blockquote>
787 *
788 * @param srcBegin index of the first character in the string
789 * to copy.
790 * @param srcEnd index after the last character in the string
791 * to copy.
792 * @param dst the destination array.
793 * @param dstBegin the start offset in the destination array.
794 * @exception IndexOutOfBoundsException If any of the following
795 * is true:
796 * <ul><li>{@code srcBegin} is negative.
797 * <li>{@code srcBegin} is greater than {@code srcEnd}
798 * <li>{@code srcEnd} is greater than the length of this
799 * string
800 * <li>{@code dstBegin} is negative
801 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
802 * {@code dst.length}</ul>
803 */
804 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
805 if (srcBegin < 0) {
806 throw new StringIndexOutOfBoundsException(srcBegin);
807 }
808 if (srcEnd > value.length) {
809 throw new StringIndexOutOfBoundsException(srcEnd);
810 }
811 if (srcBegin > srcEnd) {
812 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
813 }
814 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin);
815 }
816
817 /**
818 * Copies characters from this string into the destination byte array. Each
819 * byte receives the 8 low-order bits of the corresponding character. The
820 * eight high-order bits of each character are not copied and do not
821 * participate in the transfer in any way.
822 *
823 * <p> The first character to be copied is at index {@code srcBegin}; the
824 * last character to be copied is at index {@code srcEnd-1}. The total
825 * number of characters to be copied is {@code srcEnd-srcBegin}. The
826 * characters, converted to bytes, are copied into the subarray of {@code
827 * dst} starting at index {@code dstBegin} and ending at index:
828 *
829 * <blockquote><pre>
830 * dstbegin + (srcEnd-srcBegin) - 1
831 * </pre></blockquote>
832 *
833 * @deprecated This method does not properly convert characters into
834 * bytes. As of JDK 1.1, the preferred way to do this is via the
835 * {@link #getBytes()} method, which uses the platform's default charset.
836 *
837 * @param srcBegin
838 * Index of the first character in the string to copy
839 *
840 * @param srcEnd
841 * Index after the last character in the string to copy
842 *
843 * @param dst
844 * The destination array
845 *
846 * @param dstBegin
847 * The start offset in the destination array
848 *
849 * @throws IndexOutOfBoundsException
850 * If any of the following is true:
851 * <ul>
852 * <li> {@code srcBegin} is negative
853 * <li> {@code srcBegin} is greater than {@code srcEnd}
854 * <li> {@code srcEnd} is greater than the length of this String
855 * <li> {@code dstBegin} is negative
856 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
857 * dst.length}
858 * </ul>
859 */
860 @Deprecated
861 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
862 if (srcBegin < 0) {
863 throw new StringIndexOutOfBoundsException(srcBegin);
864 }
865 if (srcEnd > value.length) {
866 throw new StringIndexOutOfBoundsException(srcEnd);
867 }
868 if (srcBegin > srcEnd) {
869 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
870 }
871 Objects.requireNonNull(dst);
872
873 int j = dstBegin;
874 int n = srcEnd;
875 int i = srcBegin;
876 char[] val = value; /* avoid getfield opcode */
877
878 while (i < n) {
879 dst[j++] = (byte)val[i++];
880 }
881 }
882
883 /**
884 * Encodes this {@code String} into a sequence of bytes using the named
885 * charset, storing the result into a new byte array.
886 *
887 * <p> The behavior of this method when this string cannot be encoded in
888 * the given charset is unspecified. The {@link
889 * java.nio.charset.CharsetEncoder} class should be used when more control
890 * over the encoding process is required.
891 *
892 * @param charsetName
893 * The name of a supported {@linkplain java.nio.charset.Charset
894 * charset}
895 *
896 * @return The resultant byte array
897 *
898 * @throws UnsupportedEncodingException
899 * If the named charset is not supported
900 *
901 * @since 1.1
902 */
903 public byte[] getBytes(String charsetName)
904 throws UnsupportedEncodingException {
905 if (charsetName == null) throw new NullPointerException();
906 return StringCoding.encode(charsetName, value, 0, value.length);
907 }
908
909 /**
910 * Encodes this {@code String} into a sequence of bytes using the given
911 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
912 * new byte array.
913 *
914 * <p> This method always replaces malformed-input and unmappable-character
915 * sequences with this charset's default replacement byte array. The
916 * {@link java.nio.charset.CharsetEncoder} class should be used when more
917 * control over the encoding process is required.
918 *
919 * @param charset
920 * The {@linkplain java.nio.charset.Charset} to be used to encode
921 * the {@code String}
922 *
923 * @return The resultant byte array
924 *
925 * @since 1.6
926 */
927 public byte[] getBytes(Charset charset) {
928 if (charset == null) throw new NullPointerException();
929 return StringCoding.encode(charset, value, 0, value.length);
930 }
931
932 /**
933 * Encodes this {@code String} into a sequence of bytes using the
934 * platform's default charset, storing the result into a new byte array.
935 *
936 * <p> The behavior of this method when this string cannot be encoded in
937 * the default charset is unspecified. The {@link
938 * java.nio.charset.CharsetEncoder} class should be used when more control
939 * over the encoding process is required.
940 *
941 * @return The resultant byte array
942 *
943 * @since 1.1
944 */
945 public byte[] getBytes() {
946 return StringCoding.encode(value, 0, value.length);
947 }
948
949 /**
950 * Compares this string to the specified object. The result is {@code
951 * true} if and only if the argument is not {@code null} and is a {@code
952 * String} object that represents the same sequence of characters as this
953 * object.
954 *
955 * @param anObject
956 * The object to compare this {@code String} against
957 *
958 * @return {@code true} if the given object represents a {@code String}
959 * equivalent to this string, {@code false} otherwise
960 *
961 * @see #compareTo(String)
962 * @see #equalsIgnoreCase(String)
963 */
964 public boolean equals(Object anObject) {
965 if (this == anObject) {
966 return true;
967 }
968 if (anObject instanceof String) {
969 String anotherString = (String)anObject;
970 int n = value.length;
971 if (n == anotherString.value.length) {
972 char v1[] = value;
973 char v2[] = anotherString.value;
974 int i = 0;
975 while (n-- != 0) {
976 if (v1[i] != v2[i])
977 return false;
978 i++;
979 }
980 return true;
981 }
982 }
983 return false;
984 }
985
986 /**
987 * Compares this string to the specified {@code StringBuffer}. The result
988 * is {@code true} if and only if this {@code String} represents the same
989 * sequence of characters as the specified {@code StringBuffer}. This method
990 * synchronizes on the {@code StringBuffer}.
991 *
992 * @param sb
993 * The {@code StringBuffer} to compare this {@code String} against
994 *
995 * @return {@code true} if this {@code String} represents the same
996 * sequence of characters as the specified {@code StringBuffer},
997 * {@code false} otherwise
998 *
999 * @since 1.4
1000 */
1001 public boolean contentEquals(StringBuffer sb) {
1002 return contentEquals((CharSequence)sb);
1003 }
1004
1005 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1006 char v1[] = value;
1007 char v2[] = sb.getValue();
1008 int n = v1.length;
1009 if (n != sb.length()) {
1010 return false;
1011 }
1012 for (int i = 0; i < n; i++) {
1013 if (v1[i] != v2[i]) {
1014 return false;
1015 }
1016 }
1017 return true;
1018 }
1019
1020 /**
1021 * Compares this string to the specified {@code CharSequence}. The
1022 * result is {@code true} if and only if this {@code String} represents the
1023 * same sequence of char values as the specified sequence. Note that if the
1024 * {@code CharSequence} is a {@code StringBuffer} then the method
1025 * synchronizes on it.
1026 *
1027 * @param cs
1028 * The sequence to compare this {@code String} against
1029 *
1030 * @return {@code true} if this {@code String} represents the same
1031 * sequence of char values as the specified sequence, {@code
1032 * false} otherwise
1033 *
1034 * @since 1.5
1035 */
1036 public boolean contentEquals(CharSequence cs) {
1037 // Argument is a StringBuffer, StringBuilder
1038 if (cs instanceof AbstractStringBuilder) {
1039 if (cs instanceof StringBuffer) {
1040 synchronized(cs) {
1041 return nonSyncContentEquals((AbstractStringBuilder)cs);
1042 }
1043 } else {
1044 return nonSyncContentEquals((AbstractStringBuilder)cs);
1045 }
1046 }
1047 // Argument is a String
1048 if (cs instanceof String) {
1049 return equals((String)cs);
1050 }
1051 // Argument is a generic CharSequence
1052 char v1[] = value;
1053 int n = v1.length;
1054 if (n != cs.length()) {
1055 return false;
1056 }
1057 for (int i = 0; i < n; i++) {
1058 if (v1[i] != cs.charAt(i)) {
1059 return false;
1060 }
1061 }
1062 return true;
1063 }
1064
1065 /**
1066 * Compares this {@code String} to another {@code String}, ignoring case
1067 * considerations. Two strings are considered equal ignoring case if they
1068 * are of the same length and corresponding characters in the two strings
1069 * are equal ignoring case.
1070 *
1071 * <p> Two characters {@code c1} and {@code c2} are considered the same
1072 * ignoring case if at least one of the following is true:
1073 * <ul>
1074 * <li> The two characters are the same (as compared by the
1075 * {@code ==} operator)
1076 * <li> Applying the method {@link
1077 * java.lang.Character#toUpperCase(char)} to each character
1078 * produces the same result
1079 * <li> Applying the method {@link
1080 * java.lang.Character#toLowerCase(char)} to each character
1081 * produces the same result
1082 * </ul>
1083 *
1084 * @param anotherString
1085 * The {@code String} to compare this {@code String} against
1086 *
1087 * @return {@code true} if the argument is not {@code null} and it
1088 * represents an equivalent {@code String} ignoring case; {@code
1089 * false} otherwise
1090 *
1091 * @see #equals(Object)
1092 */
1093 public boolean equalsIgnoreCase(String anotherString) {
1094 return (this == anotherString) ? true
1095 : (anotherString != null)
1096 && (anotherString.value.length == value.length)
1097 && regionMatches(true, 0, anotherString, 0, value.length);
1098 }
1099
1100 /**
1101 * Compares two strings lexicographically.
1102 * The comparison is based on the Unicode value of each character in
1103 * the strings. The character sequence represented by this
1104 * {@code String} object is compared lexicographically to the
1105 * character sequence represented by the argument string. The result is
1106 * a negative integer if this {@code String} object
1107 * lexicographically precedes the argument string. The result is a
1108 * positive integer if this {@code String} object lexicographically
1109 * follows the argument string. The result is zero if the strings
1110 * are equal; {@code compareTo} returns {@code 0} exactly when
1111 * the {@link #equals(Object)} method would return {@code true}.
1112 * <p>
1113 * This is the definition of lexicographic ordering. If two strings are
1114 * different, then either they have different characters at some index
1115 * that is a valid index for both strings, or their lengths are different,
1116 * or both. If they have different characters at one or more index
1117 * positions, let <i>k</i> be the smallest such index; then the string
1118 * whose character at position <i>k</i> has the smaller value, as
1119 * determined by using the < operator, lexicographically precedes the
1120 * other string. In this case, {@code compareTo} returns the
1121 * difference of the two character values at position {@code k} in
1122 * the two string -- that is, the value:
1123 * <blockquote><pre>
1124 * this.charAt(k)-anotherString.charAt(k)
1125 * </pre></blockquote>
1126 * If there is no index position at which they differ, then the shorter
1127 * string lexicographically precedes the longer string. In this case,
1128 * {@code compareTo} returns the difference of the lengths of the
1129 * strings -- that is, the value:
1130 * <blockquote><pre>
1131 * this.length()-anotherString.length()
1132 * </pre></blockquote>
1133 *
1134 * @param anotherString the {@code String} to be compared.
1135 * @return the value {@code 0} if the argument string is equal to
1136 * this string; a value less than {@code 0} if this string
1137 * is lexicographically less than the string argument; and a
1138 * value greater than {@code 0} if this string is
1139 * lexicographically greater than the string argument.
1140 */
1141 public int compareTo(String anotherString) {
1142 int len1 = value.length;
1143 int len2 = anotherString.value.length;
1144 int lim = Math.min(len1, len2);
1145 char v1[] = value;
1146 char v2[] = anotherString.value;
1147
1148 int k = 0;
1149 while (k < lim) {
1150 char c1 = v1[k];
1151 char c2 = v2[k];
1152 if (c1 != c2) {
1153 return c1 - c2;
1154 }
1155 k++;
1156 }
1157 return len1 - len2;
1158 }
1159
1160 /**
1161 * A Comparator that orders {@code String} objects as by
1162 * {@code compareToIgnoreCase}. This comparator is serializable.
1163 * <p>
1164 * Note that this Comparator does <em>not</em> take locale into account,
1165 * and will result in an unsatisfactory ordering for certain locales.
1166 * The java.text package provides <em>Collators</em> to allow
1167 * locale-sensitive ordering.
1168 *
1169 * @see java.text.Collator#compare(String, String)
1170 * @since 1.2
1171 */
1172 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1173 = new CaseInsensitiveComparator();
1174 private static class CaseInsensitiveComparator
1175 implements Comparator<String>, java.io.Serializable {
1176 // use serialVersionUID from JDK 1.2.2 for interoperability
1177 private static final long serialVersionUID = 8575799808933029326L;
1178
1179 public int compare(String s1, String s2) {
1180 int n1 = s1.length();
1181 int n2 = s2.length();
1182 int min = Math.min(n1, n2);
1183 for (int i = 0; i < min; i++) {
1184 char c1 = s1.charAt(i);
1185 char c2 = s2.charAt(i);
1186 if (c1 != c2) {
1187 c1 = Character.toUpperCase(c1);
1188 c2 = Character.toUpperCase(c2);
1189 if (c1 != c2) {
1190 c1 = Character.toLowerCase(c1);
1191 c2 = Character.toLowerCase(c2);
1192 if (c1 != c2) {
1193 // No overflow because of numeric promotion
1194 return c1 - c2;
1195 }
1196 }
1197 }
1198 }
1199 return n1 - n2;
1200 }
1201
1202 /** Replaces the de-serialized object. */
1203 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1204 }
1205
1206 /**
1207 * Compares two strings lexicographically, ignoring case
1208 * differences. This method returns an integer whose sign is that of
1209 * calling {@code compareTo} with normalized versions of the strings
1210 * where case differences have been eliminated by calling
1211 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1212 * each character.
1213 * <p>
1214 * Note that this method does <em>not</em> take locale into account,
1215 * and will result in an unsatisfactory ordering for certain locales.
1216 * The java.text package provides <em>collators</em> to allow
1217 * locale-sensitive ordering.
1218 *
1219 * @param str the {@code String} to be compared.
1220 * @return a negative integer, zero, or a positive integer as the
1221 * specified String is greater than, equal to, or less
1222 * than this String, ignoring case considerations.
1223 * @see java.text.Collator#compare(String, String)
1224 * @since 1.2
1225 */
1226 public int compareToIgnoreCase(String str) {
1227 return CASE_INSENSITIVE_ORDER.compare(this, str);
1228 }
1229
1230 /**
1231 * Tests if two string regions are equal.
1232 * <p>
1233 * A substring of this {@code String} object is compared to a substring
1234 * of the argument other. The result is true if these substrings
1235 * represent identical character sequences. The substring of this
1236 * {@code String} object to be compared begins at index {@code toffset}
1237 * and has length {@code len}. The substring of other to be compared
1238 * begins at index {@code ooffset} and has length {@code len}. The
1239 * result is {@code false} if and only if at least one of the following
1240 * is true:
1241 * <ul><li>{@code toffset} is negative.
1242 * <li>{@code ooffset} is negative.
1243 * <li>{@code toffset+len} is greater than the length of this
1244 * {@code String} object.
1245 * <li>{@code ooffset+len} is greater than the length of the other
1246 * argument.
1247 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1248 * such that:
1249 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1250 * <i>k</i>{@code )}
1251 * </ul>
1252 *
1253 * @param toffset the starting offset of the subregion in this string.
1254 * @param other the string argument.
1255 * @param ooffset the starting offset of the subregion in the string
1256 * argument.
1257 * @param len the number of characters to compare.
1258 * @return {@code true} if the specified subregion of this string
1259 * exactly matches the specified subregion of the string argument;
1260 * {@code false} otherwise.
1261 */
1262 public boolean regionMatches(int toffset, String other, int ooffset,
1263 int len) {
1264 char ta[] = value;
1265 int to = toffset;
1266 char pa[] = other.value;
1267 int po = ooffset;
1268 // Note: toffset, ooffset, or len might be near -1>>>1.
1269 if ((ooffset < 0) || (toffset < 0)
1270 || (toffset > (long)value.length - len)
1271 || (ooffset > (long)other.value.length - len)) {
1272 return false;
1273 }
1274 while (len-- > 0) {
1275 if (ta[to++] != pa[po++]) {
1276 return false;
1277 }
1278 }
1279 return true;
1280 }
1281
1282 /**
1283 * Tests if two string regions are equal.
1284 * <p>
1285 * A substring of this {@code String} object is compared to a substring
1286 * of the argument {@code other}. The result is {@code true} if these
1287 * substrings represent character sequences that are the same, ignoring
1288 * case if and only if {@code ignoreCase} is true. The substring of
1289 * this {@code String} object to be compared begins at index
1290 * {@code toffset} and has length {@code len}. The substring of
1291 * {@code other} to be compared begins at index {@code ooffset} and
1292 * has length {@code len}. The result is {@code false} if and only if
1293 * at least one of the following is true:
1294 * <ul><li>{@code toffset} is negative.
1295 * <li>{@code ooffset} is negative.
1296 * <li>{@code toffset+len} is greater than the length of this
1297 * {@code String} object.
1298 * <li>{@code ooffset+len} is greater than the length of the other
1299 * argument.
1300 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1301 * integer <i>k</i> less than {@code len} such that:
1302 * <blockquote><pre>
1303 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1304 * </pre></blockquote>
1305 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1306 * integer <i>k</i> less than {@code len} such that:
1307 * <blockquote><pre>
1308 * Character.toLowerCase(this.charAt(toffset+k)) !=
1309 Character.toLowerCase(other.charAt(ooffset+k))
1310 * </pre></blockquote>
1311 * and:
1312 * <blockquote><pre>
1313 * Character.toUpperCase(this.charAt(toffset+k)) !=
1314 * Character.toUpperCase(other.charAt(ooffset+k))
1315 * </pre></blockquote>
1316 * </ul>
1317 *
1318 * @param ignoreCase if {@code true}, ignore case when comparing
1319 * characters.
1320 * @param toffset the starting offset of the subregion in this
1321 * string.
1322 * @param other the string argument.
1323 * @param ooffset the starting offset of the subregion in the string
1324 * argument.
1325 * @param len the number of characters to compare.
1326 * @return {@code true} if the specified subregion of this string
1327 * matches the specified subregion of the string argument;
1328 * {@code false} otherwise. Whether the matching is exact
1329 * or case insensitive depends on the {@code ignoreCase}
1330 * argument.
1331 */
1332 public boolean regionMatches(boolean ignoreCase, int toffset,
1333 String other, int ooffset, int len) {
1334 char ta[] = value;
1335 int to = toffset;
1336 char pa[] = other.value;
1337 int po = ooffset;
1338 // Note: toffset, ooffset, or len might be near -1>>>1.
1339 if ((ooffset < 0) || (toffset < 0)
1340 || (toffset > (long)value.length - len)
1341 || (ooffset > (long)other.value.length - len)) {
1342 return false;
1343 }
1344 while (len-- > 0) {
1345 char c1 = ta[to++];
1346 char c2 = pa[po++];
1347 if (c1 == c2) {
1348 continue;
1349 }
1350 if (ignoreCase) {
1351 // If characters don't match but case may be ignored,
1352 // try converting both characters to uppercase.
1353 // If the results match, then the comparison scan should
1354 // continue.
1355 char u1 = Character.toUpperCase(c1);
1356 char u2 = Character.toUpperCase(c2);
1357 if (u1 == u2) {
1358 continue;
1359 }
1360 // Unfortunately, conversion to uppercase does not work properly
1361 // for the Georgian alphabet, which has strange rules about case
1362 // conversion. So we need to make one last check before
1363 // exiting.
1364 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1365 continue;
1366 }
1367 }
1368 return false;
1369 }
1370 return true;
1371 }
1372
1373 /**
1374 * Tests if the substring of this string beginning at the
1375 * specified index starts with the specified prefix.
1376 *
1377 * @param prefix the prefix.
1378 * @param toffset where to begin looking in this string.
1379 * @return {@code true} if the character sequence represented by the
1380 * argument is a prefix of the substring of this object starting
1381 * at index {@code toffset}; {@code false} otherwise.
1382 * The result is {@code false} if {@code toffset} is
1383 * negative or greater than the length of this
1384 * {@code String} object; otherwise the result is the same
1385 * as the result of the expression
1386 * <pre>
1387 * this.substring(toffset).startsWith(prefix)
1388 * </pre>
1389 */
1390 public boolean startsWith(String prefix, int toffset) {
1391 char ta[] = value;
1392 int to = toffset;
1393 char pa[] = prefix.value;
1394 int po = 0;
1395 int pc = prefix.value.length;
1396 // Note: toffset might be near -1>>>1.
1397 if ((toffset < 0) || (toffset > value.length - pc)) {
1398 return false;
1399 }
1400 while (--pc >= 0) {
1401 if (ta[to++] != pa[po++]) {
1402 return false;
1403 }
1404 }
1405 return true;
1406 }
1407
1408 /**
1409 * Tests if this string starts with the specified prefix.
1410 *
1411 * @param prefix the prefix.
1412 * @return {@code true} if the character sequence represented by the
1413 * argument is a prefix of the character sequence represented by
1414 * this string; {@code false} otherwise.
1415 * Note also that {@code true} will be returned if the
1416 * argument is an empty string or is equal to this
1417 * {@code String} object as determined by the
1418 * {@link #equals(Object)} method.
1419 * @since 1.0
1420 */
1421 public boolean startsWith(String prefix) {
1422 return startsWith(prefix, 0);
1423 }
1424
1425 /**
1426 * Tests if this string ends with the specified suffix.
1427 *
1428 * @param suffix the suffix.
1429 * @return {@code true} if the character sequence represented by the
1430 * argument is a suffix of the character sequence represented by
1431 * this object; {@code false} otherwise. Note that the
1432 * result will be {@code true} if the argument is the
1433 * empty string or is equal to this {@code String} object
1434 * as determined by the {@link #equals(Object)} method.
1435 */
1436 public boolean endsWith(String suffix) {
1437 return startsWith(suffix, value.length - suffix.value.length);
1438 }
1439
1440 /**
1441 * Returns a hash code for this string. The hash code for a
1442 * {@code String} object is computed as
1443 * <blockquote><pre>
1444 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1445 * </pre></blockquote>
1446 * using {@code int} arithmetic, where {@code s[i]} is the
1447 * <i>i</i>th character of the string, {@code n} is the length of
1448 * the string, and {@code ^} indicates exponentiation.
1449 * (The hash value of the empty string is zero.)
1450 *
1451 * @return a hash code value for this object.
1452 */
1453 public int hashCode() {
1454 int h = hash;
1455 if (h == 0) {
1456 for (char v : value) {
1457 h = 31 * h + v;
1458 }
1459 hash = h;
1460 }
1461 return h;
1462 }
1463
1464 /**
1465 * Returns the index within this string of the first occurrence of
1466 * the specified character. If a character with value
1467 * {@code ch} occurs in the character sequence represented by
1468 * this {@code String} object, then the index (in Unicode
1469 * code units) of the first such occurrence is returned. For
1470 * values of {@code ch} in the range from 0 to 0xFFFF
1471 * (inclusive), this is the smallest value <i>k</i> such that:
1472 * <blockquote><pre>
1473 * this.charAt(<i>k</i>) == ch
1474 * </pre></blockquote>
1475 * is true. For other values of {@code ch}, it is the
1476 * smallest value <i>k</i> such that:
1477 * <blockquote><pre>
1478 * this.codePointAt(<i>k</i>) == ch
1479 * </pre></blockquote>
1480 * is true. In either case, if no such character occurs in this
1481 * string, then {@code -1} is returned.
1482 *
1483 * @param ch a character (Unicode code point).
1484 * @return the index of the first occurrence of the character in the
1485 * character sequence represented by this object, or
1486 * {@code -1} if the character does not occur.
1487 */
1488 public int indexOf(int ch) {
1489 return indexOf(ch, 0);
1490 }
1491
1492 /**
1493 * Returns the index within this string of the first occurrence of the
1494 * specified character, starting the search at the specified index.
1495 * <p>
1496 * If a character with value {@code ch} occurs in the
1497 * character sequence represented by this {@code String}
1498 * object at an index no smaller than {@code fromIndex}, then
1499 * the index of the first such occurrence is returned. For values
1500 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1501 * this is the smallest value <i>k</i> such that:
1502 * <blockquote><pre>
1503 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1504 * </pre></blockquote>
1505 * is true. For other values of {@code ch}, it is the
1506 * smallest value <i>k</i> such that:
1507 * <blockquote><pre>
1508 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1509 * </pre></blockquote>
1510 * is true. In either case, if no such character occurs in this
1511 * string at or after position {@code fromIndex}, then
1512 * {@code -1} is returned.
1513 *
1514 * <p>
1515 * There is no restriction on the value of {@code fromIndex}. If it
1516 * is negative, it has the same effect as if it were zero: this entire
1517 * string may be searched. If it is greater than the length of this
1518 * string, it has the same effect as if it were equal to the length of
1519 * this string: {@code -1} is returned.
1520 *
1521 * <p>All indices are specified in {@code char} values
1522 * (Unicode code units).
1523 *
1524 * @param ch a character (Unicode code point).
1525 * @param fromIndex the index to start the search from.
1526 * @return the index of the first occurrence of the character in the
1527 * character sequence represented by this object that is greater
1528 * than or equal to {@code fromIndex}, or {@code -1}
1529 * if the character does not occur.
1530 */
1531 public int indexOf(int ch, int fromIndex) {
1532 final int max = value.length;
1533 if (fromIndex < 0) {
1534 fromIndex = 0;
1535 } else if (fromIndex >= max) {
1536 // Note: fromIndex might be near -1>>>1.
1537 return -1;
1538 }
1539
1540 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1541 // handle most cases here (ch is a BMP code point or a
1542 // negative value (invalid code point))
1543 final char[] value = this.value;
1544 for (int i = fromIndex; i < max; i++) {
1545 if (value[i] == ch) {
1546 return i;
1547 }
1548 }
1549 return -1;
1550 } else {
1551 return indexOfSupplementary(ch, fromIndex);
1552 }
1553 }
1554
1555 /**
1556 * Handles (rare) calls of indexOf with a supplementary character.
1557 */
1558 private int indexOfSupplementary(int ch, int fromIndex) {
1559 if (Character.isValidCodePoint(ch)) {
1560 final char[] value = this.value;
1561 final char hi = Character.highSurrogate(ch);
1562 final char lo = Character.lowSurrogate(ch);
1563 final int max = value.length - 1;
1564 for (int i = fromIndex; i < max; i++) {
1565 if (value[i] == hi && value[i + 1] == lo) {
1566 return i;
1567 }
1568 }
1569 }
1570 return -1;
1571 }
1572
1573 /**
1574 * Returns the index within this string of the last occurrence of
1575 * the specified character. For values of {@code ch} in the
1576 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1577 * units) returned is the largest value <i>k</i> such that:
1578 * <blockquote><pre>
1579 * this.charAt(<i>k</i>) == ch
1580 * </pre></blockquote>
1581 * is true. For other values of {@code ch}, it is the
1582 * largest value <i>k</i> such that:
1583 * <blockquote><pre>
1584 * this.codePointAt(<i>k</i>) == ch
1585 * </pre></blockquote>
1586 * is true. In either case, if no such character occurs in this
1587 * string, then {@code -1} is returned. The
1588 * {@code String} is searched backwards starting at the last
1589 * character.
1590 *
1591 * @param ch a character (Unicode code point).
1592 * @return the index of the last occurrence of the character in the
1593 * character sequence represented by this object, or
1594 * {@code -1} if the character does not occur.
1595 */
1596 public int lastIndexOf(int ch) {
1597 return lastIndexOf(ch, value.length - 1);
1598 }
1599
1600 /**
1601 * Returns the index within this string of the last occurrence of
1602 * the specified character, searching backward starting at the
1603 * specified index. For values of {@code ch} in the range
1604 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1605 * value <i>k</i> such that:
1606 * <blockquote><pre>
1607 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1608 * </pre></blockquote>
1609 * is true. For other values of {@code ch}, it is the
1610 * largest value <i>k</i> such that:
1611 * <blockquote><pre>
1612 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1613 * </pre></blockquote>
1614 * is true. In either case, if no such character occurs in this
1615 * string at or before position {@code fromIndex}, then
1616 * {@code -1} is returned.
1617 *
1618 * <p>All indices are specified in {@code char} values
1619 * (Unicode code units).
1620 *
1621 * @param ch a character (Unicode code point).
1622 * @param fromIndex the index to start the search from. There is no
1623 * restriction on the value of {@code fromIndex}. If it is
1624 * greater than or equal to the length of this string, it has
1625 * the same effect as if it were equal to one less than the
1626 * length of this string: this entire string may be searched.
1627 * If it is negative, it has the same effect as if it were -1:
1628 * -1 is returned.
1629 * @return the index of the last occurrence of the character in the
1630 * character sequence represented by this object that is less
1631 * than or equal to {@code fromIndex}, or {@code -1}
1632 * if the character does not occur before that point.
1633 */
1634 public int lastIndexOf(int ch, int fromIndex) {
1635 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1636 // handle most cases here (ch is a BMP code point or a
1637 // negative value (invalid code point))
1638 final char[] value = this.value;
1639 int i = Math.min(fromIndex, value.length - 1);
1640 for (; i >= 0; i--) {
1641 if (value[i] == ch) {
1642 return i;
1643 }
1644 }
1645 return -1;
1646 } else {
1647 return lastIndexOfSupplementary(ch, fromIndex);
1648 }
1649 }
1650
1651 /**
1652 * Handles (rare) calls of lastIndexOf with a supplementary character.
1653 */
1654 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1655 if (Character.isValidCodePoint(ch)) {
1656 final char[] value = this.value;
1657 char hi = Character.highSurrogate(ch);
1658 char lo = Character.lowSurrogate(ch);
1659 int i = Math.min(fromIndex, value.length - 2);
1660 for (; i >= 0; i--) {
1661 if (value[i] == hi && value[i + 1] == lo) {
1662 return i;
1663 }
1664 }
1665 }
1666 return -1;
1667 }
1668
1669 /**
1670 * Returns the index within this string of the first occurrence of the
1671 * specified substring.
1672 *
1673 * <p>The returned index is the smallest value {@code k} for which:
1674 * <pre>{@code
1675 * this.startsWith(str, k)
1676 * }</pre>
1677 * If no such value of {@code k} exists, then {@code -1} is returned.
1678 *
1679 * @param str the substring to search for.
1680 * @return the index of the first occurrence of the specified substring,
1681 * or {@code -1} if there is no such occurrence.
1682 */
1683 public int indexOf(String str) {
1684 return indexOf(str, 0);
1685 }
1686
1687 /**
1688 * Returns the index within this string of the first occurrence of the
1689 * specified substring, starting at the specified index.
1690 *
1691 * <p>The returned index is the smallest value {@code k} for which:
1692 * <pre>{@code
1693 * k >= Math.min(fromIndex, this.length()) &&
1694 * this.startsWith(str, k)
1695 * }</pre>
1696 * If no such value of {@code k} exists, then {@code -1} is returned.
1697 *
1698 * @param str the substring to search for.
1699 * @param fromIndex the index from which to start the search.
1700 * @return the index of the first occurrence of the specified substring,
1701 * starting at the specified index,
1702 * or {@code -1} if there is no such occurrence.
1703 */
1704 public int indexOf(String str, int fromIndex) {
1705 return indexOf(value, 0, value.length,
1706 str.value, 0, str.value.length, fromIndex);
1707 }
1708
1709 /**
1710 * Code shared by String and AbstractStringBuilder to do searches. The
1711 * source is the character array being searched, and the target
1712 * is the string being searched for.
1713 *
1714 * @param source the characters being searched.
1715 * @param sourceOffset offset of the source string.
1716 * @param sourceCount count of the source string.
1717 * @param target the characters being searched for.
1718 * @param fromIndex the index to begin searching from.
1719 */
1720 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1721 String target, int fromIndex) {
1722 return indexOf(source, sourceOffset, sourceCount,
1723 target.value, 0, target.value.length,
1724 fromIndex);
1725 }
1726
1727 /**
1728 * Code shared by String and StringBuffer to do searches. The
1729 * source is the character array being searched, and the target
1730 * is the string being searched for.
1731 *
1732 * @param source the characters being searched.
1733 * @param sourceOffset offset of the source string.
1734 * @param sourceCount count of the source string.
1735 * @param target the characters being searched for.
1736 * @param targetOffset offset of the target string.
1737 * @param targetCount count of the target string.
1738 * @param fromIndex the index to begin searching from.
1739 */
1740 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1741 char[] target, int targetOffset, int targetCount,
1742 int fromIndex) {
1743 if (fromIndex >= sourceCount) {
1744 return (targetCount == 0 ? sourceCount : -1);
1745 }
1746 if (fromIndex < 0) {
1747 fromIndex = 0;
1748 }
1749 if (targetCount == 0) {
1750 return fromIndex;
1751 }
1752
1753 char first = target[targetOffset];
1754 int max = sourceOffset + (sourceCount - targetCount);
1755
1756 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1757 /* Look for first character. */
1758 if (source[i] != first) {
1759 while (++i <= max && source[i] != first);
1760 }
1761
1762 /* Found first character, now look at the rest of v2 */
1763 if (i <= max) {
1764 int j = i + 1;
1765 int end = j + targetCount - 1;
1766 for (int k = targetOffset + 1; j < end && source[j]
1767 == target[k]; j++, k++);
1768
1769 if (j == end) {
1770 /* Found whole string. */
1771 return i - sourceOffset;
1772 }
1773 }
1774 }
1775 return -1;
1776 }
1777
1778 /**
1779 * Returns the index within this string of the last occurrence of the
1780 * specified substring. The last occurrence of the empty string ""
1781 * is considered to occur at the index value {@code this.length()}.
1782 *
1783 * <p>The returned index is the largest value {@code k} for which:
1784 * <pre>{@code
1785 * this.startsWith(str, k)
1786 * }</pre>
1787 * If no such value of {@code k} exists, then {@code -1} is returned.
1788 *
1789 * @param str the substring to search for.
1790 * @return the index of the last occurrence of the specified substring,
1791 * or {@code -1} if there is no such occurrence.
1792 */
1793 public int lastIndexOf(String str) {
1794 return lastIndexOf(str, value.length);
1795 }
1796
1797 /**
1798 * Returns the index within this string of the last occurrence of the
1799 * specified substring, searching backward starting at the specified index.
1800 *
1801 * <p>The returned index is the largest value {@code k} for which:
1802 * <pre>{@code
1803 * k <= Math.min(fromIndex, this.length()) &&
1804 * this.startsWith(str, k)
1805 * }</pre>
1806 * If no such value of {@code k} exists, then {@code -1} is returned.
1807 *
1808 * @param str the substring to search for.
1809 * @param fromIndex the index to start the search from.
1810 * @return the index of the last occurrence of the specified substring,
1811 * searching backward from the specified index,
1812 * or {@code -1} if there is no such occurrence.
1813 */
1814 public int lastIndexOf(String str, int fromIndex) {
1815 return lastIndexOf(value, 0, value.length,
1816 str.value, 0, str.value.length, fromIndex);
1817 }
1818
1819 /**
1820 * Code shared by String and AbstractStringBuilder to do searches. The
1821 * source is the character array being searched, and the target
1822 * is the string being searched for.
1823 *
1824 * @param source the characters being searched.
1825 * @param sourceOffset offset of the source string.
1826 * @param sourceCount count of the source string.
1827 * @param target the characters being searched for.
1828 * @param fromIndex the index to begin searching from.
1829 */
1830 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1831 String target, int fromIndex) {
1832 return lastIndexOf(source, sourceOffset, sourceCount,
1833 target.value, 0, target.value.length,
1834 fromIndex);
1835 }
1836
1837 /**
1838 * Code shared by String and StringBuffer to do searches. The
1839 * source is the character array being searched, and the target
1840 * is the string being searched for.
1841 *
1842 * @param source the characters being searched.
1843 * @param sourceOffset offset of the source string.
1844 * @param sourceCount count of the source string.
1845 * @param target the characters being searched for.
1846 * @param targetOffset offset of the target string.
1847 * @param targetCount count of the target string.
1848 * @param fromIndex the index to begin searching from.
1849 */
1850 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1851 char[] target, int targetOffset, int targetCount,
1852 int fromIndex) {
1853 /*
1854 * Check arguments; return immediately where possible. For
1855 * consistency, don't check for null str.
1856 */
1857 int rightIndex = sourceCount - targetCount;
1858 if (fromIndex < 0) {
1859 return -1;
1860 }
1861 if (fromIndex > rightIndex) {
1862 fromIndex = rightIndex;
1863 }
1864 /* Empty string always matches. */
1865 if (targetCount == 0) {
1866 return fromIndex;
1867 }
1868
1869 int strLastIndex = targetOffset + targetCount - 1;
1870 char strLastChar = target[strLastIndex];
1871 int min = sourceOffset + targetCount - 1;
1872 int i = min + fromIndex;
1873
1874 startSearchForLastChar:
1875 while (true) {
1876 while (i >= min && source[i] != strLastChar) {
1877 i--;
1878 }
1879 if (i < min) {
1880 return -1;
1881 }
1882 int j = i - 1;
1883 int start = j - (targetCount - 1);
1884 int k = strLastIndex - 1;
1885
1886 while (j > start) {
1887 if (source[j--] != target[k--]) {
1888 i--;
1889 continue startSearchForLastChar;
1890 }
1891 }
1892 return start - sourceOffset + 1;
1893 }
1894 }
1895
1896 /**
1897 * Returns a string that is a substring of this string. The
1898 * substring begins with the character at the specified index and
1899 * extends to the end of this string. <p>
1900 * Examples:
1901 * <blockquote><pre>
1902 * "unhappy".substring(2) returns "happy"
1903 * "Harbison".substring(3) returns "bison"
1904 * "emptiness".substring(9) returns "" (an empty string)
1905 * </pre></blockquote>
1906 *
1907 * @param beginIndex the beginning index, inclusive.
1908 * @return the specified substring.
1909 * @exception IndexOutOfBoundsException if
1910 * {@code beginIndex} is negative or larger than the
1911 * length of this {@code String} object.
1912 */
1913 public String substring(int beginIndex) {
1914 if (beginIndex < 0) {
1915 throw new StringIndexOutOfBoundsException(beginIndex);
1916 }
1917 int subLen = value.length - beginIndex;
1918 if (subLen < 0) {
1919 throw new StringIndexOutOfBoundsException(subLen);
1920 }
1921 return (beginIndex == 0) ? this : new String(value, beginIndex, subLen);
1922 }
1923
1924 /**
1925 * Returns a string that is a substring of this string. The
1926 * substring begins at the specified {@code beginIndex} and
1927 * extends to the character at index {@code endIndex - 1}.
1928 * Thus the length of the substring is {@code endIndex-beginIndex}.
1929 * <p>
1930 * Examples:
1931 * <blockquote><pre>
1932 * "hamburger".substring(4, 8) returns "urge"
1933 * "smiles".substring(1, 5) returns "mile"
1934 * </pre></blockquote>
1935 *
1936 * @param beginIndex the beginning index, inclusive.
1937 * @param endIndex the ending index, exclusive.
1938 * @return the specified substring.
1939 * @exception IndexOutOfBoundsException if the
1940 * {@code beginIndex} is negative, or
1941 * {@code endIndex} is larger than the length of
1942 * this {@code String} object, or
1943 * {@code beginIndex} is larger than
1944 * {@code endIndex}.
1945 */
1946 public String substring(int beginIndex, int endIndex) {
1947 if (beginIndex < 0) {
1948 throw new StringIndexOutOfBoundsException(beginIndex);
1949 }
1950 if (endIndex > value.length) {
1951 throw new StringIndexOutOfBoundsException(endIndex);
1952 }
1953 int subLen = endIndex - beginIndex;
1954 if (subLen < 0) {
1955 throw new StringIndexOutOfBoundsException(subLen);
1956 }
1957 return ((beginIndex == 0) && (endIndex == value.length)) ? this
1958 : new String(value, beginIndex, subLen);
1959 }
1960
1961 /**
1962 * Returns a character sequence that is a subsequence of this sequence.
1963 *
1964 * <p> An invocation of this method of the form
1965 *
1966 * <blockquote><pre>
1967 * str.subSequence(begin, end)</pre></blockquote>
1968 *
1969 * behaves in exactly the same way as the invocation
1970 *
1971 * <blockquote><pre>
1972 * str.substring(begin, end)</pre></blockquote>
1973 *
1974 * @apiNote
1975 * This method is defined so that the {@code String} class can implement
1976 * the {@link CharSequence} interface.
1977 *
1978 * @param beginIndex the begin index, inclusive.
1979 * @param endIndex the end index, exclusive.
1980 * @return the specified subsequence.
1981 *
1982 * @throws IndexOutOfBoundsException
1983 * if {@code beginIndex} or {@code endIndex} is negative,
1984 * if {@code endIndex} is greater than {@code length()},
1985 * or if {@code beginIndex} is greater than {@code endIndex}
1986 *
1987 * @since 1.4
1988 * @spec JSR-51
1989 */
1990 public CharSequence subSequence(int beginIndex, int endIndex) {
1991 return this.substring(beginIndex, endIndex);
1992 }
1993
1994 /**
1995 * Concatenates the specified string to the end of this string.
1996 * <p>
1997 * If the length of the argument string is {@code 0}, then this
1998 * {@code String} object is returned. Otherwise, a
1999 * {@code String} object is returned that represents a character
2000 * sequence that is the concatenation of the character sequence
2001 * represented by this {@code String} object and the character
2002 * sequence represented by the argument string.<p>
2003 * Examples:
2004 * <blockquote><pre>
2005 * "cares".concat("s") returns "caress"
2006 * "to".concat("get").concat("her") returns "together"
2007 * </pre></blockquote>
2008 *
2009 * @param str the {@code String} that is concatenated to the end
2010 * of this {@code String}.
2011 * @return a string that represents the concatenation of this object's
2012 * characters followed by the string argument's characters.
2013 */
2014 public String concat(String str) {
2015 int otherLen = str.length();
2016 if (otherLen == 0) {
2017 return this;
2018 }
2019 int len = value.length;
2020 char buf[] = Arrays.copyOf(value, len + otherLen);
2021 str.getChars(buf, len);
2022 return new String(buf, true);
2023 }
2024
2025 /**
2026 * Returns a string resulting from replacing all occurrences of
2027 * {@code oldChar} in this string with {@code newChar}.
2028 * <p>
2029 * If the character {@code oldChar} does not occur in the
2030 * character sequence represented by this {@code String} object,
2031 * then a reference to this {@code String} object is returned.
2032 * Otherwise, a {@code String} object is returned that
2033 * represents a character sequence identical to the character sequence
2034 * represented by this {@code String} object, except that every
2035 * occurrence of {@code oldChar} is replaced by an occurrence
2036 * of {@code newChar}.
2037 * <p>
2038 * Examples:
2039 * <blockquote><pre>
2040 * "mesquite in your cellar".replace('e', 'o')
2041 * returns "mosquito in your collar"
2042 * "the war of baronets".replace('r', 'y')
2043 * returns "the way of bayonets"
2044 * "sparring with a purple porpoise".replace('p', 't')
2045 * returns "starring with a turtle tortoise"
2046 * "JonL".replace('q', 'x') returns "JonL" (no change)
2047 * </pre></blockquote>
2048 *
2049 * @param oldChar the old character.
2050 * @param newChar the new character.
2051 * @return a string derived from this string by replacing every
2052 * occurrence of {@code oldChar} with {@code newChar}.
2053 */
2054 public String replace(char oldChar, char newChar) {
2055 if (oldChar != newChar) {
2056 int len = value.length;
2057 int i = -1;
2058 char[] val = value; /* avoid getfield opcode */
2059
2060 while (++i < len) {
2061 if (val[i] == oldChar) {
2062 break;
2063 }
2064 }
2065 if (i < len) {
2066 char buf[] = new char[len];
2067 for (int j = 0; j < i; j++) {
2068 buf[j] = val[j];
2069 }
2070 while (i < len) {
2071 char c = val[i];
2072 buf[i] = (c == oldChar) ? newChar : c;
2073 i++;
2074 }
2075 return new String(buf, true);
2076 }
2077 }
2078 return this;
2079 }
2080
2081 /**
2082 * Tells whether or not this string matches the given <a
2083 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2084 *
2085 * <p> An invocation of this method of the form
2086 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2087 * same result as the expression
2088 *
2089 * <blockquote>
2090 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2091 * matches(<i>regex</i>, <i>str</i>)}
2092 * </blockquote>
2093 *
2094 * @param regex
2095 * the regular expression to which this string is to be matched
2096 *
2097 * @return {@code true} if, and only if, this string matches the
2098 * given regular expression
2099 *
2100 * @throws PatternSyntaxException
2101 * if the regular expression's syntax is invalid
2102 *
2103 * @see java.util.regex.Pattern
2104 *
2105 * @since 1.4
2106 * @spec JSR-51
2107 */
2108 public boolean matches(String regex) {
2109 return Pattern.matches(regex, this);
2110 }
2111
2112 /**
2113 * Returns true if and only if this string contains the specified
2114 * sequence of char values.
2115 *
2116 * @param s the sequence to search for
2117 * @return true if this string contains {@code s}, false otherwise
2118 * @since 1.5
2119 */
2120 public boolean contains(CharSequence s) {
2121 return indexOf(s.toString()) >= 0;
2122 }
2123
2124 /**
2125 * Replaces the first substring of this string that matches the given <a
2126 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2127 * given replacement.
2128 *
2129 * <p> An invocation of this method of the form
2130 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2131 * yields exactly the same result as the expression
2132 *
2133 * <blockquote>
2134 * <code>
2135 * {@link java.util.regex.Pattern}.{@link
2136 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2137 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2138 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2139 * </code>
2140 * </blockquote>
2141 *
2142 *<p>
2143 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2144 * replacement string may cause the results to be different than if it were
2145 * being treated as a literal replacement string; see
2146 * {@link java.util.regex.Matcher#replaceFirst}.
2147 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2148 * meaning of these characters, if desired.
2149 *
2150 * @param regex
2151 * the regular expression to which this string is to be matched
2152 * @param replacement
2153 * the string to be substituted for the first match
2154 *
2155 * @return The resulting {@code String}
2156 *
2157 * @throws PatternSyntaxException
2158 * if the regular expression's syntax is invalid
2159 *
2160 * @see java.util.regex.Pattern
2161 *
2162 * @since 1.4
2163 * @spec JSR-51
2164 */
2165 public String replaceFirst(String regex, String replacement) {
2166 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2167 }
2168
2169 /**
2170 * Replaces each substring of this string that matches the given <a
2171 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2172 * given replacement.
2173 *
2174 * <p> An invocation of this method of the form
2175 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2176 * yields exactly the same result as the expression
2177 *
2178 * <blockquote>
2179 * <code>
2180 * {@link java.util.regex.Pattern}.{@link
2181 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2182 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2183 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2184 * </code>
2185 * </blockquote>
2186 *
2187 *<p>
2188 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2189 * replacement string may cause the results to be different than if it were
2190 * being treated as a literal replacement string; see
2191 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2192 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2193 * meaning of these characters, if desired.
2194 *
2195 * @param regex
2196 * the regular expression to which this string is to be matched
2197 * @param replacement
2198 * the string to be substituted for each match
2199 *
2200 * @return The resulting {@code String}
2201 *
2202 * @throws PatternSyntaxException
2203 * if the regular expression's syntax is invalid
2204 *
2205 * @see java.util.regex.Pattern
2206 *
2207 * @since 1.4
2208 * @spec JSR-51
2209 */
2210 public String replaceAll(String regex, String replacement) {
2211 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2212 }
2213
2214 /**
2215 * Replaces each substring of this string that matches the literal target
2216 * sequence with the specified literal replacement sequence. The
2217 * replacement proceeds from the beginning of the string to the end, for
2218 * example, replacing "aa" with "b" in the string "aaa" will result in
2219 * "ba" rather than "ab".
2220 *
2221 * @param target The sequence of char values to be replaced
2222 * @param replacement The replacement sequence of char values
2223 * @return The resulting string
2224 * @since 1.5
2225 */
2226 public String replace(CharSequence target, CharSequence replacement) {
2227 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
2228 this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
2229 }
2230
2231 /**
2232 * Splits this string around matches of the given
2233 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2234 *
2235 * <p> The array returned by this method contains each substring of this
2236 * string that is terminated by another substring that matches the given
2237 * expression or is terminated by the end of the string. The substrings in
2238 * the array are in the order in which they occur in this string. If the
2239 * expression does not match any part of the input then the resulting array
2240 * has just one element, namely this string.
2241 *
2242 * <p> When there is a positive-width match at the beginning of this
2243 * string then an empty leading substring is included at the beginning
2244 * of the resulting array. A zero-width match at the beginning however
2245 * never produces such empty leading substring.
2246 *
2247 * <p> The {@code limit} parameter controls the number of times the
2248 * pattern is applied and therefore affects the length of the resulting
2249 * array. If the limit <i>n</i> is greater than zero then the pattern
2250 * will be applied at most <i>n</i> - 1 times, the array's
2251 * length will be no greater than <i>n</i>, and the array's last entry
2252 * will contain all input beyond the last matched delimiter. If <i>n</i>
2253 * is non-positive then the pattern will be applied as many times as
2254 * possible and the array can have any length. If <i>n</i> is zero then
2255 * the pattern will be applied as many times as possible, the array can
2256 * have any length, and trailing empty strings will be discarded.
2257 *
2258 * <p> The string {@code "boo:and:foo"}, for example, yields the
2259 * following results with these parameters:
2260 *
2261 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2262 * <tr>
2263 * <th>Regex</th>
2264 * <th>Limit</th>
2265 * <th>Result</th>
2266 * </tr>
2267 * <tr><td align=center>:</td>
2268 * <td align=center>2</td>
2269 * <td>{@code { "boo", "and:foo" }}</td></tr>
2270 * <tr><td align=center>:</td>
2271 * <td align=center>5</td>
2272 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2273 * <tr><td align=center>:</td>
2274 * <td align=center>-2</td>
2275 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2276 * <tr><td align=center>o</td>
2277 * <td align=center>5</td>
2278 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2279 * <tr><td align=center>o</td>
2280 * <td align=center>-2</td>
2281 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2282 * <tr><td align=center>o</td>
2283 * <td align=center>0</td>
2284 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2285 * </table></blockquote>
2286 *
2287 * <p> An invocation of this method of the form
2288 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2289 * yields the same result as the expression
2290 *
2291 * <blockquote>
2292 * <code>
2293 * {@link java.util.regex.Pattern}.{@link
2294 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2295 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2296 * </code>
2297 * </blockquote>
2298 *
2299 *
2300 * @param regex
2301 * the delimiting regular expression
2302 *
2303 * @param limit
2304 * the result threshold, as described above
2305 *
2306 * @return the array of strings computed by splitting this string
2307 * around matches of the given regular expression
2308 *
2309 * @throws PatternSyntaxException
2310 * if the regular expression's syntax is invalid
2311 *
2312 * @see java.util.regex.Pattern
2313 *
2314 * @since 1.4
2315 * @spec JSR-51
2316 */
2317 public String[] split(String regex, int limit) {
2318 /* fastpath if the regex is a
2319 (1)one-char String and this character is not one of the
2320 RegEx's meta characters ".$|()[{^?*+\\", or
2321 (2)two-char String and the first char is the backslash and
2322 the second is not the ascii digit or ascii letter.
2323 */
2324 char ch = 0;
2325 if (((regex.value.length == 1 &&
2326 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2327 (regex.length() == 2 &&
2328 regex.charAt(0) == '\\' &&
2329 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2330 ((ch-'a')|('z'-ch)) < 0 &&
2331 ((ch-'A')|('Z'-ch)) < 0)) &&
2332 (ch < Character.MIN_HIGH_SURROGATE ||
2333 ch > Character.MAX_LOW_SURROGATE))
2334 {
2335 int off = 0;
2336 int next = 0;
2337 boolean limited = limit > 0;
2338 ArrayList<String> list = new ArrayList<>();
2339 while ((next = indexOf(ch, off)) != -1) {
2340 if (!limited || list.size() < limit - 1) {
2341 list.add(substring(off, next));
2342 off = next + 1;
2343 } else { // last one
2344 //assert (list.size() == limit - 1);
2345 list.add(substring(off, value.length));
2346 off = value.length;
2347 break;
2348 }
2349 }
2350 // If no match was found, return this
2351 if (off == 0)
2352 return new String[]{this};
2353
2354 // Add remaining segment
2355 if (!limited || list.size() < limit)
2356 list.add(substring(off, value.length));
2357
2358 // Construct result
2359 int resultSize = list.size();
2360 if (limit == 0) {
2361 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2362 resultSize--;
2363 }
2364 }
2365 String[] result = new String[resultSize];
2366 return list.subList(0, resultSize).toArray(result);
2367 }
2368 return Pattern.compile(regex).split(this, limit);
2369 }
2370
2371 /**
2372 * Splits this string around matches of the given <a
2373 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2374 *
2375 * <p> This method works as if by invoking the two-argument {@link
2376 * #split(String, int) split} method with the given expression and a limit
2377 * argument of zero. Trailing empty strings are therefore not included in
2378 * the resulting array.
2379 *
2380 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2381 * results with these expressions:
2382 *
2383 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2384 * <tr>
2385 * <th>Regex</th>
2386 * <th>Result</th>
2387 * </tr>
2388 * <tr><td align=center>:</td>
2389 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2390 * <tr><td align=center>o</td>
2391 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2392 * </table></blockquote>
2393 *
2394 *
2395 * @param regex
2396 * the delimiting regular expression
2397 *
2398 * @return the array of strings computed by splitting this string
2399 * around matches of the given regular expression
2400 *
2401 * @throws PatternSyntaxException
2402 * if the regular expression's syntax is invalid
2403 *
2404 * @see java.util.regex.Pattern
2405 *
2406 * @since 1.4
2407 * @spec JSR-51
2408 */
2409 public String[] split(String regex) {
2410 return split(regex, 0);
2411 }
2412
2413 /**
2414 * Returns a new String composed of copies of the
2415 * {@code CharSequence elements} joined together with a copy of
2416 * the specified {@code delimiter}.
2417 *
2418 * <blockquote>For example,
2419 * <pre>{@code
2420 * String message = String.join("-", "Java", "is", "cool");
2421 * // message returned is: "Java-is-cool"
2422 * }</pre></blockquote>
2423 *
2424 * Note that if an element is null, then {@code "null"} is added.
2425 *
2426 * @param delimiter the delimiter that separates each element
2427 * @param elements the elements to join together.
2428 *
2429 * @return a new {@code String} that is composed of the {@code elements}
2430 * separated by the {@code delimiter}
2431 *
2432 * @throws NullPointerException If {@code delimiter} or {@code elements}
2433 * is {@code null}
2434 *
2435 * @see java.util.StringJoiner
2436 * @since 1.8
2437 */
2438 public static String join(CharSequence delimiter, CharSequence... elements) {
2439 Objects.requireNonNull(delimiter);
2440 Objects.requireNonNull(elements);
2441 // Number of elements not likely worth Arrays.stream overhead.
2442 StringJoiner joiner = new StringJoiner(delimiter);
2443 for (CharSequence cs: elements) {
2444 joiner.add(cs);
2445 }
2446 return joiner.toString();
2447 }
2448
2449 /**
2450 * Returns a new {@code String} composed of copies of the
2451 * {@code CharSequence elements} joined together with a copy of the
2452 * specified {@code delimiter}.
2453 *
2454 * <blockquote>For example,
2455 * <pre>{@code
2456 * List<String> strings = new LinkedList<>();
2457 * strings.add("Java");strings.add("is");
2458 * strings.add("cool");
2459 * String message = String.join(" ", strings);
2460 * //message returned is: "Java is cool"
2461 *
2462 * Set<String> strings = new LinkedHashSet<>();
2463 * strings.add("Java"); strings.add("is");
2464 * strings.add("very"); strings.add("cool");
2465 * String message = String.join("-", strings);
2466 * //message returned is: "Java-is-very-cool"
2467 * }</pre></blockquote>
2468 *
2469 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2470 *
2471 * @param delimiter a sequence of characters that is used to separate each
2472 * of the {@code elements} in the resulting {@code String}
2473 * @param elements an {@code Iterable} that will have its {@code elements}
2474 * joined together.
2475 *
2476 * @return a new {@code String} that is composed from the {@code elements}
2477 * argument
2478 *
2479 * @throws NullPointerException If {@code delimiter} or {@code elements}
2480 * is {@code null}
2481 *
2482 * @see #join(CharSequence,CharSequence...)
2483 * @see java.util.StringJoiner
2484 * @since 1.8
2485 */
2486 public static String join(CharSequence delimiter,
2487 Iterable<? extends CharSequence> elements) {
2488 Objects.requireNonNull(delimiter);
2489 Objects.requireNonNull(elements);
2490 StringJoiner joiner = new StringJoiner(delimiter);
2491 for (CharSequence cs: elements) {
2492 joiner.add(cs);
2493 }
2494 return joiner.toString();
2495 }
2496
2497 /**
2498 * Converts all of the characters in this {@code String} to lower
2499 * case using the rules of the given {@code Locale}. Case mapping is based
2500 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2501 * class. Since case mappings are not always 1:1 char mappings, the resulting
2502 * {@code String} may be a different length than the original {@code String}.
2503 * <p>
2504 * Examples of lowercase mappings are in the following table:
2505 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2506 * <tr>
2507 * <th>Language Code of Locale</th>
2508 * <th>Upper Case</th>
2509 * <th>Lower Case</th>
2510 * <th>Description</th>
2511 * </tr>
2512 * <tr>
2513 * <td>tr (Turkish)</td>
2514 * <td>\u0130</td>
2515 * <td>\u0069</td>
2516 * <td>capital letter I with dot above -> small letter i</td>
2517 * </tr>
2518 * <tr>
2519 * <td>tr (Turkish)</td>
2520 * <td>\u0049</td>
2521 * <td>\u0131</td>
2522 * <td>capital letter I -> small letter dotless i </td>
2523 * </tr>
2524 * <tr>
2525 * <td>(all)</td>
2526 * <td>French Fries</td>
2527 * <td>french fries</td>
2528 * <td>lowercased all chars in String</td>
2529 * </tr>
2530 * <tr>
2531 * <td>(all)</td>
2532 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2533 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2534 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2535 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2536 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2537 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2538 * <td>lowercased all chars in String</td>
2539 * </tr>
2540 * </table>
2541 *
2542 * @param locale use the case transformation rules for this locale
2543 * @return the {@code String}, converted to lowercase.
2544 * @see java.lang.String#toLowerCase()
2545 * @see java.lang.String#toUpperCase()
2546 * @see java.lang.String#toUpperCase(Locale)
2547 * @since 1.1
2548 */
2549 public String toLowerCase(Locale locale) {
2550 if (locale == null) {
2551 throw new NullPointerException();
2552 }
2553 int first;
2554 boolean hasSurr = false;
2555 final int len = value.length;
2556
2557 // Now check if there are any characters that need to be changed, or are surrogate
2558 for (first = 0 ; first < len; first++) {
2559 int cp = (int)value[first];
2560 if (Character.isSurrogate((char)cp)) {
2561 hasSurr = true;
2562 break;
2563 }
2564 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR
2565 break;
2566 }
2567 }
2568 if (first == len)
2569 return this;
2570 char[] result = new char[len];
2571 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2572 // lowerCase characters.
2573 String lang = locale.getLanguage();
2574 if (lang == "tr" || lang == "az" || lang == "lt") {
2575 return toLowerCaseEx(result, first, locale, true);
2576 }
2577 if (hasSurr) {
2578 return toLowerCaseEx(result, first, locale, false);
2579 }
2580 for (int i = first; i < len; i++) {
2581 int cp = (int)value[i];
2582 if (cp == '\u03A3' || // GREEK CAPITAL LETTER SIGMA
2583 Character.isSurrogate((char)cp)) {
2584 return toLowerCaseEx(result, i, locale, false);
2585 }
2586 if (cp == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE
2587 return toLowerCaseEx(result, i, locale, true);
2588 }
2589 cp = Character.toLowerCase(cp);
2590 if (!Character.isBmpCodePoint(cp)) {
2591 return toLowerCaseEx(result, i, locale, false);
2592 }
2593 result[i] = (char)cp;
2594 }
2595 return new String(result, true);
2596 }
2597
2598 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) {
2599 int resultOffset = first;
2600 int srcCount;
2601 for (int i = first; i < value.length; i += srcCount) {
2602 int srcChar = (int)value[i];
2603 int lowerChar;
2604 char[] lowerCharArray;
2605 srcCount = 1;
2606 if (Character.isSurrogate((char)srcChar)) {
2607 srcChar = codePointAt(i);
2608 srcCount = Character.charCount(srcChar);
2609 }
2610 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2611 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2612 } else {
2613 lowerChar = Character.toLowerCase(srcChar);
2614 }
2615 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp
2616 result[resultOffset++] = (char)lowerChar;
2617 } else {
2618 if (lowerChar == Character.ERROR) {
2619 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2620 } else if (srcCount == 2) {
2621 resultOffset += Character.toChars(lowerChar, result, resultOffset);
2622 continue;
2623 } else {
2624 lowerCharArray = Character.toChars(lowerChar);
2625 }
2626 /* Grow result if needed */
2627 int mapLen = lowerCharArray.length;
2628 if (mapLen > srcCount) {
2629 char[] result2 = new char[result.length + mapLen - srcCount];
2630 System.arraycopy(result, 0, result2, 0, resultOffset);
2631 result = result2;
2632 }
2633 for (int x = 0; x < mapLen; ++x) {
2634 result[resultOffset++] = lowerCharArray[x];
2635 }
2636 }
2637 }
2638 return new String(result, 0, resultOffset);
2639 }
2640
2641 /**
2642 * Converts all of the characters in this {@code String} to lower
2643 * case using the rules of the default locale. This is equivalent to calling
2644 * {@code toLowerCase(Locale.getDefault())}.
2645 * <p>
2646 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2647 * results if used for strings that are intended to be interpreted locale
2648 * independently.
2649 * Examples are programming language identifiers, protocol keys, and HTML
2650 * tags.
2651 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2652 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2653 * LATIN SMALL LETTER DOTLESS I character.
2654 * To obtain correct results for locale insensitive strings, use
2655 * {@code toLowerCase(Locale.ROOT)}.
2656 *
2657 * @return the {@code String}, converted to lowercase.
2658 * @see java.lang.String#toLowerCase(Locale)
2659 */
2660 public String toLowerCase() {
2661 return toLowerCase(Locale.getDefault());
2662 }
2663
2664 /**
2665 * Converts all of the characters in this {@code String} to upper
2666 * case using the rules of the given {@code Locale}. Case mapping is based
2667 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2668 * class. Since case mappings are not always 1:1 char mappings, the resulting
2669 * {@code String} may be a different length than the original {@code String}.
2670 * <p>
2671 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2672 *
2673 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2674 * <tr>
2675 * <th>Language Code of Locale</th>
2676 * <th>Lower Case</th>
2677 * <th>Upper Case</th>
2678 * <th>Description</th>
2679 * </tr>
2680 * <tr>
2681 * <td>tr (Turkish)</td>
2682 * <td>\u0069</td>
2683 * <td>\u0130</td>
2684 * <td>small letter i -> capital letter I with dot above</td>
2685 * </tr>
2686 * <tr>
2687 * <td>tr (Turkish)</td>
2688 * <td>\u0131</td>
2689 * <td>\u0049</td>
2690 * <td>small letter dotless i -> capital letter I</td>
2691 * </tr>
2692 * <tr>
2693 * <td>(all)</td>
2694 * <td>\u00df</td>
2695 * <td>\u0053 \u0053</td>
2696 * <td>small letter sharp s -> two letters: SS</td>
2697 * </tr>
2698 * <tr>
2699 * <td>(all)</td>
2700 * <td>Fahrvergnügen</td>
2701 * <td>FAHRVERGNÜGEN</td>
2702 * <td></td>
2703 * </tr>
2704 * </table>
2705 * @param locale use the case transformation rules for this locale
2706 * @return the {@code String}, converted to uppercase.
2707 * @see java.lang.String#toUpperCase()
2708 * @see java.lang.String#toLowerCase()
2709 * @see java.lang.String#toLowerCase(Locale)
2710 * @since 1.1
2711 */
2712 public String toUpperCase(Locale locale) {
2713 if (locale == null) {
2714 throw new NullPointerException();
2715 }
2716 int first;
2717 boolean hasSurr = false;
2718 final int len = value.length;
2719
2720 // Now check if there are any characters that need to be changed, or are surrogate
2721 for (first = 0 ; first < len; first++ ) {
2722 int cp = (int)value[first];
2723 if (Character.isSurrogate((char)cp)) {
2724 hasSurr = true;
2725 break;
2726 }
2727 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR
2728 break;
2729 }
2730 }
2731 if (first == len) {
2732 return this;
2733 }
2734 char[] result = new char[len];
2735 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2736 // upperCase characters.
2737 String lang = locale.getLanguage();
2738 if (lang == "tr" || lang == "az" || lang == "lt") {
2739 return toUpperCaseEx(result, first, locale, true);
2740 }
2741 if (hasSurr) {
2742 return toUpperCaseEx(result, first, locale, false);
2743 }
2744 for (int i = first; i < len; i++) {
2745 int cp = (int)value[i];
2746 if (Character.isSurrogate((char)cp)) {
2747 return toUpperCaseEx(result, i, locale, false);
2748 }
2749 cp = Character.toUpperCaseEx(cp);
2750 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp
2751 return toUpperCaseEx(result, i, locale, false);
2752 }
2753 result[i] = (char)cp;
2754 }
2755 return new String(result, true);
2756 }
2757
2758 private String toUpperCaseEx(char[] result, int first, Locale locale,
2759 boolean localeDependent) {
2760 int resultOffset = first;
2761 int srcCount;
2762 for (int i = first; i < value.length; i += srcCount) {
2763 int srcChar = (int)value[i];
2764 int upperChar;
2765 char[] upperCharArray;
2766 srcCount = 1;
2767 if (Character.isSurrogate((char)srcChar)) {
2768 srcChar = codePointAt(i);
2769 srcCount = Character.charCount(srcChar);
2770 }
2771 if (localeDependent) {
2772 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2773 } else {
2774 upperChar = Character.toUpperCaseEx(srcChar);
2775 }
2776 if (Character.isBmpCodePoint(upperChar)) {
2777 result[resultOffset++] = (char)upperChar;
2778 } else {
2779 if (upperChar == Character.ERROR) {
2780 if (localeDependent) {
2781 upperCharArray =
2782 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
2783 } else {
2784 upperCharArray = Character.toUpperCaseCharArray(srcChar);
2785 }
2786 } else if (srcCount == 2) {
2787 resultOffset += Character.toChars(upperChar, result, resultOffset);
2788 continue;
2789 } else {
2790 upperCharArray = Character.toChars(upperChar);
2791 }
2792 /* Grow result if needed */
2793 int mapLen = upperCharArray.length;
2794 if (mapLen > srcCount) {
2795 char[] result2 = new char[result.length + mapLen - srcCount];
2796 System.arraycopy(result, 0, result2, 0, resultOffset);
2797 result = result2;
2798 }
2799 for (int x = 0; x < mapLen; ++x) {
2800 result[resultOffset++] = upperCharArray[x];
2801 }
2802 }
2803 }
2804 return new String(result, 0, resultOffset);
2805 }
2806
2807 /**
2808 * Converts all of the characters in this {@code String} to upper
2809 * case using the rules of the default locale. This method is equivalent to
2810 * {@code toUpperCase(Locale.getDefault())}.
2811 * <p>
2812 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2813 * results if used for strings that are intended to be interpreted locale
2814 * independently.
2815 * Examples are programming language identifiers, protocol keys, and HTML
2816 * tags.
2817 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2818 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2819 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2820 * To obtain correct results for locale insensitive strings, use
2821 * {@code toUpperCase(Locale.ROOT)}.
2822 *
2823 * @return the {@code String}, converted to uppercase.
2824 * @see java.lang.String#toUpperCase(Locale)
2825 */
2826 public String toUpperCase() {
2827 return toUpperCase(Locale.getDefault());
2828 }
2829
2830 /**
2831 * Returns a string whose value is this string, with any leading and trailing
2832 * whitespace removed.
2833 * <p>
2834 * If this {@code String} object represents an empty character
2835 * sequence, or the first and last characters of character sequence
2836 * represented by this {@code String} object both have codes
2837 * greater than {@code '\u005Cu0020'} (the space character), then a
2838 * reference to this {@code String} object is returned.
2839 * <p>
2840 * Otherwise, if there is no character with a code greater than
2841 * {@code '\u005Cu0020'} in the string, then a
2842 * {@code String} object representing an empty string is
2843 * returned.
2844 * <p>
2845 * Otherwise, let <i>k</i> be the index of the first character in the
2846 * string whose code is greater than {@code '\u005Cu0020'}, and let
2847 * <i>m</i> be the index of the last character in the string whose code
2848 * is greater than {@code '\u005Cu0020'}. A {@code String}
2849 * object is returned, representing the substring of this string that
2850 * begins with the character at index <i>k</i> and ends with the
2851 * character at index <i>m</i>-that is, the result of
2852 * {@code this.substring(k, m + 1)}.
2853 * <p>
2854 * This method may be used to trim whitespace (as defined above) from
2855 * the beginning and end of a string.
2856 *
2857 * @return A string whose value is this string, with any leading and trailing white
2858 * space removed, or this string if it has no leading or
2859 * trailing white space.
2860 */
2861 public String trim() {
2862 int len = value.length;
2863 int st = 0;
2864 char[] val = value; /* avoid getfield opcode */
2865
2866 while ((st < len) && (val[st] <= ' ')) {
2867 st++;
2868 }
2869 while ((st < len) && (val[len - 1] <= ' ')) {
2870 len--;
2871 }
2872 return ((st > 0) || (len < value.length)) ? substring(st, len) : this;
2873 }
2874
2875 /**
2876 * This object (which is already a string!) is itself returned.
2877 *
2878 * @return the string itself.
2879 */
2880 public String toString() {
2881 return this;
2882 }
2883
2884 /**
2885 * Converts this string to a new character array.
2886 *
2887 * @return a newly allocated character array whose length is the length
2888 * of this string and whose contents are initialized to contain
2889 * the character sequence represented by this string.
2890 */
2891 public char[] toCharArray() {
2892 // Cannot use Arrays.copyOf because of class initialization order issues
2893 char result[] = new char[value.length];
2894 System.arraycopy(value, 0, result, 0, value.length);
2895 return result;
2896 }
2897
2898 /**
2899 * Returns a formatted string using the specified format string and
2900 * arguments.
2901 *
2902 * <p> The locale always used is the one returned by {@link
2903 * java.util.Locale#getDefault() Locale.getDefault()}.
2904 *
2905 * @param format
2906 * A <a href="../util/Formatter.html#syntax">format string</a>
2907 *
2908 * @param args
2909 * Arguments referenced by the format specifiers in the format
2910 * string. If there are more arguments than format specifiers, the
2911 * extra arguments are ignored. The number of arguments is
2912 * variable and may be zero. The maximum number of arguments is
2913 * limited by the maximum dimension of a Java array as defined by
2914 * <cite>The Java™ Virtual Machine Specification</cite>.
2915 * The behaviour on a
2916 * {@code null} argument depends on the <a
2917 * href="../util/Formatter.html#syntax">conversion</a>.
2918 *
2919 * @throws java.util.IllegalFormatException
2920 * If a format string contains an illegal syntax, a format
2921 * specifier that is incompatible with the given arguments,
2922 * insufficient arguments given the format string, or other
2923 * illegal conditions. For specification of all possible
2924 * formatting errors, see the <a
2925 * href="../util/Formatter.html#detail">Details</a> section of the
2926 * formatter class specification.
2927 *
2928 * @return A formatted string
2929 *
2930 * @see java.util.Formatter
2931 * @since 1.5
2932 */
2933 public static String format(String format, Object... args) {
2934 return new Formatter().format(format, args).toString();
2935 }
2936
2937 /**
2938 * Returns a formatted string using the specified locale, format string,
2939 * and arguments.
2940 *
2941 * @param l
2942 * The {@linkplain java.util.Locale locale} to apply during
2943 * formatting. If {@code l} is {@code null} then no localization
2944 * is applied.
2945 *
2946 * @param format
2947 * A <a href="../util/Formatter.html#syntax">format string</a>
2948 *
2949 * @param args
2950 * Arguments referenced by the format specifiers in the format
2951 * string. If there are more arguments than format specifiers, the
2952 * extra arguments are ignored. The number of arguments is
2953 * variable and may be zero. The maximum number of arguments is
2954 * limited by the maximum dimension of a Java array as defined by
2955 * <cite>The Java™ Virtual Machine Specification</cite>.
2956 * The behaviour on a
2957 * {@code null} argument depends on the
2958 * <a href="../util/Formatter.html#syntax">conversion</a>.
2959 *
2960 * @throws java.util.IllegalFormatException
2961 * If a format string contains an illegal syntax, a format
2962 * specifier that is incompatible with the given arguments,
2963 * insufficient arguments given the format string, or other
2964 * illegal conditions. For specification of all possible
2965 * formatting errors, see the <a
2966 * href="../util/Formatter.html#detail">Details</a> section of the
2967 * formatter class specification
2968 *
2969 * @return A formatted string
2970 *
2971 * @see java.util.Formatter
2972 * @since 1.5
2973 */
2974 public static String format(Locale l, String format, Object... args) {
2975 return new Formatter(l).format(format, args).toString();
2976 }
2977
2978 /**
2979 * Returns the string representation of the {@code Object} argument.
2980 *
2981 * @param obj an {@code Object}.
2982 * @return if the argument is {@code null}, then a string equal to
2983 * {@code "null"}; otherwise, the value of
2984 * {@code obj.toString()} is returned.
2985 * @see java.lang.Object#toString()
2986 */
2987 public static String valueOf(Object obj) {
2988 return (obj == null) ? "null" : obj.toString();
2989 }
2990
2991 /**
2992 * Returns the string representation of the {@code char} array
2993 * argument. The contents of the character array are copied; subsequent
2994 * modification of the character array does not affect the returned
2995 * string.
2996 *
2997 * @param data the character array.
2998 * @return a {@code String} that contains the characters of the
2999 * character array.
3000 */
3001 public static String valueOf(char data[]) {
3002 return new String(data);
3003 }
3004
3005 /**
3006 * Returns the string representation of a specific subarray of the
3007 * {@code char} array argument.
3008 * <p>
3009 * The {@code offset} argument is the index of the first
3010 * character of the subarray. The {@code count} argument
3011 * specifies the length of the subarray. The contents of the subarray
3012 * are copied; subsequent modification of the character array does not
3013 * affect the returned string.
3014 *
3015 * @param data the character array.
3016 * @param offset initial offset of the subarray.
3017 * @param count length of the subarray.
3018 * @return a {@code String} that contains the characters of the
3019 * specified subarray of the character array.
3020 * @exception IndexOutOfBoundsException if {@code offset} is
3021 * negative, or {@code count} is negative, or
3022 * {@code offset+count} is larger than
3023 * {@code data.length}.
3024 */
3025 public static String valueOf(char data[], int offset, int count) {
3026 return new String(data, offset, count);
3027 }
3028
3029 /**
3030 * Equivalent to {@link #valueOf(char[], int, int)}.
3031 *
3032 * @param data the character array.
3033 * @param offset initial offset of the subarray.
3034 * @param count length of the subarray.
3035 * @return a {@code String} that contains the characters of the
3036 * specified subarray of the character array.
3037 * @exception IndexOutOfBoundsException if {@code offset} is
3038 * negative, or {@code count} is negative, or
3039 * {@code offset+count} is larger than
3040 * {@code data.length}.
3041 */
3042 public static String copyValueOf(char data[], int offset, int count) {
3043 return new String(data, offset, count);
3044 }
3045
3046 /**
3047 * Equivalent to {@link #valueOf(char[])}.
3048 *
3049 * @param data the character array.
3050 * @return a {@code String} that contains the characters of the
3051 * character array.
3052 */
3053 public static String copyValueOf(char data[]) {
3054 return new String(data);
3055 }
3056
3057 /**
3058 * Returns the string representation of the {@code boolean} argument.
3059 *
3060 * @param b a {@code boolean}.
3061 * @return if the argument is {@code true}, a string equal to
3062 * {@code "true"} is returned; otherwise, a string equal to
3063 * {@code "false"} is returned.
3064 */
3065 public static String valueOf(boolean b) {
3066 return b ? "true" : "false";
3067 }
3068
3069 /**
3070 * Returns the string representation of the {@code char}
3071 * argument.
3072 *
3073 * @param c a {@code char}.
3074 * @return a string of length {@code 1} containing
3075 * as its single character the argument {@code c}.
3076 */
3077 public static String valueOf(char c) {
3078 char data[] = {c};
3079 return new String(data, true);
3080 }
3081
3082 /**
3083 * Returns the string representation of the {@code int} argument.
3084 * <p>
3085 * The representation is exactly the one returned by the
3086 * {@code Integer.toString} method of one argument.
3087 *
3088 * @param i an {@code int}.
3089 * @return a string representation of the {@code int} argument.
3090 * @see java.lang.Integer#toString(int, int)
3091 */
3092 public static String valueOf(int i) {
3093 return Integer.toString(i);
3094 }
3095
3096 /**
3097 * Returns the string representation of the {@code long} argument.
3098 * <p>
3099 * The representation is exactly the one returned by the
3100 * {@code Long.toString} method of one argument.
3101 *
3102 * @param l a {@code long}.
3103 * @return a string representation of the {@code long} argument.
3104 * @see java.lang.Long#toString(long)
3105 */
3106 public static String valueOf(long l) {
3107 return Long.toString(l);
3108 }
3109
3110 /**
3111 * Returns the string representation of the {@code float} argument.
3112 * <p>
3113 * The representation is exactly the one returned by the
3114 * {@code Float.toString} method of one argument.
3115 *
3116 * @param f a {@code float}.
3117 * @return a string representation of the {@code float} argument.
3118 * @see java.lang.Float#toString(float)
3119 */
3120 public static String valueOf(float f) {
3121 return Float.toString(f);
3122 }
3123
3124 /**
3125 * Returns the string representation of the {@code double} argument.
3126 * <p>
3127 * The representation is exactly the one returned by the
3128 * {@code Double.toString} method of one argument.
3129 *
3130 * @param d a {@code double}.
3131 * @return a string representation of the {@code double} argument.
3132 * @see java.lang.Double#toString(double)
3133 */
3134 public static String valueOf(double d) {
3135 return Double.toString(d);
3136 }
3137
3138 /**
3139 * Returns a canonical representation for the string object.
3140 * <p>
3141 * A pool of strings, initially empty, is maintained privately by the
3142 * class {@code String}.
3143 * <p>
3144 * When the intern method is invoked, if the pool already contains a
3145 * string equal to this {@code String} object as determined by
3146 * the {@link #equals(Object)} method, then the string from the pool is
3147 * returned. Otherwise, this {@code String} object is added to the
3148 * pool and a reference to this {@code String} object is returned.
3149 * <p>
3150 * It follows that for any two strings {@code s} and {@code t},
3151 * {@code s.intern() == t.intern()} is {@code true}
3152 * if and only if {@code s.equals(t)} is {@code true}.
3153 * <p>
3154 * All literal strings and string-valued constant expressions are
3155 * interned. String literals are defined in section 3.10.5 of the
3156 * <cite>The Java™ Language Specification</cite>.
3157 *
3158 * @return a string that has the same contents as this string, but is
3159 * guaranteed to be from a pool of unique strings.
3160 */
3161 public native String intern();
3162 }