1 /* 2 * Copyright (c) 1994, 2015, Oracle and/or its affiliates. All rights reserved. 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4 * 5 * This code is free software; you can redistribute it and/or modify it 6 * under the terms of the GNU General Public License version 2 only, as 7 * published by the Free Software Foundation. Oracle designates this 8 * particular file as subject to the "Classpath" exception as provided 9 * by Oracle in the LICENSE file that accompanied this code. 10 * 11 * This code is distributed in the hope that it will be useful, but WITHOUT 12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 14 * version 2 for more details (a copy is included in the LICENSE file that 15 * accompanied this code). 16 * 17 * You should have received a copy of the GNU General Public License version 18 * 2 along with this work; if not, write to the Free Software Foundation, 19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 20 * 21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 22 * or visit www.oracle.com if you need additional information or have any 23 * questions. 24 */ 25 26 package java.lang; 27 28 import java.io.ObjectStreamField; 29 import java.io.UnsupportedEncodingException; 30 import java.nio.charset.Charset; 31 import java.util.ArrayList; 32 import java.util.Arrays; 33 import java.util.Comparator; 34 import java.util.Formatter; 35 import java.util.Locale; 36 import java.util.Objects; 37 import java.util.Spliterator; 38 import java.util.StringJoiner; 39 import java.util.regex.Matcher; 40 import java.util.regex.Pattern; 41 import java.util.regex.PatternSyntaxException; 42 import java.util.stream.IntStream; 43 import java.util.stream.StreamSupport; 44 import jdk.internal.HotSpotIntrinsicCandidate; 45 import jdk.internal.vm.annotation.Stable; 46 47 /** 48 * The {@code String} class represents character strings. All 49 * string literals in Java programs, such as {@code "abc"}, are 50 * implemented as instances of this class. 51 * <p> 52 * Strings are constant; their values cannot be changed after they 53 * are created. String buffers support mutable strings. 54 * Because String objects are immutable they can be shared. For example: 55 * <blockquote><pre> 56 * String str = "abc"; 57 * </pre></blockquote><p> 58 * is equivalent to: 59 * <blockquote><pre> 60 * char data[] = {'a', 'b', 'c'}; 61 * String str = new String(data); 62 * </pre></blockquote><p> 63 * Here are some more examples of how strings can be used: 64 * <blockquote><pre> 65 * System.out.println("abc"); 66 * String cde = "cde"; 67 * System.out.println("abc" + cde); 68 * String c = "abc".substring(2,3); 69 * String d = cde.substring(1, 2); 70 * </pre></blockquote> 71 * <p> 72 * The class {@code String} includes methods for examining 73 * individual characters of the sequence, for comparing strings, for 74 * searching strings, for extracting substrings, and for creating a 75 * copy of a string with all characters translated to uppercase or to 76 * lowercase. Case mapping is based on the Unicode Standard version 77 * specified by the {@link java.lang.Character Character} class. 78 * <p> 79 * The Java language provides special support for the string 80 * concatenation operator ( + ), and for conversion of 81 * other objects to strings. String concatenation is implemented 82 * through the {@code StringBuilder}(or {@code StringBuffer}) 83 * class and its {@code append} method. 84 * String conversions are implemented through the method 85 * {@code toString}, defined by {@code Object} and 86 * inherited by all classes in Java. For additional information on 87 * string concatenation and conversion, see Gosling, Joy, and Steele, 88 * <i>The Java Language Specification</i>. 89 * 90 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor 91 * or method in this class will cause a {@link NullPointerException} to be 92 * thrown. 93 * 94 * <p>A {@code String} represents a string in the UTF-16 format 95 * in which <em>supplementary characters</em> are represented by <em>surrogate 96 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 97 * Character Representations</a> in the {@code Character} class for 98 * more information). 99 * Index values refer to {@code char} code units, so a supplementary 100 * character uses two positions in a {@code String}. 101 * <p>The {@code String} class provides methods for dealing with 102 * Unicode code points (i.e., characters), in addition to those for 103 * dealing with Unicode code units (i.e., {@code char} values). 104 * 105 * <p>Unless otherwise noted, methods for comparing Strings do not take locale 106 * into account. The {@link java.text.Collator} class provides methods for 107 * finer-grain, locale-sensitive String comparison. 108 * 109 * @author Lee Boynton 110 * @author Arthur van Hoff 111 * @author Martin Buchholz 112 * @author Ulf Zibis 113 * @see java.lang.Object#toString() 114 * @see java.lang.StringBuffer 115 * @see java.lang.StringBuilder 116 * @see java.nio.charset.Charset 117 * @since 1.0 118 */ 119 120 public final class String 121 implements java.io.Serializable, Comparable<String>, CharSequence { 122 123 /** 124 * The value is used for character storage. 125 * 126 * @implNote This field is trusted by the VM, and is a subject to 127 * constant folding if String instance is constant. Overwriting this 128 * field after construction will cause problems. 129 * 130 * Additionally, it is marked with {@link Stable} to trust the contents 131 * of the array. No other facility in JDK provides this functionality (yet). 132 * {@link Stable} is safe here, because value is never null. 133 */ 134 @Stable 135 private final byte[] value; 136 137 /** 138 * The identifier of the encoding used to encode the bytes in 139 * {@code value}. The supported values in this implementation are 140 * 141 * LATIN1 142 * UTF16 143 * 144 * @implNote This field is trusted by the VM, and is a subject to 145 * constant folding if String instance is constant. Overwriting this 146 * field after construction will cause problems. 147 */ 148 private final byte coder; 149 150 /** Cache the hash code for the string */ 151 private int hash; // Default to 0 152 153 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 154 private static final long serialVersionUID = -6849794470754667710L; 155 156 /** 157 * If String compaction is disabled, the bytes in {@code value} are 158 * always encoded in UTF16. 159 * 160 * For methods with several possible implementation paths, when String 161 * compaction is disabled, only one code path is taken. 162 * 163 * The instance field value is generally opaque to optimizing JIT 164 * compilers. Therefore, in performance-sensitive place, an explicit 165 * check of the static boolean {@code COMPACT_STRINGS} is done first 166 * before checking the {@code coder} field since the static boolean 167 * {@code COMPACT_STRINGS} would be constant folded away by an 168 * optimizing JIT compiler. The idioms for these cases are as follows. 169 * 170 * For code such as: 171 * 172 * if (coder == LATIN1) { ... } 173 * 174 * can be written more optimally as 175 * 176 * if (coder() == LATIN1) { ... } 177 * 178 * or: 179 * 180 * if (COMPACT_STRINGS && coder == LATIN1) { ... } 181 * 182 * An optimizing JIT compiler can fold the above conditional as: 183 * 184 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... } 185 * COMPACT_STRINGS == false => if (false) { ... } 186 * 187 * @implNote 188 * The actual value for this field is injected by JVM. The static 189 * initialization block is used to set the value here to communicate 190 * that this static final field is not statically foldable, and to 191 * avoid any possible circular dependency during vm initialization. 192 */ 193 static final boolean COMPACT_STRINGS; 194 195 static { 196 COMPACT_STRINGS = true; 197 } 198 199 /** 200 * Class String is special cased within the Serialization Stream Protocol. 201 * 202 * A String instance is written into an ObjectOutputStream according to 203 * <a href="{@docRoot}/../platform/serialization/spec/output.html"> 204 * Object Serialization Specification, Section 6.2, "Stream Elements"</a> 205 */ 206 private static final ObjectStreamField[] serialPersistentFields = 207 new ObjectStreamField[0]; 208 209 /** 210 * Initializes a newly created {@code String} object so that it represents 211 * an empty character sequence. Note that use of this constructor is 212 * unnecessary since Strings are immutable. 213 */ 214 public String() { 215 this.value = "".value; 216 this.coder = "".coder; 217 } 218 219 /** 220 * Initializes a newly created {@code String} object so that it represents 221 * the same sequence of characters as the argument; in other words, the 222 * newly created string is a copy of the argument string. Unless an 223 * explicit copy of {@code original} is needed, use of this constructor is 224 * unnecessary since Strings are immutable. 225 * 226 * @param original 227 * A {@code String} 228 */ 229 @HotSpotIntrinsicCandidate 230 public String(String original) { 231 this.value = original.value; 232 this.coder = original.coder; 233 this.hash = original.hash; 234 } 235 236 /** 237 * Allocates a new {@code String} so that it represents the sequence of 238 * characters currently contained in the character array argument. The 239 * contents of the character array are copied; subsequent modification of 240 * the character array does not affect the newly created string. 241 * 242 * @param value 243 * The initial value of the string 244 */ 245 public String(char value[]) { 246 this(value, 0, value.length, null); 247 } 248 249 /** 250 * Allocates a new {@code String} that contains characters from a subarray 251 * of the character array argument. The {@code offset} argument is the 252 * index of the first character of the subarray and the {@code count} 253 * argument specifies the length of the subarray. The contents of the 254 * subarray are copied; subsequent modification of the character array does 255 * not affect the newly created string. 256 * 257 * @param value 258 * Array that is the source of characters 259 * 260 * @param offset 261 * The initial offset 262 * 263 * @param count 264 * The length 265 * 266 * @throws IndexOutOfBoundsException 267 * If {@code offset} is negative, {@code count} is negative, or 268 * {@code offset} is greater than {@code value.length - count} 269 */ 270 public String(char value[], int offset, int count) { 271 this(value, offset, count, rangeCheck(value, offset, count)); 272 } 273 274 private static Void rangeCheck(char[] value, int offset, int count) { 275 checkBoundsOffCount(offset, count, value.length); 276 return null; 277 } 278 279 /** 280 * Allocates a new {@code String} that contains characters from a subarray 281 * of the <a href="Character.html#unicode">Unicode code point</a> array 282 * argument. The {@code offset} argument is the index of the first code 283 * point of the subarray and the {@code count} argument specifies the 284 * length of the subarray. The contents of the subarray are converted to 285 * {@code char}s; subsequent modification of the {@code int} array does not 286 * affect the newly created string. 287 * 288 * @param codePoints 289 * Array that is the source of Unicode code points 290 * 291 * @param offset 292 * The initial offset 293 * 294 * @param count 295 * The length 296 * 297 * @throws IllegalArgumentException 298 * If any invalid Unicode code point is found in {@code 299 * codePoints} 300 * 301 * @throws IndexOutOfBoundsException 302 * If {@code offset} is negative, {@code count} is negative, or 303 * {@code offset} is greater than {@code codePoints.length - count} 304 * 305 * @since 1.5 306 */ 307 public String(int[] codePoints, int offset, int count) { 308 checkBoundsOffCount(offset, count, codePoints.length); 309 if (count == 0) { 310 this.value = "".value; 311 this.coder = "".coder; 312 return; 313 } 314 if (COMPACT_STRINGS) { 315 byte[] val = StringLatin1.toBytes(codePoints, offset, count); 316 if (val != null) { 317 this.coder = LATIN1; 318 this.value = val; 319 return; 320 } 321 } 322 this.coder = UTF16; 323 this.value = StringUTF16.toBytes(codePoints, offset, count); 324 } 325 326 /** 327 * Allocates a new {@code String} constructed from a subarray of an array 328 * of 8-bit integer values. 329 * 330 * <p> The {@code offset} argument is the index of the first byte of the 331 * subarray, and the {@code count} argument specifies the length of the 332 * subarray. 333 * 334 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 335 * specified in the method above. 336 * 337 * @deprecated This method does not properly convert bytes into characters. 338 * As of JDK 1.1, the preferred way to do this is via the 339 * {@code String} constructors that take a {@link 340 * java.nio.charset.Charset}, charset name, or that use the platform's 341 * default charset. 342 * 343 * @param ascii 344 * The bytes to be converted to characters 345 * 346 * @param hibyte 347 * The top 8 bits of each 16-bit Unicode code unit 348 * 349 * @param offset 350 * The initial offset 351 * @param count 352 * The length 353 * 354 * @throws IndexOutOfBoundsException 355 * If {@code offset} is negative, {@code count} is negative, or 356 * {@code offset} is greater than {@code ascii.length - count} 357 * 358 * @see #String(byte[], int) 359 * @see #String(byte[], int, int, java.lang.String) 360 * @see #String(byte[], int, int, java.nio.charset.Charset) 361 * @see #String(byte[], int, int) 362 * @see #String(byte[], java.lang.String) 363 * @see #String(byte[], java.nio.charset.Charset) 364 * @see #String(byte[]) 365 */ 366 @Deprecated(since="1.1") 367 public String(byte ascii[], int hibyte, int offset, int count) { 368 checkBoundsOffCount(offset, count, ascii.length); 369 if (count == 0) { 370 this.value = "".value; 371 this.coder = "".coder; 372 return; 373 } 374 if (COMPACT_STRINGS && (byte)hibyte == 0) { 375 this.value = Arrays.copyOfRange(ascii, offset, offset + count); 376 this.coder = LATIN1; 377 } else { 378 hibyte <<= 8; 379 byte[] val = StringUTF16.newBytesFor(count); 380 for (int i = 0; i < count; i++) { 381 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff)); 382 } 383 this.value = val; 384 this.coder = UTF16; 385 } 386 } 387 388 /** 389 * Allocates a new {@code String} containing characters constructed from 390 * an array of 8-bit integer values. Each character <i>c</i>in the 391 * resulting string is constructed from the corresponding component 392 * <i>b</i> in the byte array such that: 393 * 394 * <blockquote><pre> 395 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 396 * | (<b><i>b</i></b> & 0xff)) 397 * </pre></blockquote> 398 * 399 * @deprecated This method does not properly convert bytes into 400 * characters. As of JDK 1.1, the preferred way to do this is via the 401 * {@code String} constructors that take a {@link 402 * java.nio.charset.Charset}, charset name, or that use the platform's 403 * default charset. 404 * 405 * @param ascii 406 * The bytes to be converted to characters 407 * 408 * @param hibyte 409 * The top 8 bits of each 16-bit Unicode code unit 410 * 411 * @see #String(byte[], int, int, java.lang.String) 412 * @see #String(byte[], int, int, java.nio.charset.Charset) 413 * @see #String(byte[], int, int) 414 * @see #String(byte[], java.lang.String) 415 * @see #String(byte[], java.nio.charset.Charset) 416 * @see #String(byte[]) 417 */ 418 @Deprecated(since="1.1") 419 public String(byte ascii[], int hibyte) { 420 this(ascii, hibyte, 0, ascii.length); 421 } 422 423 /** 424 * Constructs a new {@code String} by decoding the specified subarray of 425 * bytes using the specified charset. The length of the new {@code String} 426 * is a function of the charset, and hence may not be equal to the length 427 * of the subarray. 428 * 429 * <p> The behavior of this constructor when the given bytes are not valid 430 * in the given charset is unspecified. The {@link 431 * java.nio.charset.CharsetDecoder} class should be used when more control 432 * over the decoding process is required. 433 * 434 * @param bytes 435 * The bytes to be decoded into characters 436 * 437 * @param offset 438 * The index of the first byte to decode 439 * 440 * @param length 441 * The number of bytes to decode 442 443 * @param charsetName 444 * The name of a supported {@linkplain java.nio.charset.Charset 445 * charset} 446 * 447 * @throws UnsupportedEncodingException 448 * If the named charset is not supported 449 * 450 * @throws IndexOutOfBoundsException 451 * If {@code offset} is negative, {@code length} is negative, or 452 * {@code offset} is greater than {@code bytes.length - length} 453 * 454 * @since 1.1 455 */ 456 public String(byte bytes[], int offset, int length, String charsetName) 457 throws UnsupportedEncodingException { 458 if (charsetName == null) 459 throw new NullPointerException("charsetName"); 460 checkBoundsOffCount(offset, length, bytes.length); 461 StringCoding.Result ret = 462 StringCoding.decode(charsetName, bytes, offset, length); 463 this.value = ret.value; 464 this.coder = ret.coder; 465 } 466 467 /** 468 * Constructs a new {@code String} by decoding the specified subarray of 469 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 470 * The length of the new {@code String} is a function of the charset, and 471 * hence may not be equal to the length of the subarray. 472 * 473 * <p> This method always replaces malformed-input and unmappable-character 474 * sequences with this charset's default replacement string. The {@link 475 * java.nio.charset.CharsetDecoder} class should be used when more control 476 * over the decoding process is required. 477 * 478 * @param bytes 479 * The bytes to be decoded into characters 480 * 481 * @param offset 482 * The index of the first byte to decode 483 * 484 * @param length 485 * The number of bytes to decode 486 * 487 * @param charset 488 * The {@linkplain java.nio.charset.Charset charset} to be used to 489 * decode the {@code bytes} 490 * 491 * @throws IndexOutOfBoundsException 492 * If {@code offset} is negative, {@code length} is negative, or 493 * {@code offset} is greater than {@code bytes.length - length} 494 * 495 * @since 1.6 496 */ 497 public String(byte bytes[], int offset, int length, Charset charset) { 498 if (charset == null) 499 throw new NullPointerException("charset"); 500 checkBoundsOffCount(offset, length, bytes.length); 501 StringCoding.Result ret = 502 StringCoding.decode(charset, bytes, offset, length); 503 this.value = ret.value; 504 this.coder = ret.coder; 505 } 506 507 /** 508 * Constructs a new {@code String} by decoding the specified array of bytes 509 * using the specified {@linkplain java.nio.charset.Charset charset}. The 510 * length of the new {@code String} is a function of the charset, and hence 511 * may not be equal to the length of the byte array. 512 * 513 * <p> The behavior of this constructor when the given bytes are not valid 514 * in the given charset is unspecified. The {@link 515 * java.nio.charset.CharsetDecoder} class should be used when more control 516 * over the decoding process is required. 517 * 518 * @param bytes 519 * The bytes to be decoded into characters 520 * 521 * @param charsetName 522 * The name of a supported {@linkplain java.nio.charset.Charset 523 * charset} 524 * 525 * @throws UnsupportedEncodingException 526 * If the named charset is not supported 527 * 528 * @since 1.1 529 */ 530 public String(byte bytes[], String charsetName) 531 throws UnsupportedEncodingException { 532 this(bytes, 0, bytes.length, charsetName); 533 } 534 535 /** 536 * Constructs a new {@code String} by decoding the specified array of 537 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 538 * The length of the new {@code String} is a function of the charset, and 539 * hence may not be equal to the length of the byte array. 540 * 541 * <p> This method always replaces malformed-input and unmappable-character 542 * sequences with this charset's default replacement string. The {@link 543 * java.nio.charset.CharsetDecoder} class should be used when more control 544 * over the decoding process is required. 545 * 546 * @param bytes 547 * The bytes to be decoded into characters 548 * 549 * @param charset 550 * The {@linkplain java.nio.charset.Charset charset} to be used to 551 * decode the {@code bytes} 552 * 553 * @since 1.6 554 */ 555 public String(byte bytes[], Charset charset) { 556 this(bytes, 0, bytes.length, charset); 557 } 558 559 /** 560 * Constructs a new {@code String} by decoding the specified subarray of 561 * bytes using the platform's default charset. The length of the new 562 * {@code String} is a function of the charset, and hence may not be equal 563 * to the length of the subarray. 564 * 565 * <p> The behavior of this constructor when the given bytes are not valid 566 * in the default charset is unspecified. The {@link 567 * java.nio.charset.CharsetDecoder} class should be used when more control 568 * over the decoding process is required. 569 * 570 * @param bytes 571 * The bytes to be decoded into characters 572 * 573 * @param offset 574 * The index of the first byte to decode 575 * 576 * @param length 577 * The number of bytes to decode 578 * 579 * @throws IndexOutOfBoundsException 580 * If {@code offset} is negative, {@code length} is negative, or 581 * {@code offset} is greater than {@code bytes.length - length} 582 * 583 * @since 1.1 584 */ 585 public String(byte bytes[], int offset, int length) { 586 checkBoundsOffCount(offset, length, bytes.length); 587 StringCoding.Result ret = StringCoding.decode(bytes, offset, length); 588 this.value = ret.value; 589 this.coder = ret.coder; 590 } 591 592 /** 593 * Constructs a new {@code String} by decoding the specified array of bytes 594 * using the platform's default charset. The length of the new {@code 595 * String} is a function of the charset, and hence may not be equal to the 596 * length of the byte array. 597 * 598 * <p> The behavior of this constructor when the given bytes are not valid 599 * in the default charset is unspecified. The {@link 600 * java.nio.charset.CharsetDecoder} class should be used when more control 601 * over the decoding process is required. 602 * 603 * @param bytes 604 * The bytes to be decoded into characters 605 * 606 * @since 1.1 607 */ 608 public String(byte[] bytes) { 609 this(bytes, 0, bytes.length); 610 } 611 612 /** 613 * Allocates a new string that contains the sequence of characters 614 * currently contained in the string buffer argument. The contents of the 615 * string buffer are copied; subsequent modification of the string buffer 616 * does not affect the newly created string. 617 * 618 * @param buffer 619 * A {@code StringBuffer} 620 */ 621 public String(StringBuffer buffer) { 622 this(buffer.toString()); 623 } 624 625 /** 626 * Allocates a new string that contains the sequence of characters 627 * currently contained in the string builder argument. The contents of the 628 * string builder are copied; subsequent modification of the string builder 629 * does not affect the newly created string. 630 * 631 * <p> This constructor is provided to ease migration to {@code 632 * StringBuilder}. Obtaining a string from a string builder via the {@code 633 * toString} method is likely to run faster and is generally preferred. 634 * 635 * @param builder 636 * A {@code StringBuilder} 637 * 638 * @since 1.5 639 */ 640 public String(StringBuilder builder) { 641 this(builder, null); 642 } 643 644 /* 645 * Package private constructor which shares value array for speed. 646 * this constructor is always expected to be called with share==true. 647 * a separate constructor is needed because we already have a public 648 * String(char[]) constructor that makes a copy of the given char[]. 649 */ 650 // TBD: this is kept for package internal use (Thread/System), 651 // should be removed if they all have a byte[] version 652 String(char[] val, boolean share) { 653 // assert share : "unshared not supported"; 654 this(val, 0, val.length, null); 655 } 656 657 /** 658 * Returns the length of this string. 659 * The length is equal to the number of <a href="Character.html#unicode">Unicode 660 * code units</a> in the string. 661 * 662 * @return the length of the sequence of characters represented by this 663 * object. 664 */ 665 public int length() { 666 return value.length >> coder(); 667 } 668 669 /** 670 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 671 * 672 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 673 * {@code false} 674 * 675 * @since 1.6 676 */ 677 public boolean isEmpty() { 678 return value.length == 0; 679 } 680 681 /** 682 * Returns the {@code char} value at the 683 * specified index. An index ranges from {@code 0} to 684 * {@code length() - 1}. The first {@code char} value of the sequence 685 * is at index {@code 0}, the next at index {@code 1}, 686 * and so on, as for array indexing. 687 * 688 * <p>If the {@code char} value specified by the index is a 689 * <a href="Character.html#unicode">surrogate</a>, the surrogate 690 * value is returned. 691 * 692 * @param index the index of the {@code char} value. 693 * @return the {@code char} value at the specified index of this string. 694 * The first {@code char} value is at index {@code 0}. 695 * @exception IndexOutOfBoundsException if the {@code index} 696 * argument is negative or not less than the length of this 697 * string. 698 */ 699 public char charAt(int index) { 700 if (isLatin1()) { 701 return StringLatin1.charAt(value, index); 702 } else { 703 return StringUTF16.charAt(value, index); 704 } 705 } 706 707 /** 708 * Returns the character (Unicode code point) at the specified 709 * index. The index refers to {@code char} values 710 * (Unicode code units) and ranges from {@code 0} to 711 * {@link #length()}{@code - 1}. 712 * 713 * <p> If the {@code char} value specified at the given index 714 * is in the high-surrogate range, the following index is less 715 * than the length of this {@code String}, and the 716 * {@code char} value at the following index is in the 717 * low-surrogate range, then the supplementary code point 718 * corresponding to this surrogate pair is returned. Otherwise, 719 * the {@code char} value at the given index is returned. 720 * 721 * @param index the index to the {@code char} values 722 * @return the code point value of the character at the 723 * {@code index} 724 * @exception IndexOutOfBoundsException if the {@code index} 725 * argument is negative or not less than the length of this 726 * string. 727 * @since 1.5 728 */ 729 public int codePointAt(int index) { 730 if (isLatin1()) { 731 checkIndex(index, value.length); 732 return value[index] & 0xff; 733 } 734 int length = value.length >> 1; 735 checkIndex(index, length); 736 return StringUTF16.codePointAt(value, index, length); 737 } 738 739 /** 740 * Returns the character (Unicode code point) before the specified 741 * index. The index refers to {@code char} values 742 * (Unicode code units) and ranges from {@code 1} to {@link 743 * CharSequence#length() length}. 744 * 745 * <p> If the {@code char} value at {@code (index - 1)} 746 * is in the low-surrogate range, {@code (index - 2)} is not 747 * negative, and the {@code char} value at {@code (index - 748 * 2)} is in the high-surrogate range, then the 749 * supplementary code point value of the surrogate pair is 750 * returned. If the {@code char} value at {@code index - 751 * 1} is an unpaired low-surrogate or a high-surrogate, the 752 * surrogate value is returned. 753 * 754 * @param index the index following the code point that should be returned 755 * @return the Unicode code point value before the given index. 756 * @exception IndexOutOfBoundsException if the {@code index} 757 * argument is less than 1 or greater than the length 758 * of this string. 759 * @since 1.5 760 */ 761 public int codePointBefore(int index) { 762 int i = index - 1; 763 if (i < 0 || i >= length()) { 764 throw new StringIndexOutOfBoundsException(index); 765 } 766 if (isLatin1()) { 767 return (value[i] & 0xff); 768 } 769 return StringUTF16.codePointBefore(value, index); 770 } 771 772 /** 773 * Returns the number of Unicode code points in the specified text 774 * range of this {@code String}. The text range begins at the 775 * specified {@code beginIndex} and extends to the 776 * {@code char} at index {@code endIndex - 1}. Thus the 777 * length (in {@code char}s) of the text range is 778 * {@code endIndex-beginIndex}. Unpaired surrogates within 779 * the text range count as one code point each. 780 * 781 * @param beginIndex the index to the first {@code char} of 782 * the text range. 783 * @param endIndex the index after the last {@code char} of 784 * the text range. 785 * @return the number of Unicode code points in the specified text 786 * range 787 * @exception IndexOutOfBoundsException if the 788 * {@code beginIndex} is negative, or {@code endIndex} 789 * is larger than the length of this {@code String}, or 790 * {@code beginIndex} is larger than {@code endIndex}. 791 * @since 1.5 792 */ 793 public int codePointCount(int beginIndex, int endIndex) { 794 if (beginIndex < 0 || beginIndex > endIndex || 795 endIndex > length()) { 796 throw new IndexOutOfBoundsException(); 797 } 798 if (isLatin1()) { 799 return endIndex - beginIndex; 800 } 801 return StringUTF16.codePointCount(value, beginIndex, endIndex); 802 } 803 804 /** 805 * Returns the index within this {@code String} that is 806 * offset from the given {@code index} by 807 * {@code codePointOffset} code points. Unpaired surrogates 808 * within the text range given by {@code index} and 809 * {@code codePointOffset} count as one code point each. 810 * 811 * @param index the index to be offset 812 * @param codePointOffset the offset in code points 813 * @return the index within this {@code String} 814 * @exception IndexOutOfBoundsException if {@code index} 815 * is negative or larger then the length of this 816 * {@code String}, or if {@code codePointOffset} is positive 817 * and the substring starting with {@code index} has fewer 818 * than {@code codePointOffset} code points, 819 * or if {@code codePointOffset} is negative and the substring 820 * before {@code index} has fewer than the absolute value 821 * of {@code codePointOffset} code points. 822 * @since 1.5 823 */ 824 public int offsetByCodePoints(int index, int codePointOffset) { 825 if (index < 0 || index > length()) { 826 throw new IndexOutOfBoundsException(); 827 } 828 return Character.offsetByCodePoints(this, index, codePointOffset); 829 } 830 831 /** 832 * Copies characters from this string into the destination character 833 * array. 834 * <p> 835 * The first character to be copied is at index {@code srcBegin}; 836 * the last character to be copied is at index {@code srcEnd-1} 837 * (thus the total number of characters to be copied is 838 * {@code srcEnd-srcBegin}). The characters are copied into the 839 * subarray of {@code dst} starting at index {@code dstBegin} 840 * and ending at index: 841 * <blockquote><pre> 842 * dstBegin + (srcEnd-srcBegin) - 1 843 * </pre></blockquote> 844 * 845 * @param srcBegin index of the first character in the string 846 * to copy. 847 * @param srcEnd index after the last character in the string 848 * to copy. 849 * @param dst the destination array. 850 * @param dstBegin the start offset in the destination array. 851 * @exception IndexOutOfBoundsException If any of the following 852 * is true: 853 * <ul><li>{@code srcBegin} is negative. 854 * <li>{@code srcBegin} is greater than {@code srcEnd} 855 * <li>{@code srcEnd} is greater than the length of this 856 * string 857 * <li>{@code dstBegin} is negative 858 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 859 * {@code dst.length}</ul> 860 */ 861 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 862 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 863 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 864 if (isLatin1()) { 865 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin); 866 } else { 867 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin); 868 } 869 } 870 871 /** 872 * Copies characters from this string into the destination byte array. Each 873 * byte receives the 8 low-order bits of the corresponding character. The 874 * eight high-order bits of each character are not copied and do not 875 * participate in the transfer in any way. 876 * 877 * <p> The first character to be copied is at index {@code srcBegin}; the 878 * last character to be copied is at index {@code srcEnd-1}. The total 879 * number of characters to be copied is {@code srcEnd-srcBegin}. The 880 * characters, converted to bytes, are copied into the subarray of {@code 881 * dst} starting at index {@code dstBegin} and ending at index: 882 * 883 * <blockquote><pre> 884 * dstBegin + (srcEnd-srcBegin) - 1 885 * </pre></blockquote> 886 * 887 * @deprecated This method does not properly convert characters into 888 * bytes. As of JDK 1.1, the preferred way to do this is via the 889 * {@link #getBytes()} method, which uses the platform's default charset. 890 * 891 * @param srcBegin 892 * Index of the first character in the string to copy 893 * 894 * @param srcEnd 895 * Index after the last character in the string to copy 896 * 897 * @param dst 898 * The destination array 899 * 900 * @param dstBegin 901 * The start offset in the destination array 902 * 903 * @throws IndexOutOfBoundsException 904 * If any of the following is true: 905 * <ul> 906 * <li> {@code srcBegin} is negative 907 * <li> {@code srcBegin} is greater than {@code srcEnd} 908 * <li> {@code srcEnd} is greater than the length of this String 909 * <li> {@code dstBegin} is negative 910 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 911 * dst.length} 912 * </ul> 913 */ 914 @Deprecated(since="1.1") 915 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 916 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 917 Objects.requireNonNull(dst); 918 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 919 if (isLatin1()) { 920 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 921 } else { 922 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 923 } 924 } 925 926 /** 927 * Encodes this {@code String} into a sequence of bytes using the named 928 * charset, storing the result into a new byte array. 929 * 930 * <p> The behavior of this method when this string cannot be encoded in 931 * the given charset is unspecified. The {@link 932 * java.nio.charset.CharsetEncoder} class should be used when more control 933 * over the encoding process is required. 934 * 935 * @param charsetName 936 * The name of a supported {@linkplain java.nio.charset.Charset 937 * charset} 938 * 939 * @return The resultant byte array 940 * 941 * @throws UnsupportedEncodingException 942 * If the named charset is not supported 943 * 944 * @since 1.1 945 */ 946 public byte[] getBytes(String charsetName) 947 throws UnsupportedEncodingException { 948 if (charsetName == null) throw new NullPointerException(); 949 return StringCoding.encode(charsetName, coder(), value); 950 } 951 952 /** 953 * Encodes this {@code String} into a sequence of bytes using the given 954 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 955 * new byte array. 956 * 957 * <p> This method always replaces malformed-input and unmappable-character 958 * sequences with this charset's default replacement byte array. The 959 * {@link java.nio.charset.CharsetEncoder} class should be used when more 960 * control over the encoding process is required. 961 * 962 * @param charset 963 * The {@linkplain java.nio.charset.Charset} to be used to encode 964 * the {@code String} 965 * 966 * @return The resultant byte array 967 * 968 * @since 1.6 969 */ 970 public byte[] getBytes(Charset charset) { 971 if (charset == null) throw new NullPointerException(); 972 return StringCoding.encode(charset, coder(), value); 973 } 974 975 /** 976 * Encodes this {@code String} into a sequence of bytes using the 977 * platform's default charset, storing the result into a new byte array. 978 * 979 * <p> The behavior of this method when this string cannot be encoded in 980 * the default charset is unspecified. The {@link 981 * java.nio.charset.CharsetEncoder} class should be used when more control 982 * over the encoding process is required. 983 * 984 * @return The resultant byte array 985 * 986 * @since 1.1 987 */ 988 public byte[] getBytes() { 989 return StringCoding.encode(coder(), value); 990 } 991 992 /** 993 * Compares this string to the specified object. The result is {@code 994 * true} if and only if the argument is not {@code null} and is a {@code 995 * String} object that represents the same sequence of characters as this 996 * object. 997 * 998 * <p>For finer-grained String comparison, refer to 999 * {@link java.text.Collator}. 1000 * 1001 * @param anObject 1002 * The object to compare this {@code String} against 1003 * 1004 * @return {@code true} if the given object represents a {@code String} 1005 * equivalent to this string, {@code false} otherwise 1006 * 1007 * @see #compareTo(String) 1008 * @see #equalsIgnoreCase(String) 1009 */ 1010 public boolean equals(Object anObject) { 1011 if (this == anObject) { 1012 return true; 1013 } 1014 if (anObject instanceof String) { 1015 String aString = (String)anObject; 1016 if (coder() == aString.coder()) { 1017 return isLatin1() ? StringLatin1.equals(value, aString.value) 1018 : StringUTF16.equals(value, aString.value); 1019 } 1020 } 1021 return false; 1022 } 1023 1024 /** 1025 * Compares this string to the specified {@code StringBuffer}. The result 1026 * is {@code true} if and only if this {@code String} represents the same 1027 * sequence of characters as the specified {@code StringBuffer}. This method 1028 * synchronizes on the {@code StringBuffer}. 1029 * 1030 * <p>For finer-grained String comparison, refer to 1031 * {@link java.text.Collator}. 1032 * 1033 * @param sb 1034 * The {@code StringBuffer} to compare this {@code String} against 1035 * 1036 * @return {@code true} if this {@code String} represents the same 1037 * sequence of characters as the specified {@code StringBuffer}, 1038 * {@code false} otherwise 1039 * 1040 * @since 1.4 1041 */ 1042 public boolean contentEquals(StringBuffer sb) { 1043 return contentEquals((CharSequence)sb); 1044 } 1045 1046 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1047 int len = length(); 1048 if (len != sb.length()) { 1049 return false; 1050 } 1051 byte v1[] = value; 1052 byte v2[] = sb.getValue(); 1053 if (coder() == sb.getCoder()) { 1054 int n = v1.length; 1055 for (int i = 0; i < n; i++) { 1056 if (v1[i] != v2[i]) { 1057 return false; 1058 } 1059 } 1060 } else { 1061 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal" 1062 return false; 1063 } 1064 for (int i = 0; i < len; i++) { 1065 if ((char)(v1[i] & 0xff) != StringUTF16.getChar(v2, i)) { 1066 return false; 1067 } 1068 } 1069 } 1070 return true; 1071 } 1072 1073 /** 1074 * Compares this string to the specified {@code CharSequence}. The 1075 * result is {@code true} if and only if this {@code String} represents the 1076 * same sequence of char values as the specified sequence. Note that if the 1077 * {@code CharSequence} is a {@code StringBuffer} then the method 1078 * synchronizes on it. 1079 * 1080 * <p>For finer-grained String comparison, refer to 1081 * {@link java.text.Collator}. 1082 * 1083 * @param cs 1084 * The sequence to compare this {@code String} against 1085 * 1086 * @return {@code true} if this {@code String} represents the same 1087 * sequence of char values as the specified sequence, {@code 1088 * false} otherwise 1089 * 1090 * @since 1.5 1091 */ 1092 public boolean contentEquals(CharSequence cs) { 1093 // Argument is a StringBuffer, StringBuilder 1094 if (cs instanceof AbstractStringBuilder) { 1095 if (cs instanceof StringBuffer) { 1096 synchronized(cs) { 1097 return nonSyncContentEquals((AbstractStringBuilder)cs); 1098 } 1099 } else { 1100 return nonSyncContentEquals((AbstractStringBuilder)cs); 1101 } 1102 } 1103 // Argument is a String 1104 if (cs instanceof String) { 1105 return equals(cs); 1106 } 1107 // Argument is a generic CharSequence 1108 int n = cs.length(); 1109 if (n != length()) { 1110 return false; 1111 } 1112 byte[] val = this.value; 1113 if (isLatin1()) { 1114 for (int i = 0; i < n; i++) { 1115 if ((val[i] & 0xff) != cs.charAt(i)) { 1116 return false; 1117 } 1118 } 1119 } else { 1120 for (int i = 0; i < n; i++) { 1121 if (StringUTF16.getChar(val, i) != cs.charAt(i)) { 1122 return false; 1123 } 1124 } 1125 } 1126 return true; 1127 } 1128 1129 /** 1130 * Compares this {@code String} to another {@code String}, ignoring case 1131 * considerations. Two strings are considered equal ignoring case if they 1132 * are of the same length and corresponding characters in the two strings 1133 * are equal ignoring case. 1134 * 1135 * <p> Two characters {@code c1} and {@code c2} are considered the same 1136 * ignoring case if at least one of the following is true: 1137 * <ul> 1138 * <li> The two characters are the same (as compared by the 1139 * {@code ==} operator) 1140 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))} 1141 * on each character produces the same result 1142 * </ul> 1143 * 1144 * <p>Note that this method does <em>not</em> take locale into account, and 1145 * will result in unsatisfactory results for certain locales. The 1146 * {@link java.text.Collator} class provides locale-sensitive comparison. 1147 * 1148 * @param anotherString 1149 * The {@code String} to compare this {@code String} against 1150 * 1151 * @return {@code true} if the argument is not {@code null} and it 1152 * represents an equivalent {@code String} ignoring case; {@code 1153 * false} otherwise 1154 * 1155 * @see #equals(Object) 1156 */ 1157 public boolean equalsIgnoreCase(String anotherString) { 1158 return (this == anotherString) ? true 1159 : (anotherString != null) 1160 && (anotherString.length() == length()) 1161 && regionMatches(true, 0, anotherString, 0, length()); 1162 } 1163 1164 /** 1165 * Compares two strings lexicographically. 1166 * The comparison is based on the Unicode value of each character in 1167 * the strings. The character sequence represented by this 1168 * {@code String} object is compared lexicographically to the 1169 * character sequence represented by the argument string. The result is 1170 * a negative integer if this {@code String} object 1171 * lexicographically precedes the argument string. The result is a 1172 * positive integer if this {@code String} object lexicographically 1173 * follows the argument string. The result is zero if the strings 1174 * are equal; {@code compareTo} returns {@code 0} exactly when 1175 * the {@link #equals(Object)} method would return {@code true}. 1176 * <p> 1177 * This is the definition of lexicographic ordering. If two strings are 1178 * different, then either they have different characters at some index 1179 * that is a valid index for both strings, or their lengths are different, 1180 * or both. If they have different characters at one or more index 1181 * positions, let <i>k</i> be the smallest such index; then the string 1182 * whose character at position <i>k</i> has the smaller value, as 1183 * determined by using the {@code <} operator, lexicographically precedes the 1184 * other string. In this case, {@code compareTo} returns the 1185 * difference of the two character values at position {@code k} in 1186 * the two string -- that is, the value: 1187 * <blockquote><pre> 1188 * this.charAt(k)-anotherString.charAt(k) 1189 * </pre></blockquote> 1190 * If there is no index position at which they differ, then the shorter 1191 * string lexicographically precedes the longer string. In this case, 1192 * {@code compareTo} returns the difference of the lengths of the 1193 * strings -- that is, the value: 1194 * <blockquote><pre> 1195 * this.length()-anotherString.length() 1196 * </pre></blockquote> 1197 * 1198 * <p>For finer-grained String comparison, refer to 1199 * {@link java.text.Collator}. 1200 * 1201 * @param anotherString the {@code String} to be compared. 1202 * @return the value {@code 0} if the argument string is equal to 1203 * this string; a value less than {@code 0} if this string 1204 * is lexicographically less than the string argument; and a 1205 * value greater than {@code 0} if this string is 1206 * lexicographically greater than the string argument. 1207 */ 1208 public int compareTo(String anotherString) { 1209 byte v1[] = value; 1210 byte v2[] = anotherString.value; 1211 if (coder() == anotherString.coder()) { 1212 return isLatin1() ? StringLatin1.compareTo(v1, v2) 1213 : StringUTF16.compareTo(v1, v2); 1214 } 1215 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2) 1216 : StringUTF16.compareToLatin1(v1, v2); 1217 } 1218 1219 /** 1220 * A Comparator that orders {@code String} objects as by 1221 * {@code compareToIgnoreCase}. This comparator is serializable. 1222 * <p> 1223 * Note that this Comparator does <em>not</em> take locale into account, 1224 * and will result in an unsatisfactory ordering for certain locales. 1225 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1226 * 1227 * @see java.text.Collator 1228 * @since 1.2 1229 */ 1230 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1231 = new CaseInsensitiveComparator(); 1232 private static class CaseInsensitiveComparator 1233 implements Comparator<String>, java.io.Serializable { 1234 // use serialVersionUID from JDK 1.2.2 for interoperability 1235 private static final long serialVersionUID = 8575799808933029326L; 1236 1237 public int compare(String s1, String s2) { 1238 byte v1[] = s1.value; 1239 byte v2[] = s2.value; 1240 if (s1.coder() == s2.coder()) { 1241 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2) 1242 : StringUTF16.compareToCI(v1, v2); 1243 } 1244 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2) 1245 : StringUTF16.compareToCI_Latin1(v1, v2); 1246 } 1247 1248 /** Replaces the de-serialized object. */ 1249 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1250 } 1251 1252 /** 1253 * Compares two strings lexicographically, ignoring case 1254 * differences. This method returns an integer whose sign is that of 1255 * calling {@code compareTo} with normalized versions of the strings 1256 * where case differences have been eliminated by calling 1257 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1258 * each character. 1259 * <p> 1260 * Note that this method does <em>not</em> take locale into account, 1261 * and will result in an unsatisfactory ordering for certain locales. 1262 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1263 * 1264 * @param str the {@code String} to be compared. 1265 * @return a negative integer, zero, or a positive integer as the 1266 * specified String is greater than, equal to, or less 1267 * than this String, ignoring case considerations. 1268 * @see java.text.Collator 1269 * @since 1.2 1270 */ 1271 public int compareToIgnoreCase(String str) { 1272 return CASE_INSENSITIVE_ORDER.compare(this, str); 1273 } 1274 1275 /** 1276 * Tests if two string regions are equal. 1277 * <p> 1278 * A substring of this {@code String} object is compared to a substring 1279 * of the argument other. The result is true if these substrings 1280 * represent identical character sequences. The substring of this 1281 * {@code String} object to be compared begins at index {@code toffset} 1282 * and has length {@code len}. The substring of other to be compared 1283 * begins at index {@code ooffset} and has length {@code len}. The 1284 * result is {@code false} if and only if at least one of the following 1285 * is true: 1286 * <ul><li>{@code toffset} is negative. 1287 * <li>{@code ooffset} is negative. 1288 * <li>{@code toffset+len} is greater than the length of this 1289 * {@code String} object. 1290 * <li>{@code ooffset+len} is greater than the length of the other 1291 * argument. 1292 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1293 * such that: 1294 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1295 * <i>k</i>{@code )} 1296 * </ul> 1297 * 1298 * <p>Note that this method does <em>not</em> take locale into account. The 1299 * {@link java.text.Collator} class provides locale-sensitive comparison. 1300 * 1301 * @param toffset the starting offset of the subregion in this string. 1302 * @param other the string argument. 1303 * @param ooffset the starting offset of the subregion in the string 1304 * argument. 1305 * @param len the number of characters to compare. 1306 * @return {@code true} if the specified subregion of this string 1307 * exactly matches the specified subregion of the string argument; 1308 * {@code false} otherwise. 1309 */ 1310 public boolean regionMatches(int toffset, String other, int ooffset, int len) { 1311 byte tv[] = value; 1312 byte ov[] = other.value; 1313 // Note: toffset, ooffset, or len might be near -1>>>1. 1314 if ((ooffset < 0) || (toffset < 0) || 1315 (toffset > (long)length() - len) || 1316 (ooffset > (long)other.length() - len)) { 1317 return false; 1318 } 1319 if (coder() == other.coder()) { 1320 if (!isLatin1() && (len > 0)) { 1321 toffset = toffset << 1; 1322 ooffset = ooffset << 1; 1323 len = len << 1; 1324 } 1325 while (len-- > 0) { 1326 if (tv[toffset++] != ov[ooffset++]) { 1327 return false; 1328 } 1329 } 1330 } else { 1331 if (coder() == LATIN1) { 1332 while (len-- > 0) { 1333 if (StringLatin1.getChar(tv, toffset++) != 1334 StringUTF16.getChar(ov, ooffset++)) { 1335 return false; 1336 } 1337 } 1338 } else { 1339 while (len-- > 0) { 1340 if (StringUTF16.getChar(tv, toffset++) != 1341 StringLatin1.getChar(ov, ooffset++)) { 1342 return false; 1343 } 1344 } 1345 } 1346 } 1347 return true; 1348 } 1349 1350 /** 1351 * Tests if two string regions are equal. 1352 * <p> 1353 * A substring of this {@code String} object is compared to a substring 1354 * of the argument {@code other}. The result is {@code true} if these 1355 * substrings represent character sequences that are the same, ignoring 1356 * case if and only if {@code ignoreCase} is true. The substring of 1357 * this {@code String} object to be compared begins at index 1358 * {@code toffset} and has length {@code len}. The substring of 1359 * {@code other} to be compared begins at index {@code ooffset} and 1360 * has length {@code len}. The result is {@code false} if and only if 1361 * at least one of the following is true: 1362 * <ul><li>{@code toffset} is negative. 1363 * <li>{@code ooffset} is negative. 1364 * <li>{@code toffset+len} is greater than the length of this 1365 * {@code String} object. 1366 * <li>{@code ooffset+len} is greater than the length of the other 1367 * argument. 1368 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1369 * integer <i>k</i> less than {@code len} such that: 1370 * <blockquote><pre> 1371 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1372 * </pre></blockquote> 1373 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1374 * integer <i>k</i> less than {@code len} such that: 1375 * <blockquote><pre> 1376 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) != 1377 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k))) 1378 * </pre></blockquote> 1379 * </ul> 1380 * 1381 * <p>Note that this method does <em>not</em> take locale into account, 1382 * and will result in unsatisfactory results for certain locales when 1383 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class 1384 * provides locale-sensitive comparison. 1385 * 1386 * @param ignoreCase if {@code true}, ignore case when comparing 1387 * characters. 1388 * @param toffset the starting offset of the subregion in this 1389 * string. 1390 * @param other the string argument. 1391 * @param ooffset the starting offset of the subregion in the string 1392 * argument. 1393 * @param len the number of characters to compare. 1394 * @return {@code true} if the specified subregion of this string 1395 * matches the specified subregion of the string argument; 1396 * {@code false} otherwise. Whether the matching is exact 1397 * or case insensitive depends on the {@code ignoreCase} 1398 * argument. 1399 */ 1400 public boolean regionMatches(boolean ignoreCase, int toffset, 1401 String other, int ooffset, int len) { 1402 if (!ignoreCase) { 1403 return regionMatches(toffset, other, ooffset, len); 1404 } 1405 // Note: toffset, ooffset, or len might be near -1>>>1. 1406 if ((ooffset < 0) || (toffset < 0) 1407 || (toffset > (long)length() - len) 1408 || (ooffset > (long)other.length() - len)) { 1409 return false; 1410 } 1411 byte tv[] = value; 1412 byte ov[] = other.value; 1413 if (coder() == other.coder()) { 1414 return isLatin1() 1415 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len) 1416 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len); 1417 } 1418 return isLatin1() 1419 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len) 1420 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len); 1421 } 1422 1423 /** 1424 * Tests if the substring of this string beginning at the 1425 * specified index starts with the specified prefix. 1426 * 1427 * @param prefix the prefix. 1428 * @param toffset where to begin looking in this string. 1429 * @return {@code true} if the character sequence represented by the 1430 * argument is a prefix of the substring of this object starting 1431 * at index {@code toffset}; {@code false} otherwise. 1432 * The result is {@code false} if {@code toffset} is 1433 * negative or greater than the length of this 1434 * {@code String} object; otherwise the result is the same 1435 * as the result of the expression 1436 * <pre> 1437 * this.substring(toffset).startsWith(prefix) 1438 * </pre> 1439 */ 1440 public boolean startsWith(String prefix, int toffset) { 1441 // Note: toffset might be near -1>>>1. 1442 if (toffset < 0 || toffset > length() - prefix.length()) { 1443 return false; 1444 } 1445 byte ta[] = value; 1446 byte pa[] = prefix.value; 1447 int po = 0; 1448 int pc = pa.length; 1449 if (coder() == prefix.coder()) { 1450 int to = isLatin1() ? toffset : toffset << 1; 1451 while (po < pc) { 1452 if (ta[to++] != pa[po++]) { 1453 return false; 1454 } 1455 } 1456 } else { 1457 if (isLatin1()) { // && pcoder == UTF16 1458 return false; 1459 } 1460 // coder == UTF16 && pcoder == LATIN1) 1461 while (po < pc) { 1462 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) { 1463 return false; 1464 } 1465 } 1466 } 1467 return true; 1468 } 1469 1470 /** 1471 * Tests if this string starts with the specified prefix. 1472 * 1473 * @param prefix the prefix. 1474 * @return {@code true} if the character sequence represented by the 1475 * argument is a prefix of the character sequence represented by 1476 * this string; {@code false} otherwise. 1477 * Note also that {@code true} will be returned if the 1478 * argument is an empty string or is equal to this 1479 * {@code String} object as determined by the 1480 * {@link #equals(Object)} method. 1481 * @since 1.0 1482 */ 1483 public boolean startsWith(String prefix) { 1484 return startsWith(prefix, 0); 1485 } 1486 1487 /** 1488 * Tests if this string ends with the specified suffix. 1489 * 1490 * @param suffix the suffix. 1491 * @return {@code true} if the character sequence represented by the 1492 * argument is a suffix of the character sequence represented by 1493 * this object; {@code false} otherwise. Note that the 1494 * result will be {@code true} if the argument is the 1495 * empty string or is equal to this {@code String} object 1496 * as determined by the {@link #equals(Object)} method. 1497 */ 1498 public boolean endsWith(String suffix) { 1499 return startsWith(suffix, length() - suffix.length()); 1500 } 1501 1502 /** 1503 * Returns a hash code for this string. The hash code for a 1504 * {@code String} object is computed as 1505 * <blockquote><pre> 1506 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1507 * </pre></blockquote> 1508 * using {@code int} arithmetic, where {@code s[i]} is the 1509 * <i>i</i>th character of the string, {@code n} is the length of 1510 * the string, and {@code ^} indicates exponentiation. 1511 * (The hash value of the empty string is zero.) 1512 * 1513 * @return a hash code value for this object. 1514 */ 1515 public int hashCode() { 1516 if (hash == 0 && value.length > 0) { 1517 hash = isLatin1() ? StringLatin1.hashCode(value) 1518 : StringUTF16.hashCode(value); 1519 } 1520 return hash; 1521 } 1522 1523 /** 1524 * Returns the index within this string of the first occurrence of 1525 * the specified character. If a character with value 1526 * {@code ch} occurs in the character sequence represented by 1527 * this {@code String} object, then the index (in Unicode 1528 * code units) of the first such occurrence is returned. For 1529 * values of {@code ch} in the range from 0 to 0xFFFF 1530 * (inclusive), this is the smallest value <i>k</i> such that: 1531 * <blockquote><pre> 1532 * this.charAt(<i>k</i>) == ch 1533 * </pre></blockquote> 1534 * is true. For other values of {@code ch}, it is the 1535 * smallest value <i>k</i> such that: 1536 * <blockquote><pre> 1537 * this.codePointAt(<i>k</i>) == ch 1538 * </pre></blockquote> 1539 * is true. In either case, if no such character occurs in this 1540 * string, then {@code -1} is returned. 1541 * 1542 * @param ch a character (Unicode code point). 1543 * @return the index of the first occurrence of the character in the 1544 * character sequence represented by this object, or 1545 * {@code -1} if the character does not occur. 1546 */ 1547 public int indexOf(int ch) { 1548 return indexOf(ch, 0); 1549 } 1550 1551 /** 1552 * Returns the index within this string of the first occurrence of the 1553 * specified character, starting the search at the specified index. 1554 * <p> 1555 * If a character with value {@code ch} occurs in the 1556 * character sequence represented by this {@code String} 1557 * object at an index no smaller than {@code fromIndex}, then 1558 * the index of the first such occurrence is returned. For values 1559 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1560 * this is the smallest value <i>k</i> such that: 1561 * <blockquote><pre> 1562 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1563 * </pre></blockquote> 1564 * is true. For other values of {@code ch}, it is the 1565 * smallest value <i>k</i> such that: 1566 * <blockquote><pre> 1567 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1568 * </pre></blockquote> 1569 * is true. In either case, if no such character occurs in this 1570 * string at or after position {@code fromIndex}, then 1571 * {@code -1} is returned. 1572 * 1573 * <p> 1574 * There is no restriction on the value of {@code fromIndex}. If it 1575 * is negative, it has the same effect as if it were zero: this entire 1576 * string may be searched. If it is greater than the length of this 1577 * string, it has the same effect as if it were equal to the length of 1578 * this string: {@code -1} is returned. 1579 * 1580 * <p>All indices are specified in {@code char} values 1581 * (Unicode code units). 1582 * 1583 * @param ch a character (Unicode code point). 1584 * @param fromIndex the index to start the search from. 1585 * @return the index of the first occurrence of the character in the 1586 * character sequence represented by this object that is greater 1587 * than or equal to {@code fromIndex}, or {@code -1} 1588 * if the character does not occur. 1589 */ 1590 public int indexOf(int ch, int fromIndex) { 1591 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex) 1592 : StringUTF16.indexOf(value, ch, fromIndex); 1593 } 1594 1595 /** 1596 * Returns the index within this string of the last occurrence of 1597 * the specified character. For values of {@code ch} in the 1598 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1599 * units) returned is the largest value <i>k</i> such that: 1600 * <blockquote><pre> 1601 * this.charAt(<i>k</i>) == ch 1602 * </pre></blockquote> 1603 * is true. For other values of {@code ch}, it is the 1604 * largest value <i>k</i> such that: 1605 * <blockquote><pre> 1606 * this.codePointAt(<i>k</i>) == ch 1607 * </pre></blockquote> 1608 * is true. In either case, if no such character occurs in this 1609 * string, then {@code -1} is returned. The 1610 * {@code String} is searched backwards starting at the last 1611 * character. 1612 * 1613 * @param ch a character (Unicode code point). 1614 * @return the index of the last occurrence of the character in the 1615 * character sequence represented by this object, or 1616 * {@code -1} if the character does not occur. 1617 */ 1618 public int lastIndexOf(int ch) { 1619 return lastIndexOf(ch, length() - 1); 1620 } 1621 1622 /** 1623 * Returns the index within this string of the last occurrence of 1624 * the specified character, searching backward starting at the 1625 * specified index. For values of {@code ch} in the range 1626 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1627 * value <i>k</i> such that: 1628 * <blockquote><pre> 1629 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1630 * </pre></blockquote> 1631 * is true. For other values of {@code ch}, it is the 1632 * largest value <i>k</i> such that: 1633 * <blockquote><pre> 1634 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1635 * </pre></blockquote> 1636 * is true. In either case, if no such character occurs in this 1637 * string at or before position {@code fromIndex}, then 1638 * {@code -1} is returned. 1639 * 1640 * <p>All indices are specified in {@code char} values 1641 * (Unicode code units). 1642 * 1643 * @param ch a character (Unicode code point). 1644 * @param fromIndex the index to start the search from. There is no 1645 * restriction on the value of {@code fromIndex}. If it is 1646 * greater than or equal to the length of this string, it has 1647 * the same effect as if it were equal to one less than the 1648 * length of this string: this entire string may be searched. 1649 * If it is negative, it has the same effect as if it were -1: 1650 * -1 is returned. 1651 * @return the index of the last occurrence of the character in the 1652 * character sequence represented by this object that is less 1653 * than or equal to {@code fromIndex}, or {@code -1} 1654 * if the character does not occur before that point. 1655 */ 1656 public int lastIndexOf(int ch, int fromIndex) { 1657 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex) 1658 : StringUTF16.lastIndexOf(value, ch, fromIndex); 1659 } 1660 1661 /** 1662 * Returns the index within this string of the first occurrence of the 1663 * specified substring. 1664 * 1665 * <p>The returned index is the smallest value {@code k} for which: 1666 * <pre>{@code 1667 * this.startsWith(str, k) 1668 * }</pre> 1669 * If no such value of {@code k} exists, then {@code -1} is returned. 1670 * 1671 * @param str the substring to search for. 1672 * @return the index of the first occurrence of the specified substring, 1673 * or {@code -1} if there is no such occurrence. 1674 */ 1675 public int indexOf(String str) { 1676 if (coder() == str.coder()) { 1677 return isLatin1() ? StringLatin1.indexOf(value, str.value) 1678 : StringUTF16.indexOf(value, str.value); 1679 } 1680 if (coder() == LATIN1) { // str.coder == UTF16 1681 return -1; 1682 } 1683 return StringUTF16.indexOfLatin1(value, str.value); 1684 } 1685 1686 /** 1687 * Returns the index within this string of the first occurrence of the 1688 * specified substring, starting at the specified index. 1689 * 1690 * <p>The returned index is the smallest value {@code k} for which: 1691 * <pre>{@code 1692 * k >= Math.min(fromIndex, this.length()) && 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 * @param fromIndex the index from which to start the search. 1699 * @return the index of the first occurrence of the specified substring, 1700 * starting at the specified index, 1701 * or {@code -1} if there is no such occurrence. 1702 */ 1703 public int indexOf(String str, int fromIndex) { 1704 return indexOf(value, coder(), length(), str, fromIndex); 1705 } 1706 1707 /** 1708 * Code shared by String and AbstractStringBuilder to do searches. The 1709 * source is the character array being searched, and the target 1710 * is the string being searched for. 1711 * 1712 * @param src the characters being searched. 1713 * @param srcCoder the coder of the source string. 1714 * @param srcCount length of the source string. 1715 * @param tgtStr the characters being searched for. 1716 * @param fromIndex the index to begin searching from. 1717 */ 1718 static int indexOf(byte[] src, byte srcCoder, int srcCount, 1719 String tgtStr, int fromIndex) { 1720 byte[] tgt = tgtStr.value; 1721 byte tgtCoder = tgtStr.coder(); 1722 int tgtCount = tgtStr.length(); 1723 1724 if (fromIndex >= srcCount) { 1725 return (tgtCount == 0 ? srcCount : -1); 1726 } 1727 if (fromIndex < 0) { 1728 fromIndex = 0; 1729 } 1730 if (tgtCount == 0) { 1731 return fromIndex; 1732 } 1733 if (srcCoder == tgtCoder) { 1734 return srcCoder == LATIN1 1735 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex) 1736 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex); 1737 } 1738 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1739 return -1; 1740 } 1741 // srcCoder == UTF16 && tgtCoder == LATIN1) { 1742 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex); 1743 } 1744 1745 /** 1746 * Returns the index within this string of the last occurrence of the 1747 * specified substring. The last occurrence of the empty string "" 1748 * is considered to occur at the index value {@code this.length()}. 1749 * 1750 * <p>The returned index is the largest value {@code k} for which: 1751 * <pre>{@code 1752 * this.startsWith(str, k) 1753 * }</pre> 1754 * If no such value of {@code k} exists, then {@code -1} is returned. 1755 * 1756 * @param str the substring to search for. 1757 * @return the index of the last occurrence of the specified substring, 1758 * or {@code -1} if there is no such occurrence. 1759 */ 1760 public int lastIndexOf(String str) { 1761 return lastIndexOf(str, length()); 1762 } 1763 1764 /** 1765 * Returns the index within this string of the last occurrence of the 1766 * specified substring, searching backward starting at the specified index. 1767 * 1768 * <p>The returned index is the largest value {@code k} for which: 1769 * <pre>{@code 1770 * k <= Math.min(fromIndex, this.length()) && 1771 * this.startsWith(str, k) 1772 * }</pre> 1773 * If no such value of {@code k} exists, then {@code -1} is returned. 1774 * 1775 * @param str the substring to search for. 1776 * @param fromIndex the index to start the search from. 1777 * @return the index of the last occurrence of the specified substring, 1778 * searching backward from the specified index, 1779 * or {@code -1} if there is no such occurrence. 1780 */ 1781 public int lastIndexOf(String str, int fromIndex) { 1782 return lastIndexOf(value, coder(), length(), str, fromIndex); 1783 } 1784 1785 /** 1786 * Code shared by String and AbstractStringBuilder to do searches. The 1787 * source is the character array being searched, and the target 1788 * is the string being searched for. 1789 * 1790 * @param src the characters being searched. 1791 * @param srcCoder coder handles the mapping between bytes/chars 1792 * @param srcCount count of the source string. 1793 * @param tgt the characters being searched for. 1794 * @param fromIndex the index to begin searching from. 1795 */ 1796 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount, 1797 String tgtStr, int fromIndex) { 1798 byte[] tgt = tgtStr.value; 1799 byte tgtCoder = tgtStr.coder(); 1800 int tgtCount = tgtStr.length(); 1801 /* 1802 * Check arguments; return immediately where possible. For 1803 * consistency, don't check for null str. 1804 */ 1805 int rightIndex = srcCount - tgtCount; 1806 if (fromIndex < 0) { 1807 return -1; 1808 } 1809 if (fromIndex > rightIndex) { 1810 fromIndex = rightIndex; 1811 } 1812 /* Empty string always matches. */ 1813 if (tgtCount == 0) { 1814 return fromIndex; 1815 } 1816 if (srcCoder == tgtCoder) { 1817 return srcCoder == LATIN1 1818 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex) 1819 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex); 1820 } 1821 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1822 return -1; 1823 } 1824 // srcCoder == UTF16 && tgtCoder == LATIN1 1825 int min = tgtCount - 1; 1826 int i = min + fromIndex; 1827 int strLastIndex = tgtCount - 1; 1828 1829 char strLastChar = (char)(tgt[strLastIndex] & 0xff); 1830 startSearchForLastChar: 1831 while (true) { 1832 while (i >= min && StringUTF16.getChar(src, i) != strLastChar) { 1833 i--; 1834 } 1835 if (i < min) { 1836 return -1; 1837 } 1838 int j = i - 1; 1839 int start = j - strLastIndex; 1840 int k = strLastIndex - 1; 1841 while (j > start) { 1842 if (StringUTF16.getChar(src, j--) != (tgt[k--] & 0xff)) { 1843 i--; 1844 continue startSearchForLastChar; 1845 } 1846 } 1847 return start + 1; 1848 } 1849 } 1850 1851 /** 1852 * Returns a string that is a substring of this string. The 1853 * substring begins with the character at the specified index and 1854 * extends to the end of this string. <p> 1855 * Examples: 1856 * <blockquote><pre> 1857 * "unhappy".substring(2) returns "happy" 1858 * "Harbison".substring(3) returns "bison" 1859 * "emptiness".substring(9) returns "" (an empty string) 1860 * </pre></blockquote> 1861 * 1862 * @param beginIndex the beginning index, inclusive. 1863 * @return the specified substring. 1864 * @exception IndexOutOfBoundsException if 1865 * {@code beginIndex} is negative or larger than the 1866 * length of this {@code String} object. 1867 */ 1868 public String substring(int beginIndex) { 1869 if (beginIndex < 0) { 1870 throw new StringIndexOutOfBoundsException(beginIndex); 1871 } 1872 int subLen = length() - beginIndex; 1873 if (subLen < 0) { 1874 throw new StringIndexOutOfBoundsException(subLen); 1875 } 1876 if (beginIndex == 0) { 1877 return this; 1878 } 1879 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1880 : StringUTF16.newString(value, beginIndex, subLen); 1881 } 1882 1883 /** 1884 * Returns a string that is a substring of this string. The 1885 * substring begins at the specified {@code beginIndex} and 1886 * extends to the character at index {@code endIndex - 1}. 1887 * Thus the length of the substring is {@code endIndex-beginIndex}. 1888 * <p> 1889 * Examples: 1890 * <blockquote><pre> 1891 * "hamburger".substring(4, 8) returns "urge" 1892 * "smiles".substring(1, 5) returns "mile" 1893 * </pre></blockquote> 1894 * 1895 * @param beginIndex the beginning index, inclusive. 1896 * @param endIndex the ending index, exclusive. 1897 * @return the specified substring. 1898 * @exception IndexOutOfBoundsException if the 1899 * {@code beginIndex} is negative, or 1900 * {@code endIndex} is larger than the length of 1901 * this {@code String} object, or 1902 * {@code beginIndex} is larger than 1903 * {@code endIndex}. 1904 */ 1905 public String substring(int beginIndex, int endIndex) { 1906 int length = length(); 1907 checkBoundsBeginEnd(beginIndex, endIndex, length); 1908 int subLen = endIndex - beginIndex; 1909 if (beginIndex == 0 && endIndex == length) { 1910 return this; 1911 } 1912 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1913 : StringUTF16.newString(value, beginIndex, subLen); 1914 } 1915 1916 /** 1917 * Returns a character sequence that is a subsequence of this sequence. 1918 * 1919 * <p> An invocation of this method of the form 1920 * 1921 * <blockquote><pre> 1922 * str.subSequence(begin, end)</pre></blockquote> 1923 * 1924 * behaves in exactly the same way as the invocation 1925 * 1926 * <blockquote><pre> 1927 * str.substring(begin, end)</pre></blockquote> 1928 * 1929 * @apiNote 1930 * This method is defined so that the {@code String} class can implement 1931 * the {@link CharSequence} interface. 1932 * 1933 * @param beginIndex the begin index, inclusive. 1934 * @param endIndex the end index, exclusive. 1935 * @return the specified subsequence. 1936 * 1937 * @throws IndexOutOfBoundsException 1938 * if {@code beginIndex} or {@code endIndex} is negative, 1939 * if {@code endIndex} is greater than {@code length()}, 1940 * or if {@code beginIndex} is greater than {@code endIndex} 1941 * 1942 * @since 1.4 1943 * @spec JSR-51 1944 */ 1945 public CharSequence subSequence(int beginIndex, int endIndex) { 1946 return this.substring(beginIndex, endIndex); 1947 } 1948 1949 /** 1950 * Concatenates the specified string to the end of this string. 1951 * <p> 1952 * If the length of the argument string is {@code 0}, then this 1953 * {@code String} object is returned. Otherwise, a 1954 * {@code String} object is returned that represents a character 1955 * sequence that is the concatenation of the character sequence 1956 * represented by this {@code String} object and the character 1957 * sequence represented by the argument string.<p> 1958 * Examples: 1959 * <blockquote><pre> 1960 * "cares".concat("s") returns "caress" 1961 * "to".concat("get").concat("her") returns "together" 1962 * </pre></blockquote> 1963 * 1964 * @param str the {@code String} that is concatenated to the end 1965 * of this {@code String}. 1966 * @return a string that represents the concatenation of this object's 1967 * characters followed by the string argument's characters. 1968 */ 1969 public String concat(String str) { 1970 int olen = str.length(); 1971 if (olen == 0) { 1972 return this; 1973 } 1974 if (coder() == str.coder()) { 1975 byte[] val = this.value; 1976 byte[] oval = str.value; 1977 int len = val.length + oval.length; 1978 byte[] buf = Arrays.copyOf(val, len); 1979 System.arraycopy(oval, 0, buf, val.length, oval.length); 1980 return new String(buf, coder); 1981 } 1982 int len = length(); 1983 byte[] buf = StringUTF16.newBytesFor(len + olen); 1984 getBytes(buf, 0, UTF16); 1985 str.getBytes(buf, len, UTF16); 1986 return new String(buf, UTF16); 1987 } 1988 1989 /** 1990 * Returns a string resulting from replacing all occurrences of 1991 * {@code oldChar} in this string with {@code newChar}. 1992 * <p> 1993 * If the character {@code oldChar} does not occur in the 1994 * character sequence represented by this {@code String} object, 1995 * then a reference to this {@code String} object is returned. 1996 * Otherwise, a {@code String} object is returned that 1997 * represents a character sequence identical to the character sequence 1998 * represented by this {@code String} object, except that every 1999 * occurrence of {@code oldChar} is replaced by an occurrence 2000 * of {@code newChar}. 2001 * <p> 2002 * Examples: 2003 * <blockquote><pre> 2004 * "mesquite in your cellar".replace('e', 'o') 2005 * returns "mosquito in your collar" 2006 * "the war of baronets".replace('r', 'y') 2007 * returns "the way of bayonets" 2008 * "sparring with a purple porpoise".replace('p', 't') 2009 * returns "starring with a turtle tortoise" 2010 * "JonL".replace('q', 'x') returns "JonL" (no change) 2011 * </pre></blockquote> 2012 * 2013 * @param oldChar the old character. 2014 * @param newChar the new character. 2015 * @return a string derived from this string by replacing every 2016 * occurrence of {@code oldChar} with {@code newChar}. 2017 */ 2018 public String replace(char oldChar, char newChar) { 2019 if (oldChar != newChar) { 2020 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar) 2021 : StringUTF16.replace(value, oldChar, newChar); 2022 if (ret != null) { 2023 return ret; 2024 } 2025 } 2026 return this; 2027 } 2028 2029 /** 2030 * Tells whether or not this string matches the given <a 2031 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2032 * 2033 * <p> An invocation of this method of the form 2034 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2035 * same result as the expression 2036 * 2037 * <blockquote> 2038 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2039 * matches(<i>regex</i>, <i>str</i>)} 2040 * </blockquote> 2041 * 2042 * @param regex 2043 * the regular expression to which this string is to be matched 2044 * 2045 * @return {@code true} if, and only if, this string matches the 2046 * given regular expression 2047 * 2048 * @throws PatternSyntaxException 2049 * if the regular expression's syntax is invalid 2050 * 2051 * @see java.util.regex.Pattern 2052 * 2053 * @since 1.4 2054 * @spec JSR-51 2055 */ 2056 public boolean matches(String regex) { 2057 return Pattern.matches(regex, this); 2058 } 2059 2060 /** 2061 * Returns true if and only if this string contains the specified 2062 * sequence of char values. 2063 * 2064 * @param s the sequence to search for 2065 * @return true if this string contains {@code s}, false otherwise 2066 * @since 1.5 2067 */ 2068 public boolean contains(CharSequence s) { 2069 return indexOf(s.toString()) >= 0; 2070 } 2071 2072 /** 2073 * Replaces the first substring of this string that matches the given <a 2074 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2075 * given replacement. 2076 * 2077 * <p> An invocation of this method of the form 2078 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2079 * yields exactly the same result as the expression 2080 * 2081 * <blockquote> 2082 * <code> 2083 * {@link java.util.regex.Pattern}.{@link 2084 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2085 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2086 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>) 2087 * </code> 2088 * </blockquote> 2089 * 2090 *<p> 2091 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2092 * replacement string may cause the results to be different than if it were 2093 * being treated as a literal replacement string; see 2094 * {@link java.util.regex.Matcher#replaceFirst}. 2095 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2096 * meaning of these characters, if desired. 2097 * 2098 * @param regex 2099 * the regular expression to which this string is to be matched 2100 * @param replacement 2101 * the string to be substituted for the first match 2102 * 2103 * @return The resulting {@code String} 2104 * 2105 * @throws PatternSyntaxException 2106 * if the regular expression's syntax is invalid 2107 * 2108 * @see java.util.regex.Pattern 2109 * 2110 * @since 1.4 2111 * @spec JSR-51 2112 */ 2113 public String replaceFirst(String regex, String replacement) { 2114 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2115 } 2116 2117 /** 2118 * Replaces each substring of this string that matches the given <a 2119 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2120 * given replacement. 2121 * 2122 * <p> An invocation of this method of the form 2123 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2124 * yields exactly the same result as the expression 2125 * 2126 * <blockquote> 2127 * <code> 2128 * {@link java.util.regex.Pattern}.{@link 2129 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2130 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2131 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2132 * </code> 2133 * </blockquote> 2134 * 2135 *<p> 2136 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2137 * replacement string may cause the results to be different than if it were 2138 * being treated as a literal replacement string; see 2139 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2140 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2141 * meaning of these characters, if desired. 2142 * 2143 * @param regex 2144 * the regular expression to which this string is to be matched 2145 * @param replacement 2146 * the string to be substituted for each match 2147 * 2148 * @return The resulting {@code String} 2149 * 2150 * @throws PatternSyntaxException 2151 * if the regular expression's syntax is invalid 2152 * 2153 * @see java.util.regex.Pattern 2154 * 2155 * @since 1.4 2156 * @spec JSR-51 2157 */ 2158 public String replaceAll(String regex, String replacement) { 2159 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2160 } 2161 2162 /** 2163 * Replaces each substring of this string that matches the literal target 2164 * sequence with the specified literal replacement sequence. The 2165 * replacement proceeds from the beginning of the string to the end, for 2166 * example, replacing "aa" with "b" in the string "aaa" will result in 2167 * "ba" rather than "ab". 2168 * 2169 * @param target The sequence of char values to be replaced 2170 * @param replacement The replacement sequence of char values 2171 * @return The resulting string 2172 * @since 1.5 2173 */ 2174 public String replace(CharSequence target, CharSequence replacement) { 2175 String tgtStr = target.toString(); 2176 String replStr = replacement.toString(); 2177 int j = indexOf(tgtStr); 2178 if (j < 0) { 2179 return this; 2180 } 2181 int tgtLen = tgtStr.length(); 2182 int tgtLen1 = Math.max(tgtLen, 1); 2183 int thisLen = length(); 2184 2185 int newLenHint = thisLen - tgtLen + replStr.length(); 2186 if (newLenHint < 0) { 2187 throw new OutOfMemoryError(); 2188 } 2189 StringBuilder sb = new StringBuilder(newLenHint); 2190 int i = 0; 2191 do { 2192 sb.append(this, i, j).append(replStr); 2193 i = j + tgtLen; 2194 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0); 2195 return sb.append(this, i, thisLen).toString(); 2196 } 2197 2198 /** 2199 * Splits this string around matches of the given 2200 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2201 * 2202 * <p> The array returned by this method contains each substring of this 2203 * string that is terminated by another substring that matches the given 2204 * expression or is terminated by the end of the string. The substrings in 2205 * the array are in the order in which they occur in this string. If the 2206 * expression does not match any part of the input then the resulting array 2207 * has just one element, namely this string. 2208 * 2209 * <p> When there is a positive-width match at the beginning of this 2210 * string then an empty leading substring is included at the beginning 2211 * of the resulting array. A zero-width match at the beginning however 2212 * never produces such empty leading substring. 2213 * 2214 * <p> The {@code limit} parameter controls the number of times the 2215 * pattern is applied and therefore affects the length of the resulting 2216 * array. If the limit <i>n</i> is greater than zero then the pattern 2217 * will be applied at most <i>n</i> - 1 times, the array's 2218 * length will be no greater than <i>n</i>, and the array's last entry 2219 * will contain all input beyond the last matched delimiter. If <i>n</i> 2220 * is non-positive then the pattern will be applied as many times as 2221 * possible and the array can have any length. If <i>n</i> is zero then 2222 * the pattern will be applied as many times as possible, the array can 2223 * have any length, and trailing empty strings will be discarded. 2224 * 2225 * <p> The string {@code "boo:and:foo"}, for example, yields the 2226 * following results with these parameters: 2227 * 2228 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2229 * <tr> 2230 * <th>Regex</th> 2231 * <th>Limit</th> 2232 * <th>Result</th> 2233 * </tr> 2234 * <tr><td align=center>:</td> 2235 * <td align=center>2</td> 2236 * <td>{@code { "boo", "and:foo" }}</td></tr> 2237 * <tr><td align=center>:</td> 2238 * <td align=center>5</td> 2239 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2240 * <tr><td align=center>:</td> 2241 * <td align=center>-2</td> 2242 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2243 * <tr><td align=center>o</td> 2244 * <td align=center>5</td> 2245 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2246 * <tr><td align=center>o</td> 2247 * <td align=center>-2</td> 2248 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2249 * <tr><td align=center>o</td> 2250 * <td align=center>0</td> 2251 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2252 * </table></blockquote> 2253 * 2254 * <p> An invocation of this method of the form 2255 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2256 * yields the same result as the expression 2257 * 2258 * <blockquote> 2259 * <code> 2260 * {@link java.util.regex.Pattern}.{@link 2261 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2262 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2263 * </code> 2264 * </blockquote> 2265 * 2266 * 2267 * @param regex 2268 * the delimiting regular expression 2269 * 2270 * @param limit 2271 * the result threshold, as described above 2272 * 2273 * @return the array of strings computed by splitting this string 2274 * around matches of the given regular expression 2275 * 2276 * @throws PatternSyntaxException 2277 * if the regular expression's syntax is invalid 2278 * 2279 * @see java.util.regex.Pattern 2280 * 2281 * @since 1.4 2282 * @spec JSR-51 2283 */ 2284 public String[] split(String regex, int limit) { 2285 /* fastpath if the regex is a 2286 (1)one-char String and this character is not one of the 2287 RegEx's meta characters ".$|()[{^?*+\\", or 2288 (2)two-char String and the first char is the backslash and 2289 the second is not the ascii digit or ascii letter. 2290 */ 2291 char ch = 0; 2292 if (((regex.length() == 1 && 2293 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2294 (regex.length() == 2 && 2295 regex.charAt(0) == '\\' && 2296 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2297 ((ch-'a')|('z'-ch)) < 0 && 2298 ((ch-'A')|('Z'-ch)) < 0)) && 2299 (ch < Character.MIN_HIGH_SURROGATE || 2300 ch > Character.MAX_LOW_SURROGATE)) 2301 { 2302 int off = 0; 2303 int next = 0; 2304 boolean limited = limit > 0; 2305 ArrayList<String> list = new ArrayList<>(); 2306 while ((next = indexOf(ch, off)) != -1) { 2307 if (!limited || list.size() < limit - 1) { 2308 list.add(substring(off, next)); 2309 off = next + 1; 2310 } else { // last one 2311 //assert (list.size() == limit - 1); 2312 int last = length(); 2313 list.add(substring(off, last)); 2314 off = last; 2315 break; 2316 } 2317 } 2318 // If no match was found, return this 2319 if (off == 0) 2320 return new String[]{this}; 2321 2322 // Add remaining segment 2323 if (!limited || list.size() < limit) 2324 list.add(substring(off, length())); 2325 2326 // Construct result 2327 int resultSize = list.size(); 2328 if (limit == 0) { 2329 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) { 2330 resultSize--; 2331 } 2332 } 2333 String[] result = new String[resultSize]; 2334 return list.subList(0, resultSize).toArray(result); 2335 } 2336 return Pattern.compile(regex).split(this, limit); 2337 } 2338 2339 /** 2340 * Splits this string around matches of the given <a 2341 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2342 * 2343 * <p> This method works as if by invoking the two-argument {@link 2344 * #split(String, int) split} method with the given expression and a limit 2345 * argument of zero. Trailing empty strings are therefore not included in 2346 * the resulting array. 2347 * 2348 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2349 * results with these expressions: 2350 * 2351 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2352 * <tr> 2353 * <th>Regex</th> 2354 * <th>Result</th> 2355 * </tr> 2356 * <tr><td align=center>:</td> 2357 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2358 * <tr><td align=center>o</td> 2359 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2360 * </table></blockquote> 2361 * 2362 * 2363 * @param regex 2364 * the delimiting regular expression 2365 * 2366 * @return the array of strings computed by splitting this string 2367 * around matches of the given regular expression 2368 * 2369 * @throws PatternSyntaxException 2370 * if the regular expression's syntax is invalid 2371 * 2372 * @see java.util.regex.Pattern 2373 * 2374 * @since 1.4 2375 * @spec JSR-51 2376 */ 2377 public String[] split(String regex) { 2378 return split(regex, 0); 2379 } 2380 2381 /** 2382 * Returns a new String composed of copies of the 2383 * {@code CharSequence elements} joined together with a copy of 2384 * the specified {@code delimiter}. 2385 * 2386 * <blockquote>For example, 2387 * <pre>{@code 2388 * String message = String.join("-", "Java", "is", "cool"); 2389 * // message returned is: "Java-is-cool" 2390 * }</pre></blockquote> 2391 * 2392 * Note that if an element is null, then {@code "null"} is added. 2393 * 2394 * @param delimiter the delimiter that separates each element 2395 * @param elements the elements to join together. 2396 * 2397 * @return a new {@code String} that is composed of the {@code elements} 2398 * separated by the {@code delimiter} 2399 * 2400 * @throws NullPointerException If {@code delimiter} or {@code elements} 2401 * is {@code null} 2402 * 2403 * @see java.util.StringJoiner 2404 * @since 1.8 2405 */ 2406 public static String join(CharSequence delimiter, CharSequence... elements) { 2407 Objects.requireNonNull(delimiter); 2408 Objects.requireNonNull(elements); 2409 // Number of elements not likely worth Arrays.stream overhead. 2410 StringJoiner joiner = new StringJoiner(delimiter); 2411 for (CharSequence cs: elements) { 2412 joiner.add(cs); 2413 } 2414 return joiner.toString(); 2415 } 2416 2417 /** 2418 * Returns a new {@code String} composed of copies of the 2419 * {@code CharSequence elements} joined together with a copy of the 2420 * specified {@code delimiter}. 2421 * 2422 * <blockquote>For example, 2423 * <pre>{@code 2424 * List<String> strings = new LinkedList<>(); 2425 * strings.add("Java");strings.add("is"); 2426 * strings.add("cool"); 2427 * String message = String.join(" ", strings); 2428 * //message returned is: "Java is cool" 2429 * 2430 * Set<String> strings = new LinkedHashSet<>(); 2431 * strings.add("Java"); strings.add("is"); 2432 * strings.add("very"); strings.add("cool"); 2433 * String message = String.join("-", strings); 2434 * //message returned is: "Java-is-very-cool" 2435 * }</pre></blockquote> 2436 * 2437 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2438 * 2439 * @param delimiter a sequence of characters that is used to separate each 2440 * of the {@code elements} in the resulting {@code String} 2441 * @param elements an {@code Iterable} that will have its {@code elements} 2442 * joined together. 2443 * 2444 * @return a new {@code String} that is composed from the {@code elements} 2445 * argument 2446 * 2447 * @throws NullPointerException If {@code delimiter} or {@code elements} 2448 * is {@code null} 2449 * 2450 * @see #join(CharSequence,CharSequence...) 2451 * @see java.util.StringJoiner 2452 * @since 1.8 2453 */ 2454 public static String join(CharSequence delimiter, 2455 Iterable<? extends CharSequence> elements) { 2456 Objects.requireNonNull(delimiter); 2457 Objects.requireNonNull(elements); 2458 StringJoiner joiner = new StringJoiner(delimiter); 2459 for (CharSequence cs: elements) { 2460 joiner.add(cs); 2461 } 2462 return joiner.toString(); 2463 } 2464 2465 /** 2466 * Converts all of the characters in this {@code String} to lower 2467 * case using the rules of the given {@code Locale}. Case mapping is based 2468 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2469 * class. Since case mappings are not always 1:1 char mappings, the resulting 2470 * {@code String} may be a different length than the original {@code String}. 2471 * <p> 2472 * Examples of lowercase mappings are in the following table: 2473 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2474 * <tr> 2475 * <th>Language Code of Locale</th> 2476 * <th>Upper Case</th> 2477 * <th>Lower Case</th> 2478 * <th>Description</th> 2479 * </tr> 2480 * <tr> 2481 * <td>tr (Turkish)</td> 2482 * <td>\u0130</td> 2483 * <td>\u0069</td> 2484 * <td>capital letter I with dot above -> small letter i</td> 2485 * </tr> 2486 * <tr> 2487 * <td>tr (Turkish)</td> 2488 * <td>\u0049</td> 2489 * <td>\u0131</td> 2490 * <td>capital letter I -> small letter dotless i </td> 2491 * </tr> 2492 * <tr> 2493 * <td>(all)</td> 2494 * <td>French Fries</td> 2495 * <td>french fries</td> 2496 * <td>lowercased all chars in String</td> 2497 * </tr> 2498 * <tr> 2499 * <td>(all)</td> 2500 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2501 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2502 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2503 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2504 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2505 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2506 * <td>lowercased all chars in String</td> 2507 * </tr> 2508 * </table> 2509 * 2510 * @param locale use the case transformation rules for this locale 2511 * @return the {@code String}, converted to lowercase. 2512 * @see java.lang.String#toLowerCase() 2513 * @see java.lang.String#toUpperCase() 2514 * @see java.lang.String#toUpperCase(Locale) 2515 * @since 1.1 2516 */ 2517 public String toLowerCase(Locale locale) { 2518 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale) 2519 : StringUTF16.toLowerCase(this, value, locale); 2520 } 2521 2522 /** 2523 * Converts all of the characters in this {@code String} to lower 2524 * case using the rules of the default locale. This is equivalent to calling 2525 * {@code toLowerCase(Locale.getDefault())}. 2526 * <p> 2527 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2528 * results if used for strings that are intended to be interpreted locale 2529 * independently. 2530 * Examples are programming language identifiers, protocol keys, and HTML 2531 * tags. 2532 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2533 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2534 * LATIN SMALL LETTER DOTLESS I character. 2535 * To obtain correct results for locale insensitive strings, use 2536 * {@code toLowerCase(Locale.ROOT)}. 2537 * 2538 * @return the {@code String}, converted to lowercase. 2539 * @see java.lang.String#toLowerCase(Locale) 2540 */ 2541 public String toLowerCase() { 2542 return toLowerCase(Locale.getDefault()); 2543 } 2544 2545 /** 2546 * Converts all of the characters in this {@code String} to upper 2547 * case using the rules of the given {@code Locale}. Case mapping is based 2548 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2549 * class. Since case mappings are not always 1:1 char mappings, the resulting 2550 * {@code String} may be a different length than the original {@code String}. 2551 * <p> 2552 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2553 * 2554 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2555 * <tr> 2556 * <th>Language Code of Locale</th> 2557 * <th>Lower Case</th> 2558 * <th>Upper Case</th> 2559 * <th>Description</th> 2560 * </tr> 2561 * <tr> 2562 * <td>tr (Turkish)</td> 2563 * <td>\u0069</td> 2564 * <td>\u0130</td> 2565 * <td>small letter i -> capital letter I with dot above</td> 2566 * </tr> 2567 * <tr> 2568 * <td>tr (Turkish)</td> 2569 * <td>\u0131</td> 2570 * <td>\u0049</td> 2571 * <td>small letter dotless i -> capital letter I</td> 2572 * </tr> 2573 * <tr> 2574 * <td>(all)</td> 2575 * <td>\u00df</td> 2576 * <td>\u0053 \u0053</td> 2577 * <td>small letter sharp s -> two letters: SS</td> 2578 * </tr> 2579 * <tr> 2580 * <td>(all)</td> 2581 * <td>Fahrvergnügen</td> 2582 * <td>FAHRVERGNÜGEN</td> 2583 * <td></td> 2584 * </tr> 2585 * </table> 2586 * @param locale use the case transformation rules for this locale 2587 * @return the {@code String}, converted to uppercase. 2588 * @see java.lang.String#toUpperCase() 2589 * @see java.lang.String#toLowerCase() 2590 * @see java.lang.String#toLowerCase(Locale) 2591 * @since 1.1 2592 */ 2593 public String toUpperCase(Locale locale) { 2594 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale) 2595 : StringUTF16.toUpperCase(this, value, locale); 2596 } 2597 2598 /** 2599 * Converts all of the characters in this {@code String} to upper 2600 * case using the rules of the default locale. This method is equivalent to 2601 * {@code toUpperCase(Locale.getDefault())}. 2602 * <p> 2603 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2604 * results if used for strings that are intended to be interpreted locale 2605 * independently. 2606 * Examples are programming language identifiers, protocol keys, and HTML 2607 * tags. 2608 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2609 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2610 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2611 * To obtain correct results for locale insensitive strings, use 2612 * {@code toUpperCase(Locale.ROOT)}. 2613 * 2614 * @return the {@code String}, converted to uppercase. 2615 * @see java.lang.String#toUpperCase(Locale) 2616 */ 2617 public String toUpperCase() { 2618 return toUpperCase(Locale.getDefault()); 2619 } 2620 2621 /** 2622 * Returns a string whose value is this string, with any leading and trailing 2623 * whitespace removed. 2624 * <p> 2625 * If this {@code String} object represents an empty character 2626 * sequence, or the first and last characters of character sequence 2627 * represented by this {@code String} object both have codes 2628 * greater than {@code '\u005Cu0020'} (the space character), then a 2629 * reference to this {@code String} object is returned. 2630 * <p> 2631 * Otherwise, if there is no character with a code greater than 2632 * {@code '\u005Cu0020'} in the string, then a 2633 * {@code String} object representing an empty string is 2634 * returned. 2635 * <p> 2636 * Otherwise, let <i>k</i> be the index of the first character in the 2637 * string whose code is greater than {@code '\u005Cu0020'}, and let 2638 * <i>m</i> be the index of the last character in the string whose code 2639 * is greater than {@code '\u005Cu0020'}. A {@code String} 2640 * object is returned, representing the substring of this string that 2641 * begins with the character at index <i>k</i> and ends with the 2642 * character at index <i>m</i>-that is, the result of 2643 * {@code this.substring(k, m + 1)}. 2644 * <p> 2645 * This method may be used to trim whitespace (as defined above) from 2646 * the beginning and end of a string. 2647 * 2648 * @return A string whose value is this string, with any leading and trailing white 2649 * space removed, or this string if it has no leading or 2650 * trailing white space. 2651 */ 2652 public String trim() { 2653 String ret = isLatin1() ? StringLatin1.trim(value) 2654 : StringUTF16.trim(value); 2655 return ret == null ? this : ret; 2656 } 2657 2658 /** 2659 * This object (which is already a string!) is itself returned. 2660 * 2661 * @return the string itself. 2662 */ 2663 public String toString() { 2664 return this; 2665 } 2666 2667 /** 2668 * Returns a stream of {@code int} zero-extending the {@code char} values 2669 * from this sequence. Any char which maps to a <a 2670 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code 2671 * point</a> is passed through uninterpreted. 2672 * 2673 * @return an IntStream of char values from this sequence 2674 * @since 9 2675 */ 2676 @Override 2677 public IntStream chars() { 2678 return StreamSupport.intStream( 2679 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2680 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE), 2681 false); 2682 } 2683 2684 2685 /** 2686 * Returns a stream of code point values from this sequence. Any surrogate 2687 * pairs encountered in the sequence are combined as if by {@linkplain 2688 * Character#toCodePoint Character.toCodePoint} and the result is passed 2689 * to the stream. Any other code units, including ordinary BMP characters, 2690 * unpaired surrogates, and undefined code units, are zero-extended to 2691 * {@code int} values which are then passed to the stream. 2692 * 2693 * @return an IntStream of Unicode code points from this sequence 2694 * @since 9 2695 */ 2696 @Override 2697 public IntStream codePoints() { 2698 return StreamSupport.intStream( 2699 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2700 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE), 2701 false); 2702 } 2703 2704 /** 2705 * Converts this string to a new character array. 2706 * 2707 * @return a newly allocated character array whose length is the length 2708 * of this string and whose contents are initialized to contain 2709 * the character sequence represented by this string. 2710 */ 2711 public char[] toCharArray() { 2712 return isLatin1() ? StringLatin1.toChars(value) 2713 : StringUTF16.toChars(value); 2714 } 2715 2716 /** 2717 * Returns a formatted string using the specified format string and 2718 * arguments. 2719 * 2720 * <p> The locale always used is the one returned by {@link 2721 * java.util.Locale#getDefault() Locale.getDefault()}. 2722 * 2723 * @param format 2724 * A <a href="../util/Formatter.html#syntax">format string</a> 2725 * 2726 * @param args 2727 * Arguments referenced by the format specifiers in the format 2728 * string. If there are more arguments than format specifiers, the 2729 * extra arguments are ignored. The number of arguments is 2730 * variable and may be zero. The maximum number of arguments is 2731 * limited by the maximum dimension of a Java array as defined by 2732 * <cite>The Java™ Virtual Machine Specification</cite>. 2733 * The behaviour on a 2734 * {@code null} argument depends on the <a 2735 * href="../util/Formatter.html#syntax">conversion</a>. 2736 * 2737 * @throws java.util.IllegalFormatException 2738 * If a format string contains an illegal syntax, a format 2739 * specifier that is incompatible with the given arguments, 2740 * insufficient arguments given the format string, or other 2741 * illegal conditions. For specification of all possible 2742 * formatting errors, see the <a 2743 * href="../util/Formatter.html#detail">Details</a> section of the 2744 * formatter class specification. 2745 * 2746 * @return A formatted string 2747 * 2748 * @see java.util.Formatter 2749 * @since 1.5 2750 */ 2751 public static String format(String format, Object... args) { 2752 return new Formatter().format(format, args).toString(); 2753 } 2754 2755 /** 2756 * Returns a formatted string using the specified locale, format string, 2757 * and arguments. 2758 * 2759 * @param l 2760 * The {@linkplain java.util.Locale locale} to apply during 2761 * formatting. If {@code l} is {@code null} then no localization 2762 * is applied. 2763 * 2764 * @param format 2765 * A <a href="../util/Formatter.html#syntax">format string</a> 2766 * 2767 * @param args 2768 * Arguments referenced by the format specifiers in the format 2769 * string. If there are more arguments than format specifiers, the 2770 * extra arguments are ignored. The number of arguments is 2771 * variable and may be zero. The maximum number of arguments is 2772 * limited by the maximum dimension of a Java array as defined by 2773 * <cite>The Java™ Virtual Machine Specification</cite>. 2774 * The behaviour on a 2775 * {@code null} argument depends on the 2776 * <a href="../util/Formatter.html#syntax">conversion</a>. 2777 * 2778 * @throws java.util.IllegalFormatException 2779 * If a format string contains an illegal syntax, a format 2780 * specifier that is incompatible with the given arguments, 2781 * insufficient arguments given the format string, or other 2782 * illegal conditions. For specification of all possible 2783 * formatting errors, see the <a 2784 * href="../util/Formatter.html#detail">Details</a> section of the 2785 * formatter class specification 2786 * 2787 * @return A formatted string 2788 * 2789 * @see java.util.Formatter 2790 * @since 1.5 2791 */ 2792 public static String format(Locale l, String format, Object... args) { 2793 return new Formatter(l).format(format, args).toString(); 2794 } 2795 2796 /** 2797 * Returns the string representation of the {@code Object} argument. 2798 * 2799 * @param obj an {@code Object}. 2800 * @return if the argument is {@code null}, then a string equal to 2801 * {@code "null"}; otherwise, the value of 2802 * {@code obj.toString()} is returned. 2803 * @see java.lang.Object#toString() 2804 */ 2805 public static String valueOf(Object obj) { 2806 return (obj == null) ? "null" : obj.toString(); 2807 } 2808 2809 /** 2810 * Returns the string representation of the {@code char} array 2811 * argument. The contents of the character array are copied; subsequent 2812 * modification of the character array does not affect the returned 2813 * string. 2814 * 2815 * @param data the character array. 2816 * @return a {@code String} that contains the characters of the 2817 * character array. 2818 */ 2819 public static String valueOf(char data[]) { 2820 return new String(data); 2821 } 2822 2823 /** 2824 * Returns the string representation of a specific subarray of the 2825 * {@code char} array argument. 2826 * <p> 2827 * The {@code offset} argument is the index of the first 2828 * character of the subarray. The {@code count} argument 2829 * specifies the length of the subarray. The contents of the subarray 2830 * are copied; subsequent modification of the character array does not 2831 * affect the returned string. 2832 * 2833 * @param data the character array. 2834 * @param offset initial offset of the subarray. 2835 * @param count length of the subarray. 2836 * @return a {@code String} that contains the characters of the 2837 * specified subarray of the character array. 2838 * @exception IndexOutOfBoundsException if {@code offset} is 2839 * negative, or {@code count} is negative, or 2840 * {@code offset+count} is larger than 2841 * {@code data.length}. 2842 */ 2843 public static String valueOf(char data[], int offset, int count) { 2844 return new String(data, offset, count); 2845 } 2846 2847 /** 2848 * Equivalent to {@link #valueOf(char[], int, int)}. 2849 * 2850 * @param data the character array. 2851 * @param offset initial offset of the subarray. 2852 * @param count length of the subarray. 2853 * @return a {@code String} that contains the characters of the 2854 * specified subarray of the character array. 2855 * @exception IndexOutOfBoundsException if {@code offset} is 2856 * negative, or {@code count} is negative, or 2857 * {@code offset+count} is larger than 2858 * {@code data.length}. 2859 */ 2860 public static String copyValueOf(char data[], int offset, int count) { 2861 return new String(data, offset, count); 2862 } 2863 2864 /** 2865 * Equivalent to {@link #valueOf(char[])}. 2866 * 2867 * @param data the character array. 2868 * @return a {@code String} that contains the characters of the 2869 * character array. 2870 */ 2871 public static String copyValueOf(char data[]) { 2872 return new String(data); 2873 } 2874 2875 /** 2876 * Returns the string representation of the {@code boolean} argument. 2877 * 2878 * @param b a {@code boolean}. 2879 * @return if the argument is {@code true}, a string equal to 2880 * {@code "true"} is returned; otherwise, a string equal to 2881 * {@code "false"} is returned. 2882 */ 2883 public static String valueOf(boolean b) { 2884 return b ? "true" : "false"; 2885 } 2886 2887 /** 2888 * Returns the string representation of the {@code char} 2889 * argument. 2890 * 2891 * @param c a {@code char}. 2892 * @return a string of length {@code 1} containing 2893 * as its single character the argument {@code c}. 2894 */ 2895 public static String valueOf(char c) { 2896 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) { 2897 return new String(StringLatin1.toBytes(c), LATIN1); 2898 } 2899 return new String(StringUTF16.toBytes(c), UTF16); 2900 } 2901 2902 /** 2903 * Returns the string representation of the {@code int} argument. 2904 * <p> 2905 * The representation is exactly the one returned by the 2906 * {@code Integer.toString} method of one argument. 2907 * 2908 * @param i an {@code int}. 2909 * @return a string representation of the {@code int} argument. 2910 * @see java.lang.Integer#toString(int, int) 2911 */ 2912 public static String valueOf(int i) { 2913 return Integer.toString(i); 2914 } 2915 2916 /** 2917 * Returns the string representation of the {@code long} argument. 2918 * <p> 2919 * The representation is exactly the one returned by the 2920 * {@code Long.toString} method of one argument. 2921 * 2922 * @param l a {@code long}. 2923 * @return a string representation of the {@code long} argument. 2924 * @see java.lang.Long#toString(long) 2925 */ 2926 public static String valueOf(long l) { 2927 return Long.toString(l); 2928 } 2929 2930 /** 2931 * Returns the string representation of the {@code float} argument. 2932 * <p> 2933 * The representation is exactly the one returned by the 2934 * {@code Float.toString} method of one argument. 2935 * 2936 * @param f a {@code float}. 2937 * @return a string representation of the {@code float} argument. 2938 * @see java.lang.Float#toString(float) 2939 */ 2940 public static String valueOf(float f) { 2941 return Float.toString(f); 2942 } 2943 2944 /** 2945 * Returns the string representation of the {@code double} argument. 2946 * <p> 2947 * The representation is exactly the one returned by the 2948 * {@code Double.toString} method of one argument. 2949 * 2950 * @param d a {@code double}. 2951 * @return a string representation of the {@code double} argument. 2952 * @see java.lang.Double#toString(double) 2953 */ 2954 public static String valueOf(double d) { 2955 return Double.toString(d); 2956 } 2957 2958 /** 2959 * Returns a canonical representation for the string object. 2960 * <p> 2961 * A pool of strings, initially empty, is maintained privately by the 2962 * class {@code String}. 2963 * <p> 2964 * When the intern method is invoked, if the pool already contains a 2965 * string equal to this {@code String} object as determined by 2966 * the {@link #equals(Object)} method, then the string from the pool is 2967 * returned. Otherwise, this {@code String} object is added to the 2968 * pool and a reference to this {@code String} object is returned. 2969 * <p> 2970 * It follows that for any two strings {@code s} and {@code t}, 2971 * {@code s.intern() == t.intern()} is {@code true} 2972 * if and only if {@code s.equals(t)} is {@code true}. 2973 * <p> 2974 * All literal strings and string-valued constant expressions are 2975 * interned. String literals are defined in section 3.10.5 of the 2976 * <cite>The Java™ Language Specification</cite>. 2977 * 2978 * @return a string that has the same contents as this string, but is 2979 * guaranteed to be from a pool of unique strings. 2980 */ 2981 public native String intern(); 2982 2983 //////////////////////////////////////////////////////////////// 2984 2985 /** 2986 * Copy character bytes from this string into dst starting at dstBegin. 2987 * This method doesn't perform any range checking. 2988 * 2989 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two 2990 * coders are different, and dst is big enough (range check) 2991 * 2992 * @param dstBegin the char index, not offset of byte[] 2993 * @param coder the coder of dst[] 2994 */ 2995 void getBytes(byte dst[], int dstBegin, byte coder) { 2996 if (coder() == coder) { 2997 System.arraycopy(value, 0, dst, dstBegin << coder, value.length); 2998 } else { // this.coder == LATIN && coder == UTF16 2999 StringLatin1.inflate(value, 0, dst, dstBegin, value.length); 3000 } 3001 } 3002 3003 /* 3004 * Package private constructor. Trailing Void argument is there for 3005 * disambiguating it against other (public) constructors. 3006 * 3007 * Stores the char[] value into a byte[] that each byte represents 3008 * the8 low-order bits of the corresponding character, if the char[] 3009 * contains only latin1 character. Or a byte[] that stores all 3010 * characters in their byte sequences defined by the {@code StringUTF16}. 3011 */ 3012 String(char[] value, int off, int len, Void sig) { 3013 if (len == 0) { 3014 this.value = "".value; 3015 this.coder = "".coder; 3016 return; 3017 } 3018 if (COMPACT_STRINGS) { 3019 byte[] val = StringUTF16.compress(value, off, len); 3020 if (val != null) { 3021 this.value = val; 3022 this.coder = LATIN1; 3023 return; 3024 } 3025 } 3026 this.coder = UTF16; 3027 this.value = StringUTF16.toBytes(value, off, len); 3028 } 3029 3030 /* 3031 * Package private constructor. Trailing Void argument is there for 3032 * disambiguating it against other (public) constructors. 3033 */ 3034 String(AbstractStringBuilder asb, Void sig) { 3035 byte[] val = asb.getValue(); 3036 int length = asb.length(); 3037 if (asb.isLatin1()) { 3038 this.coder = LATIN1; 3039 this.value = Arrays.copyOfRange(val, 0, length); 3040 } else { 3041 if (COMPACT_STRINGS) { 3042 byte[] buf = StringUTF16.compress(val, 0, length); 3043 if (buf != null) { 3044 this.coder = LATIN1; 3045 this.value = buf; 3046 return; 3047 } 3048 } 3049 this.coder = UTF16; 3050 this.value = Arrays.copyOfRange(val, 0, length << 1); 3051 } 3052 } 3053 3054 /* 3055 * Package private constructor which shares value array for speed. 3056 */ 3057 String(byte[] value, byte coder) { 3058 this.value = value; 3059 this.coder = coder; 3060 } 3061 3062 byte coder() { 3063 return COMPACT_STRINGS ? coder : UTF16; 3064 } 3065 3066 private boolean isLatin1() { 3067 return COMPACT_STRINGS && coder == LATIN1; 3068 } 3069 3070 static final byte LATIN1 = 0; 3071 static final byte UTF16 = 1; 3072 3073 /* 3074 * StringIndexOutOfBoundsException if {@code index} is 3075 * negative or greater than or equal to {@code length}. 3076 */ 3077 static void checkIndex(int index, int length) { 3078 if (index < 0 || index >= length) { 3079 throw new StringIndexOutOfBoundsException("index " + index); 3080 } 3081 } 3082 3083 /* 3084 * StringIndexOutOfBoundsException if {@code offset} 3085 * is negative or greater than {@code length}. 3086 */ 3087 static void checkOffset(int offset, int length) { 3088 if (offset < 0 || offset > length) { 3089 throw new StringIndexOutOfBoundsException("offset " + offset + 3090 ",length " + length); 3091 } 3092 } 3093 3094 /* 3095 * Check {@code offset}, {@code count} against {@code 0} and {@code length} 3096 * bounds. 3097 * 3098 * @throws StringIndexOutOfBoundsException 3099 * If {@code offset} is negative, {@code count} is negative, 3100 * or {@code offset} is greater than {@code length - count} 3101 */ 3102 static void checkBoundsOffCount(int offset, int count, int length) { 3103 if (offset < 0 || count < 0 || offset > length - count) { 3104 throw new StringIndexOutOfBoundsException( 3105 "offset " + offset + ", count " + count + ", length " + length); 3106 } 3107 } 3108 3109 /* 3110 * Check {@code begin}, {@code end} against {@code 0} and {@code length} 3111 * bounds. 3112 * 3113 * @throws StringIndexOutOfBoundsException 3114 * If {@code begin} is negative, {@code begin} is greater than 3115 * {@code end}, or {@code end} is greater than {@code length}. 3116 */ 3117 private static void checkBoundsBeginEnd(int begin, int end, int length) { 3118 if (begin < 0 || begin > end || end > length) { 3119 throw new StringIndexOutOfBoundsException( 3120 "begin " + begin + ", end " + end + ", length " + length); 3121 } 3122 } 3123 }