1 /* 2 * Copyright (c) 1994, 2015, Oracle and/or its affiliates. All rights reserved. 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4 * 5 * This code is free software; you can redistribute it and/or modify it 6 * under the terms of the GNU General Public License version 2 only, as 7 * published by the Free Software Foundation. Oracle designates this 8 * particular file as subject to the "Classpath" exception as provided 9 * by Oracle in the LICENSE file that accompanied this code. 10 * 11 * This code is distributed in the hope that it will be useful, but WITHOUT 12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 14 * version 2 for more details (a copy is included in the LICENSE file that 15 * accompanied this code). 16 * 17 * You should have received a copy of the GNU General Public License version 18 * 2 along with this work; if not, write to the Free Software Foundation, 19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 20 * 21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 22 * or visit www.oracle.com if you need additional information or have any 23 * questions. 24 */ 25 26 package java.lang; 27 28 import java.io.ObjectStreamField; 29 import java.io.UnsupportedEncodingException; 30 import java.nio.charset.Charset; 31 import java.util.ArrayList; 32 import java.util.Arrays; 33 import java.util.Comparator; 34 import java.util.Formatter; 35 import java.util.Locale; 36 import java.util.Objects; 37 import java.util.Spliterator; 38 import java.util.StringJoiner; 39 import java.util.function.IntConsumer; 40 import java.util.regex.Matcher; 41 import java.util.regex.Pattern; 42 import java.util.regex.PatternSyntaxException; 43 import java.util.stream.IntStream; 44 import java.util.stream.StreamSupport; 45 import jdk.internal.HotSpotIntrinsicCandidate; 46 47 /** 48 * The {@code String} class represents character strings. All 49 * string literals in Java programs, such as {@code "abc"}, are 50 * implemented as instances of this class. 51 * <p> 52 * Strings are constant; their values cannot be changed after they 53 * are created. String buffers support mutable strings. 54 * Because String objects are immutable they can be shared. For example: 55 * <blockquote><pre> 56 * String str = "abc"; 57 * </pre></blockquote><p> 58 * is equivalent to: 59 * <blockquote><pre> 60 * char data[] = {'a', 'b', 'c'}; 61 * String str = new String(data); 62 * </pre></blockquote><p> 63 * Here are some more examples of how strings can be used: 64 * <blockquote><pre> 65 * System.out.println("abc"); 66 * String cde = "cde"; 67 * System.out.println("abc" + cde); 68 * String c = "abc".substring(2,3); 69 * String d = cde.substring(1, 2); 70 * </pre></blockquote> 71 * <p> 72 * The class {@code String} includes methods for examining 73 * individual characters of the sequence, for comparing strings, for 74 * searching strings, for extracting substrings, and for creating a 75 * copy of a string with all characters translated to uppercase or to 76 * lowercase. Case mapping is based on the Unicode Standard version 77 * specified by the {@link java.lang.Character Character} class. 78 * <p> 79 * The Java language provides special support for the string 80 * concatenation operator ( + ), and for conversion of 81 * other objects to strings. String concatenation is implemented 82 * through the {@code StringBuilder}(or {@code StringBuffer}) 83 * class and its {@code append} method. 84 * String conversions are implemented through the method 85 * {@code toString}, defined by {@code Object} and 86 * inherited by all classes in Java. For additional information on 87 * string concatenation and conversion, see Gosling, Joy, and Steele, 88 * <i>The Java Language Specification</i>. 89 * 90 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor 91 * or method in this class will cause a {@link NullPointerException} to be 92 * thrown. 93 * 94 * <p>A {@code String} represents a string in the UTF-16 format 95 * in which <em>supplementary characters</em> are represented by <em>surrogate 96 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 97 * Character Representations</a> in the {@code Character} class for 98 * more information). 99 * Index values refer to {@code char} code units, so a supplementary 100 * character uses two positions in a {@code String}. 101 * <p>The {@code String} class provides methods for dealing with 102 * Unicode code points (i.e., characters), in addition to those for 103 * dealing with Unicode code units (i.e., {@code char} values). 104 * 105 * <p>Unless otherwise noted, methods for comparing Strings do not take locale 106 * into account. The {@link java.text.Collator} class provides methods for 107 * finer-grain, locale-sensitive String comparison. 108 * 109 * @author Lee Boynton 110 * @author Arthur van Hoff 111 * @author Martin Buchholz 112 * @author Ulf Zibis 113 * @see java.lang.Object#toString() 114 * @see java.lang.StringBuffer 115 * @see java.lang.StringBuilder 116 * @see java.nio.charset.Charset 117 * @since 1.0 118 */ 119 120 public final class String 121 implements java.io.Serializable, Comparable<String>, CharSequence { 122 /** The value is used for character storage. */ 123 private final char value[]; 124 125 /** Cache the hash code for the string */ 126 private int hash; // Default to 0 127 128 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 129 private static final long serialVersionUID = -6849794470754667710L; 130 131 /** 132 * Class String is special cased within the Serialization Stream Protocol. 133 * 134 * A String instance is written into an ObjectOutputStream according to 135 * <a href="{@docRoot}/../platform/serialization/spec/output.html"> 136 * Object Serialization Specification, Section 6.2, "Stream Elements"</a> 137 */ 138 private static final ObjectStreamField[] serialPersistentFields = 139 new ObjectStreamField[0]; 140 141 /** 142 * Initializes a newly created {@code String} object so that it represents 143 * an empty character sequence. Note that use of this constructor is 144 * unnecessary since Strings are immutable. 145 */ 146 public String() { 147 this.value = "".value; 148 } 149 150 /** 151 * Initializes a newly created {@code String} object so that it represents 152 * the same sequence of characters as the argument; in other words, the 153 * newly created string is a copy of the argument string. Unless an 154 * explicit copy of {@code original} is needed, use of this constructor is 155 * unnecessary since Strings are immutable. 156 * 157 * @param original 158 * A {@code String} 159 */ 160 @HotSpotIntrinsicCandidate 161 public String(String original) { 162 this.value = original.value; 163 this.hash = original.hash; 164 } 165 166 /** 167 * Allocates a new {@code String} so that it represents the sequence of 168 * characters currently contained in the character array argument. The 169 * contents of the character array are copied; subsequent modification of 170 * the character array does not affect the newly created string. 171 * 172 * @param value 173 * The initial value of the string 174 */ 175 public String(char value[]) { 176 this.value = Arrays.copyOf(value, value.length); 177 } 178 179 /** 180 * Allocates a new {@code String} that contains characters from a subarray 181 * of the character array argument. The {@code offset} argument is the 182 * index of the first character of the subarray and the {@code count} 183 * argument specifies the length of the subarray. The contents of the 184 * subarray are copied; subsequent modification of the character array does 185 * not affect the newly created string. 186 * 187 * @param value 188 * Array that is the source of characters 189 * 190 * @param offset 191 * The initial offset 192 * 193 * @param count 194 * The length 195 * 196 * @throws IndexOutOfBoundsException 197 * If {@code offset} is negative, {@code count} is negative, or 198 * {@code offset} is greater than {@code value.length - count} 199 */ 200 public String(char value[], int offset, int count) { 201 if (offset < 0) { 202 throw new StringIndexOutOfBoundsException(offset); 203 } 204 if (count <= 0) { 205 if (count < 0) { 206 throw new StringIndexOutOfBoundsException(count); 207 } 208 if (offset <= value.length) { 209 this.value = "".value; 210 return; 211 } 212 } 213 // Note: offset or count might be near -1>>>1. 214 if (offset > value.length - count) { 215 throw new StringIndexOutOfBoundsException(offset + count); 216 } 217 this.value = Arrays.copyOfRange(value, offset, offset + count); 218 } 219 220 /** 221 * Allocates a new {@code String} that contains characters from a subarray 222 * of the <a href="Character.html#unicode">Unicode code point</a> array 223 * argument. The {@code offset} argument is the index of the first code 224 * point of the subarray and the {@code count} argument specifies the 225 * length of the subarray. The contents of the subarray are converted to 226 * {@code char}s; subsequent modification of the {@code int} array does not 227 * affect the newly created string. 228 * 229 * @param codePoints 230 * Array that is the source of Unicode code points 231 * 232 * @param offset 233 * The initial offset 234 * 235 * @param count 236 * The length 237 * 238 * @throws IllegalArgumentException 239 * If any invalid Unicode code point is found in {@code 240 * codePoints} 241 * 242 * @throws IndexOutOfBoundsException 243 * If {@code offset} is negative, {@code count} is negative, or 244 * {@code offset} is greater than {@code codePoints.length - count} 245 * 246 * @since 1.5 247 */ 248 public String(int[] codePoints, int offset, int count) { 249 if (offset < 0) { 250 throw new StringIndexOutOfBoundsException(offset); 251 } 252 if (count <= 0) { 253 if (count < 0) { 254 throw new StringIndexOutOfBoundsException(count); 255 } 256 if (offset <= codePoints.length) { 257 this.value = "".value; 258 return; 259 } 260 } 261 // Note: offset or count might be near -1>>>1. 262 if (offset > codePoints.length - count) { 263 throw new StringIndexOutOfBoundsException(offset + count); 264 } 265 266 final int end = offset + count; 267 268 // Pass 1: Compute precise size of char[] 269 int n = count; 270 for (int i = offset; i < end; i++) { 271 int c = codePoints[i]; 272 if (Character.isBmpCodePoint(c)) 273 continue; 274 else if (Character.isValidCodePoint(c)) 275 n++; 276 else throw new IllegalArgumentException(Integer.toString(c)); 277 } 278 279 // Pass 2: Allocate and fill in char[] 280 final char[] v = new char[n]; 281 282 for (int i = offset, j = 0; i < end; i++, j++) { 283 int c = codePoints[i]; 284 if (Character.isBmpCodePoint(c)) 285 v[j] = (char)c; 286 else 287 Character.toSurrogates(c, v, j++); 288 } 289 290 this.value = v; 291 } 292 293 /** 294 * Allocates a new {@code String} constructed from a subarray of an array 295 * of 8-bit integer values. 296 * 297 * <p> The {@code offset} argument is the index of the first byte of the 298 * subarray, and the {@code count} argument specifies the length of the 299 * subarray. 300 * 301 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 302 * specified in the method above. 303 * 304 * @deprecated This method does not properly convert bytes into characters. 305 * As of JDK 1.1, the preferred way to do this is via the 306 * {@code String} constructors that take a {@link 307 * java.nio.charset.Charset}, charset name, or that use the platform's 308 * default charset. 309 * 310 * @param ascii 311 * The bytes to be converted to characters 312 * 313 * @param hibyte 314 * The top 8 bits of each 16-bit Unicode code unit 315 * 316 * @param offset 317 * The initial offset 318 * @param count 319 * The length 320 * 321 * @throws IndexOutOfBoundsException 322 * If {@code offset} is negative, {@code count} is negative, or 323 * {@code offset} is greater than {@code ascii.length - count} 324 * 325 * @see #String(byte[], int) 326 * @see #String(byte[], int, int, java.lang.String) 327 * @see #String(byte[], int, int, java.nio.charset.Charset) 328 * @see #String(byte[], int, int) 329 * @see #String(byte[], java.lang.String) 330 * @see #String(byte[], java.nio.charset.Charset) 331 * @see #String(byte[]) 332 */ 333 @Deprecated 334 public String(byte ascii[], int hibyte, int offset, int count) { 335 checkBounds(ascii, offset, count); 336 char[] value = new char[count]; 337 338 if (hibyte == 0) { 339 for (int i = count; i-- > 0;) { 340 value[i] = (char)(ascii[i + offset] & 0xff); 341 } 342 } else { 343 hibyte <<= 8; 344 for (int i = count; i-- > 0;) { 345 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff)); 346 } 347 } 348 this.value = value; 349 } 350 351 /** 352 * Allocates a new {@code String} containing characters constructed from 353 * an array of 8-bit integer values. Each character <i>c</i>in the 354 * resulting string is constructed from the corresponding component 355 * <i>b</i> in the byte array such that: 356 * 357 * <blockquote><pre> 358 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 359 * | (<b><i>b</i></b> & 0xff)) 360 * </pre></blockquote> 361 * 362 * @deprecated This method does not properly convert bytes into 363 * characters. As of JDK 1.1, the preferred way to do this is via the 364 * {@code String} constructors that take a {@link 365 * java.nio.charset.Charset}, charset name, or that use the platform's 366 * default charset. 367 * 368 * @param ascii 369 * The bytes to be converted to characters 370 * 371 * @param hibyte 372 * The top 8 bits of each 16-bit Unicode code unit 373 * 374 * @see #String(byte[], int, int, java.lang.String) 375 * @see #String(byte[], int, int, java.nio.charset.Charset) 376 * @see #String(byte[], int, int) 377 * @see #String(byte[], java.lang.String) 378 * @see #String(byte[], java.nio.charset.Charset) 379 * @see #String(byte[]) 380 */ 381 @Deprecated 382 public String(byte ascii[], int hibyte) { 383 this(ascii, hibyte, 0, ascii.length); 384 } 385 386 /* Common private utility method used to bounds check the byte array 387 * and requested offset & length values used by the String(byte[],..) 388 * constructors. 389 */ 390 private static void checkBounds(byte[] bytes, int offset, int length) { 391 if (length < 0) 392 throw new StringIndexOutOfBoundsException(length); 393 if (offset < 0) 394 throw new StringIndexOutOfBoundsException(offset); 395 if (offset > bytes.length - length) 396 throw new StringIndexOutOfBoundsException(offset + length); 397 } 398 399 /** 400 * Constructs a new {@code String} by decoding the specified subarray of 401 * bytes using the specified charset. The length of the new {@code String} 402 * is a function of the charset, and hence may not be equal to the length 403 * of the subarray. 404 * 405 * <p> The behavior of this constructor when the given bytes are not valid 406 * in the given charset is unspecified. The {@link 407 * java.nio.charset.CharsetDecoder} class should be used when more control 408 * over the decoding process is required. 409 * 410 * @param bytes 411 * The bytes to be decoded into characters 412 * 413 * @param offset 414 * The index of the first byte to decode 415 * 416 * @param length 417 * The number of bytes to decode 418 419 * @param charsetName 420 * The name of a supported {@linkplain java.nio.charset.Charset 421 * charset} 422 * 423 * @throws UnsupportedEncodingException 424 * If the named charset is not supported 425 * 426 * @throws IndexOutOfBoundsException 427 * If {@code offset} is negative, {@code length} is negative, or 428 * {@code offset} is greater than {@code bytes.length - length} 429 * 430 * @since 1.1 431 */ 432 public String(byte bytes[], int offset, int length, String charsetName) 433 throws UnsupportedEncodingException { 434 if (charsetName == null) 435 throw new NullPointerException("charsetName"); 436 checkBounds(bytes, offset, length); 437 this.value = StringCoding.decode(charsetName, bytes, offset, length); 438 } 439 440 /** 441 * Constructs a new {@code String} by decoding the specified subarray of 442 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 443 * The length of the new {@code String} is a function of the charset, and 444 * hence may not be equal to the length of the subarray. 445 * 446 * <p> This method always replaces malformed-input and unmappable-character 447 * sequences with this charset's default replacement string. The {@link 448 * java.nio.charset.CharsetDecoder} class should be used when more control 449 * over the decoding process is required. 450 * 451 * @param bytes 452 * The bytes to be decoded into characters 453 * 454 * @param offset 455 * The index of the first byte to decode 456 * 457 * @param length 458 * The number of bytes to decode 459 * 460 * @param charset 461 * The {@linkplain java.nio.charset.Charset charset} to be used to 462 * decode the {@code bytes} 463 * 464 * @throws IndexOutOfBoundsException 465 * If {@code offset} is negative, {@code length} is negative, or 466 * {@code offset} is greater than {@code bytes.length - length} 467 * 468 * @since 1.6 469 */ 470 public String(byte bytes[], int offset, int length, Charset charset) { 471 if (charset == null) 472 throw new NullPointerException("charset"); 473 checkBounds(bytes, offset, length); 474 this.value = StringCoding.decode(charset, bytes, offset, length); 475 } 476 477 /** 478 * Constructs a new {@code String} by decoding the specified array of bytes 479 * using the specified {@linkplain java.nio.charset.Charset charset}. The 480 * length of the new {@code String} is a function of the charset, and hence 481 * may not be equal to the length of the byte array. 482 * 483 * <p> The behavior of this constructor when the given bytes are not valid 484 * in the given charset is unspecified. The {@link 485 * java.nio.charset.CharsetDecoder} class should be used when more control 486 * over the decoding process is required. 487 * 488 * @param bytes 489 * The bytes to be decoded into characters 490 * 491 * @param charsetName 492 * The name of a supported {@linkplain java.nio.charset.Charset 493 * charset} 494 * 495 * @throws UnsupportedEncodingException 496 * If the named charset is not supported 497 * 498 * @since 1.1 499 */ 500 public String(byte bytes[], String charsetName) 501 throws UnsupportedEncodingException { 502 this(bytes, 0, bytes.length, charsetName); 503 } 504 505 /** 506 * Constructs a new {@code String} by decoding the specified array of 507 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 508 * The length of the new {@code String} is a function of the charset, and 509 * hence may not be equal to the length of the byte array. 510 * 511 * <p> This method always replaces malformed-input and unmappable-character 512 * sequences with this charset's default replacement string. The {@link 513 * java.nio.charset.CharsetDecoder} class should be used when more control 514 * over the decoding process is required. 515 * 516 * @param bytes 517 * The bytes to be decoded into characters 518 * 519 * @param charset 520 * The {@linkplain java.nio.charset.Charset charset} to be used to 521 * decode the {@code bytes} 522 * 523 * @since 1.6 524 */ 525 public String(byte bytes[], Charset charset) { 526 this(bytes, 0, bytes.length, charset); 527 } 528 529 /** 530 * Constructs a new {@code String} by decoding the specified subarray of 531 * bytes using the platform's default charset. The length of the new 532 * {@code String} is a function of the charset, and hence may not be equal 533 * to the length of the subarray. 534 * 535 * <p> The behavior of this constructor when the given bytes are not valid 536 * in the default charset is unspecified. The {@link 537 * java.nio.charset.CharsetDecoder} class should be used when more control 538 * over the decoding process is required. 539 * 540 * @param bytes 541 * The bytes to be decoded into characters 542 * 543 * @param offset 544 * The index of the first byte to decode 545 * 546 * @param length 547 * The number of bytes to decode 548 * 549 * @throws IndexOutOfBoundsException 550 * If {@code offset} is negative, {@code length} is negative, or 551 * {@code offset} is greater than {@code bytes.length - length} 552 * 553 * @since 1.1 554 */ 555 public String(byte bytes[], int offset, int length) { 556 checkBounds(bytes, offset, length); 557 this.value = StringCoding.decode(bytes, offset, length); 558 } 559 560 /** 561 * Constructs a new {@code String} by decoding the specified array of bytes 562 * using the platform's default charset. The length of the new {@code 563 * String} is a function of the charset, and hence may not be equal to the 564 * length of the byte array. 565 * 566 * <p> The behavior of this constructor when the given bytes are not valid 567 * in the default charset is unspecified. The {@link 568 * java.nio.charset.CharsetDecoder} class should be used when more control 569 * over the decoding process is required. 570 * 571 * @param bytes 572 * The bytes to be decoded into characters 573 * 574 * @since 1.1 575 */ 576 public String(byte[] bytes) { 577 this(bytes, 0, bytes.length); 578 } 579 580 /** 581 * Allocates a new string that contains the sequence of characters 582 * currently contained in the string buffer argument. The contents of the 583 * string buffer are copied; subsequent modification of the string buffer 584 * does not affect the newly created string. 585 * 586 * @param buffer 587 * A {@code StringBuffer} 588 */ 589 public String(StringBuffer buffer) { 590 synchronized(buffer) { 591 this.value = Arrays.copyOf(buffer.getValue(), buffer.length()); 592 } 593 } 594 595 /** 596 * Allocates a new string that contains the sequence of characters 597 * currently contained in the string builder argument. The contents of the 598 * string builder are copied; subsequent modification of the string builder 599 * does not affect the newly created string. 600 * 601 * <p> This constructor is provided to ease migration to {@code 602 * StringBuilder}. Obtaining a string from a string builder via the {@code 603 * toString} method is likely to run faster and is generally preferred. 604 * 605 * @param builder 606 * A {@code StringBuilder} 607 * 608 * @since 1.5 609 */ 610 public String(StringBuilder builder) { 611 this.value = Arrays.copyOf(builder.getValue(), builder.length()); 612 } 613 614 /* 615 * Package private constructor which shares value array for speed. 616 * this constructor is always expected to be called with share==true. 617 * a separate constructor is needed because we already have a public 618 * String(char[]) constructor that makes a copy of the given char[]. 619 */ 620 String(char[] value, boolean share) { 621 // assert share : "unshared not supported"; 622 this.value = value; 623 } 624 625 /** 626 * Returns the length of this string. 627 * The length is equal to the number of <a href="Character.html#unicode">Unicode 628 * code units</a> in the string. 629 * 630 * @return the length of the sequence of characters represented by this 631 * object. 632 */ 633 public int length() { 634 return value.length; 635 } 636 637 /** 638 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 639 * 640 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 641 * {@code false} 642 * 643 * @since 1.6 644 */ 645 public boolean isEmpty() { 646 return value.length == 0; 647 } 648 649 /** 650 * Returns the {@code char} value at the 651 * specified index. An index ranges from {@code 0} to 652 * {@code length() - 1}. The first {@code char} value of the sequence 653 * is at index {@code 0}, the next at index {@code 1}, 654 * and so on, as for array indexing. 655 * 656 * <p>If the {@code char} value specified by the index is a 657 * <a href="Character.html#unicode">surrogate</a>, the surrogate 658 * value is returned. 659 * 660 * @param index the index of the {@code char} value. 661 * @return the {@code char} value at the specified index of this string. 662 * The first {@code char} value is at index {@code 0}. 663 * @exception IndexOutOfBoundsException if the {@code index} 664 * argument is negative or not less than the length of this 665 * string. 666 */ 667 public char charAt(int index) { 668 if ((index < 0) || (index >= value.length)) { 669 throw new StringIndexOutOfBoundsException(index); 670 } 671 return value[index]; 672 } 673 674 /** 675 * Returns the character (Unicode code point) at the specified 676 * index. The index refers to {@code char} values 677 * (Unicode code units) and ranges from {@code 0} to 678 * {@link #length()}{@code - 1}. 679 * 680 * <p> If the {@code char} value specified at the given index 681 * is in the high-surrogate range, the following index is less 682 * than the length of this {@code String}, and the 683 * {@code char} value at the following index is in the 684 * low-surrogate range, then the supplementary code point 685 * corresponding to this surrogate pair is returned. Otherwise, 686 * the {@code char} value at the given index is returned. 687 * 688 * @param index the index to the {@code char} values 689 * @return the code point value of the character at the 690 * {@code index} 691 * @exception IndexOutOfBoundsException if the {@code index} 692 * argument is negative or not less than the length of this 693 * string. 694 * @since 1.5 695 */ 696 public int codePointAt(int index) { 697 if ((index < 0) || (index >= value.length)) { 698 throw new StringIndexOutOfBoundsException(index); 699 } 700 return Character.codePointAtImpl(value, index, value.length); 701 } 702 703 /** 704 * Returns the character (Unicode code point) before the specified 705 * index. The index refers to {@code char} values 706 * (Unicode code units) and ranges from {@code 1} to {@link 707 * CharSequence#length() length}. 708 * 709 * <p> If the {@code char} value at {@code (index - 1)} 710 * is in the low-surrogate range, {@code (index - 2)} is not 711 * negative, and the {@code char} value at {@code (index - 712 * 2)} is in the high-surrogate range, then the 713 * supplementary code point value of the surrogate pair is 714 * returned. If the {@code char} value at {@code index - 715 * 1} is an unpaired low-surrogate or a high-surrogate, the 716 * surrogate value is returned. 717 * 718 * @param index the index following the code point that should be returned 719 * @return the Unicode code point value before the given index. 720 * @exception IndexOutOfBoundsException if the {@code index} 721 * argument is less than 1 or greater than the length 722 * of this string. 723 * @since 1.5 724 */ 725 public int codePointBefore(int index) { 726 int i = index - 1; 727 if ((i < 0) || (i >= value.length)) { 728 throw new StringIndexOutOfBoundsException(index); 729 } 730 return Character.codePointBeforeImpl(value, index, 0); 731 } 732 733 /** 734 * Returns the number of Unicode code points in the specified text 735 * range of this {@code String}. The text range begins at the 736 * specified {@code beginIndex} and extends to the 737 * {@code char} at index {@code endIndex - 1}. Thus the 738 * length (in {@code char}s) of the text range is 739 * {@code endIndex-beginIndex}. Unpaired surrogates within 740 * the text range count as one code point each. 741 * 742 * @param beginIndex the index to the first {@code char} of 743 * the text range. 744 * @param endIndex the index after the last {@code char} of 745 * the text range. 746 * @return the number of Unicode code points in the specified text 747 * range 748 * @exception IndexOutOfBoundsException if the 749 * {@code beginIndex} is negative, or {@code endIndex} 750 * is larger than the length of this {@code String}, or 751 * {@code beginIndex} is larger than {@code endIndex}. 752 * @since 1.5 753 */ 754 public int codePointCount(int beginIndex, int endIndex) { 755 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) { 756 throw new IndexOutOfBoundsException(); 757 } 758 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex); 759 } 760 761 /** 762 * Returns the index within this {@code String} that is 763 * offset from the given {@code index} by 764 * {@code codePointOffset} code points. Unpaired surrogates 765 * within the text range given by {@code index} and 766 * {@code codePointOffset} count as one code point each. 767 * 768 * @param index the index to be offset 769 * @param codePointOffset the offset in code points 770 * @return the index within this {@code String} 771 * @exception IndexOutOfBoundsException if {@code index} 772 * is negative or larger then the length of this 773 * {@code String}, or if {@code codePointOffset} is positive 774 * and the substring starting with {@code index} has fewer 775 * than {@code codePointOffset} code points, 776 * or if {@code codePointOffset} is negative and the substring 777 * before {@code index} has fewer than the absolute value 778 * of {@code codePointOffset} code points. 779 * @since 1.5 780 */ 781 public int offsetByCodePoints(int index, int codePointOffset) { 782 if (index < 0 || index > value.length) { 783 throw new IndexOutOfBoundsException(); 784 } 785 return Character.offsetByCodePointsImpl(value, 0, value.length, 786 index, codePointOffset); 787 } 788 789 /** 790 * Copy characters from this string into dst starting at dstBegin. 791 * This method doesn't perform any range checking. 792 */ 793 void getChars(char dst[], int dstBegin) { 794 System.arraycopy(value, 0, dst, dstBegin, value.length); 795 } 796 797 /** 798 * Copies characters from this string into the destination character 799 * array. 800 * <p> 801 * The first character to be copied is at index {@code srcBegin}; 802 * the last character to be copied is at index {@code srcEnd-1} 803 * (thus the total number of characters to be copied is 804 * {@code srcEnd-srcBegin}). The characters are copied into the 805 * subarray of {@code dst} starting at index {@code dstBegin} 806 * and ending at index: 807 * <blockquote><pre> 808 * dstBegin + (srcEnd-srcBegin) - 1 809 * </pre></blockquote> 810 * 811 * @param srcBegin index of the first character in the string 812 * to copy. 813 * @param srcEnd index after the last character in the string 814 * to copy. 815 * @param dst the destination array. 816 * @param dstBegin the start offset in the destination array. 817 * @exception IndexOutOfBoundsException If any of the following 818 * is true: 819 * <ul><li>{@code srcBegin} is negative. 820 * <li>{@code srcBegin} is greater than {@code srcEnd} 821 * <li>{@code srcEnd} is greater than the length of this 822 * string 823 * <li>{@code dstBegin} is negative 824 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 825 * {@code dst.length}</ul> 826 */ 827 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 828 if (srcBegin < 0) { 829 throw new StringIndexOutOfBoundsException(srcBegin); 830 } 831 if (srcEnd > value.length) { 832 throw new StringIndexOutOfBoundsException(srcEnd); 833 } 834 if (srcBegin > srcEnd) { 835 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 836 } 837 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin); 838 } 839 840 /** 841 * Copies characters from this string into the destination byte array. Each 842 * byte receives the 8 low-order bits of the corresponding character. The 843 * eight high-order bits of each character are not copied and do not 844 * participate in the transfer in any way. 845 * 846 * <p> The first character to be copied is at index {@code srcBegin}; the 847 * last character to be copied is at index {@code srcEnd-1}. The total 848 * number of characters to be copied is {@code srcEnd-srcBegin}. The 849 * characters, converted to bytes, are copied into the subarray of {@code 850 * dst} starting at index {@code dstBegin} and ending at index: 851 * 852 * <blockquote><pre> 853 * dstBegin + (srcEnd-srcBegin) - 1 854 * </pre></blockquote> 855 * 856 * @deprecated This method does not properly convert characters into 857 * bytes. As of JDK 1.1, the preferred way to do this is via the 858 * {@link #getBytes()} method, which uses the platform's default charset. 859 * 860 * @param srcBegin 861 * Index of the first character in the string to copy 862 * 863 * @param srcEnd 864 * Index after the last character in the string to copy 865 * 866 * @param dst 867 * The destination array 868 * 869 * @param dstBegin 870 * The start offset in the destination array 871 * 872 * @throws IndexOutOfBoundsException 873 * If any of the following is true: 874 * <ul> 875 * <li> {@code srcBegin} is negative 876 * <li> {@code srcBegin} is greater than {@code srcEnd} 877 * <li> {@code srcEnd} is greater than the length of this String 878 * <li> {@code dstBegin} is negative 879 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 880 * dst.length} 881 * </ul> 882 */ 883 @Deprecated 884 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 885 if (srcBegin < 0) { 886 throw new StringIndexOutOfBoundsException(srcBegin); 887 } 888 if (srcEnd > value.length) { 889 throw new StringIndexOutOfBoundsException(srcEnd); 890 } 891 if (srcBegin > srcEnd) { 892 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 893 } 894 Objects.requireNonNull(dst); 895 896 int j = dstBegin; 897 int n = srcEnd; 898 int i = srcBegin; 899 char[] val = value; /* avoid getfield opcode */ 900 901 while (i < n) { 902 dst[j++] = (byte)val[i++]; 903 } 904 } 905 906 /** 907 * Encodes this {@code String} into a sequence of bytes using the named 908 * charset, storing the result into a new byte array. 909 * 910 * <p> The behavior of this method when this string cannot be encoded in 911 * the given charset is unspecified. The {@link 912 * java.nio.charset.CharsetEncoder} class should be used when more control 913 * over the encoding process is required. 914 * 915 * @param charsetName 916 * The name of a supported {@linkplain java.nio.charset.Charset 917 * charset} 918 * 919 * @return The resultant byte array 920 * 921 * @throws UnsupportedEncodingException 922 * If the named charset is not supported 923 * 924 * @since 1.1 925 */ 926 public byte[] getBytes(String charsetName) 927 throws UnsupportedEncodingException { 928 if (charsetName == null) throw new NullPointerException(); 929 return StringCoding.encode(charsetName, value, 0, value.length); 930 } 931 932 /** 933 * Encodes this {@code String} into a sequence of bytes using the given 934 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 935 * new byte array. 936 * 937 * <p> This method always replaces malformed-input and unmappable-character 938 * sequences with this charset's default replacement byte array. The 939 * {@link java.nio.charset.CharsetEncoder} class should be used when more 940 * control over the encoding process is required. 941 * 942 * @param charset 943 * The {@linkplain java.nio.charset.Charset} to be used to encode 944 * the {@code String} 945 * 946 * @return The resultant byte array 947 * 948 * @since 1.6 949 */ 950 public byte[] getBytes(Charset charset) { 951 if (charset == null) throw new NullPointerException(); 952 return StringCoding.encode(charset, value, 0, value.length); 953 } 954 955 /** 956 * Encodes this {@code String} into a sequence of bytes using the 957 * platform's default charset, storing the result into a new byte array. 958 * 959 * <p> The behavior of this method when this string cannot be encoded in 960 * the default charset is unspecified. The {@link 961 * java.nio.charset.CharsetEncoder} class should be used when more control 962 * over the encoding process is required. 963 * 964 * @return The resultant byte array 965 * 966 * @since 1.1 967 */ 968 public byte[] getBytes() { 969 return StringCoding.encode(value, 0, value.length); 970 } 971 972 /** 973 * Compares this string to the specified object. The result is {@code 974 * true} if and only if the argument is not {@code null} and is a {@code 975 * String} object that represents the same sequence of characters as this 976 * object. 977 * 978 * <p>For finer-grained String comparison, refer to 979 * {@link java.text.Collator}. 980 * 981 * @param anObject 982 * The object to compare this {@code String} against 983 * 984 * @return {@code true} if the given object represents a {@code String} 985 * equivalent to this string, {@code false} otherwise 986 * 987 * @see #compareTo(String) 988 * @see #equalsIgnoreCase(String) 989 */ 990 @HotSpotIntrinsicCandidate 991 public boolean equals(Object anObject) { 992 if (this == anObject) { 993 return true; 994 } 995 if (anObject instanceof String) { 996 char[] v1 = value; 997 char[] v2 = ((String)anObject).value; 998 int n = v1.length; 999 if (n == v2.length) { 1000 int i = 0; 1001 while (n-- != 0) { 1002 if (v1[i] != v2[i]) 1003 return false; 1004 i++; 1005 } 1006 return true; 1007 } 1008 } 1009 return false; 1010 } 1011 1012 /** 1013 * Compares this string to the specified {@code StringBuffer}. The result 1014 * is {@code true} if and only if this {@code String} represents the same 1015 * sequence of characters as the specified {@code StringBuffer}. This method 1016 * synchronizes on the {@code StringBuffer}. 1017 * 1018 * <p>For finer-grained String comparison, refer to 1019 * {@link java.text.Collator}. 1020 * 1021 * @param sb 1022 * The {@code StringBuffer} to compare this {@code String} against 1023 * 1024 * @return {@code true} if this {@code String} represents the same 1025 * sequence of characters as the specified {@code StringBuffer}, 1026 * {@code false} otherwise 1027 * 1028 * @since 1.4 1029 */ 1030 public boolean contentEquals(StringBuffer sb) { 1031 return contentEquals((CharSequence)sb); 1032 } 1033 1034 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1035 char[] v1 = value; 1036 char[] v2 = sb.getValue(); 1037 int n = v1.length; 1038 if (n != sb.length()) { 1039 return false; 1040 } 1041 for (int i = 0; i < n; i++) { 1042 if (v1[i] != v2[i]) { 1043 return false; 1044 } 1045 } 1046 return true; 1047 } 1048 1049 /** 1050 * Compares this string to the specified {@code CharSequence}. The 1051 * result is {@code true} if and only if this {@code String} represents the 1052 * same sequence of char values as the specified sequence. Note that if the 1053 * {@code CharSequence} is a {@code StringBuffer} then the method 1054 * synchronizes on it. 1055 * 1056 * <p>For finer-grained String comparison, refer to 1057 * {@link java.text.Collator}. 1058 * 1059 * @param cs 1060 * The sequence to compare this {@code String} against 1061 * 1062 * @return {@code true} if this {@code String} represents the same 1063 * sequence of char values as the specified sequence, {@code 1064 * false} otherwise 1065 * 1066 * @since 1.5 1067 */ 1068 public boolean contentEquals(CharSequence cs) { 1069 // Argument is a StringBuffer, StringBuilder 1070 if (cs instanceof AbstractStringBuilder) { 1071 if (cs instanceof StringBuffer) { 1072 synchronized(cs) { 1073 return nonSyncContentEquals((AbstractStringBuilder)cs); 1074 } 1075 } else { 1076 return nonSyncContentEquals((AbstractStringBuilder)cs); 1077 } 1078 } 1079 // Argument is a String 1080 if (cs instanceof String) { 1081 return equals(cs); 1082 } 1083 // Argument is a generic CharSequence 1084 char[] v1 = value; 1085 int n = v1.length; 1086 if (n != cs.length()) { 1087 return false; 1088 } 1089 for (int i = 0; i < n; i++) { 1090 if (v1[i] != cs.charAt(i)) { 1091 return false; 1092 } 1093 } 1094 return true; 1095 } 1096 1097 /** 1098 * Compares this {@code String} to another {@code String}, ignoring case 1099 * considerations. Two strings are considered equal ignoring case if they 1100 * are of the same length and corresponding characters in the two strings 1101 * are equal ignoring case. 1102 * 1103 * <p> Two characters {@code c1} and {@code c2} are considered the same 1104 * ignoring case if at least one of the following is true: 1105 * <ul> 1106 * <li> The two characters are the same (as compared by the 1107 * {@code ==} operator) 1108 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))} 1109 * on each character produces the same result 1110 * </ul> 1111 * 1112 * <p>Note that this method does <em>not</em> take locale into account, and 1113 * will result in unsatisfactory results for certain locales. The 1114 * {@link java.text.Collator} class provides locale-sensitive comparison. 1115 * 1116 * @param anotherString 1117 * The {@code String} to compare this {@code String} against 1118 * 1119 * @return {@code true} if the argument is not {@code null} and it 1120 * represents an equivalent {@code String} ignoring case; {@code 1121 * false} otherwise 1122 * 1123 * @see #equals(Object) 1124 */ 1125 public boolean equalsIgnoreCase(String anotherString) { 1126 return (this == anotherString) ? true 1127 : (anotherString != null) 1128 && (anotherString.value.length == value.length) 1129 && regionMatches(true, 0, anotherString, 0, value.length); 1130 } 1131 1132 /** 1133 * Compares two strings lexicographically. 1134 * The comparison is based on the Unicode value of each character in 1135 * the strings. The character sequence represented by this 1136 * {@code String} object is compared lexicographically to the 1137 * character sequence represented by the argument string. The result is 1138 * a negative integer if this {@code String} object 1139 * lexicographically precedes the argument string. The result is a 1140 * positive integer if this {@code String} object lexicographically 1141 * follows the argument string. The result is zero if the strings 1142 * are equal; {@code compareTo} returns {@code 0} exactly when 1143 * the {@link #equals(Object)} method would return {@code true}. 1144 * <p> 1145 * This is the definition of lexicographic ordering. If two strings are 1146 * different, then either they have different characters at some index 1147 * that is a valid index for both strings, or their lengths are different, 1148 * or both. If they have different characters at one or more index 1149 * positions, let <i>k</i> be the smallest such index; then the string 1150 * whose character at position <i>k</i> has the smaller value, as 1151 * determined by using the {@code <} operator, lexicographically precedes the 1152 * other string. In this case, {@code compareTo} returns the 1153 * difference of the two character values at position {@code k} in 1154 * the two string -- that is, the value: 1155 * <blockquote><pre> 1156 * this.charAt(k)-anotherString.charAt(k) 1157 * </pre></blockquote> 1158 * If there is no index position at which they differ, then the shorter 1159 * string lexicographically precedes the longer string. In this case, 1160 * {@code compareTo} returns the difference of the lengths of the 1161 * strings -- that is, the value: 1162 * <blockquote><pre> 1163 * this.length()-anotherString.length() 1164 * </pre></blockquote> 1165 * 1166 * <p>For finer-grained String comparison, refer to 1167 * {@link java.text.Collator}. 1168 * 1169 * @param anotherString the {@code String} to be compared. 1170 * @return the value {@code 0} if the argument string is equal to 1171 * this string; a value less than {@code 0} if this string 1172 * is lexicographically less than the string argument; and a 1173 * value greater than {@code 0} if this string is 1174 * lexicographically greater than the string argument. 1175 */ 1176 @HotSpotIntrinsicCandidate 1177 public int compareTo(String anotherString) { 1178 char[] v1 = value; 1179 char[] v2 = anotherString.value; 1180 int len1 = v1.length; 1181 int len2 = v2.length; 1182 int lim = Math.min(len1, len2); 1183 1184 for (int k = 0; k < lim; k++) { 1185 char c1 = v1[k]; 1186 char c2 = v2[k]; 1187 if (c1 != c2) { 1188 return c1 - c2; 1189 } 1190 } 1191 return len1 - len2; 1192 } 1193 1194 /** 1195 * A Comparator that orders {@code String} objects as by 1196 * {@code compareToIgnoreCase}. This comparator is serializable. 1197 * <p> 1198 * Note that this Comparator does <em>not</em> take locale into account, 1199 * and will result in an unsatisfactory ordering for certain locales. 1200 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1201 * 1202 * @see java.text.Collator 1203 * @since 1.2 1204 */ 1205 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1206 = new CaseInsensitiveComparator(); 1207 private static class CaseInsensitiveComparator 1208 implements Comparator<String>, java.io.Serializable { 1209 // use serialVersionUID from JDK 1.2.2 for interoperability 1210 private static final long serialVersionUID = 8575799808933029326L; 1211 1212 public int compare(String s1, String s2) { 1213 int n1 = s1.length(); 1214 int n2 = s2.length(); 1215 int min = Math.min(n1, n2); 1216 for (int i = 0; i < min; i++) { 1217 char c1 = s1.charAt(i); 1218 char c2 = s2.charAt(i); 1219 if (c1 != c2) { 1220 c1 = Character.toUpperCase(c1); 1221 c2 = Character.toUpperCase(c2); 1222 if (c1 != c2) { 1223 c1 = Character.toLowerCase(c1); 1224 c2 = Character.toLowerCase(c2); 1225 if (c1 != c2) { 1226 // No overflow because of numeric promotion 1227 return c1 - c2; 1228 } 1229 } 1230 } 1231 } 1232 return n1 - n2; 1233 } 1234 1235 /** Replaces the de-serialized object. */ 1236 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1237 } 1238 1239 /** 1240 * Compares two strings lexicographically, ignoring case 1241 * differences. This method returns an integer whose sign is that of 1242 * calling {@code compareTo} with normalized versions of the strings 1243 * where case differences have been eliminated by calling 1244 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1245 * each character. 1246 * <p> 1247 * Note that this method does <em>not</em> take locale into account, 1248 * and will result in an unsatisfactory ordering for certain locales. 1249 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1250 * 1251 * @param str the {@code String} to be compared. 1252 * @return a negative integer, zero, or a positive integer as the 1253 * specified String is greater than, equal to, or less 1254 * than this String, ignoring case considerations. 1255 * @see java.text.Collator 1256 * @since 1.2 1257 */ 1258 public int compareToIgnoreCase(String str) { 1259 return CASE_INSENSITIVE_ORDER.compare(this, str); 1260 } 1261 1262 /** 1263 * Tests if two string regions are equal. 1264 * <p> 1265 * A substring of this {@code String} object is compared to a substring 1266 * of the argument other. The result is true if these substrings 1267 * represent identical character sequences. The substring of this 1268 * {@code String} object to be compared begins at index {@code toffset} 1269 * and has length {@code len}. The substring of other to be compared 1270 * begins at index {@code ooffset} and has length {@code len}. The 1271 * result is {@code false} if and only if at least one of the following 1272 * is true: 1273 * <ul><li>{@code toffset} is negative. 1274 * <li>{@code ooffset} is negative. 1275 * <li>{@code toffset+len} is greater than the length of this 1276 * {@code String} object. 1277 * <li>{@code ooffset+len} is greater than the length of the other 1278 * argument. 1279 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1280 * such that: 1281 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1282 * <i>k</i>{@code )} 1283 * </ul> 1284 * 1285 * <p>Note that this method does <em>not</em> take locale into account. The 1286 * {@link java.text.Collator} class provides locale-sensitive comparison. 1287 * 1288 * @param toffset the starting offset of the subregion in this string. 1289 * @param other the string argument. 1290 * @param ooffset the starting offset of the subregion in the string 1291 * argument. 1292 * @param len the number of characters to compare. 1293 * @return {@code true} if the specified subregion of this string 1294 * exactly matches the specified subregion of the string argument; 1295 * {@code false} otherwise. 1296 */ 1297 public boolean regionMatches(int toffset, String other, int ooffset, 1298 int len) { 1299 char[] ta = value; 1300 int to = toffset; 1301 char[] pa = other.value; 1302 int po = ooffset; 1303 // Note: toffset, ooffset, or len might be near -1>>>1. 1304 if ((ooffset < 0) || (toffset < 0) 1305 || (toffset > (long)ta.length - len) 1306 || (ooffset > (long)pa.length - len)) { 1307 return false; 1308 } 1309 while (len-- > 0) { 1310 if (ta[to++] != pa[po++]) { 1311 return false; 1312 } 1313 } 1314 return true; 1315 } 1316 1317 /** 1318 * Tests if two string regions are equal. 1319 * <p> 1320 * A substring of this {@code String} object is compared to a substring 1321 * of the argument {@code other}. The result is {@code true} if these 1322 * substrings represent character sequences that are the same, ignoring 1323 * case if and only if {@code ignoreCase} is true. The substring of 1324 * this {@code String} object to be compared begins at index 1325 * {@code toffset} and has length {@code len}. The substring of 1326 * {@code other} to be compared begins at index {@code ooffset} and 1327 * has length {@code len}. The result is {@code false} if and only if 1328 * at least one of the following is true: 1329 * <ul><li>{@code toffset} is negative. 1330 * <li>{@code ooffset} is negative. 1331 * <li>{@code toffset+len} is greater than the length of this 1332 * {@code String} object. 1333 * <li>{@code ooffset+len} is greater than the length of the other 1334 * argument. 1335 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1336 * integer <i>k</i> less than {@code len} such that: 1337 * <blockquote><pre> 1338 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1339 * </pre></blockquote> 1340 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1341 * integer <i>k</i> less than {@code len} such that: 1342 * <blockquote><pre> 1343 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) != 1344 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k))) 1345 * </pre></blockquote> 1346 * </ul> 1347 * 1348 * <p>Note that this method does <em>not</em> take locale into account, 1349 * and will result in unsatisfactory results for certain locales when 1350 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class 1351 * provides locale-sensitive comparison. 1352 * 1353 * @param ignoreCase if {@code true}, ignore case when comparing 1354 * characters. 1355 * @param toffset the starting offset of the subregion in this 1356 * string. 1357 * @param other the string argument. 1358 * @param ooffset the starting offset of the subregion in the string 1359 * argument. 1360 * @param len the number of characters to compare. 1361 * @return {@code true} if the specified subregion of this string 1362 * matches the specified subregion of the string argument; 1363 * {@code false} otherwise. Whether the matching is exact 1364 * or case insensitive depends on the {@code ignoreCase} 1365 * argument. 1366 */ 1367 public boolean regionMatches(boolean ignoreCase, int toffset, 1368 String other, int ooffset, int len) { 1369 char[] ta = value; 1370 int to = toffset; 1371 char[] pa = other.value; 1372 int po = ooffset; 1373 // Note: toffset, ooffset, or len might be near -1>>>1. 1374 if ((ooffset < 0) || (toffset < 0) 1375 || (toffset > (long)ta.length - len) 1376 || (ooffset > (long)pa.length - len)) { 1377 return false; 1378 } 1379 while (len-- > 0) { 1380 char c1 = ta[to++]; 1381 char c2 = pa[po++]; 1382 if (c1 == c2) { 1383 continue; 1384 } 1385 if (ignoreCase) { 1386 // If characters don't match but case may be ignored, 1387 // try converting both characters to uppercase. 1388 // If the results match, then the comparison scan should 1389 // continue. 1390 char u1 = Character.toUpperCase(c1); 1391 char u2 = Character.toUpperCase(c2); 1392 if (u1 == u2) { 1393 continue; 1394 } 1395 // Unfortunately, conversion to uppercase does not work properly 1396 // for the Georgian alphabet, which has strange rules about case 1397 // conversion. So we need to make one last check before 1398 // exiting. 1399 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) { 1400 continue; 1401 } 1402 } 1403 return false; 1404 } 1405 return true; 1406 } 1407 1408 /** 1409 * Tests if the substring of this string beginning at the 1410 * specified index starts with the specified prefix. 1411 * 1412 * @param prefix the prefix. 1413 * @param toffset where to begin looking in this string. 1414 * @return {@code true} if the character sequence represented by the 1415 * argument is a prefix of the substring of this object starting 1416 * at index {@code toffset}; {@code false} otherwise. 1417 * The result is {@code false} if {@code toffset} is 1418 * negative or greater than the length of this 1419 * {@code String} object; otherwise the result is the same 1420 * as the result of the expression 1421 * <pre> 1422 * this.substring(toffset).startsWith(prefix) 1423 * </pre> 1424 */ 1425 public boolean startsWith(String prefix, int toffset) { 1426 char[] ta = value; 1427 int to = toffset; 1428 char[] pa = prefix.value; 1429 int po = 0; 1430 int pc = pa.length; 1431 // Note: toffset might be near -1>>>1. 1432 if ((toffset < 0) || (toffset > ta.length - pc)) { 1433 return false; 1434 } 1435 while (--pc >= 0) { 1436 if (ta[to++] != pa[po++]) { 1437 return false; 1438 } 1439 } 1440 return true; 1441 } 1442 1443 /** 1444 * Tests if this string starts with the specified prefix. 1445 * 1446 * @param prefix the prefix. 1447 * @return {@code true} if the character sequence represented by the 1448 * argument is a prefix of the character sequence represented by 1449 * this string; {@code false} otherwise. 1450 * Note also that {@code true} will be returned if the 1451 * argument is an empty string or is equal to this 1452 * {@code String} object as determined by the 1453 * {@link #equals(Object)} method. 1454 * @since 1.0 1455 */ 1456 public boolean startsWith(String prefix) { 1457 return startsWith(prefix, 0); 1458 } 1459 1460 /** 1461 * Tests if this string ends with the specified suffix. 1462 * 1463 * @param suffix the suffix. 1464 * @return {@code true} if the character sequence represented by the 1465 * argument is a suffix of the character sequence represented by 1466 * this object; {@code false} otherwise. Note that the 1467 * result will be {@code true} if the argument is the 1468 * empty string or is equal to this {@code String} object 1469 * as determined by the {@link #equals(Object)} method. 1470 */ 1471 public boolean endsWith(String suffix) { 1472 return startsWith(suffix, value.length - suffix.value.length); 1473 } 1474 1475 /** 1476 * Returns a hash code for this string. The hash code for a 1477 * {@code String} object is computed as 1478 * <blockquote><pre> 1479 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1480 * </pre></blockquote> 1481 * using {@code int} arithmetic, where {@code s[i]} is the 1482 * <i>i</i>th character of the string, {@code n} is the length of 1483 * the string, and {@code ^} indicates exponentiation. 1484 * (The hash value of the empty string is zero.) 1485 * 1486 * @return a hash code value for this object. 1487 */ 1488 public int hashCode() { 1489 int h = hash; 1490 if (h == 0) { 1491 for (char v : value) { 1492 h = 31 * h + v; 1493 } 1494 if (h != 0) { 1495 hash = h; 1496 } 1497 } 1498 return h; 1499 } 1500 1501 /** 1502 * Returns the index within this string of the first occurrence of 1503 * the specified character. If a character with value 1504 * {@code ch} occurs in the character sequence represented by 1505 * this {@code String} object, then the index (in Unicode 1506 * code units) of the first such occurrence is returned. For 1507 * values of {@code ch} in the range from 0 to 0xFFFF 1508 * (inclusive), this is the smallest value <i>k</i> such that: 1509 * <blockquote><pre> 1510 * this.charAt(<i>k</i>) == ch 1511 * </pre></blockquote> 1512 * is true. For other values of {@code ch}, it is the 1513 * smallest value <i>k</i> such that: 1514 * <blockquote><pre> 1515 * this.codePointAt(<i>k</i>) == ch 1516 * </pre></blockquote> 1517 * is true. In either case, if no such character occurs in this 1518 * string, then {@code -1} is returned. 1519 * 1520 * @param ch a character (Unicode code point). 1521 * @return the index of the first occurrence of the character in the 1522 * character sequence represented by this object, or 1523 * {@code -1} if the character does not occur. 1524 */ 1525 public int indexOf(int ch) { 1526 return indexOf(ch, 0); 1527 } 1528 1529 /** 1530 * Returns the index within this string of the first occurrence of the 1531 * specified character, starting the search at the specified index. 1532 * <p> 1533 * If a character with value {@code ch} occurs in the 1534 * character sequence represented by this {@code String} 1535 * object at an index no smaller than {@code fromIndex}, then 1536 * the index of the first such occurrence is returned. For values 1537 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1538 * this is the smallest value <i>k</i> such that: 1539 * <blockquote><pre> 1540 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1541 * </pre></blockquote> 1542 * is true. For other values of {@code ch}, it is the 1543 * smallest value <i>k</i> such that: 1544 * <blockquote><pre> 1545 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1546 * </pre></blockquote> 1547 * is true. In either case, if no such character occurs in this 1548 * string at or after position {@code fromIndex}, then 1549 * {@code -1} is returned. 1550 * 1551 * <p> 1552 * There is no restriction on the value of {@code fromIndex}. If it 1553 * is negative, it has the same effect as if it were zero: this entire 1554 * string may be searched. If it is greater than the length of this 1555 * string, it has the same effect as if it were equal to the length of 1556 * this string: {@code -1} is returned. 1557 * 1558 * <p>All indices are specified in {@code char} values 1559 * (Unicode code units). 1560 * 1561 * @param ch a character (Unicode code point). 1562 * @param fromIndex the index to start the search from. 1563 * @return the index of the first occurrence of the character in the 1564 * character sequence represented by this object that is greater 1565 * than or equal to {@code fromIndex}, or {@code -1} 1566 * if the character does not occur. 1567 */ 1568 public int indexOf(int ch, int fromIndex) { 1569 final int max = value.length; 1570 if (fromIndex < 0) { 1571 fromIndex = 0; 1572 } else if (fromIndex >= max) { 1573 // Note: fromIndex might be near -1>>>1. 1574 return -1; 1575 } 1576 1577 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1578 // handle most cases here (ch is a BMP code point or a 1579 // negative value (invalid code point)) 1580 final char[] value = this.value; 1581 for (int i = fromIndex; i < max; i++) { 1582 if (value[i] == ch) { 1583 return i; 1584 } 1585 } 1586 return -1; 1587 } else { 1588 return indexOfSupplementary(ch, fromIndex); 1589 } 1590 } 1591 1592 /** 1593 * Handles (rare) calls of indexOf with a supplementary character. 1594 */ 1595 private int indexOfSupplementary(int ch, int fromIndex) { 1596 if (Character.isValidCodePoint(ch)) { 1597 final char[] value = this.value; 1598 final char hi = Character.highSurrogate(ch); 1599 final char lo = Character.lowSurrogate(ch); 1600 final int max = value.length - 1; 1601 for (int i = fromIndex; i < max; i++) { 1602 if (value[i] == hi && value[i + 1] == lo) { 1603 return i; 1604 } 1605 } 1606 } 1607 return -1; 1608 } 1609 1610 /** 1611 * Returns the index within this string of the last occurrence of 1612 * the specified character. For values of {@code ch} in the 1613 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1614 * units) returned is the largest value <i>k</i> such that: 1615 * <blockquote><pre> 1616 * this.charAt(<i>k</i>) == ch 1617 * </pre></blockquote> 1618 * is true. For other values of {@code ch}, it is the 1619 * largest value <i>k</i> such that: 1620 * <blockquote><pre> 1621 * this.codePointAt(<i>k</i>) == ch 1622 * </pre></blockquote> 1623 * is true. In either case, if no such character occurs in this 1624 * string, then {@code -1} is returned. The 1625 * {@code String} is searched backwards starting at the last 1626 * character. 1627 * 1628 * @param ch a character (Unicode code point). 1629 * @return the index of the last occurrence of the character in the 1630 * character sequence represented by this object, or 1631 * {@code -1} if the character does not occur. 1632 */ 1633 public int lastIndexOf(int ch) { 1634 return lastIndexOf(ch, value.length - 1); 1635 } 1636 1637 /** 1638 * Returns the index within this string of the last occurrence of 1639 * the specified character, searching backward starting at the 1640 * specified index. For values of {@code ch} in the range 1641 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1642 * value <i>k</i> such that: 1643 * <blockquote><pre> 1644 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1645 * </pre></blockquote> 1646 * is true. For other values of {@code ch}, it is the 1647 * largest value <i>k</i> such that: 1648 * <blockquote><pre> 1649 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1650 * </pre></blockquote> 1651 * is true. In either case, if no such character occurs in this 1652 * string at or before position {@code fromIndex}, then 1653 * {@code -1} is returned. 1654 * 1655 * <p>All indices are specified in {@code char} values 1656 * (Unicode code units). 1657 * 1658 * @param ch a character (Unicode code point). 1659 * @param fromIndex the index to start the search from. There is no 1660 * restriction on the value of {@code fromIndex}. If it is 1661 * greater than or equal to the length of this string, it has 1662 * the same effect as if it were equal to one less than the 1663 * length of this string: this entire string may be searched. 1664 * If it is negative, it has the same effect as if it were -1: 1665 * -1 is returned. 1666 * @return the index of the last occurrence of the character in the 1667 * character sequence represented by this object that is less 1668 * than or equal to {@code fromIndex}, or {@code -1} 1669 * if the character does not occur before that point. 1670 */ 1671 public int lastIndexOf(int ch, int fromIndex) { 1672 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1673 // handle most cases here (ch is a BMP code point or a 1674 // negative value (invalid code point)) 1675 final char[] value = this.value; 1676 int i = Math.min(fromIndex, value.length - 1); 1677 for (; i >= 0; i--) { 1678 if (value[i] == ch) { 1679 return i; 1680 } 1681 } 1682 return -1; 1683 } else { 1684 return lastIndexOfSupplementary(ch, fromIndex); 1685 } 1686 } 1687 1688 /** 1689 * Handles (rare) calls of lastIndexOf with a supplementary character. 1690 */ 1691 private int lastIndexOfSupplementary(int ch, int fromIndex) { 1692 if (Character.isValidCodePoint(ch)) { 1693 final char[] value = this.value; 1694 char hi = Character.highSurrogate(ch); 1695 char lo = Character.lowSurrogate(ch); 1696 int i = Math.min(fromIndex, value.length - 2); 1697 for (; i >= 0; i--) { 1698 if (value[i] == hi && value[i + 1] == lo) { 1699 return i; 1700 } 1701 } 1702 } 1703 return -1; 1704 } 1705 1706 /** 1707 * Returns the index within this string of the first occurrence of the 1708 * specified substring. 1709 * 1710 * <p>The returned index is the smallest value {@code k} for which: 1711 * <pre>{@code 1712 * this.startsWith(str, k) 1713 * }</pre> 1714 * If no such value of {@code k} exists, then {@code -1} is returned. 1715 * 1716 * @param str the substring to search for. 1717 * @return the index of the first occurrence of the specified substring, 1718 * or {@code -1} if there is no such occurrence. 1719 */ 1720 @HotSpotIntrinsicCandidate 1721 public int indexOf(String str) { 1722 return indexOf(str, 0); 1723 } 1724 1725 /** 1726 * Returns the index within this string of the first occurrence of the 1727 * specified substring, starting at the specified index. 1728 * 1729 * <p>The returned index is the smallest value {@code k} for which: 1730 * <pre>{@code 1731 * k >= Math.min(fromIndex, this.length()) && 1732 * this.startsWith(str, k) 1733 * }</pre> 1734 * If no such value of {@code k} exists, then {@code -1} is returned. 1735 * 1736 * @param str the substring to search for. 1737 * @param fromIndex the index from which to start the search. 1738 * @return the index of the first occurrence of the specified substring, 1739 * starting at the specified index, 1740 * or {@code -1} if there is no such occurrence. 1741 */ 1742 public int indexOf(String str, int fromIndex) { 1743 return indexOf(value, 0, value.length, 1744 str.value, 0, str.value.length, fromIndex); 1745 } 1746 1747 /** 1748 * Code shared by String and AbstractStringBuilder to do searches. The 1749 * source is the character array being searched, and the target 1750 * is the string being searched for. 1751 * 1752 * @param source the characters being searched. 1753 * @param sourceOffset offset of the source string. 1754 * @param sourceCount count of the source string. 1755 * @param target the characters being searched for. 1756 * @param fromIndex the index to begin searching from. 1757 */ 1758 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1759 String target, int fromIndex) { 1760 return indexOf(source, sourceOffset, sourceCount, 1761 target.value, 0, target.value.length, 1762 fromIndex); 1763 } 1764 1765 /** 1766 * Code shared by String and StringBuffer to do searches. The 1767 * source is the character array being searched, and the target 1768 * is the string being searched for. 1769 * 1770 * @param source the characters being searched. 1771 * @param sourceOffset offset of the source string. 1772 * @param sourceCount count of the source string. 1773 * @param target the characters being searched for. 1774 * @param targetOffset offset of the target string. 1775 * @param targetCount count of the target string. 1776 * @param fromIndex the index to begin searching from. 1777 */ 1778 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1779 char[] target, int targetOffset, int targetCount, 1780 int fromIndex) { 1781 if (fromIndex >= sourceCount) { 1782 return (targetCount == 0 ? sourceCount : -1); 1783 } 1784 if (fromIndex < 0) { 1785 fromIndex = 0; 1786 } 1787 if (targetCount == 0) { 1788 return fromIndex; 1789 } 1790 1791 char first = target[targetOffset]; 1792 int max = sourceOffset + (sourceCount - targetCount); 1793 1794 for (int i = sourceOffset + fromIndex; i <= max; i++) { 1795 /* Look for first character. */ 1796 if (source[i] != first) { 1797 while (++i <= max && source[i] != first); 1798 } 1799 1800 /* Found first character, now look at the rest of v2 */ 1801 if (i <= max) { 1802 int j = i + 1; 1803 int end = j + targetCount - 1; 1804 for (int k = targetOffset + 1; j < end && source[j] 1805 == target[k]; j++, k++); 1806 1807 if (j == end) { 1808 /* Found whole string. */ 1809 return i - sourceOffset; 1810 } 1811 } 1812 } 1813 return -1; 1814 } 1815 1816 /** 1817 * Returns the index within this string of the last occurrence of the 1818 * specified substring. The last occurrence of the empty string "" 1819 * is considered to occur at the index value {@code this.length()}. 1820 * 1821 * <p>The returned index is the largest value {@code k} for which: 1822 * <pre>{@code 1823 * this.startsWith(str, k) 1824 * }</pre> 1825 * If no such value of {@code k} exists, then {@code -1} is returned. 1826 * 1827 * @param str the substring to search for. 1828 * @return the index of the last occurrence of the specified substring, 1829 * or {@code -1} if there is no such occurrence. 1830 */ 1831 public int lastIndexOf(String str) { 1832 return lastIndexOf(str, value.length); 1833 } 1834 1835 /** 1836 * Returns the index within this string of the last occurrence of the 1837 * specified substring, searching backward starting at the specified index. 1838 * 1839 * <p>The returned index is the largest value {@code k} for which: 1840 * <pre>{@code 1841 * k <= Math.min(fromIndex, this.length()) && 1842 * this.startsWith(str, k) 1843 * }</pre> 1844 * If no such value of {@code k} exists, then {@code -1} is returned. 1845 * 1846 * @param str the substring to search for. 1847 * @param fromIndex the index to start the search from. 1848 * @return the index of the last occurrence of the specified substring, 1849 * searching backward from the specified index, 1850 * or {@code -1} if there is no such occurrence. 1851 */ 1852 public int lastIndexOf(String str, int fromIndex) { 1853 return lastIndexOf(value, 0, value.length, 1854 str.value, 0, str.value.length, fromIndex); 1855 } 1856 1857 /** 1858 * Code shared by String and AbstractStringBuilder to do searches. The 1859 * source is the character array being searched, and the target 1860 * is the string being searched for. 1861 * 1862 * @param source the characters being searched. 1863 * @param sourceOffset offset of the source string. 1864 * @param sourceCount count of the source string. 1865 * @param target the characters being searched for. 1866 * @param fromIndex the index to begin searching from. 1867 */ 1868 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1869 String target, int fromIndex) { 1870 return lastIndexOf(source, sourceOffset, sourceCount, 1871 target.value, 0, target.value.length, 1872 fromIndex); 1873 } 1874 1875 /** 1876 * Code shared by String and StringBuffer to do searches. The 1877 * source is the character array being searched, and the target 1878 * is the string being searched for. 1879 * 1880 * @param source the characters being searched. 1881 * @param sourceOffset offset of the source string. 1882 * @param sourceCount count of the source string. 1883 * @param target the characters being searched for. 1884 * @param targetOffset offset of the target string. 1885 * @param targetCount count of the target string. 1886 * @param fromIndex the index to begin searching from. 1887 */ 1888 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1889 char[] target, int targetOffset, int targetCount, 1890 int fromIndex) { 1891 /* 1892 * Check arguments; return immediately where possible. For 1893 * consistency, don't check for null str. 1894 */ 1895 int rightIndex = sourceCount - targetCount; 1896 if (fromIndex < 0) { 1897 return -1; 1898 } 1899 if (fromIndex > rightIndex) { 1900 fromIndex = rightIndex; 1901 } 1902 /* Empty string always matches. */ 1903 if (targetCount == 0) { 1904 return fromIndex; 1905 } 1906 1907 int strLastIndex = targetOffset + targetCount - 1; 1908 char strLastChar = target[strLastIndex]; 1909 int min = sourceOffset + targetCount - 1; 1910 int i = min + fromIndex; 1911 1912 startSearchForLastChar: 1913 while (true) { 1914 while (i >= min && source[i] != strLastChar) { 1915 i--; 1916 } 1917 if (i < min) { 1918 return -1; 1919 } 1920 int j = i - 1; 1921 int start = j - (targetCount - 1); 1922 int k = strLastIndex - 1; 1923 1924 while (j > start) { 1925 if (source[j--] != target[k--]) { 1926 i--; 1927 continue startSearchForLastChar; 1928 } 1929 } 1930 return start - sourceOffset + 1; 1931 } 1932 } 1933 1934 /** 1935 * Returns a string that is a substring of this string. The 1936 * substring begins with the character at the specified index and 1937 * extends to the end of this string. <p> 1938 * Examples: 1939 * <blockquote><pre> 1940 * "unhappy".substring(2) returns "happy" 1941 * "Harbison".substring(3) returns "bison" 1942 * "emptiness".substring(9) returns "" (an empty string) 1943 * </pre></blockquote> 1944 * 1945 * @param beginIndex the beginning index, inclusive. 1946 * @return the specified substring. 1947 * @exception IndexOutOfBoundsException if 1948 * {@code beginIndex} is negative or larger than the 1949 * length of this {@code String} object. 1950 */ 1951 public String substring(int beginIndex) { 1952 if (beginIndex <= 0) { 1953 if (beginIndex < 0) { 1954 throw new StringIndexOutOfBoundsException(beginIndex); 1955 } 1956 return this; 1957 } 1958 int subLen = value.length - beginIndex; 1959 if (subLen < 0) { 1960 throw new StringIndexOutOfBoundsException(subLen); 1961 } 1962 return new String(value, beginIndex, subLen); 1963 } 1964 1965 /** 1966 * Returns a string that is a substring of this string. The 1967 * substring begins at the specified {@code beginIndex} and 1968 * extends to the character at index {@code endIndex - 1}. 1969 * Thus the length of the substring is {@code endIndex-beginIndex}. 1970 * <p> 1971 * Examples: 1972 * <blockquote><pre> 1973 * "hamburger".substring(4, 8) returns "urge" 1974 * "smiles".substring(1, 5) returns "mile" 1975 * </pre></blockquote> 1976 * 1977 * @param beginIndex the beginning index, inclusive. 1978 * @param endIndex the ending index, exclusive. 1979 * @return the specified substring. 1980 * @exception IndexOutOfBoundsException if the 1981 * {@code beginIndex} is negative, or 1982 * {@code endIndex} is larger than the length of 1983 * this {@code String} object, or 1984 * {@code beginIndex} is larger than 1985 * {@code endIndex}. 1986 */ 1987 public String substring(int beginIndex, int endIndex) { 1988 if (beginIndex <= 0) { 1989 if (beginIndex < 0) { 1990 throw new StringIndexOutOfBoundsException(beginIndex); 1991 } 1992 if (endIndex == value.length) { 1993 return this; 1994 } 1995 } 1996 if (endIndex > value.length) { 1997 throw new StringIndexOutOfBoundsException(endIndex); 1998 } 1999 int subLen = endIndex - beginIndex; 2000 if (subLen < 0) { 2001 throw new StringIndexOutOfBoundsException(subLen); 2002 } 2003 return new String(value, beginIndex, subLen); 2004 } 2005 2006 /** 2007 * Returns a character sequence that is a subsequence of this sequence. 2008 * 2009 * <p> An invocation of this method of the form 2010 * 2011 * <blockquote><pre> 2012 * str.subSequence(begin, end)</pre></blockquote> 2013 * 2014 * behaves in exactly the same way as the invocation 2015 * 2016 * <blockquote><pre> 2017 * str.substring(begin, end)</pre></blockquote> 2018 * 2019 * @apiNote 2020 * This method is defined so that the {@code String} class can implement 2021 * the {@link CharSequence} interface. 2022 * 2023 * @param beginIndex the begin index, inclusive. 2024 * @param endIndex the end index, exclusive. 2025 * @return the specified subsequence. 2026 * 2027 * @throws IndexOutOfBoundsException 2028 * if {@code beginIndex} or {@code endIndex} is negative, 2029 * if {@code endIndex} is greater than {@code length()}, 2030 * or if {@code beginIndex} is greater than {@code endIndex} 2031 * 2032 * @since 1.4 2033 * @spec JSR-51 2034 */ 2035 public CharSequence subSequence(int beginIndex, int endIndex) { 2036 return this.substring(beginIndex, endIndex); 2037 } 2038 2039 /** 2040 * Concatenates the specified string to the end of this string. 2041 * <p> 2042 * If the length of the argument string is {@code 0}, then this 2043 * {@code String} object is returned. Otherwise, a 2044 * {@code String} object is returned that represents a character 2045 * sequence that is the concatenation of the character sequence 2046 * represented by this {@code String} object and the character 2047 * sequence represented by the argument string.<p> 2048 * Examples: 2049 * <blockquote><pre> 2050 * "cares".concat("s") returns "caress" 2051 * "to".concat("get").concat("her") returns "together" 2052 * </pre></blockquote> 2053 * 2054 * @param str the {@code String} that is concatenated to the end 2055 * of this {@code String}. 2056 * @return a string that represents the concatenation of this object's 2057 * characters followed by the string argument's characters. 2058 */ 2059 public String concat(String str) { 2060 int otherLen = str.length(); 2061 if (otherLen == 0) { 2062 return this; 2063 } 2064 int len = value.length; 2065 char[] buf = Arrays.copyOf(value, len + otherLen); 2066 str.getChars(buf, len); 2067 return new String(buf, true); 2068 } 2069 2070 /** 2071 * Returns a string resulting from replacing all occurrences of 2072 * {@code oldChar} in this string with {@code newChar}. 2073 * <p> 2074 * If the character {@code oldChar} does not occur in the 2075 * character sequence represented by this {@code String} object, 2076 * then a reference to this {@code String} object is returned. 2077 * Otherwise, a {@code String} object is returned that 2078 * represents a character sequence identical to the character sequence 2079 * represented by this {@code String} object, except that every 2080 * occurrence of {@code oldChar} is replaced by an occurrence 2081 * of {@code newChar}. 2082 * <p> 2083 * Examples: 2084 * <blockquote><pre> 2085 * "mesquite in your cellar".replace('e', 'o') 2086 * returns "mosquito in your collar" 2087 * "the war of baronets".replace('r', 'y') 2088 * returns "the way of bayonets" 2089 * "sparring with a purple porpoise".replace('p', 't') 2090 * returns "starring with a turtle tortoise" 2091 * "JonL".replace('q', 'x') returns "JonL" (no change) 2092 * </pre></blockquote> 2093 * 2094 * @param oldChar the old character. 2095 * @param newChar the new character. 2096 * @return a string derived from this string by replacing every 2097 * occurrence of {@code oldChar} with {@code newChar}. 2098 */ 2099 public String replace(char oldChar, char newChar) { 2100 if (oldChar != newChar) { 2101 char[] val = value; /* avoid getfield opcode */ 2102 int len = val.length; 2103 int i = -1; 2104 2105 while (++i < len) { 2106 if (val[i] == oldChar) { 2107 break; 2108 } 2109 } 2110 if (i < len) { 2111 char[] buf = new char[len]; 2112 for (int j = 0; j < i; j++) { 2113 buf[j] = val[j]; 2114 } 2115 while (i < len) { 2116 char c = val[i]; 2117 buf[i] = (c == oldChar) ? newChar : c; 2118 i++; 2119 } 2120 return new String(buf, true); 2121 } 2122 } 2123 return this; 2124 } 2125 2126 /** 2127 * Tells whether or not this string matches the given <a 2128 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2129 * 2130 * <p> An invocation of this method of the form 2131 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2132 * same result as the expression 2133 * 2134 * <blockquote> 2135 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2136 * matches(<i>regex</i>, <i>str</i>)} 2137 * </blockquote> 2138 * 2139 * @param regex 2140 * the regular expression to which this string is to be matched 2141 * 2142 * @return {@code true} if, and only if, this string matches the 2143 * given regular expression 2144 * 2145 * @throws PatternSyntaxException 2146 * if the regular expression's syntax is invalid 2147 * 2148 * @see java.util.regex.Pattern 2149 * 2150 * @since 1.4 2151 * @spec JSR-51 2152 */ 2153 public boolean matches(String regex) { 2154 return Pattern.matches(regex, this); 2155 } 2156 2157 /** 2158 * Returns true if and only if this string contains the specified 2159 * sequence of char values. 2160 * 2161 * @param s the sequence to search for 2162 * @return true if this string contains {@code s}, false otherwise 2163 * @since 1.5 2164 */ 2165 public boolean contains(CharSequence s) { 2166 return indexOf(s.toString()) >= 0; 2167 } 2168 2169 /** 2170 * Replaces the first 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 .replaceFirst(}<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#replaceFirst replaceFirst}(<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#replaceFirst}. 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 the first 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 replaceFirst(String regex, String replacement) { 2211 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2212 } 2213 2214 /** 2215 * Replaces each substring of this string that matches the given <a 2216 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2217 * given replacement. 2218 * 2219 * <p> An invocation of this method of the form 2220 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2221 * yields exactly the same result as the expression 2222 * 2223 * <blockquote> 2224 * <code> 2225 * {@link java.util.regex.Pattern}.{@link 2226 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2227 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2228 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2229 * </code> 2230 * </blockquote> 2231 * 2232 *<p> 2233 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2234 * replacement string may cause the results to be different than if it were 2235 * being treated as a literal replacement string; see 2236 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2237 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2238 * meaning of these characters, if desired. 2239 * 2240 * @param regex 2241 * the regular expression to which this string is to be matched 2242 * @param replacement 2243 * the string to be substituted for each match 2244 * 2245 * @return The resulting {@code String} 2246 * 2247 * @throws PatternSyntaxException 2248 * if the regular expression's syntax is invalid 2249 * 2250 * @see java.util.regex.Pattern 2251 * 2252 * @since 1.4 2253 * @spec JSR-51 2254 */ 2255 public String replaceAll(String regex, String replacement) { 2256 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2257 } 2258 2259 /** 2260 * Replaces each substring of this string that matches the literal target 2261 * sequence with the specified literal replacement sequence. The 2262 * replacement proceeds from the beginning of the string to the end, for 2263 * example, replacing "aa" with "b" in the string "aaa" will result in 2264 * "ba" rather than "ab". 2265 * 2266 * @param target The sequence of char values to be replaced 2267 * @param replacement The replacement sequence of char values 2268 * @return The resulting string 2269 * @since 1.5 2270 */ 2271 public String replace(CharSequence target, CharSequence replacement) { 2272 String starget = target.toString(); 2273 String srepl = replacement.toString(); 2274 int j = indexOf(starget); 2275 if (j < 0) { 2276 return this; 2277 } 2278 int targLen = starget.length(); 2279 int targLen1 = Math.max(targLen, 1); 2280 final char[] value = this.value; 2281 final char[] replValue = srepl.value; 2282 int newLenHint = value.length - targLen + replValue.length; 2283 if (newLenHint < 0) { 2284 throw new OutOfMemoryError(); 2285 } 2286 StringBuilder sb = new StringBuilder(newLenHint); 2287 int i = 0; 2288 do { 2289 sb.append(value, i, j - i) 2290 .append(replValue); 2291 i = j + targLen; 2292 } while (j < value.length && (j = indexOf(starget, j + targLen1)) > 0); 2293 2294 return sb.append(value, i, value.length - i).toString(); 2295 } 2296 2297 /** 2298 * Splits this string around matches of the given 2299 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2300 * 2301 * <p> The array returned by this method contains each substring of this 2302 * string that is terminated by another substring that matches the given 2303 * expression or is terminated by the end of the string. The substrings in 2304 * the array are in the order in which they occur in this string. If the 2305 * expression does not match any part of the input then the resulting array 2306 * has just one element, namely this string. 2307 * 2308 * <p> When there is a positive-width match at the beginning of this 2309 * string then an empty leading substring is included at the beginning 2310 * of the resulting array. A zero-width match at the beginning however 2311 * never produces such empty leading substring. 2312 * 2313 * <p> The {@code limit} parameter controls the number of times the 2314 * pattern is applied and therefore affects the length of the resulting 2315 * array. If the limit <i>n</i> is greater than zero then the pattern 2316 * will be applied at most <i>n</i> - 1 times, the array's 2317 * length will be no greater than <i>n</i>, and the array's last entry 2318 * will contain all input beyond the last matched delimiter. If <i>n</i> 2319 * is non-positive then the pattern will be applied as many times as 2320 * possible and the array can have any length. If <i>n</i> is zero then 2321 * the pattern will be applied as many times as possible, the array can 2322 * have any length, and trailing empty strings will be discarded. 2323 * 2324 * <p> The string {@code "boo:and:foo"}, for example, yields the 2325 * following results with these parameters: 2326 * 2327 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2328 * <tr> 2329 * <th>Regex</th> 2330 * <th>Limit</th> 2331 * <th>Result</th> 2332 * </tr> 2333 * <tr><td align=center>:</td> 2334 * <td align=center>2</td> 2335 * <td>{@code { "boo", "and:foo" }}</td></tr> 2336 * <tr><td align=center>:</td> 2337 * <td align=center>5</td> 2338 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2339 * <tr><td align=center>:</td> 2340 * <td align=center>-2</td> 2341 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2342 * <tr><td align=center>o</td> 2343 * <td align=center>5</td> 2344 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2345 * <tr><td align=center>o</td> 2346 * <td align=center>-2</td> 2347 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2348 * <tr><td align=center>o</td> 2349 * <td align=center>0</td> 2350 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2351 * </table></blockquote> 2352 * 2353 * <p> An invocation of this method of the form 2354 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2355 * yields the same result as the expression 2356 * 2357 * <blockquote> 2358 * <code> 2359 * {@link java.util.regex.Pattern}.{@link 2360 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2361 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2362 * </code> 2363 * </blockquote> 2364 * 2365 * 2366 * @param regex 2367 * the delimiting regular expression 2368 * 2369 * @param limit 2370 * the result threshold, as described above 2371 * 2372 * @return the array of strings computed by splitting this string 2373 * around matches of the given regular expression 2374 * 2375 * @throws PatternSyntaxException 2376 * if the regular expression's syntax is invalid 2377 * 2378 * @see java.util.regex.Pattern 2379 * 2380 * @since 1.4 2381 * @spec JSR-51 2382 */ 2383 public String[] split(String regex, int limit) { 2384 /* fastpath if the regex is a 2385 (1)one-char String and this character is not one of the 2386 RegEx's meta characters ".$|()[{^?*+\\", or 2387 (2)two-char String and the first char is the backslash and 2388 the second is not the ascii digit or ascii letter. 2389 */ 2390 char ch = 0; 2391 if (((regex.value.length == 1 && 2392 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2393 (regex.length() == 2 && 2394 regex.charAt(0) == '\\' && 2395 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2396 ((ch-'a')|('z'-ch)) < 0 && 2397 ((ch-'A')|('Z'-ch)) < 0)) && 2398 (ch < Character.MIN_HIGH_SURROGATE || 2399 ch > Character.MAX_LOW_SURROGATE)) 2400 { 2401 int off = 0; 2402 int next = 0; 2403 boolean limited = limit > 0; 2404 ArrayList<String> list = new ArrayList<>(); 2405 while ((next = indexOf(ch, off)) != -1) { 2406 if (!limited || list.size() < limit - 1) { 2407 list.add(substring(off, next)); 2408 off = next + 1; 2409 } else { // last one 2410 //assert (list.size() == limit - 1); 2411 list.add(substring(off, value.length)); 2412 off = value.length; 2413 break; 2414 } 2415 } 2416 // If no match was found, return this 2417 if (off == 0) 2418 return new String[]{this}; 2419 2420 // Add remaining segment 2421 if (!limited || list.size() < limit) 2422 list.add(substring(off, value.length)); 2423 2424 // Construct result 2425 int resultSize = list.size(); 2426 if (limit == 0) { 2427 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) { 2428 resultSize--; 2429 } 2430 } 2431 String[] result = new String[resultSize]; 2432 return list.subList(0, resultSize).toArray(result); 2433 } 2434 return Pattern.compile(regex).split(this, limit); 2435 } 2436 2437 /** 2438 * Splits this string around matches of the given <a 2439 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2440 * 2441 * <p> This method works as if by invoking the two-argument {@link 2442 * #split(String, int) split} method with the given expression and a limit 2443 * argument of zero. Trailing empty strings are therefore not included in 2444 * the resulting array. 2445 * 2446 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2447 * results with these expressions: 2448 * 2449 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2450 * <tr> 2451 * <th>Regex</th> 2452 * <th>Result</th> 2453 * </tr> 2454 * <tr><td align=center>:</td> 2455 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2456 * <tr><td align=center>o</td> 2457 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2458 * </table></blockquote> 2459 * 2460 * 2461 * @param regex 2462 * the delimiting regular expression 2463 * 2464 * @return the array of strings computed by splitting this string 2465 * around matches of the given regular expression 2466 * 2467 * @throws PatternSyntaxException 2468 * if the regular expression's syntax is invalid 2469 * 2470 * @see java.util.regex.Pattern 2471 * 2472 * @since 1.4 2473 * @spec JSR-51 2474 */ 2475 public String[] split(String regex) { 2476 return split(regex, 0); 2477 } 2478 2479 /** 2480 * Returns a new String composed of copies of the 2481 * {@code CharSequence elements} joined together with a copy of 2482 * the specified {@code delimiter}. 2483 * 2484 * <blockquote>For example, 2485 * <pre>{@code 2486 * String message = String.join("-", "Java", "is", "cool"); 2487 * // message returned is: "Java-is-cool" 2488 * }</pre></blockquote> 2489 * 2490 * Note that if an element is null, then {@code "null"} is added. 2491 * 2492 * @param delimiter the delimiter that separates each element 2493 * @param elements the elements to join together. 2494 * 2495 * @return a new {@code String} that is composed of the {@code elements} 2496 * separated by the {@code delimiter} 2497 * 2498 * @throws NullPointerException If {@code delimiter} or {@code elements} 2499 * is {@code null} 2500 * 2501 * @see java.util.StringJoiner 2502 * @since 1.8 2503 */ 2504 public static String join(CharSequence delimiter, CharSequence... elements) { 2505 Objects.requireNonNull(delimiter); 2506 Objects.requireNonNull(elements); 2507 // Number of elements not likely worth Arrays.stream overhead. 2508 StringJoiner joiner = new StringJoiner(delimiter); 2509 for (CharSequence cs: elements) { 2510 joiner.add(cs); 2511 } 2512 return joiner.toString(); 2513 } 2514 2515 /** 2516 * Returns a new {@code String} composed of copies of the 2517 * {@code CharSequence elements} joined together with a copy of the 2518 * specified {@code delimiter}. 2519 * 2520 * <blockquote>For example, 2521 * <pre>{@code 2522 * List<String> strings = new LinkedList<>(); 2523 * strings.add("Java");strings.add("is"); 2524 * strings.add("cool"); 2525 * String message = String.join(" ", strings); 2526 * //message returned is: "Java is cool" 2527 * 2528 * Set<String> strings = new LinkedHashSet<>(); 2529 * strings.add("Java"); strings.add("is"); 2530 * strings.add("very"); strings.add("cool"); 2531 * String message = String.join("-", strings); 2532 * //message returned is: "Java-is-very-cool" 2533 * }</pre></blockquote> 2534 * 2535 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2536 * 2537 * @param delimiter a sequence of characters that is used to separate each 2538 * of the {@code elements} in the resulting {@code String} 2539 * @param elements an {@code Iterable} that will have its {@code elements} 2540 * joined together. 2541 * 2542 * @return a new {@code String} that is composed from the {@code elements} 2543 * argument 2544 * 2545 * @throws NullPointerException If {@code delimiter} or {@code elements} 2546 * is {@code null} 2547 * 2548 * @see #join(CharSequence,CharSequence...) 2549 * @see java.util.StringJoiner 2550 * @since 1.8 2551 */ 2552 public static String join(CharSequence delimiter, 2553 Iterable<? extends CharSequence> elements) { 2554 Objects.requireNonNull(delimiter); 2555 Objects.requireNonNull(elements); 2556 StringJoiner joiner = new StringJoiner(delimiter); 2557 for (CharSequence cs: elements) { 2558 joiner.add(cs); 2559 } 2560 return joiner.toString(); 2561 } 2562 2563 /** 2564 * Converts all of the characters in this {@code String} to lower 2565 * case using the rules of the given {@code Locale}. Case mapping is based 2566 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2567 * class. Since case mappings are not always 1:1 char mappings, the resulting 2568 * {@code String} may be a different length than the original {@code String}. 2569 * <p> 2570 * Examples of lowercase mappings are in the following table: 2571 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2572 * <tr> 2573 * <th>Language Code of Locale</th> 2574 * <th>Upper Case</th> 2575 * <th>Lower Case</th> 2576 * <th>Description</th> 2577 * </tr> 2578 * <tr> 2579 * <td>tr (Turkish)</td> 2580 * <td>\u0130</td> 2581 * <td>\u0069</td> 2582 * <td>capital letter I with dot above -> small letter i</td> 2583 * </tr> 2584 * <tr> 2585 * <td>tr (Turkish)</td> 2586 * <td>\u0049</td> 2587 * <td>\u0131</td> 2588 * <td>capital letter I -> small letter dotless i </td> 2589 * </tr> 2590 * <tr> 2591 * <td>(all)</td> 2592 * <td>French Fries</td> 2593 * <td>french fries</td> 2594 * <td>lowercased all chars in String</td> 2595 * </tr> 2596 * <tr> 2597 * <td>(all)</td> 2598 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2599 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2600 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2601 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2602 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2603 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2604 * <td>lowercased all chars in String</td> 2605 * </tr> 2606 * </table> 2607 * 2608 * @param locale use the case transformation rules for this locale 2609 * @return the {@code String}, converted to lowercase. 2610 * @see java.lang.String#toLowerCase() 2611 * @see java.lang.String#toUpperCase() 2612 * @see java.lang.String#toUpperCase(Locale) 2613 * @since 1.1 2614 */ 2615 public String toLowerCase(Locale locale) { 2616 if (locale == null) { 2617 throw new NullPointerException(); 2618 } 2619 int first; 2620 boolean hasSurr = false; 2621 final int len = value.length; 2622 2623 // Now check if there are any characters that need to be changed, or are surrogate 2624 for (first = 0 ; first < len; first++) { 2625 int cp = (int)value[first]; 2626 if (Character.isSurrogate((char)cp)) { 2627 hasSurr = true; 2628 break; 2629 } 2630 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR 2631 break; 2632 } 2633 } 2634 if (first == len) 2635 return this; 2636 char[] result = new char[len]; 2637 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2638 // lowerCase characters. 2639 String lang = locale.getLanguage(); 2640 if (lang == "tr" || lang == "az" || lang == "lt") { 2641 return toLowerCaseEx(result, first, locale, true); 2642 } 2643 if (hasSurr) { 2644 return toLowerCaseEx(result, first, locale, false); 2645 } 2646 for (int i = first; i < len; i++) { 2647 int cp = (int)value[i]; 2648 if (cp == '\u03A3' || // GREEK CAPITAL LETTER SIGMA 2649 Character.isSurrogate((char)cp)) { 2650 return toLowerCaseEx(result, i, locale, false); 2651 } 2652 if (cp == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE 2653 return toLowerCaseEx(result, i, locale, true); 2654 } 2655 cp = Character.toLowerCase(cp); 2656 if (!Character.isBmpCodePoint(cp)) { 2657 return toLowerCaseEx(result, i, locale, false); 2658 } 2659 result[i] = (char)cp; 2660 } 2661 return new String(result, true); 2662 } 2663 2664 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) { 2665 int resultOffset = first; 2666 int srcCount; 2667 for (int i = first; i < value.length; i += srcCount) { 2668 int srcChar = (int)value[i]; 2669 int lowerChar; 2670 char[] lowerCharArray; 2671 srcCount = 1; 2672 if (Character.isSurrogate((char)srcChar)) { 2673 srcChar = codePointAt(i); 2674 srcCount = Character.charCount(srcChar); 2675 } 2676 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA 2677 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale); 2678 } else { 2679 lowerChar = Character.toLowerCase(srcChar); 2680 } 2681 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp 2682 result[resultOffset++] = (char)lowerChar; 2683 } else { 2684 if (lowerChar == Character.ERROR) { 2685 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale); 2686 } else if (srcCount == 2) { 2687 resultOffset += Character.toChars(lowerChar, result, resultOffset); 2688 continue; 2689 } else { 2690 lowerCharArray = Character.toChars(lowerChar); 2691 } 2692 /* Grow result if needed */ 2693 int mapLen = lowerCharArray.length; 2694 if (mapLen > srcCount) { 2695 char[] result2 = new char[result.length + mapLen - srcCount]; 2696 System.arraycopy(result, 0, result2, 0, resultOffset); 2697 result = result2; 2698 } 2699 for (int x = 0; x < mapLen; ++x) { 2700 result[resultOffset++] = lowerCharArray[x]; 2701 } 2702 } 2703 } 2704 return new String(result, 0, resultOffset); 2705 } 2706 2707 /** 2708 * Converts all of the characters in this {@code String} to lower 2709 * case using the rules of the default locale. This is equivalent to calling 2710 * {@code toLowerCase(Locale.getDefault())}. 2711 * <p> 2712 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2713 * results if used for strings that are intended to be interpreted locale 2714 * independently. 2715 * Examples are programming language identifiers, protocol keys, and HTML 2716 * tags. 2717 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2718 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2719 * LATIN SMALL LETTER DOTLESS I character. 2720 * To obtain correct results for locale insensitive strings, use 2721 * {@code toLowerCase(Locale.ROOT)}. 2722 * 2723 * @return the {@code String}, converted to lowercase. 2724 * @see java.lang.String#toLowerCase(Locale) 2725 */ 2726 public String toLowerCase() { 2727 return toLowerCase(Locale.getDefault()); 2728 } 2729 2730 /** 2731 * Converts all of the characters in this {@code String} to upper 2732 * case using the rules of the given {@code Locale}. Case mapping is based 2733 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2734 * class. Since case mappings are not always 1:1 char mappings, the resulting 2735 * {@code String} may be a different length than the original {@code String}. 2736 * <p> 2737 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2738 * 2739 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2740 * <tr> 2741 * <th>Language Code of Locale</th> 2742 * <th>Lower Case</th> 2743 * <th>Upper Case</th> 2744 * <th>Description</th> 2745 * </tr> 2746 * <tr> 2747 * <td>tr (Turkish)</td> 2748 * <td>\u0069</td> 2749 * <td>\u0130</td> 2750 * <td>small letter i -> capital letter I with dot above</td> 2751 * </tr> 2752 * <tr> 2753 * <td>tr (Turkish)</td> 2754 * <td>\u0131</td> 2755 * <td>\u0049</td> 2756 * <td>small letter dotless i -> capital letter I</td> 2757 * </tr> 2758 * <tr> 2759 * <td>(all)</td> 2760 * <td>\u00df</td> 2761 * <td>\u0053 \u0053</td> 2762 * <td>small letter sharp s -> two letters: SS</td> 2763 * </tr> 2764 * <tr> 2765 * <td>(all)</td> 2766 * <td>Fahrvergnügen</td> 2767 * <td>FAHRVERGNÜGEN</td> 2768 * <td></td> 2769 * </tr> 2770 * </table> 2771 * @param locale use the case transformation rules for this locale 2772 * @return the {@code String}, converted to uppercase. 2773 * @see java.lang.String#toUpperCase() 2774 * @see java.lang.String#toLowerCase() 2775 * @see java.lang.String#toLowerCase(Locale) 2776 * @since 1.1 2777 */ 2778 public String toUpperCase(Locale locale) { 2779 if (locale == null) { 2780 throw new NullPointerException(); 2781 } 2782 int first; 2783 boolean hasSurr = false; 2784 final int len = value.length; 2785 2786 // Now check if there are any characters that need to be changed, or are surrogate 2787 for (first = 0 ; first < len; first++ ) { 2788 int cp = (int)value[first]; 2789 if (Character.isSurrogate((char)cp)) { 2790 hasSurr = true; 2791 break; 2792 } 2793 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR 2794 break; 2795 } 2796 } 2797 if (first == len) { 2798 return this; 2799 } 2800 char[] result = new char[len]; 2801 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2802 // upperCase characters. 2803 String lang = locale.getLanguage(); 2804 if (lang == "tr" || lang == "az" || lang == "lt") { 2805 return toUpperCaseEx(result, first, locale, true); 2806 } 2807 if (hasSurr) { 2808 return toUpperCaseEx(result, first, locale, false); 2809 } 2810 for (int i = first; i < len; i++) { 2811 int cp = (int)value[i]; 2812 if (Character.isSurrogate((char)cp)) { 2813 return toUpperCaseEx(result, i, locale, false); 2814 } 2815 cp = Character.toUpperCaseEx(cp); 2816 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp 2817 return toUpperCaseEx(result, i, locale, false); 2818 } 2819 result[i] = (char)cp; 2820 } 2821 return new String(result, true); 2822 } 2823 2824 private String toUpperCaseEx(char[] result, int first, Locale locale, 2825 boolean localeDependent) { 2826 int resultOffset = first; 2827 int srcCount; 2828 for (int i = first; i < value.length; i += srcCount) { 2829 int srcChar = (int)value[i]; 2830 int upperChar; 2831 char[] upperCharArray; 2832 srcCount = 1; 2833 if (Character.isSurrogate((char)srcChar)) { 2834 srcChar = codePointAt(i); 2835 srcCount = Character.charCount(srcChar); 2836 } 2837 if (localeDependent) { 2838 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale); 2839 } else { 2840 upperChar = Character.toUpperCaseEx(srcChar); 2841 } 2842 if (Character.isBmpCodePoint(upperChar)) { 2843 result[resultOffset++] = (char)upperChar; 2844 } else { 2845 if (upperChar == Character.ERROR) { 2846 if (localeDependent) { 2847 upperCharArray = 2848 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale); 2849 } else { 2850 upperCharArray = Character.toUpperCaseCharArray(srcChar); 2851 } 2852 } else if (srcCount == 2) { 2853 resultOffset += Character.toChars(upperChar, result, resultOffset); 2854 continue; 2855 } else { 2856 upperCharArray = Character.toChars(upperChar); 2857 } 2858 /* Grow result if needed */ 2859 int mapLen = upperCharArray.length; 2860 if (mapLen > srcCount) { 2861 char[] result2 = new char[result.length + mapLen - srcCount]; 2862 System.arraycopy(result, 0, result2, 0, resultOffset); 2863 result = result2; 2864 } 2865 for (int x = 0; x < mapLen; ++x) { 2866 result[resultOffset++] = upperCharArray[x]; 2867 } 2868 } 2869 } 2870 return new String(result, 0, resultOffset); 2871 } 2872 2873 /** 2874 * Converts all of the characters in this {@code String} to upper 2875 * case using the rules of the default locale. This method is equivalent to 2876 * {@code toUpperCase(Locale.getDefault())}. 2877 * <p> 2878 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2879 * results if used for strings that are intended to be interpreted locale 2880 * independently. 2881 * Examples are programming language identifiers, protocol keys, and HTML 2882 * tags. 2883 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2884 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2885 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2886 * To obtain correct results for locale insensitive strings, use 2887 * {@code toUpperCase(Locale.ROOT)}. 2888 * 2889 * @return the {@code String}, converted to uppercase. 2890 * @see java.lang.String#toUpperCase(Locale) 2891 */ 2892 public String toUpperCase() { 2893 return toUpperCase(Locale.getDefault()); 2894 } 2895 2896 /** 2897 * Returns a string whose value is this string, with any leading and trailing 2898 * whitespace removed. 2899 * <p> 2900 * If this {@code String} object represents an empty character 2901 * sequence, or the first and last characters of character sequence 2902 * represented by this {@code String} object both have codes 2903 * greater than {@code '\u005Cu0020'} (the space character), then a 2904 * reference to this {@code String} object is returned. 2905 * <p> 2906 * Otherwise, if there is no character with a code greater than 2907 * {@code '\u005Cu0020'} in the string, then a 2908 * {@code String} object representing an empty string is 2909 * returned. 2910 * <p> 2911 * Otherwise, let <i>k</i> be the index of the first character in the 2912 * string whose code is greater than {@code '\u005Cu0020'}, and let 2913 * <i>m</i> be the index of the last character in the string whose code 2914 * is greater than {@code '\u005Cu0020'}. A {@code String} 2915 * object is returned, representing the substring of this string that 2916 * begins with the character at index <i>k</i> and ends with the 2917 * character at index <i>m</i>-that is, the result of 2918 * {@code this.substring(k, m + 1)}. 2919 * <p> 2920 * This method may be used to trim whitespace (as defined above) from 2921 * the beginning and end of a string. 2922 * 2923 * @return A string whose value is this string, with any leading and trailing white 2924 * space removed, or this string if it has no leading or 2925 * trailing white space. 2926 */ 2927 public String trim() { 2928 char[] val = value; /* avoid getfield opcode */ 2929 int end = val.length; 2930 int beg = 0; 2931 2932 while ((beg < end) && (val[beg] <= ' ')) { 2933 beg++; 2934 } 2935 while ((beg < end) && (val[end - 1] <= ' ')) { 2936 end--; 2937 } 2938 return substring(beg, end); 2939 } 2940 2941 /** 2942 * This object (which is already a string!) is itself returned. 2943 * 2944 * @return the string itself. 2945 */ 2946 public String toString() { 2947 return this; 2948 } 2949 2950 static class IntCharArraySpliterator implements Spliterator.OfInt { 2951 private final char[] array; 2952 private int index; // current index, modified on advance/split 2953 private final int fence; // one past last index 2954 private final int cs; 2955 2956 IntCharArraySpliterator(char[] array, int acs) { 2957 this(array, 0, array.length, acs); 2958 } 2959 2960 IntCharArraySpliterator(char[] array, int origin, int fence, int acs) { 2961 this.array = array; 2962 this.index = origin; 2963 this.fence = fence; 2964 this.cs = acs | Spliterator.ORDERED | Spliterator.SIZED 2965 | Spliterator.SUBSIZED; 2966 } 2967 2968 @Override 2969 public OfInt trySplit() { 2970 int lo = index, mid = (lo + fence) >>> 1; 2971 return (lo >= mid) 2972 ? null 2973 : new IntCharArraySpliterator(array, lo, index = mid, cs); 2974 } 2975 2976 @Override 2977 public void forEachRemaining(IntConsumer action) { 2978 char[] a; int i, hi; // hoist accesses and checks from loop 2979 if (action == null) 2980 throw new NullPointerException(); 2981 if ((a = array).length >= (hi = fence) && 2982 (i = index) >= 0 && i < (index = hi)) { 2983 do { action.accept(a[i]); } while (++i < hi); 2984 } 2985 } 2986 2987 @Override 2988 public boolean tryAdvance(IntConsumer action) { 2989 if (action == null) 2990 throw new NullPointerException(); 2991 if (index >= 0 && index < fence) { 2992 action.accept(array[index++]); 2993 return true; 2994 } 2995 return false; 2996 } 2997 2998 @Override 2999 public long estimateSize() { return (long)(fence - index); } 3000 3001 @Override 3002 public int characteristics() { 3003 return cs; 3004 } 3005 } 3006 3007 /** 3008 * Returns a stream of {@code int} zero-extending the {@code char} values 3009 * from this sequence. Any char which maps to a <a 3010 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code 3011 * point</a> is passed through uninterpreted. 3012 * 3013 * @return an IntStream of char values from this sequence 3014 * @since 1.9 3015 */ 3016 @Override 3017 public IntStream chars() { 3018 return StreamSupport.intStream( 3019 new IntCharArraySpliterator(value, Spliterator.IMMUTABLE), false); 3020 } 3021 3022 static class CodePointsSpliterator implements Spliterator.OfInt { 3023 private final char[] array; 3024 private int index; // current index, modified on advance/split 3025 private final int fence; // one past last index 3026 private final int cs; 3027 3028 CodePointsSpliterator(char[] array, int acs) { 3029 this(array, 0, array.length, acs); 3030 } 3031 3032 CodePointsSpliterator(char[] array, int origin, int fence, int acs) { 3033 this.array = array; 3034 this.index = origin; 3035 this.fence = fence; 3036 this.cs = acs | Spliterator.ORDERED; 3037 } 3038 3039 @Override 3040 public OfInt trySplit() { 3041 int lo = index, mid = (lo + fence) >>> 1; 3042 if (lo >= mid) 3043 return null; 3044 3045 int midOneLess; 3046 // If the mid-point intersects a surrogate pair 3047 if (Character.isLowSurrogate(array[mid]) && 3048 Character.isHighSurrogate(array[midOneLess = (mid -1)])) { 3049 // If there is only one pair it cannot be split 3050 if (lo >= midOneLess) 3051 return null; 3052 // Shift the mid-point to align with the surrogate pair 3053 return new CodePointsSpliterator(array, lo, index = midOneLess, cs); 3054 } 3055 return new CodePointsSpliterator(array, lo, index = mid, cs); 3056 } 3057 3058 @Override 3059 public void forEachRemaining(IntConsumer action) { 3060 char[] a; int i, hi; // hoist accesses and checks from loop 3061 if (action == null) 3062 throw new NullPointerException(); 3063 if ((a = array).length >= (hi = fence) && 3064 (i = index) >= 0 && i < (index = hi)) { 3065 do { 3066 i = advance(a, i, hi, action); 3067 } while (i < hi); 3068 } 3069 } 3070 3071 @Override 3072 public boolean tryAdvance(IntConsumer action) { 3073 if (action == null) 3074 throw new NullPointerException(); 3075 if (index >= 0 && index < fence) { 3076 index = advance(array, index, fence, action); 3077 return true; 3078 } 3079 return false; 3080 } 3081 3082 // Advance one code point from the index, i, and return the next 3083 // index to advance from 3084 private static int advance(char[] a, int i, int hi, IntConsumer action) { 3085 char c1 = a[i++]; 3086 int cp = c1; 3087 if (Character.isHighSurrogate(c1) && i < hi) { 3088 char c2 = a[i]; 3089 if (Character.isLowSurrogate(c2)) { 3090 i++; 3091 cp = Character.toCodePoint(c1, c2); 3092 } 3093 } 3094 action.accept(cp); 3095 return i; 3096 } 3097 3098 @Override 3099 public long estimateSize() { return (long)(fence - index); } 3100 3101 @Override 3102 public int characteristics() { 3103 return cs; 3104 } 3105 } 3106 3107 /** 3108 * Returns a stream of code point values from this sequence. Any surrogate 3109 * pairs encountered in the sequence are combined as if by {@linkplain 3110 * Character#toCodePoint Character.toCodePoint} and the result is passed 3111 * to the stream. Any other code units, including ordinary BMP characters, 3112 * unpaired surrogates, and undefined code units, are zero-extended to 3113 * {@code int} values which are then passed to the stream. 3114 * 3115 * @return an IntStream of Unicode code points from this sequence 3116 * @since 1.9 3117 */ 3118 @Override 3119 public IntStream codePoints() { 3120 return StreamSupport.intStream( 3121 new CodePointsSpliterator(value, Spliterator.IMMUTABLE), false); 3122 } 3123 3124 /** 3125 * Converts this string to a new character array. 3126 * 3127 * @return a newly allocated character array whose length is the length 3128 * of this string and whose contents are initialized to contain 3129 * the character sequence represented by this string. 3130 */ 3131 public char[] toCharArray() { 3132 // Cannot use Arrays.copyOf because of class initialization order issues 3133 char[] result = new char[value.length]; 3134 System.arraycopy(value, 0, result, 0, value.length); 3135 return result; 3136 } 3137 3138 /** 3139 * Returns a formatted string using the specified format string and 3140 * arguments. 3141 * 3142 * <p> The locale always used is the one returned by {@link 3143 * java.util.Locale#getDefault() Locale.getDefault()}. 3144 * 3145 * @param format 3146 * A <a href="../util/Formatter.html#syntax">format string</a> 3147 * 3148 * @param args 3149 * Arguments referenced by the format specifiers in the format 3150 * string. If there are more arguments than format specifiers, the 3151 * extra arguments are ignored. The number of arguments is 3152 * variable and may be zero. The maximum number of arguments is 3153 * limited by the maximum dimension of a Java array as defined by 3154 * <cite>The Java™ Virtual Machine Specification</cite>. 3155 * The behaviour on a 3156 * {@code null} argument depends on the <a 3157 * href="../util/Formatter.html#syntax">conversion</a>. 3158 * 3159 * @throws java.util.IllegalFormatException 3160 * If a format string contains an illegal syntax, a format 3161 * specifier that is incompatible with the given arguments, 3162 * insufficient arguments given the format string, or other 3163 * illegal conditions. For specification of all possible 3164 * formatting errors, see the <a 3165 * href="../util/Formatter.html#detail">Details</a> section of the 3166 * formatter class specification. 3167 * 3168 * @return A formatted string 3169 * 3170 * @see java.util.Formatter 3171 * @since 1.5 3172 */ 3173 public static String format(String format, Object... args) { 3174 return new Formatter().format(format, args).toString(); 3175 } 3176 3177 /** 3178 * Returns a formatted string using the specified locale, format string, 3179 * and arguments. 3180 * 3181 * @param l 3182 * The {@linkplain java.util.Locale locale} to apply during 3183 * formatting. If {@code l} is {@code null} then no localization 3184 * is applied. 3185 * 3186 * @param format 3187 * A <a href="../util/Formatter.html#syntax">format string</a> 3188 * 3189 * @param args 3190 * Arguments referenced by the format specifiers in the format 3191 * string. If there are more arguments than format specifiers, the 3192 * extra arguments are ignored. The number of arguments is 3193 * variable and may be zero. The maximum number of arguments is 3194 * limited by the maximum dimension of a Java array as defined by 3195 * <cite>The Java™ Virtual Machine Specification</cite>. 3196 * The behaviour on a 3197 * {@code null} argument depends on the 3198 * <a href="../util/Formatter.html#syntax">conversion</a>. 3199 * 3200 * @throws java.util.IllegalFormatException 3201 * If a format string contains an illegal syntax, a format 3202 * specifier that is incompatible with the given arguments, 3203 * insufficient arguments given the format string, or other 3204 * illegal conditions. For specification of all possible 3205 * formatting errors, see the <a 3206 * href="../util/Formatter.html#detail">Details</a> section of the 3207 * formatter class specification 3208 * 3209 * @return A formatted string 3210 * 3211 * @see java.util.Formatter 3212 * @since 1.5 3213 */ 3214 public static String format(Locale l, String format, Object... args) { 3215 return new Formatter(l).format(format, args).toString(); 3216 } 3217 3218 /** 3219 * Returns the string representation of the {@code Object} argument. 3220 * 3221 * @param obj an {@code Object}. 3222 * @return if the argument is {@code null}, then a string equal to 3223 * {@code "null"}; otherwise, the value of 3224 * {@code obj.toString()} is returned. 3225 * @see java.lang.Object#toString() 3226 */ 3227 public static String valueOf(Object obj) { 3228 return (obj == null) ? "null" : obj.toString(); 3229 } 3230 3231 /** 3232 * Returns the string representation of the {@code char} array 3233 * argument. The contents of the character array are copied; subsequent 3234 * modification of the character array does not affect the returned 3235 * string. 3236 * 3237 * @param data the character array. 3238 * @return a {@code String} that contains the characters of the 3239 * character array. 3240 */ 3241 public static String valueOf(char data[]) { 3242 return new String(data); 3243 } 3244 3245 /** 3246 * Returns the string representation of a specific subarray of the 3247 * {@code char} array argument. 3248 * <p> 3249 * The {@code offset} argument is the index of the first 3250 * character of the subarray. The {@code count} argument 3251 * specifies the length of the subarray. The contents of the subarray 3252 * are copied; subsequent modification of the character array does not 3253 * affect the returned string. 3254 * 3255 * @param data the character array. 3256 * @param offset initial offset of the subarray. 3257 * @param count length of the subarray. 3258 * @return a {@code String} that contains the characters of the 3259 * specified subarray of the character array. 3260 * @exception IndexOutOfBoundsException if {@code offset} is 3261 * negative, or {@code count} is negative, or 3262 * {@code offset+count} is larger than 3263 * {@code data.length}. 3264 */ 3265 public static String valueOf(char data[], int offset, int count) { 3266 return new String(data, offset, count); 3267 } 3268 3269 /** 3270 * Equivalent to {@link #valueOf(char[], int, int)}. 3271 * 3272 * @param data the character array. 3273 * @param offset initial offset of the subarray. 3274 * @param count length of the subarray. 3275 * @return a {@code String} that contains the characters of the 3276 * specified subarray of the character array. 3277 * @exception IndexOutOfBoundsException if {@code offset} is 3278 * negative, or {@code count} is negative, or 3279 * {@code offset+count} is larger than 3280 * {@code data.length}. 3281 */ 3282 public static String copyValueOf(char data[], int offset, int count) { 3283 return new String(data, offset, count); 3284 } 3285 3286 /** 3287 * Equivalent to {@link #valueOf(char[])}. 3288 * 3289 * @param data the character array. 3290 * @return a {@code String} that contains the characters of the 3291 * character array. 3292 */ 3293 public static String copyValueOf(char data[]) { 3294 return new String(data); 3295 } 3296 3297 /** 3298 * Returns the string representation of the {@code boolean} argument. 3299 * 3300 * @param b a {@code boolean}. 3301 * @return if the argument is {@code true}, a string equal to 3302 * {@code "true"} is returned; otherwise, a string equal to 3303 * {@code "false"} is returned. 3304 */ 3305 public static String valueOf(boolean b) { 3306 return b ? "true" : "false"; 3307 } 3308 3309 /** 3310 * Returns the string representation of the {@code char} 3311 * argument. 3312 * 3313 * @param c a {@code char}. 3314 * @return a string of length {@code 1} containing 3315 * as its single character the argument {@code c}. 3316 */ 3317 public static String valueOf(char c) { 3318 return new String(new char[]{c}, true); 3319 } 3320 3321 /** 3322 * Returns the string representation of the {@code int} argument. 3323 * <p> 3324 * The representation is exactly the one returned by the 3325 * {@code Integer.toString} method of one argument. 3326 * 3327 * @param i an {@code int}. 3328 * @return a string representation of the {@code int} argument. 3329 * @see java.lang.Integer#toString(int, int) 3330 */ 3331 public static String valueOf(int i) { 3332 return Integer.toString(i); 3333 } 3334 3335 /** 3336 * Returns the string representation of the {@code long} argument. 3337 * <p> 3338 * The representation is exactly the one returned by the 3339 * {@code Long.toString} method of one argument. 3340 * 3341 * @param l a {@code long}. 3342 * @return a string representation of the {@code long} argument. 3343 * @see java.lang.Long#toString(long) 3344 */ 3345 public static String valueOf(long l) { 3346 return Long.toString(l); 3347 } 3348 3349 /** 3350 * Returns the string representation of the {@code float} argument. 3351 * <p> 3352 * The representation is exactly the one returned by the 3353 * {@code Float.toString} method of one argument. 3354 * 3355 * @param f a {@code float}. 3356 * @return a string representation of the {@code float} argument. 3357 * @see java.lang.Float#toString(float) 3358 */ 3359 public static String valueOf(float f) { 3360 return Float.toString(f); 3361 } 3362 3363 /** 3364 * Returns the string representation of the {@code double} argument. 3365 * <p> 3366 * The representation is exactly the one returned by the 3367 * {@code Double.toString} method of one argument. 3368 * 3369 * @param d a {@code double}. 3370 * @return a string representation of the {@code double} argument. 3371 * @see java.lang.Double#toString(double) 3372 */ 3373 public static String valueOf(double d) { 3374 return Double.toString(d); 3375 } 3376 3377 /** 3378 * Returns a canonical representation for the string object. 3379 * <p> 3380 * A pool of strings, initially empty, is maintained privately by the 3381 * class {@code String}. 3382 * <p> 3383 * When the intern method is invoked, if the pool already contains a 3384 * string equal to this {@code String} object as determined by 3385 * the {@link #equals(Object)} method, then the string from the pool is 3386 * returned. Otherwise, this {@code String} object is added to the 3387 * pool and a reference to this {@code String} object is returned. 3388 * <p> 3389 * It follows that for any two strings {@code s} and {@code t}, 3390 * {@code s.intern() == t.intern()} is {@code true} 3391 * if and only if {@code s.equals(t)} is {@code true}. 3392 * <p> 3393 * All literal strings and string-valued constant expressions are 3394 * interned. String literals are defined in section 3.10.5 of the 3395 * <cite>The Java™ Language Specification</cite>. 3396 * 3397 * @return a string that has the same contents as this string, but is 3398 * guaranteed to be from a pool of unique strings. 3399 */ 3400 public native String intern(); 3401 }