1 /* 2 * Copyright (c) 1994, 2017, 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. For additional information on string 82 * concatenation and conversion, see <i>The Java™ Language Specification</i>. 83 * 84 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor 85 * or method in this class will cause a {@link NullPointerException} to be 86 * thrown. 87 * 88 * <p>A {@code String} represents a string in the UTF-16 format 89 * in which <em>supplementary characters</em> are represented by <em>surrogate 90 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 91 * Character Representations</a> in the {@code Character} class for 92 * more information). 93 * Index values refer to {@code char} code units, so a supplementary 94 * character uses two positions in a {@code String}. 95 * <p>The {@code String} class provides methods for dealing with 96 * Unicode code points (i.e., characters), in addition to those for 97 * dealing with Unicode code units (i.e., {@code char} values). 98 * 99 * <p>Unless otherwise noted, methods for comparing Strings do not take locale 100 * into account. The {@link java.text.Collator} class provides methods for 101 * finer-grain, locale-sensitive String comparison. 102 * 103 * @implNote The implementation of the string concatenation operator is left to 104 * the discretion of a Java compiler, as long as the compiler ultimately conforms 105 * to <i>The Java™ Language Specification</i>. For example, the {@code javac} compiler 106 * may implement the operator with {@code StringBuffer}, {@code StringBuilder}, 107 * or {@code java.lang.invoke.StringConcatFactory} depending on the JDK version. The 108 * implementation of string conversion is typically through the method {@code toString}, 109 * defined by {@code Object} and inherited by all classes in Java. 110 * 111 * @author Lee Boynton 112 * @author Arthur van Hoff 113 * @author Martin Buchholz 114 * @author Ulf Zibis 115 * @see java.lang.Object#toString() 116 * @see java.lang.StringBuffer 117 * @see java.lang.StringBuilder 118 * @see java.nio.charset.Charset 119 * @since 1.0 120 * @jls 15.18.1 String Concatenation Operator + 121 */ 122 123 public final class String 124 implements java.io.Serializable, Comparable<String>, CharSequence { 125 126 /** 127 * The value is used for character storage. 128 * 129 * @implNote This field is trusted by the VM, and is a subject to 130 * constant folding if String instance is constant. Overwriting this 131 * field after construction will cause problems. 132 * 133 * Additionally, it is marked with {@link Stable} to trust the contents 134 * of the array. No other facility in JDK provides this functionality (yet). 135 * {@link Stable} is safe here, because value is never null. 136 */ 137 @Stable 138 private final byte[] value; 139 140 /** 141 * The identifier of the encoding used to encode the bytes in 142 * {@code value}. The supported values in this implementation are 143 * 144 * LATIN1 145 * UTF16 146 * 147 * @implNote This field is trusted by the VM, and is a subject to 148 * constant folding if String instance is constant. Overwriting this 149 * field after construction will cause problems. 150 */ 151 private final byte coder; 152 153 /** Cache the hash code for the string */ 154 private int hash; // Default to 0 155 156 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 157 private static final long serialVersionUID = -6849794470754667710L; 158 159 /** 160 * If String compaction is disabled, the bytes in {@code value} are 161 * always encoded in UTF16. 162 * 163 * For methods with several possible implementation paths, when String 164 * compaction is disabled, only one code path is taken. 165 * 166 * The instance field value is generally opaque to optimizing JIT 167 * compilers. Therefore, in performance-sensitive place, an explicit 168 * check of the static boolean {@code COMPACT_STRINGS} is done first 169 * before checking the {@code coder} field since the static boolean 170 * {@code COMPACT_STRINGS} would be constant folded away by an 171 * optimizing JIT compiler. The idioms for these cases are as follows. 172 * 173 * For code such as: 174 * 175 * if (coder == LATIN1) { ... } 176 * 177 * can be written more optimally as 178 * 179 * if (coder() == LATIN1) { ... } 180 * 181 * or: 182 * 183 * if (COMPACT_STRINGS && coder == LATIN1) { ... } 184 * 185 * An optimizing JIT compiler can fold the above conditional as: 186 * 187 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... } 188 * COMPACT_STRINGS == false => if (false) { ... } 189 * 190 * @implNote 191 * The actual value for this field is injected by JVM. The static 192 * initialization block is used to set the value here to communicate 193 * that this static final field is not statically foldable, and to 194 * avoid any possible circular dependency during vm initialization. 195 */ 196 static final boolean COMPACT_STRINGS; 197 198 static { 199 COMPACT_STRINGS = true; 200 } 201 202 /** 203 * Class String is special cased within the Serialization Stream Protocol. 204 * 205 * A String instance is written into an ObjectOutputStream according to 206 * <a href="{@docRoot}/../platform/serialization/spec/output.html"> 207 * Object Serialization Specification, Section 6.2, "Stream Elements"</a> 208 */ 209 private static final ObjectStreamField[] serialPersistentFields = 210 new ObjectStreamField[0]; 211 212 /** 213 * Initializes a newly created {@code String} object so that it represents 214 * an empty character sequence. Note that use of this constructor is 215 * unnecessary since Strings are immutable. 216 */ 217 public String() { 218 this.value = "".value; 219 this.coder = "".coder; 220 } 221 222 /** 223 * Initializes a newly created {@code String} object so that it represents 224 * the same sequence of characters as the argument; in other words, the 225 * newly created string is a copy of the argument string. Unless an 226 * explicit copy of {@code original} is needed, use of this constructor is 227 * unnecessary since Strings are immutable. 228 * 229 * @param original 230 * A {@code String} 231 */ 232 @HotSpotIntrinsicCandidate 233 public String(String original) { 234 this.value = original.value; 235 this.coder = original.coder; 236 this.hash = original.hash; 237 } 238 239 /** 240 * Allocates a new {@code String} so that it represents the sequence of 241 * characters currently contained in the character array argument. The 242 * contents of the character array are copied; subsequent modification of 243 * the character array does not affect the newly created string. 244 * 245 * @param value 246 * The initial value of the string 247 */ 248 public String(char value[]) { 249 this(value, 0, value.length, null); 250 } 251 252 /** 253 * Allocates a new {@code String} that contains characters from a subarray 254 * of the character array argument. The {@code offset} argument is the 255 * index of the first character of the subarray and the {@code count} 256 * argument specifies the length of the subarray. The contents of the 257 * subarray are copied; subsequent modification of the character array does 258 * not affect the newly created string. 259 * 260 * @param value 261 * Array that is the source of characters 262 * 263 * @param offset 264 * The initial offset 265 * 266 * @param count 267 * The length 268 * 269 * @throws IndexOutOfBoundsException 270 * If {@code offset} is negative, {@code count} is negative, or 271 * {@code offset} is greater than {@code value.length - count} 272 */ 273 public String(char value[], int offset, int count) { 274 this(value, offset, count, rangeCheck(value, offset, count)); 275 } 276 277 private static Void rangeCheck(char[] value, int offset, int count) { 278 checkBoundsOffCount(offset, count, value.length); 279 return null; 280 } 281 282 /** 283 * Allocates a new {@code String} that contains characters from a subarray 284 * of the <a href="Character.html#unicode">Unicode code point</a> array 285 * argument. The {@code offset} argument is the index of the first code 286 * point of the subarray and the {@code count} argument specifies the 287 * length of the subarray. The contents of the subarray are converted to 288 * {@code char}s; subsequent modification of the {@code int} array does not 289 * affect the newly created string. 290 * 291 * @param codePoints 292 * Array that is the source of Unicode code points 293 * 294 * @param offset 295 * The initial offset 296 * 297 * @param count 298 * The length 299 * 300 * @throws IllegalArgumentException 301 * If any invalid Unicode code point is found in {@code 302 * codePoints} 303 * 304 * @throws IndexOutOfBoundsException 305 * If {@code offset} is negative, {@code count} is negative, or 306 * {@code offset} is greater than {@code codePoints.length - count} 307 * 308 * @since 1.5 309 */ 310 public String(int[] codePoints, int offset, int count) { 311 checkBoundsOffCount(offset, count, codePoints.length); 312 if (count == 0) { 313 this.value = "".value; 314 this.coder = "".coder; 315 return; 316 } 317 if (COMPACT_STRINGS) { 318 byte[] val = StringLatin1.toBytes(codePoints, offset, count); 319 if (val != null) { 320 this.coder = LATIN1; 321 this.value = val; 322 return; 323 } 324 } 325 this.coder = UTF16; 326 this.value = StringUTF16.toBytes(codePoints, offset, count); 327 } 328 329 /** 330 * Allocates a new {@code String} constructed from a subarray of an array 331 * of 8-bit integer values. 332 * 333 * <p> The {@code offset} argument is the index of the first byte of the 334 * subarray, and the {@code count} argument specifies the length of the 335 * subarray. 336 * 337 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 338 * specified in the method above. 339 * 340 * @deprecated This method does not properly convert bytes into characters. 341 * As of JDK 1.1, the preferred way to do this is via the 342 * {@code String} constructors that take a {@link 343 * java.nio.charset.Charset}, charset name, or that use the platform's 344 * default charset. 345 * 346 * @param ascii 347 * The bytes to be converted to characters 348 * 349 * @param hibyte 350 * The top 8 bits of each 16-bit Unicode code unit 351 * 352 * @param offset 353 * The initial offset 354 * @param count 355 * The length 356 * 357 * @throws IndexOutOfBoundsException 358 * If {@code offset} is negative, {@code count} is negative, or 359 * {@code offset} is greater than {@code ascii.length - count} 360 * 361 * @see #String(byte[], int) 362 * @see #String(byte[], int, int, java.lang.String) 363 * @see #String(byte[], int, int, java.nio.charset.Charset) 364 * @see #String(byte[], int, int) 365 * @see #String(byte[], java.lang.String) 366 * @see #String(byte[], java.nio.charset.Charset) 367 * @see #String(byte[]) 368 */ 369 @Deprecated(since="1.1") 370 public String(byte ascii[], int hibyte, int offset, int count) { 371 checkBoundsOffCount(offset, count, ascii.length); 372 if (count == 0) { 373 this.value = "".value; 374 this.coder = "".coder; 375 return; 376 } 377 if (COMPACT_STRINGS && (byte)hibyte == 0) { 378 this.value = Arrays.copyOfRange(ascii, offset, offset + count); 379 this.coder = LATIN1; 380 } else { 381 hibyte <<= 8; 382 byte[] val = StringUTF16.newBytesFor(count); 383 for (int i = 0; i < count; i++) { 384 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff)); 385 } 386 this.value = val; 387 this.coder = UTF16; 388 } 389 } 390 391 /** 392 * Allocates a new {@code String} containing characters constructed from 393 * an array of 8-bit integer values. Each character <i>c</i>in the 394 * resulting string is constructed from the corresponding component 395 * <i>b</i> in the byte array such that: 396 * 397 * <blockquote><pre> 398 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 399 * | (<b><i>b</i></b> & 0xff)) 400 * </pre></blockquote> 401 * 402 * @deprecated This method does not properly convert bytes into 403 * characters. As of JDK 1.1, the preferred way to do this is via the 404 * {@code String} constructors that take a {@link 405 * java.nio.charset.Charset}, charset name, or that use the platform's 406 * default charset. 407 * 408 * @param ascii 409 * The bytes to be converted to characters 410 * 411 * @param hibyte 412 * The top 8 bits of each 16-bit Unicode code unit 413 * 414 * @see #String(byte[], int, int, java.lang.String) 415 * @see #String(byte[], int, int, java.nio.charset.Charset) 416 * @see #String(byte[], int, int) 417 * @see #String(byte[], java.lang.String) 418 * @see #String(byte[], java.nio.charset.Charset) 419 * @see #String(byte[]) 420 */ 421 @Deprecated(since="1.1") 422 public String(byte ascii[], int hibyte) { 423 this(ascii, hibyte, 0, ascii.length); 424 } 425 426 /** 427 * Constructs a new {@code String} by decoding the specified subarray of 428 * bytes using the specified charset. The length of the new {@code String} 429 * is a function of the charset, and hence may not be equal to the length 430 * of the subarray. 431 * 432 * <p> The behavior of this constructor when the given bytes are not valid 433 * in the given charset is unspecified. The {@link 434 * java.nio.charset.CharsetDecoder} class should be used when more control 435 * over the decoding process is required. 436 * 437 * @param bytes 438 * The bytes to be decoded into characters 439 * 440 * @param offset 441 * The index of the first byte to decode 442 * 443 * @param length 444 * The number of bytes to decode 445 446 * @param charsetName 447 * The name of a supported {@linkplain java.nio.charset.Charset 448 * charset} 449 * 450 * @throws UnsupportedEncodingException 451 * If the named charset is not supported 452 * 453 * @throws IndexOutOfBoundsException 454 * If {@code offset} is negative, {@code length} is negative, or 455 * {@code offset} is greater than {@code bytes.length - length} 456 * 457 * @since 1.1 458 */ 459 public String(byte bytes[], int offset, int length, String charsetName) 460 throws UnsupportedEncodingException { 461 if (charsetName == null) 462 throw new NullPointerException("charsetName"); 463 checkBoundsOffCount(offset, length, bytes.length); 464 StringCoding.Result ret = 465 StringCoding.decode(charsetName, bytes, offset, length); 466 this.value = ret.value; 467 this.coder = ret.coder; 468 } 469 470 /** 471 * Constructs a new {@code String} by decoding the specified subarray of 472 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 473 * The length of the new {@code String} is a function of the charset, and 474 * hence may not be equal to the length of the subarray. 475 * 476 * <p> This method always replaces malformed-input and unmappable-character 477 * sequences with this charset's default replacement string. The {@link 478 * java.nio.charset.CharsetDecoder} class should be used when more control 479 * over the decoding process is required. 480 * 481 * @param bytes 482 * The bytes to be decoded into characters 483 * 484 * @param offset 485 * The index of the first byte to decode 486 * 487 * @param length 488 * The number of bytes to decode 489 * 490 * @param charset 491 * The {@linkplain java.nio.charset.Charset charset} to be used to 492 * decode the {@code bytes} 493 * 494 * @throws IndexOutOfBoundsException 495 * If {@code offset} is negative, {@code length} is negative, or 496 * {@code offset} is greater than {@code bytes.length - length} 497 * 498 * @since 1.6 499 */ 500 public String(byte bytes[], int offset, int length, Charset charset) { 501 if (charset == null) 502 throw new NullPointerException("charset"); 503 checkBoundsOffCount(offset, length, bytes.length); 504 StringCoding.Result ret = 505 StringCoding.decode(charset, bytes, offset, length); 506 this.value = ret.value; 507 this.coder = ret.coder; 508 } 509 510 /** 511 * Constructs a new {@code String} by decoding the specified array of bytes 512 * using the specified {@linkplain java.nio.charset.Charset charset}. The 513 * length of the new {@code String} is a function of the charset, and hence 514 * may not be equal to the length of the byte array. 515 * 516 * <p> The behavior of this constructor when the given bytes are not valid 517 * in the given charset is unspecified. The {@link 518 * java.nio.charset.CharsetDecoder} class should be used when more control 519 * over the decoding process is required. 520 * 521 * @param bytes 522 * The bytes to be decoded into characters 523 * 524 * @param charsetName 525 * The name of a supported {@linkplain java.nio.charset.Charset 526 * charset} 527 * 528 * @throws UnsupportedEncodingException 529 * If the named charset is not supported 530 * 531 * @since 1.1 532 */ 533 public String(byte bytes[], String charsetName) 534 throws UnsupportedEncodingException { 535 this(bytes, 0, bytes.length, charsetName); 536 } 537 538 /** 539 * Constructs a new {@code String} by decoding the specified array of 540 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 541 * The length of the new {@code String} is a function of the charset, and 542 * hence may not be equal to the length of the byte array. 543 * 544 * <p> This method always replaces malformed-input and unmappable-character 545 * sequences with this charset's default replacement string. The {@link 546 * java.nio.charset.CharsetDecoder} class should be used when more control 547 * over the decoding process is required. 548 * 549 * @param bytes 550 * The bytes to be decoded into characters 551 * 552 * @param charset 553 * The {@linkplain java.nio.charset.Charset charset} to be used to 554 * decode the {@code bytes} 555 * 556 * @since 1.6 557 */ 558 public String(byte bytes[], Charset charset) { 559 this(bytes, 0, bytes.length, charset); 560 } 561 562 /** 563 * Constructs a new {@code String} by decoding the specified subarray of 564 * bytes using the platform's default charset. The length of the new 565 * {@code String} is a function of the charset, and hence may not be equal 566 * to the length of the subarray. 567 * 568 * <p> The behavior of this constructor when the given bytes are not valid 569 * in the default charset is unspecified. The {@link 570 * java.nio.charset.CharsetDecoder} class should be used when more control 571 * over the decoding process is required. 572 * 573 * @param bytes 574 * The bytes to be decoded into characters 575 * 576 * @param offset 577 * The index of the first byte to decode 578 * 579 * @param length 580 * The number of bytes to decode 581 * 582 * @throws IndexOutOfBoundsException 583 * If {@code offset} is negative, {@code length} is negative, or 584 * {@code offset} is greater than {@code bytes.length - length} 585 * 586 * @since 1.1 587 */ 588 public String(byte bytes[], int offset, int length) { 589 checkBoundsOffCount(offset, length, bytes.length); 590 StringCoding.Result ret = StringCoding.decode(bytes, offset, length); 591 this.value = ret.value; 592 this.coder = ret.coder; 593 } 594 595 /** 596 * Constructs a new {@code String} by decoding the specified array of bytes 597 * using the platform's default charset. The length of the new {@code 598 * String} is a function of the charset, and hence may not be equal to the 599 * length of the byte array. 600 * 601 * <p> The behavior of this constructor when the given bytes are not valid 602 * in the default charset is unspecified. The {@link 603 * java.nio.charset.CharsetDecoder} class should be used when more control 604 * over the decoding process is required. 605 * 606 * @param bytes 607 * The bytes to be decoded into characters 608 * 609 * @since 1.1 610 */ 611 public String(byte[] bytes) { 612 this(bytes, 0, bytes.length); 613 } 614 615 /** 616 * Allocates a new string that contains the sequence of characters 617 * currently contained in the string buffer argument. The contents of the 618 * string buffer are copied; subsequent modification of the string buffer 619 * does not affect the newly created string. 620 * 621 * @param buffer 622 * A {@code StringBuffer} 623 */ 624 public String(StringBuffer buffer) { 625 this(buffer.toString()); 626 } 627 628 /** 629 * Allocates a new string that contains the sequence of characters 630 * currently contained in the string builder argument. The contents of the 631 * string builder are copied; subsequent modification of the string builder 632 * does not affect the newly created string. 633 * 634 * <p> This constructor is provided to ease migration to {@code 635 * StringBuilder}. Obtaining a string from a string builder via the {@code 636 * toString} method is likely to run faster and is generally preferred. 637 * 638 * @param builder 639 * A {@code StringBuilder} 640 * 641 * @since 1.5 642 */ 643 public String(StringBuilder builder) { 644 this(builder, null); 645 } 646 647 /* 648 * Package private constructor which shares value array for speed. 649 * this constructor is always expected to be called with share==true. 650 * a separate constructor is needed because we already have a public 651 * String(char[]) constructor that makes a copy of the given char[]. 652 */ 653 // TBD: this is kept for package internal use (Thread/System), 654 // should be removed if they all have a byte[] version 655 String(char[] val, boolean share) { 656 // assert share : "unshared not supported"; 657 this(val, 0, val.length, null); 658 } 659 660 /** 661 * Returns the length of this string. 662 * The length is equal to the number of <a href="Character.html#unicode">Unicode 663 * code units</a> in the string. 664 * 665 * @return the length of the sequence of characters represented by this 666 * object. 667 */ 668 public int length() { 669 return value.length >> coder(); 670 } 671 672 /** 673 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 674 * 675 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 676 * {@code false} 677 * 678 * @since 1.6 679 */ 680 public boolean isEmpty() { 681 return value.length == 0; 682 } 683 684 /** 685 * Returns the {@code char} value at the 686 * specified index. An index ranges from {@code 0} to 687 * {@code length() - 1}. The first {@code char} value of the sequence 688 * is at index {@code 0}, the next at index {@code 1}, 689 * and so on, as for array indexing. 690 * 691 * <p>If the {@code char} value specified by the index is a 692 * <a href="Character.html#unicode">surrogate</a>, the surrogate 693 * value is returned. 694 * 695 * @param index the index of the {@code char} value. 696 * @return the {@code char} value at the specified index of this string. 697 * The first {@code char} value is at index {@code 0}. 698 * @exception IndexOutOfBoundsException if the {@code index} 699 * argument is negative or not less than the length of this 700 * string. 701 */ 702 public char charAt(int index) { 703 if (isLatin1()) { 704 return StringLatin1.charAt(value, index); 705 } else { 706 return StringUTF16.charAt(value, index); 707 } 708 } 709 710 /** 711 * Returns the character (Unicode code point) at the specified 712 * index. The index refers to {@code char} values 713 * (Unicode code units) and ranges from {@code 0} to 714 * {@link #length()}{@code - 1}. 715 * 716 * <p> If the {@code char} value specified at the given index 717 * is in the high-surrogate range, the following index is less 718 * than the length of this {@code String}, and the 719 * {@code char} value at the following index is in the 720 * low-surrogate range, then the supplementary code point 721 * corresponding to this surrogate pair is returned. Otherwise, 722 * the {@code char} value at the given index is returned. 723 * 724 * @param index the index to the {@code char} values 725 * @return the code point value of the character at the 726 * {@code index} 727 * @exception IndexOutOfBoundsException if the {@code index} 728 * argument is negative or not less than the length of this 729 * string. 730 * @since 1.5 731 */ 732 public int codePointAt(int index) { 733 if (isLatin1()) { 734 checkIndex(index, value.length); 735 return value[index] & 0xff; 736 } 737 int length = value.length >> 1; 738 checkIndex(index, length); 739 return StringUTF16.codePointAt(value, index, length); 740 } 741 742 /** 743 * Returns the character (Unicode code point) before the specified 744 * index. The index refers to {@code char} values 745 * (Unicode code units) and ranges from {@code 1} to {@link 746 * CharSequence#length() length}. 747 * 748 * <p> If the {@code char} value at {@code (index - 1)} 749 * is in the low-surrogate range, {@code (index - 2)} is not 750 * negative, and the {@code char} value at {@code (index - 751 * 2)} is in the high-surrogate range, then the 752 * supplementary code point value of the surrogate pair is 753 * returned. If the {@code char} value at {@code index - 754 * 1} is an unpaired low-surrogate or a high-surrogate, the 755 * surrogate value is returned. 756 * 757 * @param index the index following the code point that should be returned 758 * @return the Unicode code point value before the given index. 759 * @exception IndexOutOfBoundsException if the {@code index} 760 * argument is less than 1 or greater than the length 761 * of this string. 762 * @since 1.5 763 */ 764 public int codePointBefore(int index) { 765 int i = index - 1; 766 if (i < 0 || i >= length()) { 767 throw new StringIndexOutOfBoundsException(index); 768 } 769 if (isLatin1()) { 770 return (value[i] & 0xff); 771 } 772 return StringUTF16.codePointBefore(value, index); 773 } 774 775 /** 776 * Returns the number of Unicode code points in the specified text 777 * range of this {@code String}. The text range begins at the 778 * specified {@code beginIndex} and extends to the 779 * {@code char} at index {@code endIndex - 1}. Thus the 780 * length (in {@code char}s) of the text range is 781 * {@code endIndex-beginIndex}. Unpaired surrogates within 782 * the text range count as one code point each. 783 * 784 * @param beginIndex the index to the first {@code char} of 785 * the text range. 786 * @param endIndex the index after the last {@code char} of 787 * the text range. 788 * @return the number of Unicode code points in the specified text 789 * range 790 * @exception IndexOutOfBoundsException if the 791 * {@code beginIndex} is negative, or {@code endIndex} 792 * is larger than the length of this {@code String}, or 793 * {@code beginIndex} is larger than {@code endIndex}. 794 * @since 1.5 795 */ 796 public int codePointCount(int beginIndex, int endIndex) { 797 if (beginIndex < 0 || beginIndex > endIndex || 798 endIndex > length()) { 799 throw new IndexOutOfBoundsException(); 800 } 801 if (isLatin1()) { 802 return endIndex - beginIndex; 803 } 804 return StringUTF16.codePointCount(value, beginIndex, endIndex); 805 } 806 807 /** 808 * Returns the index within this {@code String} that is 809 * offset from the given {@code index} by 810 * {@code codePointOffset} code points. Unpaired surrogates 811 * within the text range given by {@code index} and 812 * {@code codePointOffset} count as one code point each. 813 * 814 * @param index the index to be offset 815 * @param codePointOffset the offset in code points 816 * @return the index within this {@code String} 817 * @exception IndexOutOfBoundsException if {@code index} 818 * is negative or larger then the length of this 819 * {@code String}, or if {@code codePointOffset} is positive 820 * and the substring starting with {@code index} has fewer 821 * than {@code codePointOffset} code points, 822 * or if {@code codePointOffset} is negative and the substring 823 * before {@code index} has fewer than the absolute value 824 * of {@code codePointOffset} code points. 825 * @since 1.5 826 */ 827 public int offsetByCodePoints(int index, int codePointOffset) { 828 if (index < 0 || index > length()) { 829 throw new IndexOutOfBoundsException(); 830 } 831 return Character.offsetByCodePoints(this, index, codePointOffset); 832 } 833 834 /** 835 * Copies characters from this string into the destination character 836 * array. 837 * <p> 838 * The first character to be copied is at index {@code srcBegin}; 839 * the last character to be copied is at index {@code srcEnd-1} 840 * (thus the total number of characters to be copied is 841 * {@code srcEnd-srcBegin}). The characters are copied into the 842 * subarray of {@code dst} starting at index {@code dstBegin} 843 * and ending at index: 844 * <blockquote><pre> 845 * dstBegin + (srcEnd-srcBegin) - 1 846 * </pre></blockquote> 847 * 848 * @param srcBegin index of the first character in the string 849 * to copy. 850 * @param srcEnd index after the last character in the string 851 * to copy. 852 * @param dst the destination array. 853 * @param dstBegin the start offset in the destination array. 854 * @exception IndexOutOfBoundsException If any of the following 855 * is true: 856 * <ul><li>{@code srcBegin} is negative. 857 * <li>{@code srcBegin} is greater than {@code srcEnd} 858 * <li>{@code srcEnd} is greater than the length of this 859 * string 860 * <li>{@code dstBegin} is negative 861 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 862 * {@code dst.length}</ul> 863 */ 864 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 865 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 866 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 867 if (isLatin1()) { 868 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin); 869 } else { 870 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin); 871 } 872 } 873 874 /** 875 * Copies characters from this string into the destination byte array. Each 876 * byte receives the 8 low-order bits of the corresponding character. The 877 * eight high-order bits of each character are not copied and do not 878 * participate in the transfer in any way. 879 * 880 * <p> The first character to be copied is at index {@code srcBegin}; the 881 * last character to be copied is at index {@code srcEnd-1}. The total 882 * number of characters to be copied is {@code srcEnd-srcBegin}. The 883 * characters, converted to bytes, are copied into the subarray of {@code 884 * dst} starting at index {@code dstBegin} and ending at index: 885 * 886 * <blockquote><pre> 887 * dstBegin + (srcEnd-srcBegin) - 1 888 * </pre></blockquote> 889 * 890 * @deprecated This method does not properly convert characters into 891 * bytes. As of JDK 1.1, the preferred way to do this is via the 892 * {@link #getBytes()} method, which uses the platform's default charset. 893 * 894 * @param srcBegin 895 * Index of the first character in the string to copy 896 * 897 * @param srcEnd 898 * Index after the last character in the string to copy 899 * 900 * @param dst 901 * The destination array 902 * 903 * @param dstBegin 904 * The start offset in the destination array 905 * 906 * @throws IndexOutOfBoundsException 907 * If any of the following is true: 908 * <ul> 909 * <li> {@code srcBegin} is negative 910 * <li> {@code srcBegin} is greater than {@code srcEnd} 911 * <li> {@code srcEnd} is greater than the length of this String 912 * <li> {@code dstBegin} is negative 913 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 914 * dst.length} 915 * </ul> 916 */ 917 @Deprecated(since="1.1") 918 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 919 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 920 Objects.requireNonNull(dst); 921 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 922 if (isLatin1()) { 923 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 924 } else { 925 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 926 } 927 } 928 929 /** 930 * Encodes this {@code String} into a sequence of bytes using the named 931 * charset, storing the result into a new byte array. 932 * 933 * <p> The behavior of this method when this string cannot be encoded in 934 * the given charset is unspecified. The {@link 935 * java.nio.charset.CharsetEncoder} class should be used when more control 936 * over the encoding process is required. 937 * 938 * @param charsetName 939 * The name of a supported {@linkplain java.nio.charset.Charset 940 * charset} 941 * 942 * @return The resultant byte array 943 * 944 * @throws UnsupportedEncodingException 945 * If the named charset is not supported 946 * 947 * @since 1.1 948 */ 949 public byte[] getBytes(String charsetName) 950 throws UnsupportedEncodingException { 951 if (charsetName == null) throw new NullPointerException(); 952 return StringCoding.encode(charsetName, coder(), value); 953 } 954 955 /** 956 * Encodes this {@code String} into a sequence of bytes using the given 957 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 958 * new byte array. 959 * 960 * <p> This method always replaces malformed-input and unmappable-character 961 * sequences with this charset's default replacement byte array. The 962 * {@link java.nio.charset.CharsetEncoder} class should be used when more 963 * control over the encoding process is required. 964 * 965 * @param charset 966 * The {@linkplain java.nio.charset.Charset} to be used to encode 967 * the {@code String} 968 * 969 * @return The resultant byte array 970 * 971 * @since 1.6 972 */ 973 public byte[] getBytes(Charset charset) { 974 if (charset == null) throw new NullPointerException(); 975 return StringCoding.encode(charset, coder(), value); 976 } 977 978 /** 979 * Encodes this {@code String} into a sequence of bytes using the 980 * platform's default charset, storing the result into a new byte array. 981 * 982 * <p> The behavior of this method when this string cannot be encoded in 983 * the default charset is unspecified. The {@link 984 * java.nio.charset.CharsetEncoder} class should be used when more control 985 * over the encoding process is required. 986 * 987 * @return The resultant byte array 988 * 989 * @since 1.1 990 */ 991 public byte[] getBytes() { 992 return StringCoding.encode(coder(), value); 993 } 994 995 /** 996 * Compares this string to the specified object. The result is {@code 997 * true} if and only if the argument is not {@code null} and is a {@code 998 * String} object that represents the same sequence of characters as this 999 * object. 1000 * 1001 * <p>For finer-grained String comparison, refer to 1002 * {@link java.text.Collator}. 1003 * 1004 * @param anObject 1005 * The object to compare this {@code String} against 1006 * 1007 * @return {@code true} if the given object represents a {@code String} 1008 * equivalent to this string, {@code false} otherwise 1009 * 1010 * @see #compareTo(String) 1011 * @see #equalsIgnoreCase(String) 1012 */ 1013 public boolean equals(Object anObject) { 1014 if (this == anObject) { 1015 return true; 1016 } 1017 if (anObject instanceof String) { 1018 String aString = (String)anObject; 1019 if (coder() == aString.coder()) { 1020 return isLatin1() ? StringLatin1.equals(value, aString.value) 1021 : StringUTF16.equals(value, aString.value); 1022 } 1023 } 1024 return false; 1025 } 1026 1027 /** 1028 * Compares this string to the specified {@code StringBuffer}. The result 1029 * is {@code true} if and only if this {@code String} represents the same 1030 * sequence of characters as the specified {@code StringBuffer}. This method 1031 * synchronizes on the {@code StringBuffer}. 1032 * 1033 * <p>For finer-grained String comparison, refer to 1034 * {@link java.text.Collator}. 1035 * 1036 * @param sb 1037 * The {@code StringBuffer} to compare this {@code String} against 1038 * 1039 * @return {@code true} if this {@code String} represents the same 1040 * sequence of characters as the specified {@code StringBuffer}, 1041 * {@code false} otherwise 1042 * 1043 * @since 1.4 1044 */ 1045 public boolean contentEquals(StringBuffer sb) { 1046 return contentEquals((CharSequence)sb); 1047 } 1048 1049 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1050 int len = length(); 1051 if (len != sb.length()) { 1052 return false; 1053 } 1054 byte v1[] = value; 1055 byte v2[] = sb.getValue(); 1056 if (coder() == sb.getCoder()) { 1057 int n = v1.length; 1058 for (int i = 0; i < n; i++) { 1059 if (v1[i] != v2[i]) { 1060 return false; 1061 } 1062 } 1063 } else { 1064 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal" 1065 return false; 1066 } 1067 return StringUTF16.contentEquals(v1, v2, len); 1068 } 1069 return true; 1070 } 1071 1072 /** 1073 * Compares this string to the specified {@code CharSequence}. The 1074 * result is {@code true} if and only if this {@code String} represents the 1075 * same sequence of char values as the specified sequence. Note that if the 1076 * {@code CharSequence} is a {@code StringBuffer} then the method 1077 * synchronizes on it. 1078 * 1079 * <p>For finer-grained String comparison, refer to 1080 * {@link java.text.Collator}. 1081 * 1082 * @param cs 1083 * The sequence to compare this {@code String} against 1084 * 1085 * @return {@code true} if this {@code String} represents the same 1086 * sequence of char values as the specified sequence, {@code 1087 * false} otherwise 1088 * 1089 * @since 1.5 1090 */ 1091 public boolean contentEquals(CharSequence cs) { 1092 // Argument is a StringBuffer, StringBuilder 1093 if (cs instanceof AbstractStringBuilder) { 1094 if (cs instanceof StringBuffer) { 1095 synchronized(cs) { 1096 return nonSyncContentEquals((AbstractStringBuilder)cs); 1097 } 1098 } else { 1099 return nonSyncContentEquals((AbstractStringBuilder)cs); 1100 } 1101 } 1102 // Argument is a String 1103 if (cs instanceof String) { 1104 return equals(cs); 1105 } 1106 // Argument is a generic CharSequence 1107 int n = cs.length(); 1108 if (n != length()) { 1109 return false; 1110 } 1111 byte[] val = this.value; 1112 if (isLatin1()) { 1113 for (int i = 0; i < n; i++) { 1114 if ((val[i] & 0xff) != cs.charAt(i)) { 1115 return false; 1116 } 1117 } 1118 } else { 1119 if (!StringUTF16.contentEquals(val, cs, n)) { 1120 return false; 1121 } 1122 } 1123 return true; 1124 } 1125 1126 /** 1127 * Compares this {@code String} to another {@code String}, ignoring case 1128 * considerations. Two strings are considered equal ignoring case if they 1129 * are of the same length and corresponding characters in the two strings 1130 * are equal ignoring case. 1131 * 1132 * <p> Two characters {@code c1} and {@code c2} are considered the same 1133 * ignoring case if at least one of the following is true: 1134 * <ul> 1135 * <li> The two characters are the same (as compared by the 1136 * {@code ==} operator) 1137 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))} 1138 * on each character produces the same result 1139 * </ul> 1140 * 1141 * <p>Note that this method does <em>not</em> take locale into account, and 1142 * will result in unsatisfactory results for certain locales. The 1143 * {@link java.text.Collator} class provides locale-sensitive comparison. 1144 * 1145 * @param anotherString 1146 * The {@code String} to compare this {@code String} against 1147 * 1148 * @return {@code true} if the argument is not {@code null} and it 1149 * represents an equivalent {@code String} ignoring case; {@code 1150 * false} otherwise 1151 * 1152 * @see #equals(Object) 1153 */ 1154 public boolean equalsIgnoreCase(String anotherString) { 1155 return (this == anotherString) ? true 1156 : (anotherString != null) 1157 && (anotherString.length() == length()) 1158 && regionMatches(true, 0, anotherString, 0, length()); 1159 } 1160 1161 /** 1162 * Compares two strings lexicographically. 1163 * The comparison is based on the Unicode value of each character in 1164 * the strings. The character sequence represented by this 1165 * {@code String} object is compared lexicographically to the 1166 * character sequence represented by the argument string. The result is 1167 * a negative integer if this {@code String} object 1168 * lexicographically precedes the argument string. The result is a 1169 * positive integer if this {@code String} object lexicographically 1170 * follows the argument string. The result is zero if the strings 1171 * are equal; {@code compareTo} returns {@code 0} exactly when 1172 * the {@link #equals(Object)} method would return {@code true}. 1173 * <p> 1174 * This is the definition of lexicographic ordering. If two strings are 1175 * different, then either they have different characters at some index 1176 * that is a valid index for both strings, or their lengths are different, 1177 * or both. If they have different characters at one or more index 1178 * positions, let <i>k</i> be the smallest such index; then the string 1179 * whose character at position <i>k</i> has the smaller value, as 1180 * determined by using the {@code <} operator, lexicographically precedes the 1181 * other string. In this case, {@code compareTo} returns the 1182 * difference of the two character values at position {@code k} in 1183 * the two string -- that is, the value: 1184 * <blockquote><pre> 1185 * this.charAt(k)-anotherString.charAt(k) 1186 * </pre></blockquote> 1187 * If there is no index position at which they differ, then the shorter 1188 * string lexicographically precedes the longer string. In this case, 1189 * {@code compareTo} returns the difference of the lengths of the 1190 * strings -- that is, the value: 1191 * <blockquote><pre> 1192 * this.length()-anotherString.length() 1193 * </pre></blockquote> 1194 * 1195 * <p>For finer-grained String comparison, refer to 1196 * {@link java.text.Collator}. 1197 * 1198 * @param anotherString the {@code String} to be compared. 1199 * @return the value {@code 0} if the argument string is equal to 1200 * this string; a value less than {@code 0} if this string 1201 * is lexicographically less than the string argument; and a 1202 * value greater than {@code 0} if this string is 1203 * lexicographically greater than the string argument. 1204 */ 1205 public int compareTo(String anotherString) { 1206 byte v1[] = value; 1207 byte v2[] = anotherString.value; 1208 if (coder() == anotherString.coder()) { 1209 return isLatin1() ? StringLatin1.compareTo(v1, v2) 1210 : StringUTF16.compareTo(v1, v2); 1211 } 1212 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2) 1213 : StringUTF16.compareToLatin1(v1, v2); 1214 } 1215 1216 /** 1217 * A Comparator that orders {@code String} objects as by 1218 * {@code compareToIgnoreCase}. This comparator is serializable. 1219 * <p> 1220 * Note that this Comparator does <em>not</em> take locale into account, 1221 * and will result in an unsatisfactory ordering for certain locales. 1222 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1223 * 1224 * @see java.text.Collator 1225 * @since 1.2 1226 */ 1227 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1228 = new CaseInsensitiveComparator(); 1229 private static class CaseInsensitiveComparator 1230 implements Comparator<String>, java.io.Serializable { 1231 // use serialVersionUID from JDK 1.2.2 for interoperability 1232 private static final long serialVersionUID = 8575799808933029326L; 1233 1234 public int compare(String s1, String s2) { 1235 byte v1[] = s1.value; 1236 byte v2[] = s2.value; 1237 if (s1.coder() == s2.coder()) { 1238 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2) 1239 : StringUTF16.compareToCI(v1, v2); 1240 } 1241 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2) 1242 : StringUTF16.compareToCI_Latin1(v1, v2); 1243 } 1244 1245 /** Replaces the de-serialized object. */ 1246 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1247 } 1248 1249 /** 1250 * Compares two strings lexicographically, ignoring case 1251 * differences. This method returns an integer whose sign is that of 1252 * calling {@code compareTo} with normalized versions of the strings 1253 * where case differences have been eliminated by calling 1254 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1255 * each character. 1256 * <p> 1257 * Note that this method does <em>not</em> take locale into account, 1258 * and will result in an unsatisfactory ordering for certain locales. 1259 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1260 * 1261 * @param str the {@code String} to be compared. 1262 * @return a negative integer, zero, or a positive integer as the 1263 * specified String is greater than, equal to, or less 1264 * than this String, ignoring case considerations. 1265 * @see java.text.Collator 1266 * @since 1.2 1267 */ 1268 public int compareToIgnoreCase(String str) { 1269 return CASE_INSENSITIVE_ORDER.compare(this, str); 1270 } 1271 1272 /** 1273 * Tests if two string regions are equal. 1274 * <p> 1275 * A substring of this {@code String} object is compared to a substring 1276 * of the argument other. The result is true if these substrings 1277 * represent identical character sequences. The substring of this 1278 * {@code String} object to be compared begins at index {@code toffset} 1279 * and has length {@code len}. The substring of other to be compared 1280 * begins at index {@code ooffset} and has length {@code len}. The 1281 * result is {@code false} if and only if at least one of the following 1282 * is true: 1283 * <ul><li>{@code toffset} is negative. 1284 * <li>{@code ooffset} is negative. 1285 * <li>{@code toffset+len} is greater than the length of this 1286 * {@code String} object. 1287 * <li>{@code ooffset+len} is greater than the length of the other 1288 * argument. 1289 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1290 * such that: 1291 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1292 * <i>k</i>{@code )} 1293 * </ul> 1294 * 1295 * <p>Note that this method does <em>not</em> take locale into account. The 1296 * {@link java.text.Collator} class provides locale-sensitive comparison. 1297 * 1298 * @param toffset the starting offset of the subregion in this string. 1299 * @param other the string argument. 1300 * @param ooffset the starting offset of the subregion in the string 1301 * argument. 1302 * @param len the number of characters to compare. 1303 * @return {@code true} if the specified subregion of this string 1304 * exactly matches the specified subregion of the string argument; 1305 * {@code false} otherwise. 1306 */ 1307 public boolean regionMatches(int toffset, String other, int ooffset, int len) { 1308 byte tv[] = value; 1309 byte ov[] = other.value; 1310 // Note: toffset, ooffset, or len might be near -1>>>1. 1311 if ((ooffset < 0) || (toffset < 0) || 1312 (toffset > (long)length() - len) || 1313 (ooffset > (long)other.length() - len)) { 1314 return false; 1315 } 1316 if (coder() == other.coder()) { 1317 if (!isLatin1() && (len > 0)) { 1318 toffset = toffset << 1; 1319 ooffset = ooffset << 1; 1320 len = len << 1; 1321 } 1322 while (len-- > 0) { 1323 if (tv[toffset++] != ov[ooffset++]) { 1324 return false; 1325 } 1326 } 1327 } else { 1328 if (coder() == LATIN1) { 1329 while (len-- > 0) { 1330 if (StringLatin1.getChar(tv, toffset++) != 1331 StringUTF16.getChar(ov, ooffset++)) { 1332 return false; 1333 } 1334 } 1335 } else { 1336 while (len-- > 0) { 1337 if (StringUTF16.getChar(tv, toffset++) != 1338 StringLatin1.getChar(ov, ooffset++)) { 1339 return false; 1340 } 1341 } 1342 } 1343 } 1344 return true; 1345 } 1346 1347 /** 1348 * Tests if two string regions are equal. 1349 * <p> 1350 * A substring of this {@code String} object is compared to a substring 1351 * of the argument {@code other}. The result is {@code true} if these 1352 * substrings represent character sequences that are the same, ignoring 1353 * case if and only if {@code ignoreCase} is true. The substring of 1354 * this {@code String} object to be compared begins at index 1355 * {@code toffset} and has length {@code len}. The substring of 1356 * {@code other} to be compared begins at index {@code ooffset} and 1357 * has length {@code len}. The result is {@code false} if and only if 1358 * at least one of the following is true: 1359 * <ul><li>{@code toffset} is negative. 1360 * <li>{@code ooffset} is negative. 1361 * <li>{@code toffset+len} is greater than the length of this 1362 * {@code String} object. 1363 * <li>{@code ooffset+len} is greater than the length of the other 1364 * argument. 1365 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1366 * integer <i>k</i> less than {@code len} such that: 1367 * <blockquote><pre> 1368 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1369 * </pre></blockquote> 1370 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1371 * integer <i>k</i> less than {@code len} such that: 1372 * <blockquote><pre> 1373 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) != 1374 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k))) 1375 * </pre></blockquote> 1376 * </ul> 1377 * 1378 * <p>Note that this method does <em>not</em> take locale into account, 1379 * and will result in unsatisfactory results for certain locales when 1380 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class 1381 * provides locale-sensitive comparison. 1382 * 1383 * @param ignoreCase if {@code true}, ignore case when comparing 1384 * characters. 1385 * @param toffset the starting offset of the subregion in this 1386 * string. 1387 * @param other the string argument. 1388 * @param ooffset the starting offset of the subregion in the string 1389 * argument. 1390 * @param len the number of characters to compare. 1391 * @return {@code true} if the specified subregion of this string 1392 * matches the specified subregion of the string argument; 1393 * {@code false} otherwise. Whether the matching is exact 1394 * or case insensitive depends on the {@code ignoreCase} 1395 * argument. 1396 */ 1397 public boolean regionMatches(boolean ignoreCase, int toffset, 1398 String other, int ooffset, int len) { 1399 if (!ignoreCase) { 1400 return regionMatches(toffset, other, ooffset, len); 1401 } 1402 // Note: toffset, ooffset, or len might be near -1>>>1. 1403 if ((ooffset < 0) || (toffset < 0) 1404 || (toffset > (long)length() - len) 1405 || (ooffset > (long)other.length() - len)) { 1406 return false; 1407 } 1408 byte tv[] = value; 1409 byte ov[] = other.value; 1410 if (coder() == other.coder()) { 1411 return isLatin1() 1412 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len) 1413 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len); 1414 } 1415 return isLatin1() 1416 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len) 1417 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len); 1418 } 1419 1420 /** 1421 * Tests if the substring of this string beginning at the 1422 * specified index starts with the specified prefix. 1423 * 1424 * @param prefix the prefix. 1425 * @param toffset where to begin looking in this string. 1426 * @return {@code true} if the character sequence represented by the 1427 * argument is a prefix of the substring of this object starting 1428 * at index {@code toffset}; {@code false} otherwise. 1429 * The result is {@code false} if {@code toffset} is 1430 * negative or greater than the length of this 1431 * {@code String} object; otherwise the result is the same 1432 * as the result of the expression 1433 * <pre> 1434 * this.substring(toffset).startsWith(prefix) 1435 * </pre> 1436 */ 1437 public boolean startsWith(String prefix, int toffset) { 1438 // Note: toffset might be near -1>>>1. 1439 if (toffset < 0 || toffset > length() - prefix.length()) { 1440 return false; 1441 } 1442 byte ta[] = value; 1443 byte pa[] = prefix.value; 1444 int po = 0; 1445 int pc = pa.length; 1446 if (coder() == prefix.coder()) { 1447 int to = isLatin1() ? toffset : toffset << 1; 1448 while (po < pc) { 1449 if (ta[to++] != pa[po++]) { 1450 return false; 1451 } 1452 } 1453 } else { 1454 if (isLatin1()) { // && pcoder == UTF16 1455 return false; 1456 } 1457 // coder == UTF16 && pcoder == LATIN1) 1458 while (po < pc) { 1459 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) { 1460 return false; 1461 } 1462 } 1463 } 1464 return true; 1465 } 1466 1467 /** 1468 * Tests if this string starts with the specified prefix. 1469 * 1470 * @param prefix the prefix. 1471 * @return {@code true} if the character sequence represented by the 1472 * argument is a prefix of the character sequence represented by 1473 * this string; {@code false} otherwise. 1474 * Note also that {@code true} will be returned if the 1475 * argument is an empty string or is equal to this 1476 * {@code String} object as determined by the 1477 * {@link #equals(Object)} method. 1478 * @since 1.0 1479 */ 1480 public boolean startsWith(String prefix) { 1481 return startsWith(prefix, 0); 1482 } 1483 1484 /** 1485 * Tests if this string ends with the specified suffix. 1486 * 1487 * @param suffix the suffix. 1488 * @return {@code true} if the character sequence represented by the 1489 * argument is a suffix of the character sequence represented by 1490 * this object; {@code false} otherwise. Note that the 1491 * result will be {@code true} if the argument is the 1492 * empty string or is equal to this {@code String} object 1493 * as determined by the {@link #equals(Object)} method. 1494 */ 1495 public boolean endsWith(String suffix) { 1496 return startsWith(suffix, length() - suffix.length()); 1497 } 1498 1499 /** 1500 * Returns a hash code for this string. The hash code for a 1501 * {@code String} object is computed as 1502 * <blockquote><pre> 1503 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1504 * </pre></blockquote> 1505 * using {@code int} arithmetic, where {@code s[i]} is the 1506 * <i>i</i>th character of the string, {@code n} is the length of 1507 * the string, and {@code ^} indicates exponentiation. 1508 * (The hash value of the empty string is zero.) 1509 * 1510 * @return a hash code value for this object. 1511 */ 1512 public int hashCode() { 1513 int h = hash; 1514 if (h == 0 && value.length > 0) { 1515 hash = h = isLatin1() ? StringLatin1.hashCode(value) 1516 : StringUTF16.hashCode(value); 1517 } 1518 return h; 1519 } 1520 1521 /** 1522 * Returns the index within this string of the first occurrence of 1523 * the specified character. If a character with value 1524 * {@code ch} occurs in the character sequence represented by 1525 * this {@code String} object, then the index (in Unicode 1526 * code units) of the first such occurrence is returned. For 1527 * values of {@code ch} in the range from 0 to 0xFFFF 1528 * (inclusive), this is the smallest value <i>k</i> such that: 1529 * <blockquote><pre> 1530 * this.charAt(<i>k</i>) == ch 1531 * </pre></blockquote> 1532 * is true. For other values of {@code ch}, it is the 1533 * smallest value <i>k</i> such that: 1534 * <blockquote><pre> 1535 * this.codePointAt(<i>k</i>) == ch 1536 * </pre></blockquote> 1537 * is true. In either case, if no such character occurs in this 1538 * string, then {@code -1} is returned. 1539 * 1540 * @param ch a character (Unicode code point). 1541 * @return the index of the first occurrence of the character in the 1542 * character sequence represented by this object, or 1543 * {@code -1} if the character does not occur. 1544 */ 1545 public int indexOf(int ch) { 1546 return indexOf(ch, 0); 1547 } 1548 1549 /** 1550 * Returns the index within this string of the first occurrence of the 1551 * specified character, starting the search at the specified index. 1552 * <p> 1553 * If a character with value {@code ch} occurs in the 1554 * character sequence represented by this {@code String} 1555 * object at an index no smaller than {@code fromIndex}, then 1556 * the index of the first such occurrence is returned. For values 1557 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1558 * this is the smallest value <i>k</i> such that: 1559 * <blockquote><pre> 1560 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1561 * </pre></blockquote> 1562 * is true. For other values of {@code ch}, it is the 1563 * smallest value <i>k</i> such that: 1564 * <blockquote><pre> 1565 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1566 * </pre></blockquote> 1567 * is true. In either case, if no such character occurs in this 1568 * string at or after position {@code fromIndex}, then 1569 * {@code -1} is returned. 1570 * 1571 * <p> 1572 * There is no restriction on the value of {@code fromIndex}. If it 1573 * is negative, it has the same effect as if it were zero: this entire 1574 * string may be searched. If it is greater than the length of this 1575 * string, it has the same effect as if it were equal to the length of 1576 * this string: {@code -1} is returned. 1577 * 1578 * <p>All indices are specified in {@code char} values 1579 * (Unicode code units). 1580 * 1581 * @param ch a character (Unicode code point). 1582 * @param fromIndex the index to start the search from. 1583 * @return the index of the first occurrence of the character in the 1584 * character sequence represented by this object that is greater 1585 * than or equal to {@code fromIndex}, or {@code -1} 1586 * if the character does not occur. 1587 */ 1588 public int indexOf(int ch, int fromIndex) { 1589 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex) 1590 : StringUTF16.indexOf(value, ch, fromIndex); 1591 } 1592 1593 /** 1594 * Returns the index within this string of the last occurrence of 1595 * the specified character. For values of {@code ch} in the 1596 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1597 * units) returned is the largest value <i>k</i> such that: 1598 * <blockquote><pre> 1599 * this.charAt(<i>k</i>) == ch 1600 * </pre></blockquote> 1601 * is true. For other values of {@code ch}, it is the 1602 * largest value <i>k</i> such that: 1603 * <blockquote><pre> 1604 * this.codePointAt(<i>k</i>) == ch 1605 * </pre></blockquote> 1606 * is true. In either case, if no such character occurs in this 1607 * string, then {@code -1} is returned. The 1608 * {@code String} is searched backwards starting at the last 1609 * character. 1610 * 1611 * @param ch a character (Unicode code point). 1612 * @return the index of the last occurrence of the character in the 1613 * character sequence represented by this object, or 1614 * {@code -1} if the character does not occur. 1615 */ 1616 public int lastIndexOf(int ch) { 1617 return lastIndexOf(ch, length() - 1); 1618 } 1619 1620 /** 1621 * Returns the index within this string of the last occurrence of 1622 * the specified character, searching backward starting at the 1623 * specified index. For values of {@code ch} in the range 1624 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1625 * value <i>k</i> such that: 1626 * <blockquote><pre> 1627 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1628 * </pre></blockquote> 1629 * is true. For other values of {@code ch}, it is the 1630 * largest value <i>k</i> such that: 1631 * <blockquote><pre> 1632 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1633 * </pre></blockquote> 1634 * is true. In either case, if no such character occurs in this 1635 * string at or before position {@code fromIndex}, then 1636 * {@code -1} is returned. 1637 * 1638 * <p>All indices are specified in {@code char} values 1639 * (Unicode code units). 1640 * 1641 * @param ch a character (Unicode code point). 1642 * @param fromIndex the index to start the search from. There is no 1643 * restriction on the value of {@code fromIndex}. If it is 1644 * greater than or equal to the length of this string, it has 1645 * the same effect as if it were equal to one less than the 1646 * length of this string: this entire string may be searched. 1647 * If it is negative, it has the same effect as if it were -1: 1648 * -1 is returned. 1649 * @return the index of the last occurrence of the character in the 1650 * character sequence represented by this object that is less 1651 * than or equal to {@code fromIndex}, or {@code -1} 1652 * if the character does not occur before that point. 1653 */ 1654 public int lastIndexOf(int ch, int fromIndex) { 1655 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex) 1656 : StringUTF16.lastIndexOf(value, ch, fromIndex); 1657 } 1658 1659 /** 1660 * Returns the index within this string of the first occurrence of the 1661 * specified substring. 1662 * 1663 * <p>The returned index is the smallest value {@code k} for which: 1664 * <pre>{@code 1665 * this.startsWith(str, k) 1666 * }</pre> 1667 * If no such value of {@code k} exists, then {@code -1} is returned. 1668 * 1669 * @param str the substring to search for. 1670 * @return the index of the first occurrence of the specified substring, 1671 * or {@code -1} if there is no such occurrence. 1672 */ 1673 public int indexOf(String str) { 1674 if (coder() == str.coder()) { 1675 return isLatin1() ? StringLatin1.indexOf(value, str.value) 1676 : StringUTF16.indexOf(value, str.value); 1677 } 1678 if (coder() == LATIN1) { // str.coder == UTF16 1679 return -1; 1680 } 1681 return StringUTF16.indexOfLatin1(value, str.value); 1682 } 1683 1684 /** 1685 * Returns the index within this string of the first occurrence of the 1686 * specified substring, starting at the specified index. 1687 * 1688 * <p>The returned index is the smallest value {@code k} for which: 1689 * <pre>{@code 1690 * k >= Math.min(fromIndex, this.length()) && 1691 * this.startsWith(str, k) 1692 * }</pre> 1693 * If no such value of {@code k} exists, then {@code -1} is returned. 1694 * 1695 * @param str the substring to search for. 1696 * @param fromIndex the index from which to start the search. 1697 * @return the index of the first occurrence of the specified substring, 1698 * starting at the specified index, 1699 * or {@code -1} if there is no such occurrence. 1700 */ 1701 public int indexOf(String str, int fromIndex) { 1702 return indexOf(value, coder(), length(), str, fromIndex); 1703 } 1704 1705 /** 1706 * Code shared by String and AbstractStringBuilder to do searches. The 1707 * source is the character array being searched, and the target 1708 * is the string being searched for. 1709 * 1710 * @param src the characters being searched. 1711 * @param srcCoder the coder of the source string. 1712 * @param srcCount length of the source string. 1713 * @param tgtStr the characters being searched for. 1714 * @param fromIndex the index to begin searching from. 1715 */ 1716 static int indexOf(byte[] src, byte srcCoder, int srcCount, 1717 String tgtStr, int fromIndex) { 1718 byte[] tgt = tgtStr.value; 1719 byte tgtCoder = tgtStr.coder(); 1720 int tgtCount = tgtStr.length(); 1721 1722 if (fromIndex >= srcCount) { 1723 return (tgtCount == 0 ? srcCount : -1); 1724 } 1725 if (fromIndex < 0) { 1726 fromIndex = 0; 1727 } 1728 if (tgtCount == 0) { 1729 return fromIndex; 1730 } 1731 if (tgtCount > srcCount) { 1732 return -1; 1733 } 1734 if (srcCoder == tgtCoder) { 1735 return srcCoder == LATIN1 1736 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex) 1737 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex); 1738 } 1739 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1740 return -1; 1741 } 1742 // srcCoder == UTF16 && tgtCoder == LATIN1) { 1743 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex); 1744 } 1745 1746 /** 1747 * Returns the index within this string of the last occurrence of the 1748 * specified substring. The last occurrence of the empty string "" 1749 * is considered to occur at the index value {@code this.length()}. 1750 * 1751 * <p>The returned index is the largest value {@code k} for which: 1752 * <pre>{@code 1753 * this.startsWith(str, k) 1754 * }</pre> 1755 * If no such value of {@code k} exists, then {@code -1} is returned. 1756 * 1757 * @param str the substring to search for. 1758 * @return the index of the last occurrence of the specified substring, 1759 * or {@code -1} if there is no such occurrence. 1760 */ 1761 public int lastIndexOf(String str) { 1762 return lastIndexOf(str, length()); 1763 } 1764 1765 /** 1766 * Returns the index within this string of the last occurrence of the 1767 * specified substring, searching backward starting at the specified index. 1768 * 1769 * <p>The returned index is the largest value {@code k} for which: 1770 * <pre>{@code 1771 * k <= Math.min(fromIndex, this.length()) && 1772 * this.startsWith(str, k) 1773 * }</pre> 1774 * If no such value of {@code k} exists, then {@code -1} is returned. 1775 * 1776 * @param str the substring to search for. 1777 * @param fromIndex the index to start the search from. 1778 * @return the index of the last occurrence of the specified substring, 1779 * searching backward from the specified index, 1780 * or {@code -1} if there is no such occurrence. 1781 */ 1782 public int lastIndexOf(String str, int fromIndex) { 1783 return lastIndexOf(value, coder(), length(), str, fromIndex); 1784 } 1785 1786 /** 1787 * Code shared by String and AbstractStringBuilder to do searches. The 1788 * source is the character array being searched, and the target 1789 * is the string being searched for. 1790 * 1791 * @param src the characters being searched. 1792 * @param srcCoder coder handles the mapping between bytes/chars 1793 * @param srcCount count of the source string. 1794 * @param tgt the characters being searched for. 1795 * @param fromIndex the index to begin searching from. 1796 */ 1797 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount, 1798 String tgtStr, int fromIndex) { 1799 byte[] tgt = tgtStr.value; 1800 byte tgtCoder = tgtStr.coder(); 1801 int tgtCount = tgtStr.length(); 1802 /* 1803 * Check arguments; return immediately where possible. For 1804 * consistency, don't check for null str. 1805 */ 1806 int rightIndex = srcCount - tgtCount; 1807 if (fromIndex > rightIndex) { 1808 fromIndex = rightIndex; 1809 } 1810 if (fromIndex < 0) { 1811 return -1; 1812 } 1813 /* Empty string always matches. */ 1814 if (tgtCount == 0) { 1815 return fromIndex; 1816 } 1817 if (srcCoder == tgtCoder) { 1818 return srcCoder == LATIN1 1819 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex) 1820 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex); 1821 } 1822 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1823 return -1; 1824 } 1825 // srcCoder == UTF16 && tgtCoder == LATIN1 1826 return StringUTF16.lastIndexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex); 1827 } 1828 1829 /** 1830 * Returns a string that is a substring of this string. The 1831 * substring begins with the character at the specified index and 1832 * extends to the end of this string. <p> 1833 * Examples: 1834 * <blockquote><pre> 1835 * "unhappy".substring(2) returns "happy" 1836 * "Harbison".substring(3) returns "bison" 1837 * "emptiness".substring(9) returns "" (an empty string) 1838 * </pre></blockquote> 1839 * 1840 * @param beginIndex the beginning index, inclusive. 1841 * @return the specified substring. 1842 * @exception IndexOutOfBoundsException if 1843 * {@code beginIndex} is negative or larger than the 1844 * length of this {@code String} object. 1845 */ 1846 public String substring(int beginIndex) { 1847 if (beginIndex < 0) { 1848 throw new StringIndexOutOfBoundsException(beginIndex); 1849 } 1850 int subLen = length() - beginIndex; 1851 if (subLen < 0) { 1852 throw new StringIndexOutOfBoundsException(subLen); 1853 } 1854 if (beginIndex == 0) { 1855 return this; 1856 } 1857 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1858 : StringUTF16.newString(value, beginIndex, subLen); 1859 } 1860 1861 /** 1862 * Returns a string that is a substring of this string. The 1863 * substring begins at the specified {@code beginIndex} and 1864 * extends to the character at index {@code endIndex - 1}. 1865 * Thus the length of the substring is {@code endIndex-beginIndex}. 1866 * <p> 1867 * Examples: 1868 * <blockquote><pre> 1869 * "hamburger".substring(4, 8) returns "urge" 1870 * "smiles".substring(1, 5) returns "mile" 1871 * </pre></blockquote> 1872 * 1873 * @param beginIndex the beginning index, inclusive. 1874 * @param endIndex the ending index, exclusive. 1875 * @return the specified substring. 1876 * @exception IndexOutOfBoundsException if the 1877 * {@code beginIndex} is negative, or 1878 * {@code endIndex} is larger than the length of 1879 * this {@code String} object, or 1880 * {@code beginIndex} is larger than 1881 * {@code endIndex}. 1882 */ 1883 public String substring(int beginIndex, int endIndex) { 1884 int length = length(); 1885 checkBoundsBeginEnd(beginIndex, endIndex, length); 1886 int subLen = endIndex - beginIndex; 1887 if (beginIndex == 0 && endIndex == length) { 1888 return this; 1889 } 1890 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1891 : StringUTF16.newString(value, beginIndex, subLen); 1892 } 1893 1894 /** 1895 * Returns a character sequence that is a subsequence of this sequence. 1896 * 1897 * <p> An invocation of this method of the form 1898 * 1899 * <blockquote><pre> 1900 * str.subSequence(begin, end)</pre></blockquote> 1901 * 1902 * behaves in exactly the same way as the invocation 1903 * 1904 * <blockquote><pre> 1905 * str.substring(begin, end)</pre></blockquote> 1906 * 1907 * @apiNote 1908 * This method is defined so that the {@code String} class can implement 1909 * the {@link CharSequence} interface. 1910 * 1911 * @param beginIndex the begin index, inclusive. 1912 * @param endIndex the end index, exclusive. 1913 * @return the specified subsequence. 1914 * 1915 * @throws IndexOutOfBoundsException 1916 * if {@code beginIndex} or {@code endIndex} is negative, 1917 * if {@code endIndex} is greater than {@code length()}, 1918 * or if {@code beginIndex} is greater than {@code endIndex} 1919 * 1920 * @since 1.4 1921 * @spec JSR-51 1922 */ 1923 public CharSequence subSequence(int beginIndex, int endIndex) { 1924 return this.substring(beginIndex, endIndex); 1925 } 1926 1927 /** 1928 * Concatenates the specified string to the end of this string. 1929 * <p> 1930 * If the length of the argument string is {@code 0}, then this 1931 * {@code String} object is returned. Otherwise, a 1932 * {@code String} object is returned that represents a character 1933 * sequence that is the concatenation of the character sequence 1934 * represented by this {@code String} object and the character 1935 * sequence represented by the argument string.<p> 1936 * Examples: 1937 * <blockquote><pre> 1938 * "cares".concat("s") returns "caress" 1939 * "to".concat("get").concat("her") returns "together" 1940 * </pre></blockquote> 1941 * 1942 * @param str the {@code String} that is concatenated to the end 1943 * of this {@code String}. 1944 * @return a string that represents the concatenation of this object's 1945 * characters followed by the string argument's characters. 1946 */ 1947 public String concat(String str) { 1948 int olen = str.length(); 1949 if (olen == 0) { 1950 return this; 1951 } 1952 if (coder() == str.coder()) { 1953 byte[] val = this.value; 1954 byte[] oval = str.value; 1955 int len = val.length + oval.length; 1956 byte[] buf = Arrays.copyOf(val, len); 1957 System.arraycopy(oval, 0, buf, val.length, oval.length); 1958 return new String(buf, coder); 1959 } 1960 int len = length(); 1961 byte[] buf = StringUTF16.newBytesFor(len + olen); 1962 getBytes(buf, 0, UTF16); 1963 str.getBytes(buf, len, UTF16); 1964 return new String(buf, UTF16); 1965 } 1966 1967 /** 1968 * Returns a string resulting from replacing all occurrences of 1969 * {@code oldChar} in this string with {@code newChar}. 1970 * <p> 1971 * If the character {@code oldChar} does not occur in the 1972 * character sequence represented by this {@code String} object, 1973 * then a reference to this {@code String} object is returned. 1974 * Otherwise, a {@code String} object is returned that 1975 * represents a character sequence identical to the character sequence 1976 * represented by this {@code String} object, except that every 1977 * occurrence of {@code oldChar} is replaced by an occurrence 1978 * of {@code newChar}. 1979 * <p> 1980 * Examples: 1981 * <blockquote><pre> 1982 * "mesquite in your cellar".replace('e', 'o') 1983 * returns "mosquito in your collar" 1984 * "the war of baronets".replace('r', 'y') 1985 * returns "the way of bayonets" 1986 * "sparring with a purple porpoise".replace('p', 't') 1987 * returns "starring with a turtle tortoise" 1988 * "JonL".replace('q', 'x') returns "JonL" (no change) 1989 * </pre></blockquote> 1990 * 1991 * @param oldChar the old character. 1992 * @param newChar the new character. 1993 * @return a string derived from this string by replacing every 1994 * occurrence of {@code oldChar} with {@code newChar}. 1995 */ 1996 public String replace(char oldChar, char newChar) { 1997 if (oldChar != newChar) { 1998 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar) 1999 : StringUTF16.replace(value, oldChar, newChar); 2000 if (ret != null) { 2001 return ret; 2002 } 2003 } 2004 return this; 2005 } 2006 2007 /** 2008 * Tells whether or not this string matches the given <a 2009 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2010 * 2011 * <p> An invocation of this method of the form 2012 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2013 * same result as the expression 2014 * 2015 * <blockquote> 2016 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2017 * matches(<i>regex</i>, <i>str</i>)} 2018 * </blockquote> 2019 * 2020 * @param regex 2021 * the regular expression to which this string is to be matched 2022 * 2023 * @return {@code true} if, and only if, this string matches the 2024 * given regular expression 2025 * 2026 * @throws PatternSyntaxException 2027 * if the regular expression's syntax is invalid 2028 * 2029 * @see java.util.regex.Pattern 2030 * 2031 * @since 1.4 2032 * @spec JSR-51 2033 */ 2034 public boolean matches(String regex) { 2035 return Pattern.matches(regex, this); 2036 } 2037 2038 /** 2039 * Returns true if and only if this string contains the specified 2040 * sequence of char values. 2041 * 2042 * @param s the sequence to search for 2043 * @return true if this string contains {@code s}, false otherwise 2044 * @since 1.5 2045 */ 2046 public boolean contains(CharSequence s) { 2047 return indexOf(s.toString()) >= 0; 2048 } 2049 2050 /** 2051 * Replaces the first substring of this string that matches the given <a 2052 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2053 * given replacement. 2054 * 2055 * <p> An invocation of this method of the form 2056 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2057 * yields exactly the same result as the expression 2058 * 2059 * <blockquote> 2060 * <code> 2061 * {@link java.util.regex.Pattern}.{@link 2062 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2063 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2064 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>) 2065 * </code> 2066 * </blockquote> 2067 * 2068 *<p> 2069 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2070 * replacement string may cause the results to be different than if it were 2071 * being treated as a literal replacement string; see 2072 * {@link java.util.regex.Matcher#replaceFirst}. 2073 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2074 * meaning of these characters, if desired. 2075 * 2076 * @param regex 2077 * the regular expression to which this string is to be matched 2078 * @param replacement 2079 * the string to be substituted for the first match 2080 * 2081 * @return The resulting {@code String} 2082 * 2083 * @throws PatternSyntaxException 2084 * if the regular expression's syntax is invalid 2085 * 2086 * @see java.util.regex.Pattern 2087 * 2088 * @since 1.4 2089 * @spec JSR-51 2090 */ 2091 public String replaceFirst(String regex, String replacement) { 2092 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2093 } 2094 2095 /** 2096 * Replaces each substring of this string that matches the given <a 2097 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2098 * given replacement. 2099 * 2100 * <p> An invocation of this method of the form 2101 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2102 * yields exactly the same result as the expression 2103 * 2104 * <blockquote> 2105 * <code> 2106 * {@link java.util.regex.Pattern}.{@link 2107 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2108 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2109 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2110 * </code> 2111 * </blockquote> 2112 * 2113 *<p> 2114 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2115 * replacement string may cause the results to be different than if it were 2116 * being treated as a literal replacement string; see 2117 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2118 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2119 * meaning of these characters, if desired. 2120 * 2121 * @param regex 2122 * the regular expression to which this string is to be matched 2123 * @param replacement 2124 * the string to be substituted for each match 2125 * 2126 * @return The resulting {@code String} 2127 * 2128 * @throws PatternSyntaxException 2129 * if the regular expression's syntax is invalid 2130 * 2131 * @see java.util.regex.Pattern 2132 * 2133 * @since 1.4 2134 * @spec JSR-51 2135 */ 2136 public String replaceAll(String regex, String replacement) { 2137 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2138 } 2139 2140 /** 2141 * Replaces each substring of this string that matches the literal target 2142 * sequence with the specified literal replacement sequence. The 2143 * replacement proceeds from the beginning of the string to the end, for 2144 * example, replacing "aa" with "b" in the string "aaa" will result in 2145 * "ba" rather than "ab". 2146 * 2147 * @param target The sequence of char values to be replaced 2148 * @param replacement The replacement sequence of char values 2149 * @return The resulting string 2150 * @since 1.5 2151 */ 2152 public String replace(CharSequence target, CharSequence replacement) { 2153 String tgtStr = target.toString(); 2154 String replStr = replacement.toString(); 2155 int j = indexOf(tgtStr); 2156 if (j < 0) { 2157 return this; 2158 } 2159 int tgtLen = tgtStr.length(); 2160 int tgtLen1 = Math.max(tgtLen, 1); 2161 int thisLen = length(); 2162 2163 int newLenHint = thisLen - tgtLen + replStr.length(); 2164 if (newLenHint < 0) { 2165 throw new OutOfMemoryError(); 2166 } 2167 StringBuilder sb = new StringBuilder(newLenHint); 2168 int i = 0; 2169 do { 2170 sb.append(this, i, j).append(replStr); 2171 i = j + tgtLen; 2172 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0); 2173 return sb.append(this, i, thisLen).toString(); 2174 } 2175 2176 /** 2177 * Splits this string around matches of the given 2178 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2179 * 2180 * <p> The array returned by this method contains each substring of this 2181 * string that is terminated by another substring that matches the given 2182 * expression or is terminated by the end of the string. The substrings in 2183 * the array are in the order in which they occur in this string. If the 2184 * expression does not match any part of the input then the resulting array 2185 * has just one element, namely this string. 2186 * 2187 * <p> When there is a positive-width match at the beginning of this 2188 * string then an empty leading substring is included at the beginning 2189 * of the resulting array. A zero-width match at the beginning however 2190 * never produces such empty leading substring. 2191 * 2192 * <p> The {@code limit} parameter controls the number of times the 2193 * pattern is applied and therefore affects the length of the resulting 2194 * array. If the limit <i>n</i> is greater than zero then the pattern 2195 * will be applied at most <i>n</i> - 1 times, the array's 2196 * length will be no greater than <i>n</i>, and the array's last entry 2197 * will contain all input beyond the last matched delimiter. If <i>n</i> 2198 * is non-positive then the pattern will be applied as many times as 2199 * possible and the array can have any length. If <i>n</i> is zero then 2200 * the pattern will be applied as many times as possible, the array can 2201 * have any length, and trailing empty strings will be discarded. 2202 * 2203 * <p> The string {@code "boo:and:foo"}, for example, yields the 2204 * following results with these parameters: 2205 * 2206 * <blockquote><table class="plain"> 2207 * <caption style="display:none">Split example showing regex, limit, and result</caption> 2208 * <thead> 2209 * <tr> 2210 * <th>Regex</th> 2211 * <th>Limit</th> 2212 * <th>Result</th> 2213 * </tr> 2214 * </thead> 2215 * <tbody> 2216 * <tr><td style="text-align:center">:</td> 2217 * <td style="text-align:center">2</td> 2218 * <td>{@code { "boo", "and:foo" }}</td></tr> 2219 * <tr><td style="text-align:center">:</td> 2220 * <td style="text-align:center">5</td> 2221 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2222 * <tr><td style="text-align:center">:</td> 2223 * <td style="text-align:center">-2</td> 2224 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2225 * <tr><td style="text-align:center">o</td> 2226 * <td style="text-align:center">5</td> 2227 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2228 * <tr><td style="text-align:center">o</td> 2229 * <td style="text-align:center">-2</td> 2230 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2231 * <tr><td style="text-align:center">o</td> 2232 * <td style="text-align:center">0</td> 2233 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2234 * </tbody> 2235 * </table></blockquote> 2236 * 2237 * <p> An invocation of this method of the form 2238 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2239 * yields the same result as the expression 2240 * 2241 * <blockquote> 2242 * <code> 2243 * {@link java.util.regex.Pattern}.{@link 2244 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2245 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2246 * </code> 2247 * </blockquote> 2248 * 2249 * 2250 * @param regex 2251 * the delimiting regular expression 2252 * 2253 * @param limit 2254 * the result threshold, as described above 2255 * 2256 * @return the array of strings computed by splitting this string 2257 * around matches of the given regular expression 2258 * 2259 * @throws PatternSyntaxException 2260 * if the regular expression's syntax is invalid 2261 * 2262 * @see java.util.regex.Pattern 2263 * 2264 * @since 1.4 2265 * @spec JSR-51 2266 */ 2267 public String[] split(String regex, int limit) { 2268 /* fastpath if the regex is a 2269 (1)one-char String and this character is not one of the 2270 RegEx's meta characters ".$|()[{^?*+\\", or 2271 (2)two-char String and the first char is the backslash and 2272 the second is not the ascii digit or ascii letter. 2273 */ 2274 char ch = 0; 2275 if (((regex.length() == 1 && 2276 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2277 (regex.length() == 2 && 2278 regex.charAt(0) == '\\' && 2279 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2280 ((ch-'a')|('z'-ch)) < 0 && 2281 ((ch-'A')|('Z'-ch)) < 0)) && 2282 (ch < Character.MIN_HIGH_SURROGATE || 2283 ch > Character.MAX_LOW_SURROGATE)) 2284 { 2285 int off = 0; 2286 int next = 0; 2287 boolean limited = limit > 0; 2288 ArrayList<String> list = new ArrayList<>(); 2289 while ((next = indexOf(ch, off)) != -1) { 2290 if (!limited || list.size() < limit - 1) { 2291 list.add(substring(off, next)); 2292 off = next + 1; 2293 } else { // last one 2294 //assert (list.size() == limit - 1); 2295 int last = length(); 2296 list.add(substring(off, last)); 2297 off = last; 2298 break; 2299 } 2300 } 2301 // If no match was found, return this 2302 if (off == 0) 2303 return new String[]{this}; 2304 2305 // Add remaining segment 2306 if (!limited || list.size() < limit) 2307 list.add(substring(off, length())); 2308 2309 // Construct result 2310 int resultSize = list.size(); 2311 if (limit == 0) { 2312 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) { 2313 resultSize--; 2314 } 2315 } 2316 String[] result = new String[resultSize]; 2317 return list.subList(0, resultSize).toArray(result); 2318 } 2319 return Pattern.compile(regex).split(this, limit); 2320 } 2321 2322 /** 2323 * Splits this string around matches of the given <a 2324 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2325 * 2326 * <p> This method works as if by invoking the two-argument {@link 2327 * #split(String, int) split} method with the given expression and a limit 2328 * argument of zero. Trailing empty strings are therefore not included in 2329 * the resulting array. 2330 * 2331 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2332 * results with these expressions: 2333 * 2334 * <blockquote><table class="plain"> 2335 * <caption style="display:none">Split examples showing regex and result</caption> 2336 * <thead> 2337 * <tr> 2338 * <th>Regex</th> 2339 * <th>Result</th> 2340 * </tr> 2341 * </thead> 2342 * <tbody> 2343 * <tr><td style="text-align:center">:</td> 2344 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2345 * <tr><td style="text-align:center">o</td> 2346 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2347 * </tbody> 2348 * </table></blockquote> 2349 * 2350 * 2351 * @param regex 2352 * the delimiting regular expression 2353 * 2354 * @return the array of strings computed by splitting this string 2355 * around matches of the given regular expression 2356 * 2357 * @throws PatternSyntaxException 2358 * if the regular expression's syntax is invalid 2359 * 2360 * @see java.util.regex.Pattern 2361 * 2362 * @since 1.4 2363 * @spec JSR-51 2364 */ 2365 public String[] split(String regex) { 2366 return split(regex, 0); 2367 } 2368 2369 /** 2370 * Returns a new String composed of copies of the 2371 * {@code CharSequence elements} joined together with a copy of 2372 * the specified {@code delimiter}. 2373 * 2374 * <blockquote>For example, 2375 * <pre>{@code 2376 * String message = String.join("-", "Java", "is", "cool"); 2377 * // message returned is: "Java-is-cool" 2378 * }</pre></blockquote> 2379 * 2380 * Note that if an element is null, then {@code "null"} is added. 2381 * 2382 * @param delimiter the delimiter that separates each element 2383 * @param elements the elements to join together. 2384 * 2385 * @return a new {@code String} that is composed of the {@code elements} 2386 * separated by the {@code delimiter} 2387 * 2388 * @throws NullPointerException If {@code delimiter} or {@code elements} 2389 * is {@code null} 2390 * 2391 * @see java.util.StringJoiner 2392 * @since 1.8 2393 */ 2394 public static String join(CharSequence delimiter, CharSequence... elements) { 2395 Objects.requireNonNull(delimiter); 2396 Objects.requireNonNull(elements); 2397 // Number of elements not likely worth Arrays.stream overhead. 2398 StringJoiner joiner = new StringJoiner(delimiter); 2399 for (CharSequence cs: elements) { 2400 joiner.add(cs); 2401 } 2402 return joiner.toString(); 2403 } 2404 2405 /** 2406 * Returns a new {@code String} composed of copies of the 2407 * {@code CharSequence elements} joined together with a copy of the 2408 * specified {@code delimiter}. 2409 * 2410 * <blockquote>For example, 2411 * <pre>{@code 2412 * List<String> strings = List.of("Java", "is", "cool"); 2413 * String message = String.join(" ", strings); 2414 * //message returned is: "Java is cool" 2415 * 2416 * Set<String> strings = 2417 * new LinkedHashSet<>(List.of("Java", "is", "very", "cool")); 2418 * String message = String.join("-", strings); 2419 * //message returned is: "Java-is-very-cool" 2420 * }</pre></blockquote> 2421 * 2422 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2423 * 2424 * @param delimiter a sequence of characters that is used to separate each 2425 * of the {@code elements} in the resulting {@code String} 2426 * @param elements an {@code Iterable} that will have its {@code elements} 2427 * joined together. 2428 * 2429 * @return a new {@code String} that is composed from the {@code elements} 2430 * argument 2431 * 2432 * @throws NullPointerException If {@code delimiter} or {@code elements} 2433 * is {@code null} 2434 * 2435 * @see #join(CharSequence,CharSequence...) 2436 * @see java.util.StringJoiner 2437 * @since 1.8 2438 */ 2439 public static String join(CharSequence delimiter, 2440 Iterable<? extends CharSequence> elements) { 2441 Objects.requireNonNull(delimiter); 2442 Objects.requireNonNull(elements); 2443 StringJoiner joiner = new StringJoiner(delimiter); 2444 for (CharSequence cs: elements) { 2445 joiner.add(cs); 2446 } 2447 return joiner.toString(); 2448 } 2449 2450 /** 2451 * Converts all of the characters in this {@code String} to lower 2452 * case using the rules of the given {@code Locale}. Case mapping is based 2453 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2454 * class. Since case mappings are not always 1:1 char mappings, the resulting 2455 * {@code String} may be a different length than the original {@code String}. 2456 * <p> 2457 * Examples of lowercase mappings are in the following table: 2458 * <table class="plain"> 2459 * <caption style="display:none">Lowercase mapping examples showing language code of locale, upper case, lower case, and description</caption> 2460 * <thead> 2461 * <tr> 2462 * <th>Language Code of Locale</th> 2463 * <th>Upper Case</th> 2464 * <th>Lower Case</th> 2465 * <th>Description</th> 2466 * </tr> 2467 * </thead> 2468 * <tbody> 2469 * <tr> 2470 * <td>tr (Turkish)</td> 2471 * <td>\u0130</td> 2472 * <td>\u0069</td> 2473 * <td>capital letter I with dot above -> small letter i</td> 2474 * </tr> 2475 * <tr> 2476 * <td>tr (Turkish)</td> 2477 * <td>\u0049</td> 2478 * <td>\u0131</td> 2479 * <td>capital letter I -> small letter dotless i </td> 2480 * </tr> 2481 * <tr> 2482 * <td>(all)</td> 2483 * <td>French Fries</td> 2484 * <td>french fries</td> 2485 * <td>lowercased all chars in String</td> 2486 * </tr> 2487 * <tr> 2488 * <td>(all)</td> 2489 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2490 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2491 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2492 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2493 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2494 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2495 * <td>lowercased all chars in String</td> 2496 * </tr> 2497 * </tbody> 2498 * </table> 2499 * 2500 * @param locale use the case transformation rules for this locale 2501 * @return the {@code String}, converted to lowercase. 2502 * @see java.lang.String#toLowerCase() 2503 * @see java.lang.String#toUpperCase() 2504 * @see java.lang.String#toUpperCase(Locale) 2505 * @since 1.1 2506 */ 2507 public String toLowerCase(Locale locale) { 2508 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale) 2509 : StringUTF16.toLowerCase(this, value, locale); 2510 } 2511 2512 /** 2513 * Converts all of the characters in this {@code String} to lower 2514 * case using the rules of the default locale. This is equivalent to calling 2515 * {@code toLowerCase(Locale.getDefault())}. 2516 * <p> 2517 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2518 * results if used for strings that are intended to be interpreted locale 2519 * independently. 2520 * Examples are programming language identifiers, protocol keys, and HTML 2521 * tags. 2522 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2523 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2524 * LATIN SMALL LETTER DOTLESS I character. 2525 * To obtain correct results for locale insensitive strings, use 2526 * {@code toLowerCase(Locale.ROOT)}. 2527 * 2528 * @return the {@code String}, converted to lowercase. 2529 * @see java.lang.String#toLowerCase(Locale) 2530 */ 2531 public String toLowerCase() { 2532 return toLowerCase(Locale.getDefault()); 2533 } 2534 2535 /** 2536 * Converts all of the characters in this {@code String} to upper 2537 * case using the rules of the given {@code Locale}. Case mapping is based 2538 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2539 * class. Since case mappings are not always 1:1 char mappings, the resulting 2540 * {@code String} may be a different length than the original {@code String}. 2541 * <p> 2542 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2543 * 2544 * <table class="plain"> 2545 * <caption style="display:none">Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.</caption> 2546 * <thead> 2547 * <tr> 2548 * <th>Language Code of Locale</th> 2549 * <th>Lower Case</th> 2550 * <th>Upper Case</th> 2551 * <th>Description</th> 2552 * </tr> 2553 * </thead> 2554 * <tbody> 2555 * <tr> 2556 * <td>tr (Turkish)</td> 2557 * <td>\u0069</td> 2558 * <td>\u0130</td> 2559 * <td>small letter i -> capital letter I with dot above</td> 2560 * </tr> 2561 * <tr> 2562 * <td>tr (Turkish)</td> 2563 * <td>\u0131</td> 2564 * <td>\u0049</td> 2565 * <td>small letter dotless i -> capital letter I</td> 2566 * </tr> 2567 * <tr> 2568 * <td>(all)</td> 2569 * <td>\u00df</td> 2570 * <td>\u0053 \u0053</td> 2571 * <td>small letter sharp s -> two letters: SS</td> 2572 * </tr> 2573 * <tr> 2574 * <td>(all)</td> 2575 * <td>Fahrvergnügen</td> 2576 * <td>FAHRVERGNÜGEN</td> 2577 * <td></td> 2578 * </tr> 2579 * </tbody> 2580 * </table> 2581 * @param locale use the case transformation rules for this locale 2582 * @return the {@code String}, converted to uppercase. 2583 * @see java.lang.String#toUpperCase() 2584 * @see java.lang.String#toLowerCase() 2585 * @see java.lang.String#toLowerCase(Locale) 2586 * @since 1.1 2587 */ 2588 public String toUpperCase(Locale locale) { 2589 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale) 2590 : StringUTF16.toUpperCase(this, value, locale); 2591 } 2592 2593 /** 2594 * Converts all of the characters in this {@code String} to upper 2595 * case using the rules of the default locale. This method is equivalent to 2596 * {@code toUpperCase(Locale.getDefault())}. 2597 * <p> 2598 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2599 * results if used for strings that are intended to be interpreted locale 2600 * independently. 2601 * Examples are programming language identifiers, protocol keys, and HTML 2602 * tags. 2603 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2604 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2605 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2606 * To obtain correct results for locale insensitive strings, use 2607 * {@code toUpperCase(Locale.ROOT)}. 2608 * 2609 * @return the {@code String}, converted to uppercase. 2610 * @see java.lang.String#toUpperCase(Locale) 2611 */ 2612 public String toUpperCase() { 2613 return toUpperCase(Locale.getDefault()); 2614 } 2615 2616 /** 2617 * Returns a string whose value is this string, with any leading and trailing 2618 * whitespace removed. 2619 * <p> 2620 * If this {@code String} object represents an empty character 2621 * sequence, or the first and last characters of character sequence 2622 * represented by this {@code String} object both have codes 2623 * greater than {@code '\u005Cu0020'} (the space character), then a 2624 * reference to this {@code String} object is returned. 2625 * <p> 2626 * Otherwise, if there is no character with a code greater than 2627 * {@code '\u005Cu0020'} in the string, then a 2628 * {@code String} object representing an empty string is 2629 * returned. 2630 * <p> 2631 * Otherwise, let <i>k</i> be the index of the first character in the 2632 * string whose code is greater than {@code '\u005Cu0020'}, and let 2633 * <i>m</i> be the index of the last character in the string whose code 2634 * is greater than {@code '\u005Cu0020'}. A {@code String} 2635 * object is returned, representing the substring of this string that 2636 * begins with the character at index <i>k</i> and ends with the 2637 * character at index <i>m</i>-that is, the result of 2638 * {@code this.substring(k, m + 1)}. 2639 * <p> 2640 * This method may be used to trim whitespace (as defined above) from 2641 * the beginning and end of a string. 2642 * 2643 * @return A string whose value is this string, with any leading and trailing white 2644 * space removed, or this string if it has no leading or 2645 * trailing white space. 2646 */ 2647 public String trim() { 2648 String ret = isLatin1() ? StringLatin1.trim(value) 2649 : StringUTF16.trim(value); 2650 return ret == null ? this : ret; 2651 } 2652 2653 /** 2654 * This object (which is already a string!) is itself returned. 2655 * 2656 * @return the string itself. 2657 */ 2658 public String toString() { 2659 return this; 2660 } 2661 2662 /** 2663 * Returns a stream of {@code int} zero-extending the {@code char} values 2664 * from this sequence. Any char which maps to a <a 2665 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code 2666 * point</a> is passed through uninterpreted. 2667 * 2668 * @return an IntStream of char values from this sequence 2669 */ 2670 @Override 2671 public IntStream chars() { 2672 return StreamSupport.intStream( 2673 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2674 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE), 2675 false); 2676 } 2677 2678 2679 /** 2680 * Returns a stream of code point values from this sequence. Any surrogate 2681 * pairs encountered in the sequence are combined as if by {@linkplain 2682 * Character#toCodePoint Character.toCodePoint} and the result is passed 2683 * to the stream. Any other code units, including ordinary BMP characters, 2684 * unpaired surrogates, and undefined code units, are zero-extended to 2685 * {@code int} values which are then passed to the stream. 2686 * 2687 * @return an IntStream of Unicode code points from this sequence 2688 */ 2689 @Override 2690 public IntStream codePoints() { 2691 return StreamSupport.intStream( 2692 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2693 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE), 2694 false); 2695 } 2696 2697 /** 2698 * Converts this string to a new character array. 2699 * 2700 * @return a newly allocated character array whose length is the length 2701 * of this string and whose contents are initialized to contain 2702 * the character sequence represented by this string. 2703 */ 2704 public char[] toCharArray() { 2705 return isLatin1() ? StringLatin1.toChars(value) 2706 : StringUTF16.toChars(value); 2707 } 2708 2709 /** 2710 * Returns a formatted string using the specified format string and 2711 * arguments. 2712 * 2713 * <p> The locale always used is the one returned by {@link 2714 * java.util.Locale#getDefault(java.util.Locale.Category) 2715 * Locale.getDefault(Locale.Category)} with 2716 * {@link java.util.Locale.Category#FORMAT FORMAT} category specified. 2717 * 2718 * @param format 2719 * A <a href="../util/Formatter.html#syntax">format string</a> 2720 * 2721 * @param args 2722 * Arguments referenced by the format specifiers in the format 2723 * string. If there are more arguments than format specifiers, the 2724 * extra arguments are ignored. The number of arguments is 2725 * variable and may be zero. The maximum number of arguments is 2726 * limited by the maximum dimension of a Java array as defined by 2727 * <cite>The Java™ Virtual Machine Specification</cite>. 2728 * The behaviour on a 2729 * {@code null} argument depends on the <a 2730 * href="../util/Formatter.html#syntax">conversion</a>. 2731 * 2732 * @throws java.util.IllegalFormatException 2733 * If a format string contains an illegal syntax, a format 2734 * specifier that is incompatible with the given arguments, 2735 * insufficient arguments given the format string, or other 2736 * illegal conditions. For specification of all possible 2737 * formatting errors, see the <a 2738 * href="../util/Formatter.html#detail">Details</a> section of the 2739 * formatter class specification. 2740 * 2741 * @return A formatted string 2742 * 2743 * @see java.util.Formatter 2744 * @since 1.5 2745 */ 2746 public static String format(String format, Object... args) { 2747 return new Formatter().format(format, args).toString(); 2748 } 2749 2750 /** 2751 * Returns a formatted string using the specified locale, format string, 2752 * and arguments. 2753 * 2754 * @param l 2755 * The {@linkplain java.util.Locale locale} to apply during 2756 * formatting. If {@code l} is {@code null} then no localization 2757 * is applied. 2758 * 2759 * @param format 2760 * A <a href="../util/Formatter.html#syntax">format string</a> 2761 * 2762 * @param args 2763 * Arguments referenced by the format specifiers in the format 2764 * string. If there are more arguments than format specifiers, the 2765 * extra arguments are ignored. The number of arguments is 2766 * variable and may be zero. The maximum number of arguments is 2767 * limited by the maximum dimension of a Java array as defined by 2768 * <cite>The Java™ Virtual Machine Specification</cite>. 2769 * The behaviour on a 2770 * {@code null} argument depends on the 2771 * <a href="../util/Formatter.html#syntax">conversion</a>. 2772 * 2773 * @throws java.util.IllegalFormatException 2774 * If a format string contains an illegal syntax, a format 2775 * specifier that is incompatible with the given arguments, 2776 * insufficient arguments given the format string, or other 2777 * illegal conditions. For specification of all possible 2778 * formatting errors, see the <a 2779 * href="../util/Formatter.html#detail">Details</a> section of the 2780 * formatter class specification 2781 * 2782 * @return A formatted string 2783 * 2784 * @see java.util.Formatter 2785 * @since 1.5 2786 */ 2787 public static String format(Locale l, String format, Object... args) { 2788 return new Formatter(l).format(format, args).toString(); 2789 } 2790 2791 /** 2792 * Returns the string representation of the {@code Object} argument. 2793 * 2794 * @param obj an {@code Object}. 2795 * @return if the argument is {@code null}, then a string equal to 2796 * {@code "null"}; otherwise, the value of 2797 * {@code obj.toString()} is returned. 2798 * @see java.lang.Object#toString() 2799 */ 2800 public static String valueOf(Object obj) { 2801 return (obj == null) ? "null" : obj.toString(); 2802 } 2803 2804 /** 2805 * Returns the string representation of the {@code char} array 2806 * argument. The contents of the character array are copied; subsequent 2807 * modification of the character array does not affect the returned 2808 * string. 2809 * 2810 * @param data the character array. 2811 * @return a {@code String} that contains the characters of the 2812 * character array. 2813 */ 2814 public static String valueOf(char data[]) { 2815 return new String(data); 2816 } 2817 2818 /** 2819 * Returns the string representation of a specific subarray of the 2820 * {@code char} array argument. 2821 * <p> 2822 * The {@code offset} argument is the index of the first 2823 * character of the subarray. The {@code count} argument 2824 * specifies the length of the subarray. The contents of the subarray 2825 * are copied; subsequent modification of the character array does not 2826 * affect the returned string. 2827 * 2828 * @param data the character array. 2829 * @param offset initial offset of the subarray. 2830 * @param count length of the subarray. 2831 * @return a {@code String} that contains the characters of the 2832 * specified subarray of the character array. 2833 * @exception IndexOutOfBoundsException if {@code offset} is 2834 * negative, or {@code count} is negative, or 2835 * {@code offset+count} is larger than 2836 * {@code data.length}. 2837 */ 2838 public static String valueOf(char data[], int offset, int count) { 2839 return new String(data, offset, count); 2840 } 2841 2842 /** 2843 * Equivalent to {@link #valueOf(char[], int, int)}. 2844 * 2845 * @param data the character array. 2846 * @param offset initial offset of the subarray. 2847 * @param count length of the subarray. 2848 * @return a {@code String} that contains the characters of the 2849 * specified subarray of the character array. 2850 * @exception IndexOutOfBoundsException if {@code offset} is 2851 * negative, or {@code count} is negative, or 2852 * {@code offset+count} is larger than 2853 * {@code data.length}. 2854 */ 2855 public static String copyValueOf(char data[], int offset, int count) { 2856 return new String(data, offset, count); 2857 } 2858 2859 /** 2860 * Equivalent to {@link #valueOf(char[])}. 2861 * 2862 * @param data the character array. 2863 * @return a {@code String} that contains the characters of the 2864 * character array. 2865 */ 2866 public static String copyValueOf(char data[]) { 2867 return new String(data); 2868 } 2869 2870 /** 2871 * Returns the string representation of the {@code boolean} argument. 2872 * 2873 * @param b a {@code boolean}. 2874 * @return if the argument is {@code true}, a string equal to 2875 * {@code "true"} is returned; otherwise, a string equal to 2876 * {@code "false"} is returned. 2877 */ 2878 public static String valueOf(boolean b) { 2879 return b ? "true" : "false"; 2880 } 2881 2882 /** 2883 * Returns the string representation of the {@code char} 2884 * argument. 2885 * 2886 * @param c a {@code char}. 2887 * @return a string of length {@code 1} containing 2888 * as its single character the argument {@code c}. 2889 */ 2890 public static String valueOf(char c) { 2891 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) { 2892 return new String(StringLatin1.toBytes(c), LATIN1); 2893 } 2894 return new String(StringUTF16.toBytes(c), UTF16); 2895 } 2896 2897 /** 2898 * Returns the string representation of the {@code int} argument. 2899 * <p> 2900 * The representation is exactly the one returned by the 2901 * {@code Integer.toString} method of one argument. 2902 * 2903 * @param i an {@code int}. 2904 * @return a string representation of the {@code int} argument. 2905 * @see java.lang.Integer#toString(int, int) 2906 */ 2907 public static String valueOf(int i) { 2908 return Integer.toString(i); 2909 } 2910 2911 /** 2912 * Returns the string representation of the {@code long} argument. 2913 * <p> 2914 * The representation is exactly the one returned by the 2915 * {@code Long.toString} method of one argument. 2916 * 2917 * @param l a {@code long}. 2918 * @return a string representation of the {@code long} argument. 2919 * @see java.lang.Long#toString(long) 2920 */ 2921 public static String valueOf(long l) { 2922 return Long.toString(l); 2923 } 2924 2925 /** 2926 * Returns the string representation of the {@code float} argument. 2927 * <p> 2928 * The representation is exactly the one returned by the 2929 * {@code Float.toString} method of one argument. 2930 * 2931 * @param f a {@code float}. 2932 * @return a string representation of the {@code float} argument. 2933 * @see java.lang.Float#toString(float) 2934 */ 2935 public static String valueOf(float f) { 2936 return Float.toString(f); 2937 } 2938 2939 /** 2940 * Returns the string representation of the {@code double} argument. 2941 * <p> 2942 * The representation is exactly the one returned by the 2943 * {@code Double.toString} method of one argument. 2944 * 2945 * @param d a {@code double}. 2946 * @return a string representation of the {@code double} argument. 2947 * @see java.lang.Double#toString(double) 2948 */ 2949 public static String valueOf(double d) { 2950 return Double.toString(d); 2951 } 2952 2953 /** 2954 * Returns a canonical representation for the string object. 2955 * <p> 2956 * A pool of strings, initially empty, is maintained privately by the 2957 * class {@code String}. 2958 * <p> 2959 * When the intern method is invoked, if the pool already contains a 2960 * string equal to this {@code String} object as determined by 2961 * the {@link #equals(Object)} method, then the string from the pool is 2962 * returned. Otherwise, this {@code String} object is added to the 2963 * pool and a reference to this {@code String} object is returned. 2964 * <p> 2965 * It follows that for any two strings {@code s} and {@code t}, 2966 * {@code s.intern() == t.intern()} is {@code true} 2967 * if and only if {@code s.equals(t)} is {@code true}. 2968 * <p> 2969 * All literal strings and string-valued constant expressions are 2970 * interned. String literals are defined in section 3.10.5 of the 2971 * <cite>The Java™ Language Specification</cite>. 2972 * 2973 * @return a string that has the same contents as this string, but is 2974 * guaranteed to be from a pool of unique strings. 2975 * @jls 3.10.5 String Literals 2976 */ 2977 public native String intern(); 2978 2979 //////////////////////////////////////////////////////////////// 2980 2981 /** 2982 * Copy character bytes from this string into dst starting at dstBegin. 2983 * This method doesn't perform any range checking. 2984 * 2985 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two 2986 * coders are different, and dst is big enough (range check) 2987 * 2988 * @param dstBegin the char index, not offset of byte[] 2989 * @param coder the coder of dst[] 2990 */ 2991 void getBytes(byte dst[], int dstBegin, byte coder) { 2992 if (coder() == coder) { 2993 System.arraycopy(value, 0, dst, dstBegin << coder, value.length); 2994 } else { // this.coder == LATIN && coder == UTF16 2995 StringLatin1.inflate(value, 0, dst, dstBegin, value.length); 2996 } 2997 } 2998 2999 /* 3000 * Package private constructor. Trailing Void argument is there for 3001 * disambiguating it against other (public) constructors. 3002 * 3003 * Stores the char[] value into a byte[] that each byte represents 3004 * the8 low-order bits of the corresponding character, if the char[] 3005 * contains only latin1 character. Or a byte[] that stores all 3006 * characters in their byte sequences defined by the {@code StringUTF16}. 3007 */ 3008 String(char[] value, int off, int len, Void sig) { 3009 if (len == 0) { 3010 this.value = "".value; 3011 this.coder = "".coder; 3012 return; 3013 } 3014 if (COMPACT_STRINGS) { 3015 byte[] val = StringUTF16.compress(value, off, len); 3016 if (val != null) { 3017 this.value = val; 3018 this.coder = LATIN1; 3019 return; 3020 } 3021 } 3022 this.coder = UTF16; 3023 this.value = StringUTF16.toBytes(value, off, len); 3024 } 3025 3026 /* 3027 * Package private constructor. Trailing Void argument is there for 3028 * disambiguating it against other (public) constructors. 3029 */ 3030 String(AbstractStringBuilder asb, Void sig) { 3031 byte[] val = asb.getValue(); 3032 int length = asb.length(); 3033 if (asb.isLatin1()) { 3034 this.coder = LATIN1; 3035 this.value = Arrays.copyOfRange(val, 0, length); 3036 } else { 3037 if (COMPACT_STRINGS) { 3038 byte[] buf = StringUTF16.compress(val, 0, length); 3039 if (buf != null) { 3040 this.coder = LATIN1; 3041 this.value = buf; 3042 return; 3043 } 3044 } 3045 this.coder = UTF16; 3046 this.value = Arrays.copyOfRange(val, 0, length << 1); 3047 } 3048 } 3049 3050 /* 3051 * Package private constructor which shares value array for speed. 3052 */ 3053 String(byte[] value, byte coder) { 3054 this.value = value; 3055 this.coder = coder; 3056 } 3057 3058 byte coder() { 3059 return COMPACT_STRINGS ? coder : UTF16; 3060 } 3061 3062 private boolean isLatin1() { 3063 return COMPACT_STRINGS && coder == LATIN1; 3064 } 3065 3066 static final byte LATIN1 = 0; 3067 static final byte UTF16 = 1; 3068 3069 /* 3070 * StringIndexOutOfBoundsException if {@code index} is 3071 * negative or greater than or equal to {@code length}. 3072 */ 3073 static void checkIndex(int index, int length) { 3074 if (index < 0 || index >= length) { 3075 throw new StringIndexOutOfBoundsException("index " + index + 3076 ",length " + length); 3077 } 3078 } 3079 3080 /* 3081 * StringIndexOutOfBoundsException if {@code offset} 3082 * is negative or greater than {@code length}. 3083 */ 3084 static void checkOffset(int offset, int length) { 3085 if (offset < 0 || offset > length) { 3086 throw new StringIndexOutOfBoundsException("offset " + offset + 3087 ",length " + length); 3088 } 3089 } 3090 3091 /* 3092 * Check {@code offset}, {@code count} against {@code 0} and {@code length} 3093 * bounds. 3094 * 3095 * @throws StringIndexOutOfBoundsException 3096 * If {@code offset} is negative, {@code count} is negative, 3097 * or {@code offset} is greater than {@code length - count} 3098 */ 3099 static void checkBoundsOffCount(int offset, int count, int length) { 3100 if (offset < 0 || count < 0 || offset > length - count) { 3101 throw new StringIndexOutOfBoundsException( 3102 "offset " + offset + ", count " + count + ", length " + length); 3103 } 3104 } 3105 3106 /* 3107 * Check {@code begin}, {@code end} against {@code 0} and {@code length} 3108 * bounds. 3109 * 3110 * @throws StringIndexOutOfBoundsException 3111 * If {@code begin} is negative, {@code begin} is greater than 3112 * {@code end}, or {@code end} is greater than {@code length}. 3113 */ 3114 static void checkBoundsBeginEnd(int begin, int end, int length) { 3115 if (begin < 0 || begin > end || end > length) { 3116 throw new StringIndexOutOfBoundsException( 3117 "begin " + begin + ", end " + end + ", length " + length); 3118 } 3119 } 3120 }