1 /* 2 * Copyright (c) 1994, 2020, 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.lang.annotation.Native; 31 import java.lang.invoke.MethodHandles; 32 import java.lang.constant.Constable; 33 import java.lang.constant.ConstantDesc; 34 import java.nio.charset.Charset; 35 import java.util.ArrayList; 36 import java.util.Arrays; 37 import java.util.Comparator; 38 import java.util.Formatter; 39 import java.util.List; 40 import java.util.Locale; 41 import java.util.Objects; 42 import java.util.Optional; 43 import java.util.Spliterator; 44 import java.util.StringJoiner; 45 import java.util.function.Function; 46 import java.util.regex.Matcher; 47 import java.util.regex.Pattern; 48 import java.util.regex.PatternSyntaxException; 49 import java.util.stream.Collectors; 50 import java.util.stream.IntStream; 51 import java.util.stream.Stream; 52 import java.util.stream.StreamSupport; 53 import jdk.internal.HotSpotIntrinsicCandidate; 54 import jdk.internal.vm.annotation.Stable; 55 56 import static java.util.function.Predicate.not; 57 58 /** 59 * The {@code String} class represents character strings. All 60 * string literals in Java programs, such as {@code "abc"}, are 61 * implemented as instances of this class. 62 * <p> 63 * Strings are constant; their values cannot be changed after they 64 * are created. String buffers support mutable strings. 65 * Because String objects are immutable they can be shared. For example: 66 * <blockquote><pre> 67 * String str = "abc"; 68 * </pre></blockquote><p> 69 * is equivalent to: 70 * <blockquote><pre> 71 * char data[] = {'a', 'b', 'c'}; 72 * String str = new String(data); 73 * </pre></blockquote><p> 74 * Here are some more examples of how strings can be used: 75 * <blockquote><pre> 76 * System.out.println("abc"); 77 * String cde = "cde"; 78 * System.out.println("abc" + cde); 79 * String c = "abc".substring(2, 3); 80 * String d = cde.substring(1, 2); 81 * </pre></blockquote> 82 * <p> 83 * The class {@code String} includes methods for examining 84 * individual characters of the sequence, for comparing strings, for 85 * searching strings, for extracting substrings, and for creating a 86 * copy of a string with all characters translated to uppercase or to 87 * lowercase. Case mapping is based on the Unicode Standard version 88 * specified by the {@link java.lang.Character Character} class. 89 * <p> 90 * The Java language provides special support for the string 91 * concatenation operator ( + ), and for conversion of 92 * other objects to strings. For additional information on string 93 * concatenation and conversion, see <i>The Java™ Language Specification</i>. 94 * 95 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor 96 * or method in this class will cause a {@link NullPointerException} to be 97 * thrown. 98 * 99 * <p>A {@code String} represents a string in the UTF-16 format 100 * in which <em>supplementary characters</em> are represented by <em>surrogate 101 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 102 * Character Representations</a> in the {@code Character} class for 103 * more information). 104 * Index values refer to {@code char} code units, so a supplementary 105 * character uses two positions in a {@code String}. 106 * <p>The {@code String} class provides methods for dealing with 107 * Unicode code points (i.e., characters), in addition to those for 108 * dealing with Unicode code units (i.e., {@code char} values). 109 * 110 * <p>Unless otherwise noted, methods for comparing Strings do not take locale 111 * into account. The {@link java.text.Collator} class provides methods for 112 * finer-grain, locale-sensitive String comparison. 113 * 114 * @implNote The implementation of the string concatenation operator is left to 115 * the discretion of a Java compiler, as long as the compiler ultimately conforms 116 * to <i>The Java™ Language Specification</i>. For example, the {@code javac} compiler 117 * may implement the operator with {@code StringBuffer}, {@code StringBuilder}, 118 * or {@code java.lang.invoke.StringConcatFactory} depending on the JDK version. The 119 * implementation of string conversion is typically through the method {@code toString}, 120 * defined by {@code Object} and inherited by all classes in Java. 121 * 122 * @author Lee Boynton 123 * @author Arthur van Hoff 124 * @author Martin Buchholz 125 * @author Ulf Zibis 126 * @see java.lang.Object#toString() 127 * @see java.lang.StringBuffer 128 * @see java.lang.StringBuilder 129 * @see java.nio.charset.Charset 130 * @since 1.0 131 * @jls 15.18.1 String Concatenation Operator + 132 */ 133 134 public final class String 135 implements java.io.Serializable, Comparable<String>, CharSequence, 136 Constable, ConstantDesc { 137 138 /** 139 * The value is used for character storage. 140 * 141 * @implNote This field is trusted by the VM, and is a subject to 142 * constant folding if String instance is constant. Overwriting this 143 * field after construction will cause problems. 144 * 145 * Additionally, it is marked with {@link Stable} to trust the contents 146 * of the array. No other facility in JDK provides this functionality (yet). 147 * {@link Stable} is safe here, because value is never null. 148 */ 149 @Stable 150 private final byte[] value; 151 152 /** 153 * The identifier of the encoding used to encode the bytes in 154 * {@code value}. The supported values in this implementation are 155 * 156 * LATIN1 157 * UTF16 158 * 159 * @implNote This field is trusted by the VM, and is a subject to 160 * constant folding if String instance is constant. Overwriting this 161 * field after construction will cause problems. 162 */ 163 private final byte coder; 164 165 /** Cache the hash code for the string */ 166 private int hash; // Default to 0 167 168 /** 169 * Cache if the hash has been calculated as actually being zero, enabling 170 * us to avoid recalculating this. 171 */ 172 private boolean hashIsZero; // Default to false; 173 174 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 175 @java.io.Serial 176 private static final long serialVersionUID = -6849794470754667710L; 177 178 /** 179 * If String compaction is disabled, the bytes in {@code value} are 180 * always encoded in UTF16. 181 * 182 * For methods with several possible implementation paths, when String 183 * compaction is disabled, only one code path is taken. 184 * 185 * The instance field value is generally opaque to optimizing JIT 186 * compilers. Therefore, in performance-sensitive place, an explicit 187 * check of the static boolean {@code COMPACT_STRINGS} is done first 188 * before checking the {@code coder} field since the static boolean 189 * {@code COMPACT_STRINGS} would be constant folded away by an 190 * optimizing JIT compiler. The idioms for these cases are as follows. 191 * 192 * For code such as: 193 * 194 * if (coder == LATIN1) { ... } 195 * 196 * can be written more optimally as 197 * 198 * if (coder() == LATIN1) { ... } 199 * 200 * or: 201 * 202 * if (COMPACT_STRINGS && coder == LATIN1) { ... } 203 * 204 * An optimizing JIT compiler can fold the above conditional as: 205 * 206 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... } 207 * COMPACT_STRINGS == false => if (false) { ... } 208 * 209 * @implNote 210 * The actual value for this field is injected by JVM. The static 211 * initialization block is used to set the value here to communicate 212 * that this static final field is not statically foldable, and to 213 * avoid any possible circular dependency during vm initialization. 214 */ 215 static final boolean COMPACT_STRINGS; 216 217 static { 218 COMPACT_STRINGS = true; 219 } 220 221 /** 222 * Class String is special cased within the Serialization Stream Protocol. 223 * 224 * A String instance is written into an ObjectOutputStream according to 225 * <a href="{@docRoot}/../specs/serialization/protocol.html#stream-elements"> 226 * Object Serialization Specification, Section 6.2, "Stream Elements"</a> 227 */ 228 @java.io.Serial 229 private static final ObjectStreamField[] serialPersistentFields = 230 new ObjectStreamField[0]; 231 232 /** 233 * Initializes a newly created {@code String} object so that it represents 234 * an empty character sequence. Note that use of this constructor is 235 * unnecessary since Strings are immutable. 236 */ 237 public String() { 238 this.value = "".value; 239 this.coder = "".coder; 240 } 241 242 /** 243 * Initializes a newly created {@code String} object so that it represents 244 * the same sequence of characters as the argument; in other words, the 245 * newly created string is a copy of the argument string. Unless an 246 * explicit copy of {@code original} is needed, use of this constructor is 247 * unnecessary since Strings are immutable. 248 * 249 * @param original 250 * A {@code String} 251 */ 252 @HotSpotIntrinsicCandidate 253 public String(String original) { 254 this.value = original.value; 255 this.coder = original.coder; 256 this.hash = original.hash; 257 } 258 259 /** 260 * Allocates a new {@code String} so that it represents the sequence of 261 * characters currently contained in the character array argument. The 262 * contents of the character array are copied; subsequent modification of 263 * the character array does not affect the newly created string. 264 * 265 * @param value 266 * The initial value of the string 267 */ 268 public String(char value[]) { 269 this(value, 0, value.length, null); 270 } 271 272 /** 273 * Allocates a new {@code String} that contains characters from a subarray 274 * of the character array argument. The {@code offset} argument is the 275 * index of the first character of the subarray and the {@code count} 276 * argument specifies the length of the subarray. The contents of the 277 * subarray are copied; subsequent modification of the character array does 278 * not affect the newly created string. 279 * 280 * @param value 281 * Array that is the source of characters 282 * 283 * @param offset 284 * The initial offset 285 * 286 * @param count 287 * The length 288 * 289 * @throws IndexOutOfBoundsException 290 * If {@code offset} is negative, {@code count} is negative, or 291 * {@code offset} is greater than {@code value.length - count} 292 */ 293 public String(char value[], int offset, int count) { 294 this(value, offset, count, rangeCheck(value, offset, count)); 295 } 296 297 private static Void rangeCheck(char[] value, int offset, int count) { 298 checkBoundsOffCount(offset, count, value.length); 299 return null; 300 } 301 302 /** 303 * Allocates a new {@code String} that contains characters from a subarray 304 * of the <a href="Character.html#unicode">Unicode code point</a> array 305 * argument. The {@code offset} argument is the index of the first code 306 * point of the subarray and the {@code count} argument specifies the 307 * length of the subarray. The contents of the subarray are converted to 308 * {@code char}s; subsequent modification of the {@code int} array does not 309 * affect the newly created string. 310 * 311 * @param codePoints 312 * Array that is the source of Unicode code points 313 * 314 * @param offset 315 * The initial offset 316 * 317 * @param count 318 * The length 319 * 320 * @throws IllegalArgumentException 321 * If any invalid Unicode code point is found in {@code 322 * codePoints} 323 * 324 * @throws IndexOutOfBoundsException 325 * If {@code offset} is negative, {@code count} is negative, or 326 * {@code offset} is greater than {@code codePoints.length - count} 327 * 328 * @since 1.5 329 */ 330 public String(int[] codePoints, int offset, int count) { 331 checkBoundsOffCount(offset, count, codePoints.length); 332 if (count == 0) { 333 this.value = "".value; 334 this.coder = "".coder; 335 return; 336 } 337 if (COMPACT_STRINGS) { 338 byte[] val = StringLatin1.toBytes(codePoints, offset, count); 339 if (val != null) { 340 this.coder = LATIN1; 341 this.value = val; 342 return; 343 } 344 } 345 this.coder = UTF16; 346 this.value = StringUTF16.toBytes(codePoints, offset, count); 347 } 348 349 /** 350 * Allocates a new {@code String} constructed from a subarray of an array 351 * of 8-bit integer values. 352 * 353 * <p> The {@code offset} argument is the index of the first byte of the 354 * subarray, and the {@code count} argument specifies the length of the 355 * subarray. 356 * 357 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 358 * specified in the {@link #String(byte[],int) String(byte[],int)} constructor. 359 * 360 * @deprecated This method does not properly convert bytes into characters. 361 * As of JDK 1.1, the preferred way to do this is via the 362 * {@code String} constructors that take a {@link 363 * java.nio.charset.Charset}, charset name, or that use the platform's 364 * default charset. 365 * 366 * @param ascii 367 * The bytes to be converted to characters 368 * 369 * @param hibyte 370 * The top 8 bits of each 16-bit Unicode code unit 371 * 372 * @param offset 373 * The initial offset 374 * @param count 375 * The length 376 * 377 * @throws IndexOutOfBoundsException 378 * If {@code offset} is negative, {@code count} is negative, or 379 * {@code offset} is greater than {@code ascii.length - count} 380 * 381 * @see #String(byte[], int) 382 * @see #String(byte[], int, int, java.lang.String) 383 * @see #String(byte[], int, int, java.nio.charset.Charset) 384 * @see #String(byte[], int, int) 385 * @see #String(byte[], java.lang.String) 386 * @see #String(byte[], java.nio.charset.Charset) 387 * @see #String(byte[]) 388 */ 389 @Deprecated(since="1.1") 390 public String(byte ascii[], int hibyte, int offset, int count) { 391 checkBoundsOffCount(offset, count, ascii.length); 392 if (count == 0) { 393 this.value = "".value; 394 this.coder = "".coder; 395 return; 396 } 397 if (COMPACT_STRINGS && (byte)hibyte == 0) { 398 this.value = Arrays.copyOfRange(ascii, offset, offset + count); 399 this.coder = LATIN1; 400 } else { 401 hibyte <<= 8; 402 byte[] val = StringUTF16.newBytesFor(count); 403 for (int i = 0; i < count; i++) { 404 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff)); 405 } 406 this.value = val; 407 this.coder = UTF16; 408 } 409 } 410 411 /** 412 * Allocates a new {@code String} containing characters constructed from 413 * an array of 8-bit integer values. Each character <i>c</i> in the 414 * resulting string is constructed from the corresponding component 415 * <i>b</i> in the byte array such that: 416 * 417 * <blockquote><pre> 418 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 419 * | (<b><i>b</i></b> & 0xff)) 420 * </pre></blockquote> 421 * 422 * @deprecated This method does not properly convert bytes into 423 * characters. As of JDK 1.1, the preferred way to do this is via the 424 * {@code String} constructors that take a {@link 425 * java.nio.charset.Charset}, charset name, or that use the platform's 426 * default charset. 427 * 428 * @param ascii 429 * The bytes to be converted to characters 430 * 431 * @param hibyte 432 * The top 8 bits of each 16-bit Unicode code unit 433 * 434 * @see #String(byte[], int, int, java.lang.String) 435 * @see #String(byte[], int, int, java.nio.charset.Charset) 436 * @see #String(byte[], int, int) 437 * @see #String(byte[], java.lang.String) 438 * @see #String(byte[], java.nio.charset.Charset) 439 * @see #String(byte[]) 440 */ 441 @Deprecated(since="1.1") 442 public String(byte ascii[], int hibyte) { 443 this(ascii, hibyte, 0, ascii.length); 444 } 445 446 /** 447 * Constructs a new {@code String} by decoding the specified subarray of 448 * bytes using the specified charset. The length of the new {@code String} 449 * is a function of the charset, and hence may not be equal to the length 450 * of the subarray. 451 * 452 * <p> The behavior of this constructor when the given bytes are not valid 453 * in the given charset is unspecified. The {@link 454 * java.nio.charset.CharsetDecoder} class should be used when more control 455 * over the decoding process is required. 456 * 457 * @param bytes 458 * The bytes to be decoded into characters 459 * 460 * @param offset 461 * The index of the first byte to decode 462 * 463 * @param length 464 * The number of bytes to decode 465 * 466 * @param charsetName 467 * The name of a supported {@linkplain java.nio.charset.Charset 468 * charset} 469 * 470 * @throws UnsupportedEncodingException 471 * If the named charset is not supported 472 * 473 * @throws IndexOutOfBoundsException 474 * If {@code offset} is negative, {@code length} is negative, or 475 * {@code offset} is greater than {@code bytes.length - length} 476 * 477 * @since 1.1 478 */ 479 public String(byte bytes[], int offset, int length, String charsetName) 480 throws UnsupportedEncodingException { 481 if (charsetName == null) 482 throw new NullPointerException("charsetName"); 483 checkBoundsOffCount(offset, length, bytes.length); 484 StringCoding.Result ret = 485 StringCoding.decode(charsetName, bytes, offset, length); 486 this.value = ret.value; 487 this.coder = ret.coder; 488 } 489 490 /** 491 * Constructs a new {@code String} by decoding the specified subarray of 492 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 493 * The length of the new {@code String} is a function of the charset, and 494 * hence may not be equal to the length of the subarray. 495 * 496 * <p> This method always replaces malformed-input and unmappable-character 497 * sequences with this charset's default replacement string. The {@link 498 * java.nio.charset.CharsetDecoder} class should be used when more control 499 * over the decoding process is required. 500 * 501 * @param bytes 502 * The bytes to be decoded into characters 503 * 504 * @param offset 505 * The index of the first byte to decode 506 * 507 * @param length 508 * The number of bytes to decode 509 * 510 * @param charset 511 * The {@linkplain java.nio.charset.Charset charset} to be used to 512 * decode the {@code bytes} 513 * 514 * @throws IndexOutOfBoundsException 515 * If {@code offset} is negative, {@code length} is negative, or 516 * {@code offset} is greater than {@code bytes.length - length} 517 * 518 * @since 1.6 519 */ 520 public String(byte bytes[], int offset, int length, Charset charset) { 521 if (charset == null) 522 throw new NullPointerException("charset"); 523 checkBoundsOffCount(offset, length, bytes.length); 524 StringCoding.Result ret = 525 StringCoding.decode(charset, bytes, offset, length); 526 this.value = ret.value; 527 this.coder = ret.coder; 528 } 529 530 /** 531 * Constructs a new {@code String} by decoding the specified array of bytes 532 * using the specified {@linkplain java.nio.charset.Charset charset}. The 533 * length of the new {@code String} is a function of the charset, and hence 534 * may not be equal to the length of the byte array. 535 * 536 * <p> The behavior of this constructor when the given bytes are not valid 537 * in the given charset is unspecified. The {@link 538 * java.nio.charset.CharsetDecoder} class should be used when more control 539 * over the decoding process is required. 540 * 541 * @param bytes 542 * The bytes to be decoded into characters 543 * 544 * @param charsetName 545 * The name of a supported {@linkplain java.nio.charset.Charset 546 * charset} 547 * 548 * @throws UnsupportedEncodingException 549 * If the named charset is not supported 550 * 551 * @since 1.1 552 */ 553 public String(byte bytes[], String charsetName) 554 throws UnsupportedEncodingException { 555 this(bytes, 0, bytes.length, charsetName); 556 } 557 558 /** 559 * Constructs a new {@code String} by decoding the specified array of 560 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 561 * The length of the new {@code String} is a function of the charset, and 562 * hence may not be equal to the length of the byte array. 563 * 564 * <p> This method always replaces malformed-input and unmappable-character 565 * sequences with this charset's default replacement string. The {@link 566 * java.nio.charset.CharsetDecoder} class should be used when more control 567 * over the decoding process is required. 568 * 569 * @param bytes 570 * The bytes to be decoded into characters 571 * 572 * @param charset 573 * The {@linkplain java.nio.charset.Charset charset} to be used to 574 * decode the {@code bytes} 575 * 576 * @since 1.6 577 */ 578 public String(byte bytes[], Charset charset) { 579 this(bytes, 0, bytes.length, charset); 580 } 581 582 /** 583 * Constructs a new {@code String} by decoding the specified subarray of 584 * bytes using the platform's default charset. The length of the new 585 * {@code String} is a function of the charset, and hence may not be equal 586 * to the length of the subarray. 587 * 588 * <p> The behavior of this constructor when the given bytes are not valid 589 * in the default charset is unspecified. The {@link 590 * java.nio.charset.CharsetDecoder} class should be used when more control 591 * over the decoding process is required. 592 * 593 * @param bytes 594 * The bytes to be decoded into characters 595 * 596 * @param offset 597 * The index of the first byte to decode 598 * 599 * @param length 600 * The number of bytes to decode 601 * 602 * @throws IndexOutOfBoundsException 603 * If {@code offset} is negative, {@code length} is negative, or 604 * {@code offset} is greater than {@code bytes.length - length} 605 * 606 * @since 1.1 607 */ 608 public String(byte bytes[], int offset, int length) { 609 checkBoundsOffCount(offset, length, bytes.length); 610 StringCoding.Result ret = StringCoding.decode(bytes, offset, length); 611 this.value = ret.value; 612 this.coder = ret.coder; 613 } 614 615 /** 616 * Constructs a new {@code String} by decoding the specified array of bytes 617 * using the platform's default charset. The length of the new {@code 618 * String} is a function of the charset, and hence may not be equal to the 619 * length of the byte array. 620 * 621 * <p> The behavior of this constructor when the given bytes are not valid 622 * in the default charset is unspecified. The {@link 623 * java.nio.charset.CharsetDecoder} class should be used when more control 624 * over the decoding process is required. 625 * 626 * @param bytes 627 * The bytes to be decoded into characters 628 * 629 * @since 1.1 630 */ 631 public String(byte[] bytes) { 632 this(bytes, 0, bytes.length); 633 } 634 635 /** 636 * Allocates a new string that contains the sequence of characters 637 * currently contained in the string buffer argument. The contents of the 638 * string buffer are copied; subsequent modification of the string buffer 639 * does not affect the newly created string. 640 * 641 * @param buffer 642 * A {@code StringBuffer} 643 */ 644 public String(StringBuffer buffer) { 645 this(buffer.toString()); 646 } 647 648 /** 649 * Allocates a new string that contains the sequence of characters 650 * currently contained in the string builder argument. The contents of the 651 * string builder are copied; subsequent modification of the string builder 652 * does not affect the newly created string. 653 * 654 * <p> This constructor is provided to ease migration to {@code 655 * StringBuilder}. Obtaining a string from a string builder via the {@code 656 * toString} method is likely to run faster and is generally preferred. 657 * 658 * @param builder 659 * A {@code StringBuilder} 660 * 661 * @since 1.5 662 */ 663 public String(StringBuilder builder) { 664 this(builder, null); 665 } 666 667 /** 668 * Returns the length of this string. 669 * The length is equal to the number of <a href="Character.html#unicode">Unicode 670 * code units</a> in the string. 671 * 672 * @return the length of the sequence of characters represented by this 673 * object. 674 */ 675 public int length() { 676 return value.length >> coder(); 677 } 678 679 /** 680 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 681 * 682 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 683 * {@code false} 684 * 685 * @since 1.6 686 */ 687 @Override 688 public boolean isEmpty() { 689 return value.length == 0; 690 } 691 692 /** 693 * Returns the {@code char} value at the 694 * specified index. An index ranges from {@code 0} to 695 * {@code length() - 1}. The first {@code char} value of the sequence 696 * is at index {@code 0}, the next at index {@code 1}, 697 * and so on, as for array indexing. 698 * 699 * <p>If the {@code char} value specified by the index is a 700 * <a href="Character.html#unicode">surrogate</a>, the surrogate 701 * value is returned. 702 * 703 * @param index the index of the {@code char} value. 704 * @return the {@code char} value at the specified index of this string. 705 * The first {@code char} value is at index {@code 0}. 706 * @throws IndexOutOfBoundsException if the {@code index} 707 * argument is negative or not less than the length of this 708 * string. 709 */ 710 public char charAt(int index) { 711 if (isLatin1()) { 712 return StringLatin1.charAt(value, index); 713 } else { 714 return StringUTF16.charAt(value, index); 715 } 716 } 717 718 /** 719 * Returns the character (Unicode code point) at the specified 720 * index. The index refers to {@code char} values 721 * (Unicode code units) and ranges from {@code 0} to 722 * {@link #length()}{@code - 1}. 723 * 724 * <p> If the {@code char} value specified at the given index 725 * is in the high-surrogate range, the following index is less 726 * than the length of this {@code String}, and the 727 * {@code char} value at the following index is in the 728 * low-surrogate range, then the supplementary code point 729 * corresponding to this surrogate pair is returned. Otherwise, 730 * the {@code char} value at the given index is returned. 731 * 732 * @param index the index to the {@code char} values 733 * @return the code point value of the character at the 734 * {@code index} 735 * @throws IndexOutOfBoundsException if the {@code index} 736 * argument is negative or not less than the length of this 737 * string. 738 * @since 1.5 739 */ 740 public int codePointAt(int index) { 741 if (isLatin1()) { 742 checkIndex(index, value.length); 743 return value[index] & 0xff; 744 } 745 int length = value.length >> 1; 746 checkIndex(index, length); 747 return StringUTF16.codePointAt(value, index, length); 748 } 749 750 /** 751 * Returns the character (Unicode code point) before the specified 752 * index. The index refers to {@code char} values 753 * (Unicode code units) and ranges from {@code 1} to {@link 754 * CharSequence#length() length}. 755 * 756 * <p> If the {@code char} value at {@code (index - 1)} 757 * is in the low-surrogate range, {@code (index - 2)} is not 758 * negative, and the {@code char} value at {@code (index - 759 * 2)} is in the high-surrogate range, then the 760 * supplementary code point value of the surrogate pair is 761 * returned. If the {@code char} value at {@code index - 762 * 1} is an unpaired low-surrogate or a high-surrogate, the 763 * surrogate value is returned. 764 * 765 * @param index the index following the code point that should be returned 766 * @return the Unicode code point value before the given index. 767 * @throws IndexOutOfBoundsException if the {@code index} 768 * argument is less than 1 or greater than the length 769 * of this string. 770 * @since 1.5 771 */ 772 public int codePointBefore(int index) { 773 int i = index - 1; 774 if (i < 0 || i >= length()) { 775 throw new StringIndexOutOfBoundsException(index); 776 } 777 if (isLatin1()) { 778 return (value[i] & 0xff); 779 } 780 return StringUTF16.codePointBefore(value, index); 781 } 782 783 /** 784 * Returns the number of Unicode code points in the specified text 785 * range of this {@code String}. The text range begins at the 786 * specified {@code beginIndex} and extends to the 787 * {@code char} at index {@code endIndex - 1}. Thus the 788 * length (in {@code char}s) of the text range is 789 * {@code endIndex-beginIndex}. Unpaired surrogates within 790 * the text range count as one code point each. 791 * 792 * @param beginIndex the index to the first {@code char} of 793 * the text range. 794 * @param endIndex the index after the last {@code char} of 795 * the text range. 796 * @return the number of Unicode code points in the specified text 797 * range 798 * @throws IndexOutOfBoundsException if the 799 * {@code beginIndex} is negative, or {@code endIndex} 800 * is larger than the length of this {@code String}, or 801 * {@code beginIndex} is larger than {@code endIndex}. 802 * @since 1.5 803 */ 804 public int codePointCount(int beginIndex, int endIndex) { 805 if (beginIndex < 0 || beginIndex > endIndex || 806 endIndex > length()) { 807 throw new IndexOutOfBoundsException(); 808 } 809 if (isLatin1()) { 810 return endIndex - beginIndex; 811 } 812 return StringUTF16.codePointCount(value, beginIndex, endIndex); 813 } 814 815 /** 816 * Returns the index within this {@code String} that is 817 * offset from the given {@code index} by 818 * {@code codePointOffset} code points. Unpaired surrogates 819 * within the text range given by {@code index} and 820 * {@code codePointOffset} count as one code point each. 821 * 822 * @param index the index to be offset 823 * @param codePointOffset the offset in code points 824 * @return the index within this {@code String} 825 * @throws IndexOutOfBoundsException if {@code index} 826 * is negative or larger then the length of this 827 * {@code String}, or if {@code codePointOffset} is positive 828 * and the substring starting with {@code index} has fewer 829 * than {@code codePointOffset} code points, 830 * or if {@code codePointOffset} is negative and the substring 831 * before {@code index} has fewer than the absolute value 832 * of {@code codePointOffset} code points. 833 * @since 1.5 834 */ 835 public int offsetByCodePoints(int index, int codePointOffset) { 836 if (index < 0 || index > length()) { 837 throw new IndexOutOfBoundsException(); 838 } 839 return Character.offsetByCodePoints(this, index, codePointOffset); 840 } 841 842 /** 843 * Copies characters from this string into the destination character 844 * array. 845 * <p> 846 * The first character to be copied is at index {@code srcBegin}; 847 * the last character to be copied is at index {@code srcEnd-1} 848 * (thus the total number of characters to be copied is 849 * {@code srcEnd-srcBegin}). The characters are copied into the 850 * subarray of {@code dst} starting at index {@code dstBegin} 851 * and ending at index: 852 * <blockquote><pre> 853 * dstBegin + (srcEnd-srcBegin) - 1 854 * </pre></blockquote> 855 * 856 * @param srcBegin index of the first character in the string 857 * to copy. 858 * @param srcEnd index after the last character in the string 859 * to copy. 860 * @param dst the destination array. 861 * @param dstBegin the start offset in the destination array. 862 * @throws IndexOutOfBoundsException If any of the following 863 * is true: 864 * <ul><li>{@code srcBegin} is negative. 865 * <li>{@code srcBegin} is greater than {@code srcEnd} 866 * <li>{@code srcEnd} is greater than the length of this 867 * string 868 * <li>{@code dstBegin} is negative 869 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 870 * {@code dst.length}</ul> 871 */ 872 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 873 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 874 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 875 if (isLatin1()) { 876 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin); 877 } else { 878 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin); 879 } 880 } 881 882 /** 883 * Copies characters from this string into the destination byte array. Each 884 * byte receives the 8 low-order bits of the corresponding character. The 885 * eight high-order bits of each character are not copied and do not 886 * participate in the transfer in any way. 887 * 888 * <p> The first character to be copied is at index {@code srcBegin}; the 889 * last character to be copied is at index {@code srcEnd-1}. The total 890 * number of characters to be copied is {@code srcEnd-srcBegin}. The 891 * characters, converted to bytes, are copied into the subarray of {@code 892 * dst} starting at index {@code dstBegin} and ending at index: 893 * 894 * <blockquote><pre> 895 * dstBegin + (srcEnd-srcBegin) - 1 896 * </pre></blockquote> 897 * 898 * @deprecated This method does not properly convert characters into 899 * bytes. As of JDK 1.1, the preferred way to do this is via the 900 * {@link #getBytes()} method, which uses the platform's default charset. 901 * 902 * @param srcBegin 903 * Index of the first character in the string to copy 904 * 905 * @param srcEnd 906 * Index after the last character in the string to copy 907 * 908 * @param dst 909 * The destination array 910 * 911 * @param dstBegin 912 * The start offset in the destination array 913 * 914 * @throws IndexOutOfBoundsException 915 * If any of the following is true: 916 * <ul> 917 * <li> {@code srcBegin} is negative 918 * <li> {@code srcBegin} is greater than {@code srcEnd} 919 * <li> {@code srcEnd} is greater than the length of this String 920 * <li> {@code dstBegin} is negative 921 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 922 * dst.length} 923 * </ul> 924 */ 925 @Deprecated(since="1.1") 926 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 927 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 928 Objects.requireNonNull(dst); 929 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 930 if (isLatin1()) { 931 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 932 } else { 933 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 934 } 935 } 936 937 /** 938 * Encodes this {@code String} into a sequence of bytes using the named 939 * charset, storing the result into a new byte array. 940 * 941 * <p> The behavior of this method when this string cannot be encoded in 942 * the given charset is unspecified. The {@link 943 * java.nio.charset.CharsetEncoder} class should be used when more control 944 * over the encoding process is required. 945 * 946 * @param charsetName 947 * The name of a supported {@linkplain java.nio.charset.Charset 948 * charset} 949 * 950 * @return The resultant byte array 951 * 952 * @throws UnsupportedEncodingException 953 * If the named charset is not supported 954 * 955 * @since 1.1 956 */ 957 public byte[] getBytes(String charsetName) 958 throws UnsupportedEncodingException { 959 if (charsetName == null) throw new NullPointerException(); 960 return StringCoding.encode(charsetName, coder(), value); 961 } 962 963 /** 964 * Encodes this {@code String} into a sequence of bytes using the given 965 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 966 * new byte array. 967 * 968 * <p> This method always replaces malformed-input and unmappable-character 969 * sequences with this charset's default replacement byte array. The 970 * {@link java.nio.charset.CharsetEncoder} class should be used when more 971 * control over the encoding process is required. 972 * 973 * @param charset 974 * The {@linkplain java.nio.charset.Charset} to be used to encode 975 * the {@code String} 976 * 977 * @return The resultant byte array 978 * 979 * @since 1.6 980 */ 981 public byte[] getBytes(Charset charset) { 982 if (charset == null) throw new NullPointerException(); 983 return StringCoding.encode(charset, coder(), value); 984 } 985 986 /** 987 * Encodes this {@code String} into a sequence of bytes using the 988 * platform's default charset, storing the result into a new byte array. 989 * 990 * <p> The behavior of this method when this string cannot be encoded in 991 * the default charset is unspecified. The {@link 992 * java.nio.charset.CharsetEncoder} class should be used when more control 993 * over the encoding process is required. 994 * 995 * @return The resultant byte array 996 * 997 * @since 1.1 998 */ 999 public byte[] getBytes() { 1000 return StringCoding.encode(coder(), value); 1001 } 1002 1003 /** 1004 * Compares this string to the specified object. The result is {@code 1005 * true} if and only if the argument is not {@code null} and is a {@code 1006 * String} object that represents the same sequence of characters as this 1007 * object. 1008 * 1009 * <p>For finer-grained String comparison, refer to 1010 * {@link java.text.Collator}. 1011 * 1012 * @param anObject 1013 * The object to compare this {@code String} against 1014 * 1015 * @return {@code true} if the given object represents a {@code String} 1016 * equivalent to this string, {@code false} otherwise 1017 * 1018 * @see #compareTo(String) 1019 * @see #equalsIgnoreCase(String) 1020 */ 1021 public boolean equals(Object anObject) { 1022 if (this == anObject) { 1023 return true; 1024 } 1025 if (anObject instanceof String) { 1026 String aString = (String)anObject; 1027 if (!COMPACT_STRINGS || this.coder == aString.coder) { 1028 return StringLatin1.equals(value, aString.value); 1029 } 1030 } 1031 return false; 1032 } 1033 1034 /** 1035 * Compares this string to the specified {@code StringBuffer}. The result 1036 * is {@code true} if and only if this {@code String} represents the same 1037 * sequence of characters as the specified {@code StringBuffer}. This method 1038 * synchronizes on the {@code StringBuffer}. 1039 * 1040 * <p>For finer-grained String comparison, refer to 1041 * {@link java.text.Collator}. 1042 * 1043 * @param sb 1044 * The {@code StringBuffer} to compare this {@code String} against 1045 * 1046 * @return {@code true} if this {@code String} represents the same 1047 * sequence of characters as the specified {@code StringBuffer}, 1048 * {@code false} otherwise 1049 * 1050 * @since 1.4 1051 */ 1052 public boolean contentEquals(StringBuffer sb) { 1053 return contentEquals((CharSequence)sb); 1054 } 1055 1056 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1057 int len = length(); 1058 if (len != sb.length()) { 1059 return false; 1060 } 1061 byte v1[] = value; 1062 byte v2[] = sb.getValue(); 1063 byte coder = coder(); 1064 if (coder == sb.getCoder()) { 1065 int n = v1.length; 1066 for (int i = 0; i < n; i++) { 1067 if (v1[i] != v2[i]) { 1068 return false; 1069 } 1070 } 1071 } else { 1072 if (coder != LATIN1) { // utf16 str and latin1 abs can never be "equal" 1073 return false; 1074 } 1075 return StringUTF16.contentEquals(v1, v2, len); 1076 } 1077 return true; 1078 } 1079 1080 /** 1081 * Compares this string to the specified {@code CharSequence}. The 1082 * result is {@code true} if and only if this {@code String} represents the 1083 * same sequence of char values as the specified sequence. Note that if the 1084 * {@code CharSequence} is a {@code StringBuffer} then the method 1085 * synchronizes on it. 1086 * 1087 * <p>For finer-grained String comparison, refer to 1088 * {@link java.text.Collator}. 1089 * 1090 * @param cs 1091 * The sequence to compare this {@code String} against 1092 * 1093 * @return {@code true} if this {@code String} represents the same 1094 * sequence of char values as the specified sequence, {@code 1095 * false} otherwise 1096 * 1097 * @since 1.5 1098 */ 1099 public boolean contentEquals(CharSequence cs) { 1100 // Argument is a StringBuffer, StringBuilder 1101 if (cs instanceof AbstractStringBuilder) { 1102 if (cs instanceof StringBuffer) { 1103 synchronized(cs) { 1104 return nonSyncContentEquals((AbstractStringBuilder)cs); 1105 } 1106 } else { 1107 return nonSyncContentEquals((AbstractStringBuilder)cs); 1108 } 1109 } 1110 // Argument is a String 1111 if (cs instanceof String) { 1112 return equals(cs); 1113 } 1114 // Argument is a generic CharSequence 1115 int n = cs.length(); 1116 if (n != length()) { 1117 return false; 1118 } 1119 byte[] val = this.value; 1120 if (isLatin1()) { 1121 for (int i = 0; i < n; i++) { 1122 if ((val[i] & 0xff) != cs.charAt(i)) { 1123 return false; 1124 } 1125 } 1126 } else { 1127 if (!StringUTF16.contentEquals(val, cs, n)) { 1128 return false; 1129 } 1130 } 1131 return true; 1132 } 1133 1134 /** 1135 * Compares this {@code String} to another {@code String}, ignoring case 1136 * considerations. Two strings are considered equal ignoring case if they 1137 * are of the same length and corresponding characters in the two strings 1138 * are equal ignoring case. 1139 * 1140 * <p> Two characters {@code c1} and {@code c2} are considered the same 1141 * ignoring case if at least one of the following is true: 1142 * <ul> 1143 * <li> The two characters are the same (as compared by the 1144 * {@code ==} operator) 1145 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))} 1146 * on each character produces the same result 1147 * </ul> 1148 * 1149 * <p>Note that this method does <em>not</em> take locale into account, and 1150 * will result in unsatisfactory results for certain locales. The 1151 * {@link java.text.Collator} class provides locale-sensitive comparison. 1152 * 1153 * @param anotherString 1154 * The {@code String} to compare this {@code String} against 1155 * 1156 * @return {@code true} if the argument is not {@code null} and it 1157 * represents an equivalent {@code String} ignoring case; {@code 1158 * false} otherwise 1159 * 1160 * @see #equals(Object) 1161 */ 1162 public boolean equalsIgnoreCase(String anotherString) { 1163 return (this == anotherString) ? true 1164 : (anotherString != null) 1165 && (anotherString.length() == length()) 1166 && regionMatches(true, 0, anotherString, 0, length()); 1167 } 1168 1169 /** 1170 * Compares two strings lexicographically. 1171 * The comparison is based on the Unicode value of each character in 1172 * the strings. The character sequence represented by this 1173 * {@code String} object is compared lexicographically to the 1174 * character sequence represented by the argument string. The result is 1175 * a negative integer if this {@code String} object 1176 * lexicographically precedes the argument string. The result is a 1177 * positive integer if this {@code String} object lexicographically 1178 * follows the argument string. The result is zero if the strings 1179 * are equal; {@code compareTo} returns {@code 0} exactly when 1180 * the {@link #equals(Object)} method would return {@code true}. 1181 * <p> 1182 * This is the definition of lexicographic ordering. If two strings are 1183 * different, then either they have different characters at some index 1184 * that is a valid index for both strings, or their lengths are different, 1185 * or both. If they have different characters at one or more index 1186 * positions, let <i>k</i> be the smallest such index; then the string 1187 * whose character at position <i>k</i> has the smaller value, as 1188 * determined by using the {@code <} operator, lexicographically precedes the 1189 * other string. In this case, {@code compareTo} returns the 1190 * difference of the two character values at position {@code k} in 1191 * the two string -- that is, the value: 1192 * <blockquote><pre> 1193 * this.charAt(k)-anotherString.charAt(k) 1194 * </pre></blockquote> 1195 * If there is no index position at which they differ, then the shorter 1196 * string lexicographically precedes the longer string. In this case, 1197 * {@code compareTo} returns the difference of the lengths of the 1198 * strings -- that is, the value: 1199 * <blockquote><pre> 1200 * this.length()-anotherString.length() 1201 * </pre></blockquote> 1202 * 1203 * <p>For finer-grained String comparison, refer to 1204 * {@link java.text.Collator}. 1205 * 1206 * @param anotherString the {@code String} to be compared. 1207 * @return the value {@code 0} if the argument string is equal to 1208 * this string; a value less than {@code 0} if this string 1209 * is lexicographically less than the string argument; and a 1210 * value greater than {@code 0} if this string is 1211 * lexicographically greater than the string argument. 1212 */ 1213 public int compareTo(String anotherString) { 1214 byte v1[] = value; 1215 byte v2[] = anotherString.value; 1216 byte coder = coder(); 1217 if (coder == anotherString.coder()) { 1218 return coder == LATIN1 ? StringLatin1.compareTo(v1, v2) 1219 : StringUTF16.compareTo(v1, v2); 1220 } 1221 return coder == LATIN1 ? StringLatin1.compareToUTF16(v1, v2) 1222 : StringUTF16.compareToLatin1(v1, v2); 1223 } 1224 1225 /** 1226 * A Comparator that orders {@code String} objects as by 1227 * {@code compareToIgnoreCase}. This comparator is serializable. 1228 * <p> 1229 * Note that this Comparator does <em>not</em> take locale into account, 1230 * and will result in an unsatisfactory ordering for certain locales. 1231 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1232 * 1233 * @see java.text.Collator 1234 * @since 1.2 1235 */ 1236 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1237 = new CaseInsensitiveComparator(); 1238 private static class CaseInsensitiveComparator 1239 implements Comparator<String>, java.io.Serializable { 1240 // use serialVersionUID from JDK 1.2.2 for interoperability 1241 @java.io.Serial 1242 private static final long serialVersionUID = 8575799808933029326L; 1243 1244 public int compare(String s1, String s2) { 1245 byte v1[] = s1.value; 1246 byte v2[] = s2.value; 1247 byte coder = s1.coder(); 1248 if (coder == s2.coder()) { 1249 return coder == LATIN1 ? StringLatin1.compareToCI(v1, v2) 1250 : StringUTF16.compareToCI(v1, v2); 1251 } 1252 return coder == LATIN1 ? StringLatin1.compareToCI_UTF16(v1, v2) 1253 : StringUTF16.compareToCI_Latin1(v1, v2); 1254 } 1255 1256 /** Replaces the de-serialized object. */ 1257 @java.io.Serial 1258 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1259 } 1260 1261 /** 1262 * Compares two strings lexicographically, ignoring case 1263 * differences. This method returns an integer whose sign is that of 1264 * calling {@code compareTo} with normalized versions of the strings 1265 * where case differences have been eliminated by calling 1266 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1267 * each character. 1268 * <p> 1269 * Note that this method does <em>not</em> take locale into account, 1270 * and will result in an unsatisfactory ordering for certain locales. 1271 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1272 * 1273 * @param str the {@code String} to be compared. 1274 * @return a negative integer, zero, or a positive integer as the 1275 * specified String is greater than, equal to, or less 1276 * than this String, ignoring case considerations. 1277 * @see java.text.Collator 1278 * @since 1.2 1279 */ 1280 public int compareToIgnoreCase(String str) { 1281 return CASE_INSENSITIVE_ORDER.compare(this, str); 1282 } 1283 1284 /** 1285 * Tests if two string regions are equal. 1286 * <p> 1287 * A substring of this {@code String} object is compared to a substring 1288 * of the argument other. The result is true if these substrings 1289 * represent identical character sequences. The substring of this 1290 * {@code String} object to be compared begins at index {@code toffset} 1291 * and has length {@code len}. The substring of other to be compared 1292 * begins at index {@code ooffset} and has length {@code len}. The 1293 * result is {@code false} if and only if at least one of the following 1294 * is true: 1295 * <ul><li>{@code toffset} is negative. 1296 * <li>{@code ooffset} is negative. 1297 * <li>{@code toffset+len} is greater than the length of this 1298 * {@code String} object. 1299 * <li>{@code ooffset+len} is greater than the length of the other 1300 * argument. 1301 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1302 * such that: 1303 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1304 * <i>k</i>{@code )} 1305 * </ul> 1306 * 1307 * <p>Note that this method does <em>not</em> take locale into account. The 1308 * {@link java.text.Collator} class provides locale-sensitive comparison. 1309 * 1310 * @param toffset the starting offset of the subregion in this string. 1311 * @param other the string argument. 1312 * @param ooffset the starting offset of the subregion in the string 1313 * argument. 1314 * @param len the number of characters to compare. 1315 * @return {@code true} if the specified subregion of this string 1316 * exactly matches the specified subregion of the string argument; 1317 * {@code false} otherwise. 1318 */ 1319 public boolean regionMatches(int toffset, String other, int ooffset, int len) { 1320 byte tv[] = value; 1321 byte ov[] = other.value; 1322 // Note: toffset, ooffset, or len might be near -1>>>1. 1323 if ((ooffset < 0) || (toffset < 0) || 1324 (toffset > (long)length() - len) || 1325 (ooffset > (long)other.length() - len)) { 1326 return false; 1327 } 1328 byte coder = coder(); 1329 if (coder == other.coder()) { 1330 if (!isLatin1() && (len > 0)) { 1331 toffset = toffset << 1; 1332 ooffset = ooffset << 1; 1333 len = len << 1; 1334 } 1335 while (len-- > 0) { 1336 if (tv[toffset++] != ov[ooffset++]) { 1337 return false; 1338 } 1339 } 1340 } else { 1341 if (coder == LATIN1) { 1342 while (len-- > 0) { 1343 if (StringLatin1.getChar(tv, toffset++) != 1344 StringUTF16.getChar(ov, ooffset++)) { 1345 return false; 1346 } 1347 } 1348 } else { 1349 while (len-- > 0) { 1350 if (StringUTF16.getChar(tv, toffset++) != 1351 StringLatin1.getChar(ov, ooffset++)) { 1352 return false; 1353 } 1354 } 1355 } 1356 } 1357 return true; 1358 } 1359 1360 /** 1361 * Tests if two string regions are equal. 1362 * <p> 1363 * A substring of this {@code String} object is compared to a substring 1364 * of the argument {@code other}. The result is {@code true} if these 1365 * substrings represent character sequences that are the same, ignoring 1366 * case if and only if {@code ignoreCase} is true. The substring of 1367 * this {@code String} object to be compared begins at index 1368 * {@code toffset} and has length {@code len}. The substring of 1369 * {@code other} to be compared begins at index {@code ooffset} and 1370 * has length {@code len}. The result is {@code false} if and only if 1371 * at least one of the following is true: 1372 * <ul><li>{@code toffset} is negative. 1373 * <li>{@code ooffset} is negative. 1374 * <li>{@code toffset+len} is greater than the length of this 1375 * {@code String} object. 1376 * <li>{@code ooffset+len} is greater than the length of the other 1377 * argument. 1378 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1379 * integer <i>k</i> less than {@code len} such that: 1380 * <blockquote><pre> 1381 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1382 * </pre></blockquote> 1383 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1384 * integer <i>k</i> less than {@code len} such that: 1385 * <blockquote><pre> 1386 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) != 1387 * Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k))) 1388 * </pre></blockquote> 1389 * </ul> 1390 * 1391 * <p>Note that this method does <em>not</em> take locale into account, 1392 * and will result in unsatisfactory results for certain locales when 1393 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class 1394 * provides locale-sensitive comparison. 1395 * 1396 * @param ignoreCase if {@code true}, ignore case when comparing 1397 * characters. 1398 * @param toffset the starting offset of the subregion in this 1399 * string. 1400 * @param other the string argument. 1401 * @param ooffset the starting offset of the subregion in the string 1402 * argument. 1403 * @param len the number of characters to compare. 1404 * @return {@code true} if the specified subregion of this string 1405 * matches the specified subregion of the string argument; 1406 * {@code false} otherwise. Whether the matching is exact 1407 * or case insensitive depends on the {@code ignoreCase} 1408 * argument. 1409 */ 1410 public boolean regionMatches(boolean ignoreCase, int toffset, 1411 String other, int ooffset, int len) { 1412 if (!ignoreCase) { 1413 return regionMatches(toffset, other, ooffset, len); 1414 } 1415 // Note: toffset, ooffset, or len might be near -1>>>1. 1416 if ((ooffset < 0) || (toffset < 0) 1417 || (toffset > (long)length() - len) 1418 || (ooffset > (long)other.length() - len)) { 1419 return false; 1420 } 1421 byte tv[] = value; 1422 byte ov[] = other.value; 1423 byte coder = coder(); 1424 if (coder == other.coder()) { 1425 return coder == LATIN1 1426 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len) 1427 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len); 1428 } 1429 return coder == LATIN1 1430 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len) 1431 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len); 1432 } 1433 1434 /** 1435 * Tests if the substring of this string beginning at the 1436 * specified index starts with the specified prefix. 1437 * 1438 * @param prefix the prefix. 1439 * @param toffset where to begin looking in this string. 1440 * @return {@code true} if the character sequence represented by the 1441 * argument is a prefix of the substring of this object starting 1442 * at index {@code toffset}; {@code false} otherwise. 1443 * The result is {@code false} if {@code toffset} is 1444 * negative or greater than the length of this 1445 * {@code String} object; otherwise the result is the same 1446 * as the result of the expression 1447 * <pre> 1448 * this.substring(toffset).startsWith(prefix) 1449 * </pre> 1450 */ 1451 public boolean startsWith(String prefix, int toffset) { 1452 // Note: toffset might be near -1>>>1. 1453 if (toffset < 0 || toffset > length() - prefix.length()) { 1454 return false; 1455 } 1456 byte ta[] = value; 1457 byte pa[] = prefix.value; 1458 int po = 0; 1459 int pc = pa.length; 1460 byte coder = coder(); 1461 if (coder == prefix.coder()) { 1462 int to = (coder == LATIN1) ? toffset : toffset << 1; 1463 while (po < pc) { 1464 if (ta[to++] != pa[po++]) { 1465 return false; 1466 } 1467 } 1468 } else { 1469 if (coder == LATIN1) { // && pcoder == UTF16 1470 return false; 1471 } 1472 // coder == UTF16 && pcoder == LATIN1) 1473 while (po < pc) { 1474 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) { 1475 return false; 1476 } 1477 } 1478 } 1479 return true; 1480 } 1481 1482 /** 1483 * Tests if this string starts with the specified prefix. 1484 * 1485 * @param prefix the prefix. 1486 * @return {@code true} if the character sequence represented by the 1487 * argument is a prefix of the character sequence represented by 1488 * this string; {@code false} otherwise. 1489 * Note also that {@code true} will be returned if the 1490 * argument is an empty string or is equal to this 1491 * {@code String} object as determined by the 1492 * {@link #equals(Object)} method. 1493 * @since 1.0 1494 */ 1495 public boolean startsWith(String prefix) { 1496 return startsWith(prefix, 0); 1497 } 1498 1499 /** 1500 * Tests if this string ends with the specified suffix. 1501 * 1502 * @param suffix the suffix. 1503 * @return {@code true} if the character sequence represented by the 1504 * argument is a suffix of the character sequence represented by 1505 * this object; {@code false} otherwise. Note that the 1506 * result will be {@code true} if the argument is the 1507 * empty string or is equal to this {@code String} object 1508 * as determined by the {@link #equals(Object)} method. 1509 */ 1510 public boolean endsWith(String suffix) { 1511 return startsWith(suffix, length() - suffix.length()); 1512 } 1513 1514 /** 1515 * Returns a hash code for this string. The hash code for a 1516 * {@code String} object is computed as 1517 * <blockquote><pre> 1518 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1519 * </pre></blockquote> 1520 * using {@code int} arithmetic, where {@code s[i]} is the 1521 * <i>i</i>th character of the string, {@code n} is the length of 1522 * the string, and {@code ^} indicates exponentiation. 1523 * (The hash value of the empty string is zero.) 1524 * 1525 * @return a hash code value for this object. 1526 */ 1527 public int hashCode() { 1528 // The hash or hashIsZero fields are subject to a benign data race, 1529 // making it crucial to ensure that any observable result of the 1530 // calculation in this method stays correct under any possible read of 1531 // these fields. Necessary restrictions to allow this to be correct 1532 // without explicit memory fences or similar concurrency primitives is 1533 // that we can ever only write to one of these two fields for a given 1534 // String instance, and that the computation is idempotent and derived 1535 // from immutable state 1536 int h = hash; 1537 if (h == 0 && !hashIsZero) { 1538 h = isLatin1() ? StringLatin1.hashCode(value) 1539 : StringUTF16.hashCode(value); 1540 if (h == 0) { 1541 hashIsZero = true; 1542 } else { 1543 hash = h; 1544 } 1545 } 1546 return h; 1547 } 1548 1549 /** 1550 * Returns the index within this string of the first occurrence of 1551 * the specified character. If a character with value 1552 * {@code ch} occurs in the character sequence represented by 1553 * this {@code String} object, then the index (in Unicode 1554 * code units) of the first such occurrence is returned. For 1555 * values of {@code ch} in the range from 0 to 0xFFFF 1556 * (inclusive), this is the smallest value <i>k</i> such that: 1557 * <blockquote><pre> 1558 * this.charAt(<i>k</i>) == ch 1559 * </pre></blockquote> 1560 * is true. For other values of {@code ch}, it is the 1561 * smallest value <i>k</i> such that: 1562 * <blockquote><pre> 1563 * this.codePointAt(<i>k</i>) == ch 1564 * </pre></blockquote> 1565 * is true. In either case, if no such character occurs in this 1566 * string, then {@code -1} is returned. 1567 * 1568 * @param ch a character (Unicode code point). 1569 * @return the index of the first occurrence of the character in the 1570 * character sequence represented by this object, or 1571 * {@code -1} if the character does not occur. 1572 */ 1573 public int indexOf(int ch) { 1574 return indexOf(ch, 0); 1575 } 1576 1577 /** 1578 * Returns the index within this string of the first occurrence of the 1579 * specified character, starting the search at the specified index. 1580 * <p> 1581 * If a character with value {@code ch} occurs in the 1582 * character sequence represented by this {@code String} 1583 * object at an index no smaller than {@code fromIndex}, then 1584 * the index of the first such occurrence is returned. For values 1585 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1586 * this is the smallest value <i>k</i> such that: 1587 * <blockquote><pre> 1588 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1589 * </pre></blockquote> 1590 * is true. For other values of {@code ch}, it is the 1591 * smallest value <i>k</i> such that: 1592 * <blockquote><pre> 1593 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1594 * </pre></blockquote> 1595 * is true. In either case, if no such character occurs in this 1596 * string at or after position {@code fromIndex}, then 1597 * {@code -1} is returned. 1598 * 1599 * <p> 1600 * There is no restriction on the value of {@code fromIndex}. If it 1601 * is negative, it has the same effect as if it were zero: this entire 1602 * string may be searched. If it is greater than the length of this 1603 * string, it has the same effect as if it were equal to the length of 1604 * this string: {@code -1} is returned. 1605 * 1606 * <p>All indices are specified in {@code char} values 1607 * (Unicode code units). 1608 * 1609 * @param ch a character (Unicode code point). 1610 * @param fromIndex the index to start the search from. 1611 * @return the index of the first occurrence of the character in the 1612 * character sequence represented by this object that is greater 1613 * than or equal to {@code fromIndex}, or {@code -1} 1614 * if the character does not occur. 1615 */ 1616 public int indexOf(int ch, int fromIndex) { 1617 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex) 1618 : StringUTF16.indexOf(value, ch, fromIndex); 1619 } 1620 1621 /** 1622 * Returns the index within this string of the last occurrence of 1623 * the specified character. For values of {@code ch} in the 1624 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1625 * units) returned is the largest value <i>k</i> such that: 1626 * <blockquote><pre> 1627 * this.charAt(<i>k</i>) == ch 1628 * </pre></blockquote> 1629 * is true. For other values of {@code ch}, it is the 1630 * largest value <i>k</i> such that: 1631 * <blockquote><pre> 1632 * this.codePointAt(<i>k</i>) == ch 1633 * </pre></blockquote> 1634 * is true. In either case, if no such character occurs in this 1635 * string, then {@code -1} is returned. The 1636 * {@code String} is searched backwards starting at the last 1637 * character. 1638 * 1639 * @param ch a character (Unicode code point). 1640 * @return the index of the last occurrence of the character in the 1641 * character sequence represented by this object, or 1642 * {@code -1} if the character does not occur. 1643 */ 1644 public int lastIndexOf(int ch) { 1645 return lastIndexOf(ch, length() - 1); 1646 } 1647 1648 /** 1649 * Returns the index within this string of the last occurrence of 1650 * the specified character, searching backward starting at the 1651 * specified index. For values of {@code ch} in the range 1652 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1653 * value <i>k</i> such that: 1654 * <blockquote><pre> 1655 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1656 * </pre></blockquote> 1657 * is true. For other values of {@code ch}, it is the 1658 * largest value <i>k</i> such that: 1659 * <blockquote><pre> 1660 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1661 * </pre></blockquote> 1662 * is true. In either case, if no such character occurs in this 1663 * string at or before position {@code fromIndex}, then 1664 * {@code -1} is returned. 1665 * 1666 * <p>All indices are specified in {@code char} values 1667 * (Unicode code units). 1668 * 1669 * @param ch a character (Unicode code point). 1670 * @param fromIndex the index to start the search from. There is no 1671 * restriction on the value of {@code fromIndex}. If it is 1672 * greater than or equal to the length of this string, it has 1673 * the same effect as if it were equal to one less than the 1674 * length of this string: this entire string may be searched. 1675 * If it is negative, it has the same effect as if it were -1: 1676 * -1 is returned. 1677 * @return the index of the last occurrence of the character in the 1678 * character sequence represented by this object that is less 1679 * than or equal to {@code fromIndex}, or {@code -1} 1680 * if the character does not occur before that point. 1681 */ 1682 public int lastIndexOf(int ch, int fromIndex) { 1683 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex) 1684 : StringUTF16.lastIndexOf(value, ch, fromIndex); 1685 } 1686 1687 /** 1688 * Returns the index within this string of the first occurrence of the 1689 * specified substring. 1690 * 1691 * <p>The returned index is the smallest value {@code k} for which: 1692 * <pre>{@code 1693 * this.startsWith(str, k) 1694 * }</pre> 1695 * If no such value of {@code k} exists, then {@code -1} is returned. 1696 * 1697 * @param str the substring to search for. 1698 * @return the index of the first occurrence of the specified substring, 1699 * or {@code -1} if there is no such occurrence. 1700 */ 1701 public int indexOf(String str) { 1702 byte coder = coder(); 1703 if (coder == str.coder()) { 1704 return isLatin1() ? StringLatin1.indexOf(value, str.value) 1705 : StringUTF16.indexOf(value, str.value); 1706 } 1707 if (coder == LATIN1) { // str.coder == UTF16 1708 return -1; 1709 } 1710 return StringUTF16.indexOfLatin1(value, str.value); 1711 } 1712 1713 /** 1714 * Returns the index within this string of the first occurrence of the 1715 * specified substring, starting at the specified index. 1716 * 1717 * <p>The returned index is the smallest value {@code k} for which: 1718 * <pre>{@code 1719 * k >= Math.min(fromIndex, this.length()) && 1720 * this.startsWith(str, k) 1721 * }</pre> 1722 * If no such value of {@code k} exists, then {@code -1} is returned. 1723 * 1724 * @param str the substring to search for. 1725 * @param fromIndex the index from which to start the search. 1726 * @return the index of the first occurrence of the specified substring, 1727 * starting at the specified index, 1728 * or {@code -1} if there is no such occurrence. 1729 */ 1730 public int indexOf(String str, int fromIndex) { 1731 return indexOf(value, coder(), length(), str, fromIndex); 1732 } 1733 1734 /** 1735 * Code shared by String and AbstractStringBuilder to do searches. The 1736 * source is the character array being searched, and the target 1737 * is the string being searched for. 1738 * 1739 * @param src the characters being searched. 1740 * @param srcCoder the coder of the source string. 1741 * @param srcCount length of the source string. 1742 * @param tgtStr the characters being searched for. 1743 * @param fromIndex the index to begin searching from. 1744 */ 1745 static int indexOf(byte[] src, byte srcCoder, int srcCount, 1746 String tgtStr, int fromIndex) { 1747 byte[] tgt = tgtStr.value; 1748 byte tgtCoder = tgtStr.coder(); 1749 int tgtCount = tgtStr.length(); 1750 1751 if (fromIndex >= srcCount) { 1752 return (tgtCount == 0 ? srcCount : -1); 1753 } 1754 if (fromIndex < 0) { 1755 fromIndex = 0; 1756 } 1757 if (tgtCount == 0) { 1758 return fromIndex; 1759 } 1760 if (tgtCount > srcCount) { 1761 return -1; 1762 } 1763 if (srcCoder == tgtCoder) { 1764 return srcCoder == LATIN1 1765 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex) 1766 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex); 1767 } 1768 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1769 return -1; 1770 } 1771 // srcCoder == UTF16 && tgtCoder == LATIN1) { 1772 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex); 1773 } 1774 1775 /** 1776 * Returns the index within this string of the last occurrence of the 1777 * specified substring. The last occurrence of the empty string "" 1778 * is considered to occur at the index value {@code this.length()}. 1779 * 1780 * <p>The returned index is the largest value {@code k} for which: 1781 * <pre>{@code 1782 * this.startsWith(str, k) 1783 * }</pre> 1784 * If no such value of {@code k} exists, then {@code -1} is returned. 1785 * 1786 * @param str the substring to search for. 1787 * @return the index of the last occurrence of the specified substring, 1788 * or {@code -1} if there is no such occurrence. 1789 */ 1790 public int lastIndexOf(String str) { 1791 return lastIndexOf(str, length()); 1792 } 1793 1794 /** 1795 * Returns the index within this string of the last occurrence of the 1796 * specified substring, searching backward starting at the specified index. 1797 * 1798 * <p>The returned index is the largest value {@code k} for which: 1799 * <pre>{@code 1800 * k <= Math.min(fromIndex, this.length()) && 1801 * this.startsWith(str, k) 1802 * }</pre> 1803 * If no such value of {@code k} exists, then {@code -1} is returned. 1804 * 1805 * @param str the substring to search for. 1806 * @param fromIndex the index to start the search from. 1807 * @return the index of the last occurrence of the specified substring, 1808 * searching backward from the specified index, 1809 * or {@code -1} if there is no such occurrence. 1810 */ 1811 public int lastIndexOf(String str, int fromIndex) { 1812 return lastIndexOf(value, coder(), length(), str, fromIndex); 1813 } 1814 1815 /** 1816 * Code shared by String and AbstractStringBuilder to do searches. The 1817 * source is the character array being searched, and the target 1818 * is the string being searched for. 1819 * 1820 * @param src the characters being searched. 1821 * @param srcCoder coder handles the mapping between bytes/chars 1822 * @param srcCount count of the source string. 1823 * @param tgtStr the characters being searched for. 1824 * @param fromIndex the index to begin searching from. 1825 */ 1826 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount, 1827 String tgtStr, int fromIndex) { 1828 byte[] tgt = tgtStr.value; 1829 byte tgtCoder = tgtStr.coder(); 1830 int tgtCount = tgtStr.length(); 1831 /* 1832 * Check arguments; return immediately where possible. For 1833 * consistency, don't check for null str. 1834 */ 1835 int rightIndex = srcCount - tgtCount; 1836 if (fromIndex > rightIndex) { 1837 fromIndex = rightIndex; 1838 } 1839 if (fromIndex < 0) { 1840 return -1; 1841 } 1842 /* Empty string always matches. */ 1843 if (tgtCount == 0) { 1844 return fromIndex; 1845 } 1846 if (srcCoder == tgtCoder) { 1847 return srcCoder == LATIN1 1848 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex) 1849 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex); 1850 } 1851 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1852 return -1; 1853 } 1854 // srcCoder == UTF16 && tgtCoder == LATIN1 1855 return StringUTF16.lastIndexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex); 1856 } 1857 1858 /** 1859 * Returns a string that is a substring of this string. The 1860 * substring begins with the character at the specified index and 1861 * extends to the end of this string. <p> 1862 * Examples: 1863 * <blockquote><pre> 1864 * "unhappy".substring(2) returns "happy" 1865 * "Harbison".substring(3) returns "bison" 1866 * "emptiness".substring(9) returns "" (an empty string) 1867 * </pre></blockquote> 1868 * 1869 * @param beginIndex the beginning index, inclusive. 1870 * @return the specified substring. 1871 * @throws IndexOutOfBoundsException if 1872 * {@code beginIndex} is negative or larger than the 1873 * length of this {@code String} object. 1874 */ 1875 public String substring(int beginIndex) { 1876 return substring(beginIndex, length()); 1877 } 1878 1879 /** 1880 * Returns a string that is a substring of this string. The 1881 * substring begins at the specified {@code beginIndex} and 1882 * extends to the character at index {@code endIndex - 1}. 1883 * Thus the length of the substring is {@code endIndex-beginIndex}. 1884 * <p> 1885 * Examples: 1886 * <blockquote><pre> 1887 * "hamburger".substring(4, 8) returns "urge" 1888 * "smiles".substring(1, 5) returns "mile" 1889 * </pre></blockquote> 1890 * 1891 * @param beginIndex the beginning index, inclusive. 1892 * @param endIndex the ending index, exclusive. 1893 * @return the specified substring. 1894 * @throws IndexOutOfBoundsException if the 1895 * {@code beginIndex} is negative, or 1896 * {@code endIndex} is larger than the length of 1897 * this {@code String} object, or 1898 * {@code beginIndex} is larger than 1899 * {@code endIndex}. 1900 */ 1901 public String substring(int beginIndex, int endIndex) { 1902 int length = length(); 1903 checkBoundsBeginEnd(beginIndex, endIndex, length); 1904 if (beginIndex == 0 && endIndex == length) { 1905 return this; 1906 } 1907 int subLen = endIndex - beginIndex; 1908 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1909 : StringUTF16.newString(value, beginIndex, subLen); 1910 } 1911 1912 /** 1913 * Returns a character sequence that is a subsequence of this sequence. 1914 * 1915 * <p> An invocation of this method of the form 1916 * 1917 * <blockquote><pre> 1918 * str.subSequence(begin, end)</pre></blockquote> 1919 * 1920 * behaves in exactly the same way as the invocation 1921 * 1922 * <blockquote><pre> 1923 * str.substring(begin, end)</pre></blockquote> 1924 * 1925 * @apiNote 1926 * This method is defined so that the {@code String} class can implement 1927 * the {@link CharSequence} interface. 1928 * 1929 * @param beginIndex the begin index, inclusive. 1930 * @param endIndex the end index, exclusive. 1931 * @return the specified subsequence. 1932 * 1933 * @throws IndexOutOfBoundsException 1934 * if {@code beginIndex} or {@code endIndex} is negative, 1935 * if {@code endIndex} is greater than {@code length()}, 1936 * or if {@code beginIndex} is greater than {@code endIndex} 1937 * 1938 * @since 1.4 1939 * @spec JSR-51 1940 */ 1941 public CharSequence subSequence(int beginIndex, int endIndex) { 1942 return this.substring(beginIndex, endIndex); 1943 } 1944 1945 /** 1946 * Concatenates the specified string to the end of this string. 1947 * <p> 1948 * If the length of the argument string is {@code 0}, then this 1949 * {@code String} object is returned. Otherwise, a 1950 * {@code String} object is returned that represents a character 1951 * sequence that is the concatenation of the character sequence 1952 * represented by this {@code String} object and the character 1953 * sequence represented by the argument string.<p> 1954 * Examples: 1955 * <blockquote><pre> 1956 * "cares".concat("s") returns "caress" 1957 * "to".concat("get").concat("her") returns "together" 1958 * </pre></blockquote> 1959 * 1960 * @param str the {@code String} that is concatenated to the end 1961 * of this {@code String}. 1962 * @return a string that represents the concatenation of this object's 1963 * characters followed by the string argument's characters. 1964 */ 1965 public String concat(String str) { 1966 if (str.isEmpty()) { 1967 return this; 1968 } 1969 return StringConcatHelper.simpleConcat(this, str); 1970 } 1971 1972 /** 1973 * Returns a string resulting from replacing all occurrences of 1974 * {@code oldChar} in this string with {@code newChar}. 1975 * <p> 1976 * If the character {@code oldChar} does not occur in the 1977 * character sequence represented by this {@code String} object, 1978 * then a reference to this {@code String} object is returned. 1979 * Otherwise, a {@code String} object is returned that 1980 * represents a character sequence identical to the character sequence 1981 * represented by this {@code String} object, except that every 1982 * occurrence of {@code oldChar} is replaced by an occurrence 1983 * of {@code newChar}. 1984 * <p> 1985 * Examples: 1986 * <blockquote><pre> 1987 * "mesquite in your cellar".replace('e', 'o') 1988 * returns "mosquito in your collar" 1989 * "the war of baronets".replace('r', 'y') 1990 * returns "the way of bayonets" 1991 * "sparring with a purple porpoise".replace('p', 't') 1992 * returns "starring with a turtle tortoise" 1993 * "JonL".replace('q', 'x') returns "JonL" (no change) 1994 * </pre></blockquote> 1995 * 1996 * @param oldChar the old character. 1997 * @param newChar the new character. 1998 * @return a string derived from this string by replacing every 1999 * occurrence of {@code oldChar} with {@code newChar}. 2000 */ 2001 public String replace(char oldChar, char newChar) { 2002 if (oldChar != newChar) { 2003 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar) 2004 : StringUTF16.replace(value, oldChar, newChar); 2005 if (ret != null) { 2006 return ret; 2007 } 2008 } 2009 return this; 2010 } 2011 2012 /** 2013 * Tells whether or not this string matches the given <a 2014 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2015 * 2016 * <p> An invocation of this method of the form 2017 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2018 * same result as the expression 2019 * 2020 * <blockquote> 2021 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2022 * matches(<i>regex</i>, <i>str</i>)} 2023 * </blockquote> 2024 * 2025 * @param regex 2026 * the regular expression to which this string is to be matched 2027 * 2028 * @return {@code true} if, and only if, this string matches the 2029 * given regular expression 2030 * 2031 * @throws PatternSyntaxException 2032 * if the regular expression's syntax is invalid 2033 * 2034 * @see java.util.regex.Pattern 2035 * 2036 * @since 1.4 2037 * @spec JSR-51 2038 */ 2039 public boolean matches(String regex) { 2040 return Pattern.matches(regex, this); 2041 } 2042 2043 /** 2044 * Returns true if and only if this string contains the specified 2045 * sequence of char values. 2046 * 2047 * @param s the sequence to search for 2048 * @return true if this string contains {@code s}, false otherwise 2049 * @since 1.5 2050 */ 2051 public boolean contains(CharSequence s) { 2052 return indexOf(s.toString()) >= 0; 2053 } 2054 2055 /** 2056 * Replaces the first substring of this string that matches the given <a 2057 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2058 * given replacement. 2059 * 2060 * <p> An invocation of this method of the form 2061 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2062 * yields exactly the same result as the expression 2063 * 2064 * <blockquote> 2065 * <code> 2066 * {@link java.util.regex.Pattern}.{@link 2067 * java.util.regex.Pattern#compile(String) compile}(<i>regex</i>).{@link 2068 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2069 * java.util.regex.Matcher#replaceFirst(String) replaceFirst}(<i>repl</i>) 2070 * </code> 2071 * </blockquote> 2072 * 2073 *<p> 2074 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2075 * replacement string may cause the results to be different than if it were 2076 * being treated as a literal replacement string; see 2077 * {@link java.util.regex.Matcher#replaceFirst}. 2078 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2079 * meaning of these characters, if desired. 2080 * 2081 * @param regex 2082 * the regular expression to which this string is to be matched 2083 * @param replacement 2084 * the string to be substituted for the first match 2085 * 2086 * @return The resulting {@code String} 2087 * 2088 * @throws PatternSyntaxException 2089 * if the regular expression's syntax is invalid 2090 * 2091 * @see java.util.regex.Pattern 2092 * 2093 * @since 1.4 2094 * @spec JSR-51 2095 */ 2096 public String replaceFirst(String regex, String replacement) { 2097 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2098 } 2099 2100 /** 2101 * Replaces each substring of this string that matches the given <a 2102 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2103 * given replacement. 2104 * 2105 * <p> An invocation of this method of the form 2106 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2107 * yields exactly the same result as the expression 2108 * 2109 * <blockquote> 2110 * <code> 2111 * {@link java.util.regex.Pattern}.{@link 2112 * java.util.regex.Pattern#compile(String) compile}(<i>regex</i>).{@link 2113 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2114 * java.util.regex.Matcher#replaceAll(String) replaceAll}(<i>repl</i>) 2115 * </code> 2116 * </blockquote> 2117 * 2118 *<p> 2119 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2120 * replacement string may cause the results to be different than if it were 2121 * being treated as a literal replacement string; see 2122 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2123 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2124 * meaning of these characters, if desired. 2125 * 2126 * @param regex 2127 * the regular expression to which this string is to be matched 2128 * @param replacement 2129 * the string to be substituted for each match 2130 * 2131 * @return The resulting {@code String} 2132 * 2133 * @throws PatternSyntaxException 2134 * if the regular expression's syntax is invalid 2135 * 2136 * @see java.util.regex.Pattern 2137 * 2138 * @since 1.4 2139 * @spec JSR-51 2140 */ 2141 public String replaceAll(String regex, String replacement) { 2142 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2143 } 2144 2145 /** 2146 * Replaces each substring of this string that matches the literal target 2147 * sequence with the specified literal replacement sequence. The 2148 * replacement proceeds from the beginning of the string to the end, for 2149 * example, replacing "aa" with "b" in the string "aaa" will result in 2150 * "ba" rather than "ab". 2151 * 2152 * @param target The sequence of char values to be replaced 2153 * @param replacement The replacement sequence of char values 2154 * @return The resulting string 2155 * @since 1.5 2156 */ 2157 public String replace(CharSequence target, CharSequence replacement) { 2158 String trgtStr = target.toString(); 2159 String replStr = replacement.toString(); 2160 int thisLen = length(); 2161 int trgtLen = trgtStr.length(); 2162 int replLen = replStr.length(); 2163 2164 if (trgtLen > 0) { 2165 if (trgtLen == 1 && replLen == 1) { 2166 return replace(trgtStr.charAt(0), replStr.charAt(0)); 2167 } 2168 2169 boolean thisIsLatin1 = this.isLatin1(); 2170 boolean trgtIsLatin1 = trgtStr.isLatin1(); 2171 boolean replIsLatin1 = replStr.isLatin1(); 2172 String ret = (thisIsLatin1 && trgtIsLatin1 && replIsLatin1) 2173 ? StringLatin1.replace(value, thisLen, 2174 trgtStr.value, trgtLen, 2175 replStr.value, replLen) 2176 : StringUTF16.replace(value, thisLen, thisIsLatin1, 2177 trgtStr.value, trgtLen, trgtIsLatin1, 2178 replStr.value, replLen, replIsLatin1); 2179 if (ret != null) { 2180 return ret; 2181 } 2182 return this; 2183 2184 } else { // trgtLen == 0 2185 int resultLen; 2186 try { 2187 resultLen = Math.addExact(thisLen, Math.multiplyExact( 2188 Math.addExact(thisLen, 1), replLen)); 2189 } catch (ArithmeticException ignored) { 2190 throw new OutOfMemoryError("Required length exceeds implementation limit"); 2191 } 2192 2193 StringBuilder sb = new StringBuilder(resultLen); 2194 sb.append(replStr); 2195 for (int i = 0; i < thisLen; ++i) { 2196 sb.append(charAt(i)).append(replStr); 2197 } 2198 return sb.toString(); 2199 } 2200 } 2201 2202 /** 2203 * Splits this string around matches of the given 2204 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2205 * 2206 * <p> The array returned by this method contains each substring of this 2207 * string that is terminated by another substring that matches the given 2208 * expression or is terminated by the end of the string. The substrings in 2209 * the array are in the order in which they occur in this string. If the 2210 * expression does not match any part of the input then the resulting array 2211 * has just one element, namely this string. 2212 * 2213 * <p> When there is a positive-width match at the beginning of this 2214 * string then an empty leading substring is included at the beginning 2215 * of the resulting array. A zero-width match at the beginning however 2216 * never produces such empty leading substring. 2217 * 2218 * <p> The {@code limit} parameter controls the number of times the 2219 * pattern is applied and therefore affects the length of the resulting 2220 * array. 2221 * <ul> 2222 * <li><p> 2223 * If the <i>limit</i> is positive then the pattern will be applied 2224 * at most <i>limit</i> - 1 times, the array's length will be 2225 * no greater than <i>limit</i>, and the array's last entry will contain 2226 * all input beyond the last matched delimiter.</p></li> 2227 * 2228 * <li><p> 2229 * If the <i>limit</i> is zero then the pattern will be applied as 2230 * many times as possible, the array can have any length, and trailing 2231 * empty strings will be discarded.</p></li> 2232 * 2233 * <li><p> 2234 * If the <i>limit</i> is negative then the pattern will be applied 2235 * as many times as possible and the array can have any length.</p></li> 2236 * </ul> 2237 * 2238 * <p> The string {@code "boo:and:foo"}, for example, yields the 2239 * following results with these parameters: 2240 * 2241 * <blockquote><table class="plain"> 2242 * <caption style="display:none">Split example showing regex, limit, and result</caption> 2243 * <thead> 2244 * <tr> 2245 * <th scope="col">Regex</th> 2246 * <th scope="col">Limit</th> 2247 * <th scope="col">Result</th> 2248 * </tr> 2249 * </thead> 2250 * <tbody> 2251 * <tr><th scope="row" rowspan="3" style="font-weight:normal">:</th> 2252 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">2</th> 2253 * <td>{@code { "boo", "and:foo" }}</td></tr> 2254 * <tr><!-- : --> 2255 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th> 2256 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2257 * <tr><!-- : --> 2258 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th> 2259 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2260 * <tr><th scope="row" rowspan="3" style="font-weight:normal">o</th> 2261 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th> 2262 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2263 * <tr><!-- o --> 2264 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th> 2265 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2266 * <tr><!-- o --> 2267 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">0</th> 2268 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2269 * </tbody> 2270 * </table></blockquote> 2271 * 2272 * <p> An invocation of this method of the form 2273 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2274 * yields the same result as the expression 2275 * 2276 * <blockquote> 2277 * <code> 2278 * {@link java.util.regex.Pattern}.{@link 2279 * java.util.regex.Pattern#compile(String) compile}(<i>regex</i>).{@link 2280 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2281 * </code> 2282 * </blockquote> 2283 * 2284 * 2285 * @param regex 2286 * the delimiting regular expression 2287 * 2288 * @param limit 2289 * the result threshold, as described above 2290 * 2291 * @return the array of strings computed by splitting this string 2292 * around matches of the given regular expression 2293 * 2294 * @throws PatternSyntaxException 2295 * if the regular expression's syntax is invalid 2296 * 2297 * @see java.util.regex.Pattern 2298 * 2299 * @since 1.4 2300 * @spec JSR-51 2301 */ 2302 public String[] split(String regex, int limit) { 2303 /* fastpath if the regex is a 2304 * (1) one-char String and this character is not one of the 2305 * RegEx's meta characters ".$|()[{^?*+\\", or 2306 * (2) two-char String and the first char is the backslash and 2307 * the second is not the ascii digit or ascii letter. 2308 */ 2309 char ch = 0; 2310 if (((regex.length() == 1 && 2311 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2312 (regex.length() == 2 && 2313 regex.charAt(0) == '\\' && 2314 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2315 ((ch-'a')|('z'-ch)) < 0 && 2316 ((ch-'A')|('Z'-ch)) < 0)) && 2317 (ch < Character.MIN_HIGH_SURROGATE || 2318 ch > Character.MAX_LOW_SURROGATE)) 2319 { 2320 int off = 0; 2321 int next = 0; 2322 boolean limited = limit > 0; 2323 ArrayList<String> list = new ArrayList<>(); 2324 while ((next = indexOf(ch, off)) != -1) { 2325 if (!limited || list.size() < limit - 1) { 2326 list.add(substring(off, next)); 2327 off = next + 1; 2328 } else { // last one 2329 //assert (list.size() == limit - 1); 2330 int last = length(); 2331 list.add(substring(off, last)); 2332 off = last; 2333 break; 2334 } 2335 } 2336 // If no match was found, return this 2337 if (off == 0) 2338 return new String[]{this}; 2339 2340 // Add remaining segment 2341 if (!limited || list.size() < limit) 2342 list.add(substring(off, length())); 2343 2344 // Construct result 2345 int resultSize = list.size(); 2346 if (limit == 0) { 2347 while (resultSize > 0 && list.get(resultSize - 1).isEmpty()) { 2348 resultSize--; 2349 } 2350 } 2351 String[] result = new String[resultSize]; 2352 return list.subList(0, resultSize).toArray(result); 2353 } 2354 return Pattern.compile(regex).split(this, limit); 2355 } 2356 2357 /** 2358 * Splits this string around matches of the given <a 2359 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2360 * 2361 * <p> This method works as if by invoking the two-argument {@link 2362 * #split(String, int) split} method with the given expression and a limit 2363 * argument of zero. Trailing empty strings are therefore not included in 2364 * the resulting array. 2365 * 2366 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2367 * results with these expressions: 2368 * 2369 * <blockquote><table class="plain"> 2370 * <caption style="display:none">Split examples showing regex and result</caption> 2371 * <thead> 2372 * <tr> 2373 * <th scope="col">Regex</th> 2374 * <th scope="col">Result</th> 2375 * </tr> 2376 * </thead> 2377 * <tbody> 2378 * <tr><th scope="row" style="text-weight:normal">:</th> 2379 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2380 * <tr><th scope="row" style="text-weight:normal">o</th> 2381 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2382 * </tbody> 2383 * </table></blockquote> 2384 * 2385 * 2386 * @param regex 2387 * the delimiting regular expression 2388 * 2389 * @return the array of strings computed by splitting this string 2390 * around matches of the given regular expression 2391 * 2392 * @throws PatternSyntaxException 2393 * if the regular expression's syntax is invalid 2394 * 2395 * @see java.util.regex.Pattern 2396 * 2397 * @since 1.4 2398 * @spec JSR-51 2399 */ 2400 public String[] split(String regex) { 2401 return split(regex, 0); 2402 } 2403 2404 /** 2405 * Returns a new String composed of copies of the 2406 * {@code CharSequence elements} joined together with a copy of 2407 * the specified {@code delimiter}. 2408 * 2409 * <blockquote>For example, 2410 * <pre>{@code 2411 * String message = String.join("-", "Java", "is", "cool"); 2412 * // message returned is: "Java-is-cool" 2413 * }</pre></blockquote> 2414 * 2415 * Note that if an element is null, then {@code "null"} is added. 2416 * 2417 * @param delimiter the delimiter that separates each element 2418 * @param elements the elements to join together. 2419 * 2420 * @return a new {@code String} that is composed of the {@code elements} 2421 * separated by the {@code delimiter} 2422 * 2423 * @throws NullPointerException If {@code delimiter} or {@code elements} 2424 * is {@code null} 2425 * 2426 * @see java.util.StringJoiner 2427 * @since 1.8 2428 */ 2429 public static String join(CharSequence delimiter, CharSequence... elements) { 2430 Objects.requireNonNull(delimiter); 2431 Objects.requireNonNull(elements); 2432 // Number of elements not likely worth Arrays.stream overhead. 2433 StringJoiner joiner = new StringJoiner(delimiter); 2434 for (CharSequence cs: elements) { 2435 joiner.add(cs); 2436 } 2437 return joiner.toString(); 2438 } 2439 2440 /** 2441 * Returns a new {@code String} composed of copies of the 2442 * {@code CharSequence elements} joined together with a copy of the 2443 * specified {@code delimiter}. 2444 * 2445 * <blockquote>For example, 2446 * <pre>{@code 2447 * List<String> strings = List.of("Java", "is", "cool"); 2448 * String message = String.join(" ", strings); 2449 * // message returned is: "Java is cool" 2450 * 2451 * Set<String> strings = 2452 * new LinkedHashSet<>(List.of("Java", "is", "very", "cool")); 2453 * String message = String.join("-", strings); 2454 * // message returned is: "Java-is-very-cool" 2455 * }</pre></blockquote> 2456 * 2457 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2458 * 2459 * @param delimiter a sequence of characters that is used to separate each 2460 * of the {@code elements} in the resulting {@code String} 2461 * @param elements an {@code Iterable} that will have its {@code elements} 2462 * joined together. 2463 * 2464 * @return a new {@code String} that is composed from the {@code elements} 2465 * argument 2466 * 2467 * @throws NullPointerException If {@code delimiter} or {@code elements} 2468 * is {@code null} 2469 * 2470 * @see #join(CharSequence,CharSequence...) 2471 * @see java.util.StringJoiner 2472 * @since 1.8 2473 */ 2474 public static String join(CharSequence delimiter, 2475 Iterable<? extends CharSequence> elements) { 2476 Objects.requireNonNull(delimiter); 2477 Objects.requireNonNull(elements); 2478 StringJoiner joiner = new StringJoiner(delimiter); 2479 for (CharSequence cs: elements) { 2480 joiner.add(cs); 2481 } 2482 return joiner.toString(); 2483 } 2484 2485 /** 2486 * Converts all of the characters in this {@code String} to lower 2487 * case using the rules of the given {@code Locale}. Case mapping is based 2488 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2489 * class. Since case mappings are not always 1:1 char mappings, the resulting 2490 * {@code String} may be a different length than the original {@code String}. 2491 * <p> 2492 * Examples of lowercase mappings are in the following table: 2493 * <table class="plain"> 2494 * <caption style="display:none">Lowercase mapping examples showing language code of locale, upper case, lower case, and description</caption> 2495 * <thead> 2496 * <tr> 2497 * <th scope="col">Language Code of Locale</th> 2498 * <th scope="col">Upper Case</th> 2499 * <th scope="col">Lower Case</th> 2500 * <th scope="col">Description</th> 2501 * </tr> 2502 * </thead> 2503 * <tbody> 2504 * <tr> 2505 * <td>tr (Turkish)</td> 2506 * <th scope="row" style="font-weight:normal; text-align:left">\u0130</th> 2507 * <td>\u0069</td> 2508 * <td>capital letter I with dot above -> small letter i</td> 2509 * </tr> 2510 * <tr> 2511 * <td>tr (Turkish)</td> 2512 * <th scope="row" style="font-weight:normal; text-align:left">\u0049</th> 2513 * <td>\u0131</td> 2514 * <td>capital letter I -> small letter dotless i </td> 2515 * </tr> 2516 * <tr> 2517 * <td>(all)</td> 2518 * <th scope="row" style="font-weight:normal; text-align:left">French Fries</th> 2519 * <td>french fries</td> 2520 * <td>lowercased all chars in String</td> 2521 * </tr> 2522 * <tr> 2523 * <td>(all)</td> 2524 * <th scope="row" style="font-weight:normal; text-align:left"> 2525 * ΙΧΘΥΣ</th> 2526 * <td>ιχθυσ</td> 2527 * <td>lowercased all chars in String</td> 2528 * </tr> 2529 * </tbody> 2530 * </table> 2531 * 2532 * @param locale use the case transformation rules for this locale 2533 * @return the {@code String}, converted to lowercase. 2534 * @see java.lang.String#toLowerCase() 2535 * @see java.lang.String#toUpperCase() 2536 * @see java.lang.String#toUpperCase(Locale) 2537 * @since 1.1 2538 */ 2539 public String toLowerCase(Locale locale) { 2540 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale) 2541 : StringUTF16.toLowerCase(this, value, locale); 2542 } 2543 2544 /** 2545 * Converts all of the characters in this {@code String} to lower 2546 * case using the rules of the default locale. This is equivalent to calling 2547 * {@code toLowerCase(Locale.getDefault())}. 2548 * <p> 2549 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2550 * results if used for strings that are intended to be interpreted locale 2551 * independently. 2552 * Examples are programming language identifiers, protocol keys, and HTML 2553 * tags. 2554 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2555 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2556 * LATIN SMALL LETTER DOTLESS I character. 2557 * To obtain correct results for locale insensitive strings, use 2558 * {@code toLowerCase(Locale.ROOT)}. 2559 * 2560 * @return the {@code String}, converted to lowercase. 2561 * @see java.lang.String#toLowerCase(Locale) 2562 */ 2563 public String toLowerCase() { 2564 return toLowerCase(Locale.getDefault()); 2565 } 2566 2567 /** 2568 * Converts all of the characters in this {@code String} to upper 2569 * case using the rules of the given {@code Locale}. Case mapping is based 2570 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2571 * class. Since case mappings are not always 1:1 char mappings, the resulting 2572 * {@code String} may be a different length than the original {@code String}. 2573 * <p> 2574 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2575 * 2576 * <table class="plain"> 2577 * <caption style="display:none">Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.</caption> 2578 * <thead> 2579 * <tr> 2580 * <th scope="col">Language Code of Locale</th> 2581 * <th scope="col">Lower Case</th> 2582 * <th scope="col">Upper Case</th> 2583 * <th scope="col">Description</th> 2584 * </tr> 2585 * </thead> 2586 * <tbody> 2587 * <tr> 2588 * <td>tr (Turkish)</td> 2589 * <th scope="row" style="font-weight:normal; text-align:left">\u0069</th> 2590 * <td>\u0130</td> 2591 * <td>small letter i -> capital letter I with dot above</td> 2592 * </tr> 2593 * <tr> 2594 * <td>tr (Turkish)</td> 2595 * <th scope="row" style="font-weight:normal; text-align:left">\u0131</th> 2596 * <td>\u0049</td> 2597 * <td>small letter dotless i -> capital letter I</td> 2598 * </tr> 2599 * <tr> 2600 * <td>(all)</td> 2601 * <th scope="row" style="font-weight:normal; text-align:left">\u00df</th> 2602 * <td>\u0053 \u0053</td> 2603 * <td>small letter sharp s -> two letters: SS</td> 2604 * </tr> 2605 * <tr> 2606 * <td>(all)</td> 2607 * <th scope="row" style="font-weight:normal; text-align:left">Fahrvergnügen</th> 2608 * <td>FAHRVERGNÜGEN</td> 2609 * <td></td> 2610 * </tr> 2611 * </tbody> 2612 * </table> 2613 * @param locale use the case transformation rules for this locale 2614 * @return the {@code String}, converted to uppercase. 2615 * @see java.lang.String#toUpperCase() 2616 * @see java.lang.String#toLowerCase() 2617 * @see java.lang.String#toLowerCase(Locale) 2618 * @since 1.1 2619 */ 2620 public String toUpperCase(Locale locale) { 2621 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale) 2622 : StringUTF16.toUpperCase(this, value, locale); 2623 } 2624 2625 /** 2626 * Converts all of the characters in this {@code String} to upper 2627 * case using the rules of the default locale. This method is equivalent to 2628 * {@code toUpperCase(Locale.getDefault())}. 2629 * <p> 2630 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2631 * results if used for strings that are intended to be interpreted locale 2632 * independently. 2633 * Examples are programming language identifiers, protocol keys, and HTML 2634 * tags. 2635 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2636 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2637 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2638 * To obtain correct results for locale insensitive strings, use 2639 * {@code toUpperCase(Locale.ROOT)}. 2640 * 2641 * @return the {@code String}, converted to uppercase. 2642 * @see java.lang.String#toUpperCase(Locale) 2643 */ 2644 public String toUpperCase() { 2645 return toUpperCase(Locale.getDefault()); 2646 } 2647 2648 /** 2649 * Returns a string whose value is this string, with all leading 2650 * and trailing space removed, where space is defined 2651 * as any character whose codepoint is less than or equal to 2652 * {@code 'U+0020'} (the space character). 2653 * <p> 2654 * If this {@code String} object represents an empty character 2655 * sequence, or the first and last characters of character sequence 2656 * represented by this {@code String} object both have codes 2657 * that are not space (as defined above), then a 2658 * reference to this {@code String} object is returned. 2659 * <p> 2660 * Otherwise, if all characters in this string are space (as 2661 * defined above), then a {@code String} object representing an 2662 * empty string is returned. 2663 * <p> 2664 * Otherwise, let <i>k</i> be the index of the first character in the 2665 * string whose code is not a space (as defined above) and let 2666 * <i>m</i> be the index of the last character in the string whose code 2667 * is not a space (as defined above). A {@code String} 2668 * object is returned, representing the substring of this string that 2669 * begins with the character at index <i>k</i> and ends with the 2670 * character at index <i>m</i>-that is, the result of 2671 * {@code this.substring(k, m + 1)}. 2672 * <p> 2673 * This method may be used to trim space (as defined above) from 2674 * the beginning and end of a string. 2675 * 2676 * @return a string whose value is this string, with all leading 2677 * and trailing space removed, or this string if it 2678 * has no leading or trailing space. 2679 */ 2680 public String trim() { 2681 String ret = isLatin1() ? StringLatin1.trim(value) 2682 : StringUTF16.trim(value); 2683 return ret == null ? this : ret; 2684 } 2685 2686 /** 2687 * Returns a string whose value is this string, with all leading 2688 * and trailing {@linkplain Character#isWhitespace(int) white space} 2689 * removed. 2690 * <p> 2691 * If this {@code String} object represents an empty string, 2692 * or if all code points in this string are 2693 * {@linkplain Character#isWhitespace(int) white space}, then an empty string 2694 * is returned. 2695 * <p> 2696 * Otherwise, returns a substring of this string beginning with the first 2697 * code point that is not a {@linkplain Character#isWhitespace(int) white space} 2698 * up to and including the last code point that is not a 2699 * {@linkplain Character#isWhitespace(int) white space}. 2700 * <p> 2701 * This method may be used to strip 2702 * {@linkplain Character#isWhitespace(int) white space} from 2703 * the beginning and end of a string. 2704 * 2705 * @return a string whose value is this string, with all leading 2706 * and trailing white space removed 2707 * 2708 * @see Character#isWhitespace(int) 2709 * 2710 * @since 11 2711 */ 2712 public String strip() { 2713 String ret = isLatin1() ? StringLatin1.strip(value) 2714 : StringUTF16.strip(value); 2715 return ret == null ? this : ret; 2716 } 2717 2718 /** 2719 * Returns a string whose value is this string, with all leading 2720 * {@linkplain Character#isWhitespace(int) white space} removed. 2721 * <p> 2722 * If this {@code String} object represents an empty string, 2723 * or if all code points in this string are 2724 * {@linkplain Character#isWhitespace(int) white space}, then an empty string 2725 * is returned. 2726 * <p> 2727 * Otherwise, returns a substring of this string beginning with the first 2728 * code point that is not a {@linkplain Character#isWhitespace(int) white space} 2729 * up to and including the last code point of this string. 2730 * <p> 2731 * This method may be used to trim 2732 * {@linkplain Character#isWhitespace(int) white space} from 2733 * the beginning of a string. 2734 * 2735 * @return a string whose value is this string, with all leading white 2736 * space removed 2737 * 2738 * @see Character#isWhitespace(int) 2739 * 2740 * @since 11 2741 */ 2742 public String stripLeading() { 2743 String ret = isLatin1() ? StringLatin1.stripLeading(value) 2744 : StringUTF16.stripLeading(value); 2745 return ret == null ? this : ret; 2746 } 2747 2748 /** 2749 * Returns a string whose value is this string, with all trailing 2750 * {@linkplain Character#isWhitespace(int) white space} removed. 2751 * <p> 2752 * If this {@code String} object represents an empty string, 2753 * or if all characters in this string are 2754 * {@linkplain Character#isWhitespace(int) white space}, then an empty string 2755 * is returned. 2756 * <p> 2757 * Otherwise, returns a substring of this string beginning with the first 2758 * code point of this string up to and including the last code point 2759 * that is not a {@linkplain Character#isWhitespace(int) white space}. 2760 * <p> 2761 * This method may be used to trim 2762 * {@linkplain Character#isWhitespace(int) white space} from 2763 * the end of a string. 2764 * 2765 * @return a string whose value is this string, with all trailing white 2766 * space removed 2767 * 2768 * @see Character#isWhitespace(int) 2769 * 2770 * @since 11 2771 */ 2772 public String stripTrailing() { 2773 String ret = isLatin1() ? StringLatin1.stripTrailing(value) 2774 : StringUTF16.stripTrailing(value); 2775 return ret == null ? this : ret; 2776 } 2777 2778 /** 2779 * Returns {@code true} if the string is empty or contains only 2780 * {@linkplain Character#isWhitespace(int) white space} codepoints, 2781 * otherwise {@code false}. 2782 * 2783 * @return {@code true} if the string is empty or contains only 2784 * {@linkplain Character#isWhitespace(int) white space} codepoints, 2785 * otherwise {@code false} 2786 * 2787 * @see Character#isWhitespace(int) 2788 * 2789 * @since 11 2790 */ 2791 public boolean isBlank() { 2792 return indexOfNonWhitespace() == length(); 2793 } 2794 2795 /** 2796 * Returns a stream of lines extracted from this string, 2797 * separated by line terminators. 2798 * <p> 2799 * A <i>line terminator</i> is one of the following: 2800 * a line feed character {@code "\n"} (U+000A), 2801 * a carriage return character {@code "\r"} (U+000D), 2802 * or a carriage return followed immediately by a line feed 2803 * {@code "\r\n"} (U+000D U+000A). 2804 * <p> 2805 * A <i>line</i> is either a sequence of zero or more characters 2806 * followed by a line terminator, or it is a sequence of one or 2807 * more characters followed by the end of the string. A 2808 * line does not include the line terminator. 2809 * <p> 2810 * The stream returned by this method contains the lines from 2811 * this string in the order in which they occur. 2812 * 2813 * @apiNote This definition of <i>line</i> implies that an empty 2814 * string has zero lines and that there is no empty line 2815 * following a line terminator at the end of a string. 2816 * 2817 * @implNote This method provides better performance than 2818 * split("\R") by supplying elements lazily and 2819 * by faster search of new line terminators. 2820 * 2821 * @return the stream of lines extracted from this string 2822 * 2823 * @since 11 2824 */ 2825 public Stream<String> lines() { 2826 return isLatin1() ? StringLatin1.lines(value) : StringUTF16.lines(value); 2827 } 2828 2829 /** 2830 * Adjusts the indentation of each line of this string based on the value of 2831 * {@code n}, and normalizes line termination characters. 2832 * <p> 2833 * This string is conceptually separated into lines using 2834 * {@link String#lines()}. Each line is then adjusted as described below 2835 * and then suffixed with a line feed {@code "\n"} (U+000A). The resulting 2836 * lines are then concatenated and returned. 2837 * <p> 2838 * If {@code n > 0} then {@code n} spaces (U+0020) are inserted at the 2839 * beginning of each line. 2840 * <p> 2841 * If {@code n < 0} then up to {@code n} 2842 * {@linkplain Character#isWhitespace(int) white space characters} are removed 2843 * from the beginning of each line. If a given line does not contain 2844 * sufficient white space then all leading 2845 * {@linkplain Character#isWhitespace(int) white space characters} are removed. 2846 * Each white space character is treated as a single character. In 2847 * particular, the tab character {@code "\t"} (U+0009) is considered a 2848 * single character; it is not expanded. 2849 * <p> 2850 * If {@code n == 0} then the line remains unchanged. However, line 2851 * terminators are still normalized. 2852 * 2853 * @param n number of leading 2854 * {@linkplain Character#isWhitespace(int) white space characters} 2855 * to add or remove 2856 * 2857 * @return string with indentation adjusted and line endings normalized 2858 * 2859 * @see String#lines() 2860 * @see String#isBlank() 2861 * @see Character#isWhitespace(int) 2862 * 2863 * @since 12 2864 */ 2865 public String indent(int n) { 2866 if (isEmpty()) { 2867 return ""; 2868 } 2869 Stream<String> stream = lines(); 2870 if (n > 0) { 2871 final String spaces = " ".repeat(n); 2872 stream = stream.map(s -> spaces + s); 2873 } else if (n == Integer.MIN_VALUE) { 2874 stream = stream.map(s -> s.stripLeading()); 2875 } else if (n < 0) { 2876 stream = stream.map(s -> s.substring(Math.min(-n, s.indexOfNonWhitespace()))); 2877 } 2878 return stream.collect(Collectors.joining("\n", "", "\n")); 2879 } 2880 2881 private int indexOfNonWhitespace() { 2882 return isLatin1() ? StringLatin1.indexOfNonWhitespace(value) 2883 : StringUTF16.indexOfNonWhitespace(value); 2884 } 2885 2886 private int lastIndexOfNonWhitespace() { 2887 return isLatin1() ? StringLatin1.lastIndexOfNonWhitespace(value) 2888 : StringUTF16.lastIndexOfNonWhitespace(value); 2889 } 2890 2891 /** 2892 * Returns a string whose value is this string, with incidental 2893 * {@linkplain Character#isWhitespace(int) white space} removed from 2894 * the beginning and end of every line. 2895 * <p> 2896 * Incidental {@linkplain Character#isWhitespace(int) white space} 2897 * is often present in a text block to align the content with the opening 2898 * delimiter. For example, in the following code, dots represent incidental 2899 * {@linkplain Character#isWhitespace(int) white space}: 2900 * <blockquote><pre> 2901 * String html = """ 2902 * ..............<html> 2903 * .............. <body> 2904 * .............. <p>Hello, world</p> 2905 * .............. </body> 2906 * ..............</html> 2907 * .............."""; 2908 * </pre></blockquote> 2909 * This method treats the incidental 2910 * {@linkplain Character#isWhitespace(int) white space} as indentation to be 2911 * stripped, producing a string that preserves the relative indentation of 2912 * the content. Using | to visualize the start of each line of the string: 2913 * <blockquote><pre> 2914 * |<html> 2915 * | <body> 2916 * | <p>Hello, world</p> 2917 * | </body> 2918 * |</html> 2919 * </pre></blockquote> 2920 * First, the individual lines of this string are extracted. A <i>line</i> 2921 * is a sequence of zero or more characters followed by either a line 2922 * terminator or the end of the string. 2923 * If the string has at least one line terminator, the last line consists 2924 * of the characters between the last terminator and the end of the string. 2925 * Otherwise, if the string has no terminators, the last line is the start 2926 * of the string to the end of the string, in other words, the entire 2927 * string. 2928 * A line does not include the line terminator. 2929 * <p> 2930 * Then, the <i>minimum indentation</i> (min) is determined as follows: 2931 * <ul> 2932 * <li><p>For each non-blank line (as defined by {@link String#isBlank()}), 2933 * the leading {@linkplain Character#isWhitespace(int) white space} 2934 * characters are counted.</p> 2935 * </li> 2936 * <li><p>The leading {@linkplain Character#isWhitespace(int) white space} 2937 * characters on the last line are also counted even if 2938 * {@linkplain String#isBlank() blank}.</p> 2939 * </li> 2940 * </ul> 2941 * <p>The <i>min</i> value is the smallest of these counts. 2942 * <p> 2943 * For each {@linkplain String#isBlank() non-blank} line, <i>min</i> leading 2944 * {@linkplain Character#isWhitespace(int) white space} characters are 2945 * removed, and any trailing {@linkplain Character#isWhitespace(int) white 2946 * space} characters are removed. {@linkplain String#isBlank() Blank} lines 2947 * are replaced with the empty string. 2948 * 2949 * <p> 2950 * Finally, the lines are joined into a new string, using the LF character 2951 * {@code "\n"} (U+000A) to separate lines. 2952 * 2953 * @apiNote 2954 * This method's primary purpose is to shift a block of lines as far as 2955 * possible to the left, while preserving relative indentation. Lines 2956 * that were indented the least will thus have no leading 2957 * {@linkplain Character#isWhitespace(int) white space}. 2958 * The result will have the same number of line terminators as this string. 2959 * If this string ends with a line terminator then the result will end 2960 * with a line terminator. 2961 * 2962 * @implSpec 2963 * This method treats all {@linkplain Character#isWhitespace(int) white space} 2964 * characters as having equal width. As long as the indentation on every 2965 * line is consistently composed of the same character sequences, then the 2966 * result will be as described above. 2967 * 2968 * @return string with incidental indentation removed and line 2969 * terminators normalized 2970 * 2971 * @see String#lines() 2972 * @see String#isBlank() 2973 * @see String#indent(int) 2974 * @see Character#isWhitespace(int) 2975 * 2976 * @since 15 2977 * 2978 */ 2979 public String stripIndent() { 2980 int length = length(); 2981 if (length == 0) { 2982 return ""; 2983 } 2984 char lastChar = charAt(length - 1); 2985 boolean optOut = lastChar == '\n' || lastChar == '\r'; 2986 List<String> lines = lines().collect(Collectors.toList()); 2987 final int outdent = optOut ? 0 : outdent(lines); 2988 return lines.stream() 2989 .map(line -> { 2990 int firstNonWhitespace = line.indexOfNonWhitespace(); 2991 int lastNonWhitespace = line.lastIndexOfNonWhitespace(); 2992 int incidentalWhitespace = Math.min(outdent, firstNonWhitespace); 2993 return firstNonWhitespace > lastNonWhitespace 2994 ? "" : line.substring(incidentalWhitespace, lastNonWhitespace); 2995 }) 2996 .collect(Collectors.joining("\n", "", optOut ? "\n" : "")); 2997 } 2998 2999 private static int outdent(List<String> lines) { 3000 // Note: outdent is guaranteed to be zero or positive number. 3001 // If there isn't a non-blank line then the last must be blank 3002 int outdent = Integer.MAX_VALUE; 3003 for (String line : lines) { 3004 int leadingWhitespace = line.indexOfNonWhitespace(); 3005 if (leadingWhitespace != line.length()) { 3006 outdent = Integer.min(outdent, leadingWhitespace); 3007 } 3008 } 3009 String lastLine = lines.get(lines.size() - 1); 3010 if (lastLine.isBlank()) { 3011 outdent = Integer.min(outdent, lastLine.length()); 3012 } 3013 return outdent; 3014 } 3015 3016 /** 3017 * Returns a string whose value is this string, with escape sequences 3018 * translated as if in a string literal. 3019 * <p> 3020 * Escape sequences are translated as follows; 3021 * <table class="striped"> 3022 * <caption style="display:none">Translation</caption> 3023 * <thead> 3024 * <tr> 3025 * <th scope="col">Escape</th> 3026 * <th scope="col">Name</th> 3027 * <th scope="col">Translation</th> 3028 * </tr> 3029 * </thead> 3030 * <tbody> 3031 * <tr> 3032 * <th scope="row">{@code \u005Cb}</th> 3033 * <td>backspace</td> 3034 * <td>{@code U+0008}</td> 3035 * </tr> 3036 * <tr> 3037 * <th scope="row">{@code \u005Ct}</th> 3038 * <td>horizontal tab</td> 3039 * <td>{@code U+0009}</td> 3040 * </tr> 3041 * <tr> 3042 * <th scope="row">{@code \u005Cn}</th> 3043 * <td>line feed</td> 3044 * <td>{@code U+000A}</td> 3045 * </tr> 3046 * <tr> 3047 * <th scope="row">{@code \u005Cf}</th> 3048 * <td>form feed</td> 3049 * <td>{@code U+000C}</td> 3050 * </tr> 3051 * <tr> 3052 * <th scope="row">{@code \u005Cr}</th> 3053 * <td>carriage return</td> 3054 * <td>{@code U+000D}</td> 3055 * </tr> 3056 * <tr> 3057 * <th scope="row">{@code \u005Cs}</th> 3058 * <td>space</td> 3059 * <td>{@code U+0020}</td> 3060 * </tr> 3061 * <tr> 3062 * <th scope="row">{@code \u005C"}</th> 3063 * <td>double quote</td> 3064 * <td>{@code U+0022}</td> 3065 * </tr> 3066 * <tr> 3067 * <th scope="row">{@code \u005C'}</th> 3068 * <td>single quote</td> 3069 * <td>{@code U+0027}</td> 3070 * </tr> 3071 * <tr> 3072 * <th scope="row">{@code \u005C\u005C}</th> 3073 * <td>backslash</td> 3074 * <td>{@code U+005C}</td> 3075 * </tr> 3076 * <tr> 3077 * <th scope="row">{@code \u005C0 - \u005C377}</th> 3078 * <td>octal escape</td> 3079 * <td>code point equivalents</td> 3080 * </tr> 3081 * <tr> 3082 * <th scope="row">{@code \u005C<line-terminator>}</th> 3083 * <td>continuation</td> 3084 * <td>discard</td> 3085 * </tr> 3086 * </tbody> 3087 * </table> 3088 * 3089 * @implNote 3090 * This method does <em>not</em> translate Unicode escapes such as "{@code \u005cu2022}". 3091 * Unicode escapes are translated by the Java compiler when reading input characters and 3092 * are not part of the string literal specification. 3093 * 3094 * @throws IllegalArgumentException when an escape sequence is malformed. 3095 * 3096 * @return String with escape sequences translated. 3097 * 3098 * @jls 3.10.7 Escape Sequences 3099 * 3100 * @since 15 3101 */ 3102 public String translateEscapes() { 3103 if (isEmpty()) { 3104 return ""; 3105 } 3106 char[] chars = toCharArray(); 3107 int length = chars.length; 3108 int from = 0; 3109 int to = 0; 3110 while (from < length) { 3111 char ch = chars[from++]; 3112 if (ch == '\\') { 3113 ch = from < length ? chars[from++] : '\0'; 3114 switch (ch) { 3115 case 'b': 3116 ch = '\b'; 3117 break; 3118 case 'f': 3119 ch = '\f'; 3120 break; 3121 case 'n': 3122 ch = '\n'; 3123 break; 3124 case 'r': 3125 ch = '\r'; 3126 break; 3127 case 's': 3128 ch = ' '; 3129 break; 3130 case 't': 3131 ch = '\t'; 3132 break; 3133 case '\'': 3134 case '\"': 3135 case '\\': 3136 // as is 3137 break; 3138 case '0': case '1': case '2': case '3': 3139 case '4': case '5': case '6': case '7': 3140 int limit = Integer.min(from + (ch <= '3' ? 2 : 1), length); 3141 int code = ch - '0'; 3142 while (from < limit) { 3143 ch = chars[from]; 3144 if (ch < '0' || '7' < ch) { 3145 break; 3146 } 3147 from++; 3148 code = (code << 3) | (ch - '0'); 3149 } 3150 ch = (char)code; 3151 break; 3152 case '\n': 3153 continue; 3154 case '\r': 3155 if (from < length && chars[from] == '\n') { 3156 from++; 3157 } 3158 continue; 3159 default: { 3160 String msg = String.format( 3161 "Invalid escape sequence: \\%c \\\\u%04X", 3162 ch, (int)ch); 3163 throw new IllegalArgumentException(msg); 3164 } 3165 } 3166 } 3167 3168 chars[to++] = ch; 3169 } 3170 3171 return new String(chars, 0, to); 3172 } 3173 3174 /** 3175 * This method allows the application of a function to {@code this} 3176 * string. The function should expect a single String argument 3177 * and produce an {@code R} result. 3178 * <p> 3179 * Any exception thrown by {@code f()} will be propagated to the 3180 * caller. 3181 * 3182 * @param f functional interface to a apply 3183 * 3184 * @param <R> class of the result 3185 * 3186 * @return the result of applying the function to this string 3187 * 3188 * @see java.util.function.Function 3189 * 3190 * @since 12 3191 */ 3192 public <R> R transform(Function<? super String, ? extends R> f) { 3193 return f.apply(this); 3194 } 3195 3196 /** 3197 * This object (which is already a string!) is itself returned. 3198 * 3199 * @return the string itself. 3200 */ 3201 public String toString() { 3202 return this; 3203 } 3204 3205 /** 3206 * Returns a stream of {@code int} zero-extending the {@code char} values 3207 * from this sequence. Any char which maps to a <a 3208 * href="{@docRoot}/java.base/java/lang/Character.html#unicode">surrogate code 3209 * point</a> is passed through uninterpreted. 3210 * 3211 * @return an IntStream of char values from this sequence 3212 * @since 9 3213 */ 3214 @Override 3215 public IntStream chars() { 3216 return StreamSupport.intStream( 3217 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 3218 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE), 3219 false); 3220 } 3221 3222 3223 /** 3224 * Returns a stream of code point values from this sequence. Any surrogate 3225 * pairs encountered in the sequence are combined as if by {@linkplain 3226 * Character#toCodePoint Character.toCodePoint} and the result is passed 3227 * to the stream. Any other code units, including ordinary BMP characters, 3228 * unpaired surrogates, and undefined code units, are zero-extended to 3229 * {@code int} values which are then passed to the stream. 3230 * 3231 * @return an IntStream of Unicode code points from this sequence 3232 * @since 9 3233 */ 3234 @Override 3235 public IntStream codePoints() { 3236 return StreamSupport.intStream( 3237 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 3238 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE), 3239 false); 3240 } 3241 3242 /** 3243 * Converts this string to a new character array. 3244 * 3245 * @return a newly allocated character array whose length is the length 3246 * of this string and whose contents are initialized to contain 3247 * the character sequence represented by this string. 3248 */ 3249 public char[] toCharArray() { 3250 return isLatin1() ? StringLatin1.toChars(value) 3251 : StringUTF16.toChars(value); 3252 } 3253 3254 /** 3255 * Returns a formatted string using the specified format string and 3256 * arguments. 3257 * 3258 * <p> The locale always used is the one returned by {@link 3259 * java.util.Locale#getDefault(java.util.Locale.Category) 3260 * Locale.getDefault(Locale.Category)} with 3261 * {@link java.util.Locale.Category#FORMAT FORMAT} category specified. 3262 * 3263 * @param format 3264 * A <a href="../util/Formatter.html#syntax">format string</a> 3265 * 3266 * @param args 3267 * Arguments referenced by the format specifiers in the format 3268 * string. If there are more arguments than format specifiers, the 3269 * extra arguments are ignored. The number of arguments is 3270 * variable and may be zero. The maximum number of arguments is 3271 * limited by the maximum dimension of a Java array as defined by 3272 * <cite>The Java™ Virtual Machine Specification</cite>. 3273 * The behaviour on a 3274 * {@code null} argument depends on the <a 3275 * href="../util/Formatter.html#syntax">conversion</a>. 3276 * 3277 * @throws java.util.IllegalFormatException 3278 * If a format string contains an illegal syntax, a format 3279 * specifier that is incompatible with the given arguments, 3280 * insufficient arguments given the format string, or other 3281 * illegal conditions. For specification of all possible 3282 * formatting errors, see the <a 3283 * href="../util/Formatter.html#detail">Details</a> section of the 3284 * formatter class specification. 3285 * 3286 * @return A formatted string 3287 * 3288 * @see java.util.Formatter 3289 * @since 1.5 3290 */ 3291 public static String format(String format, Object... args) { 3292 return new Formatter().format(format, args).toString(); 3293 } 3294 3295 /** 3296 * Returns a formatted string using the specified locale, format string, 3297 * and arguments. 3298 * 3299 * @param l 3300 * The {@linkplain java.util.Locale locale} to apply during 3301 * formatting. If {@code l} is {@code null} then no localization 3302 * is applied. 3303 * 3304 * @param format 3305 * A <a href="../util/Formatter.html#syntax">format string</a> 3306 * 3307 * @param args 3308 * Arguments referenced by the format specifiers in the format 3309 * string. If there are more arguments than format specifiers, the 3310 * extra arguments are ignored. The number of arguments is 3311 * variable and may be zero. The maximum number of arguments is 3312 * limited by the maximum dimension of a Java array as defined by 3313 * <cite>The Java™ Virtual Machine Specification</cite>. 3314 * The behaviour on a 3315 * {@code null} argument depends on the 3316 * <a href="../util/Formatter.html#syntax">conversion</a>. 3317 * 3318 * @throws java.util.IllegalFormatException 3319 * If a format string contains an illegal syntax, a format 3320 * specifier that is incompatible with the given arguments, 3321 * insufficient arguments given the format string, or other 3322 * illegal conditions. For specification of all possible 3323 * formatting errors, see the <a 3324 * href="../util/Formatter.html#detail">Details</a> section of the 3325 * formatter class specification 3326 * 3327 * @return A formatted string 3328 * 3329 * @see java.util.Formatter 3330 * @since 1.5 3331 */ 3332 public static String format(Locale l, String format, Object... args) { 3333 return new Formatter(l).format(format, args).toString(); 3334 } 3335 3336 /** 3337 * Formats using this string as the format string, and the supplied 3338 * arguments. 3339 * 3340 * @implSpec This method is equivalent to {@code String.format(this, args)}. 3341 * 3342 * @param args 3343 * Arguments referenced by the format specifiers in this string. 3344 * 3345 * @return A formatted string 3346 * 3347 * @see java.lang.String#format(String,Object...) 3348 * @see java.util.Formatter 3349 * 3350 * @since 15 3351 * 3352 */ 3353 public String formatted(Object... args) { 3354 return new Formatter().format(this, args).toString(); 3355 } 3356 3357 /** 3358 * Returns the string representation of the {@code Object} argument. 3359 * 3360 * @param obj an {@code Object}. 3361 * @return if the argument is {@code null}, then a string equal to 3362 * {@code "null"}; otherwise, the value of 3363 * {@code obj.toString()} is returned. 3364 * @see java.lang.Object#toString() 3365 */ 3366 public static String valueOf(Object obj) { 3367 return (obj == null) ? "null" : obj.toString(); 3368 } 3369 3370 /** 3371 * Returns the string representation of the {@code char} array 3372 * argument. The contents of the character array are copied; subsequent 3373 * modification of the character array does not affect the returned 3374 * string. 3375 * 3376 * @param data the character array. 3377 * @return a {@code String} that contains the characters of the 3378 * character array. 3379 */ 3380 public static String valueOf(char data[]) { 3381 return new String(data); 3382 } 3383 3384 /** 3385 * Returns the string representation of a specific subarray of the 3386 * {@code char} array argument. 3387 * <p> 3388 * The {@code offset} argument is the index of the first 3389 * character of the subarray. The {@code count} argument 3390 * specifies the length of the subarray. The contents of the subarray 3391 * are copied; subsequent modification of the character array does not 3392 * affect the returned string. 3393 * 3394 * @param data the character array. 3395 * @param offset initial offset of the subarray. 3396 * @param count length of the subarray. 3397 * @return a {@code String} that contains the characters of the 3398 * specified subarray of the character array. 3399 * @throws IndexOutOfBoundsException if {@code offset} is 3400 * negative, or {@code count} is negative, or 3401 * {@code offset+count} is larger than 3402 * {@code data.length}. 3403 */ 3404 public static String valueOf(char data[], int offset, int count) { 3405 return new String(data, offset, count); 3406 } 3407 3408 /** 3409 * Equivalent to {@link #valueOf(char[], int, int)}. 3410 * 3411 * @param data the character array. 3412 * @param offset initial offset of the subarray. 3413 * @param count length of the subarray. 3414 * @return a {@code String} that contains the characters of the 3415 * specified subarray of the character array. 3416 * @throws IndexOutOfBoundsException if {@code offset} is 3417 * negative, or {@code count} is negative, or 3418 * {@code offset+count} is larger than 3419 * {@code data.length}. 3420 */ 3421 public static String copyValueOf(char data[], int offset, int count) { 3422 return new String(data, offset, count); 3423 } 3424 3425 /** 3426 * Equivalent to {@link #valueOf(char[])}. 3427 * 3428 * @param data the character array. 3429 * @return a {@code String} that contains the characters of the 3430 * character array. 3431 */ 3432 public static String copyValueOf(char data[]) { 3433 return new String(data); 3434 } 3435 3436 /** 3437 * Returns the string representation of the {@code boolean} argument. 3438 * 3439 * @param b a {@code boolean}. 3440 * @return if the argument is {@code true}, a string equal to 3441 * {@code "true"} is returned; otherwise, a string equal to 3442 * {@code "false"} is returned. 3443 */ 3444 public static String valueOf(boolean b) { 3445 return b ? "true" : "false"; 3446 } 3447 3448 /** 3449 * Returns the string representation of the {@code char} 3450 * argument. 3451 * 3452 * @param c a {@code char}. 3453 * @return a string of length {@code 1} containing 3454 * as its single character the argument {@code c}. 3455 */ 3456 public static String valueOf(char c) { 3457 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) { 3458 return new String(StringLatin1.toBytes(c), LATIN1); 3459 } 3460 return new String(StringUTF16.toBytes(c), UTF16); 3461 } 3462 3463 /** 3464 * Returns the string representation of the {@code int} argument. 3465 * <p> 3466 * The representation is exactly the one returned by the 3467 * {@code Integer.toString} method of one argument. 3468 * 3469 * @param i an {@code int}. 3470 * @return a string representation of the {@code int} argument. 3471 * @see java.lang.Integer#toString(int, int) 3472 */ 3473 public static String valueOf(int i) { 3474 return Integer.toString(i); 3475 } 3476 3477 /** 3478 * Returns the string representation of the {@code long} argument. 3479 * <p> 3480 * The representation is exactly the one returned by the 3481 * {@code Long.toString} method of one argument. 3482 * 3483 * @param l a {@code long}. 3484 * @return a string representation of the {@code long} argument. 3485 * @see java.lang.Long#toString(long) 3486 */ 3487 public static String valueOf(long l) { 3488 return Long.toString(l); 3489 } 3490 3491 /** 3492 * Returns the string representation of the {@code float} argument. 3493 * <p> 3494 * The representation is exactly the one returned by the 3495 * {@code Float.toString} method of one argument. 3496 * 3497 * @param f a {@code float}. 3498 * @return a string representation of the {@code float} argument. 3499 * @see java.lang.Float#toString(float) 3500 */ 3501 public static String valueOf(float f) { 3502 return Float.toString(f); 3503 } 3504 3505 /** 3506 * Returns the string representation of the {@code double} argument. 3507 * <p> 3508 * The representation is exactly the one returned by the 3509 * {@code Double.toString} method of one argument. 3510 * 3511 * @param d a {@code double}. 3512 * @return a string representation of the {@code double} argument. 3513 * @see java.lang.Double#toString(double) 3514 */ 3515 public static String valueOf(double d) { 3516 return Double.toString(d); 3517 } 3518 3519 /** 3520 * Returns a canonical representation for the string object. 3521 * <p> 3522 * A pool of strings, initially empty, is maintained privately by the 3523 * class {@code String}. 3524 * <p> 3525 * When the intern method is invoked, if the pool already contains a 3526 * string equal to this {@code String} object as determined by 3527 * the {@link #equals(Object)} method, then the string from the pool is 3528 * returned. Otherwise, this {@code String} object is added to the 3529 * pool and a reference to this {@code String} object is returned. 3530 * <p> 3531 * It follows that for any two strings {@code s} and {@code t}, 3532 * {@code s.intern() == t.intern()} is {@code true} 3533 * if and only if {@code s.equals(t)} is {@code true}. 3534 * <p> 3535 * All literal strings and string-valued constant expressions are 3536 * interned. String literals are defined in section 3.10.5 of the 3537 * <cite>The Java™ Language Specification</cite>. 3538 * 3539 * @return a string that has the same contents as this string, but is 3540 * guaranteed to be from a pool of unique strings. 3541 * @jls 3.10.5 String Literals 3542 */ 3543 public native String intern(); 3544 3545 /** 3546 * Returns a string whose value is the concatenation of this 3547 * string repeated {@code count} times. 3548 * <p> 3549 * If this string is empty or count is zero then the empty 3550 * string is returned. 3551 * 3552 * @param count number of times to repeat 3553 * 3554 * @return A string composed of this string repeated 3555 * {@code count} times or the empty string if this 3556 * string is empty or count is zero 3557 * 3558 * @throws IllegalArgumentException if the {@code count} is 3559 * negative. 3560 * 3561 * @since 11 3562 */ 3563 public String repeat(int count) { 3564 if (count < 0) { 3565 throw new IllegalArgumentException("count is negative: " + count); 3566 } 3567 if (count == 1) { 3568 return this; 3569 } 3570 final int len = value.length; 3571 if (len == 0 || count == 0) { 3572 return ""; 3573 } 3574 if (Integer.MAX_VALUE / count < len) { 3575 throw new OutOfMemoryError("Required length exceeds implementation limit"); 3576 } 3577 if (len == 1) { 3578 final byte[] single = new byte[count]; 3579 Arrays.fill(single, value[0]); 3580 return new String(single, coder); 3581 } 3582 final int limit = len * count; 3583 final byte[] multiple = new byte[limit]; 3584 System.arraycopy(value, 0, multiple, 0, len); 3585 int copied = len; 3586 for (; copied < limit - copied; copied <<= 1) { 3587 System.arraycopy(multiple, 0, multiple, copied, copied); 3588 } 3589 System.arraycopy(multiple, 0, multiple, copied, limit - copied); 3590 return new String(multiple, coder); 3591 } 3592 3593 //////////////////////////////////////////////////////////////// 3594 3595 /** 3596 * Copy character bytes from this string into dst starting at dstBegin. 3597 * This method doesn't perform any range checking. 3598 * 3599 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two 3600 * coders are different, and dst is big enough (range check) 3601 * 3602 * @param dstBegin the char index, not offset of byte[] 3603 * @param coder the coder of dst[] 3604 */ 3605 void getBytes(byte dst[], int dstBegin, byte coder) { 3606 if (coder() == coder) { 3607 System.arraycopy(value, 0, dst, dstBegin << coder, value.length); 3608 } else { // this.coder == LATIN && coder == UTF16 3609 StringLatin1.inflate(value, 0, dst, dstBegin, value.length); 3610 } 3611 } 3612 3613 /* 3614 * Package private constructor. Trailing Void argument is there for 3615 * disambiguating it against other (public) constructors. 3616 * 3617 * Stores the char[] value into a byte[] that each byte represents 3618 * the8 low-order bits of the corresponding character, if the char[] 3619 * contains only latin1 character. Or a byte[] that stores all 3620 * characters in their byte sequences defined by the {@code StringUTF16}. 3621 */ 3622 String(char[] value, int off, int len, Void sig) { 3623 if (len == 0) { 3624 this.value = "".value; 3625 this.coder = "".coder; 3626 return; 3627 } 3628 if (COMPACT_STRINGS) { 3629 byte[] val = StringUTF16.compress(value, off, len); 3630 if (val != null) { 3631 this.value = val; 3632 this.coder = LATIN1; 3633 return; 3634 } 3635 } 3636 this.coder = UTF16; 3637 this.value = StringUTF16.toBytes(value, off, len); 3638 } 3639 3640 /* 3641 * Package private constructor. Trailing Void argument is there for 3642 * disambiguating it against other (public) constructors. 3643 */ 3644 String(AbstractStringBuilder asb, Void sig) { 3645 byte[] val = asb.getValue(); 3646 int length = asb.length(); 3647 if (asb.isLatin1()) { 3648 this.coder = LATIN1; 3649 this.value = Arrays.copyOfRange(val, 0, length); 3650 } else { 3651 if (COMPACT_STRINGS) { 3652 byte[] buf = StringUTF16.compress(val, 0, length); 3653 if (buf != null) { 3654 this.coder = LATIN1; 3655 this.value = buf; 3656 return; 3657 } 3658 } 3659 this.coder = UTF16; 3660 this.value = Arrays.copyOfRange(val, 0, length << 1); 3661 } 3662 } 3663 3664 /* 3665 * Package private constructor which shares value array for speed. 3666 */ 3667 String(byte[] value, byte coder) { 3668 this.value = value; 3669 this.coder = coder; 3670 } 3671 3672 byte coder() { 3673 return COMPACT_STRINGS ? coder : UTF16; 3674 } 3675 3676 byte[] value() { 3677 return value; 3678 } 3679 3680 boolean isLatin1() { 3681 return COMPACT_STRINGS && coder == LATIN1; 3682 } 3683 3684 @Native static final byte LATIN1 = 0; 3685 @Native static final byte UTF16 = 1; 3686 3687 /* 3688 * StringIndexOutOfBoundsException if {@code index} is 3689 * negative or greater than or equal to {@code length}. 3690 */ 3691 static void checkIndex(int index, int length) { 3692 if (index < 0 || index >= length) { 3693 throw new StringIndexOutOfBoundsException("index " + index + 3694 ", length " + length); 3695 } 3696 } 3697 3698 /* 3699 * StringIndexOutOfBoundsException if {@code offset} 3700 * is negative or greater than {@code length}. 3701 */ 3702 static void checkOffset(int offset, int length) { 3703 if (offset < 0 || offset > length) { 3704 throw new StringIndexOutOfBoundsException("offset " + offset + 3705 ", length " + length); 3706 } 3707 } 3708 3709 /* 3710 * Check {@code offset}, {@code count} against {@code 0} and {@code length} 3711 * bounds. 3712 * 3713 * @throws StringIndexOutOfBoundsException 3714 * If {@code offset} is negative, {@code count} is negative, 3715 * or {@code offset} is greater than {@code length - count} 3716 */ 3717 static void checkBoundsOffCount(int offset, int count, int length) { 3718 if (offset < 0 || count < 0 || offset > length - count) { 3719 throw new StringIndexOutOfBoundsException( 3720 "offset " + offset + ", count " + count + ", length " + length); 3721 } 3722 } 3723 3724 /* 3725 * Check {@code begin}, {@code end} against {@code 0} and {@code length} 3726 * bounds. 3727 * 3728 * @throws StringIndexOutOfBoundsException 3729 * If {@code begin} is negative, {@code begin} is greater than 3730 * {@code end}, or {@code end} is greater than {@code length}. 3731 */ 3732 static void checkBoundsBeginEnd(int begin, int end, int length) { 3733 if (begin < 0 || begin > end || end > length) { 3734 throw new StringIndexOutOfBoundsException( 3735 "begin " + begin + ", end " + end + ", length " + length); 3736 } 3737 } 3738 3739 /** 3740 * Returns the string representation of the {@code codePoint} 3741 * argument. 3742 * 3743 * @param codePoint a {@code codePoint}. 3744 * @return a string of length {@code 1} or {@code 2} containing 3745 * as its single character the argument {@code codePoint}. 3746 * @throws IllegalArgumentException if the specified 3747 * {@code codePoint} is not a {@linkplain Character#isValidCodePoint 3748 * valid Unicode code point}. 3749 */ 3750 static String valueOfCodePoint(int codePoint) { 3751 if (COMPACT_STRINGS && StringLatin1.canEncode(codePoint)) { 3752 return new String(StringLatin1.toBytes((char)codePoint), LATIN1); 3753 } else if (Character.isBmpCodePoint(codePoint)) { 3754 return new String(StringUTF16.toBytes((char)codePoint), UTF16); 3755 } else if (Character.isSupplementaryCodePoint(codePoint)) { 3756 return new String(StringUTF16.toBytesSupplementary(codePoint), UTF16); 3757 } 3758 3759 throw new IllegalArgumentException( 3760 format("Not a valid Unicode code point: 0x%X", codePoint)); 3761 } 3762 3763 /** 3764 * Returns an {@link Optional} containing the nominal descriptor for this 3765 * instance, which is the instance itself. 3766 * 3767 * @return an {@link Optional} describing the {@linkplain String} instance 3768 * @since 12 3769 */ 3770 @Override 3771 public Optional<String> describeConstable() { 3772 return Optional.of(this); 3773 } 3774 3775 /** 3776 * Resolves this instance as a {@link ConstantDesc}, the result of which is 3777 * the instance itself. 3778 * 3779 * @param lookup ignored 3780 * @return the {@linkplain String} instance 3781 * @since 12 3782 */ 3783 @Override 3784 public String resolveConstantDesc(MethodHandles.Lookup lookup) { 3785 return this; 3786 } 3787 3788 }