1 /* 2 * Copyright (c) 1994, 2016, 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 checkOffset(len, v2.length >> 1); 1068 for (int i = 0; i < len; i++) { 1069 if ((char)(v1[i] & 0xff) != StringUTF16.getChar(v2, i)) { 1070 return false; 1071 } 1072 } 1073 } 1074 return true; 1075 } 1076 1077 /** 1078 * Compares this string to the specified {@code CharSequence}. The 1079 * result is {@code true} if and only if this {@code String} represents the 1080 * same sequence of char values as the specified sequence. Note that if the 1081 * {@code CharSequence} is a {@code StringBuffer} then the method 1082 * synchronizes on it. 1083 * 1084 * <p>For finer-grained String comparison, refer to 1085 * {@link java.text.Collator}. 1086 * 1087 * @param cs 1088 * The sequence to compare this {@code String} against 1089 * 1090 * @return {@code true} if this {@code String} represents the same 1091 * sequence of char values as the specified sequence, {@code 1092 * false} otherwise 1093 * 1094 * @since 1.5 1095 */ 1096 public boolean contentEquals(CharSequence cs) { 1097 // Argument is a StringBuffer, StringBuilder 1098 if (cs instanceof AbstractStringBuilder) { 1099 if (cs instanceof StringBuffer) { 1100 synchronized(cs) { 1101 return nonSyncContentEquals((AbstractStringBuilder)cs); 1102 } 1103 } else { 1104 return nonSyncContentEquals((AbstractStringBuilder)cs); 1105 } 1106 } 1107 // Argument is a String 1108 if (cs instanceof String) { 1109 return equals(cs); 1110 } 1111 // Argument is a generic CharSequence 1112 int n = cs.length(); 1113 if (n != length()) { 1114 return false; 1115 } 1116 byte[] val = this.value; 1117 if (isLatin1()) { 1118 for (int i = 0; i < n; i++) { 1119 if ((val[i] & 0xff) != cs.charAt(i)) { 1120 return false; 1121 } 1122 } 1123 } else { 1124 for (int i = 0; i < n; i++) { 1125 if (StringUTF16.getChar(val, i) != cs.charAt(i)) { 1126 return false; 1127 } 1128 } 1129 } 1130 return true; 1131 } 1132 1133 /** 1134 * Compares this {@code String} to another {@code String}, ignoring case 1135 * considerations. Two strings are considered equal ignoring case if they 1136 * are of the same length and corresponding characters in the two strings 1137 * are equal ignoring case. 1138 * 1139 * <p> Two characters {@code c1} and {@code c2} are considered the same 1140 * ignoring case if at least one of the following is true: 1141 * <ul> 1142 * <li> The two characters are the same (as compared by the 1143 * {@code ==} operator) 1144 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))} 1145 * on each character produces the same result 1146 * </ul> 1147 * 1148 * <p>Note that this method does <em>not</em> take locale into account, and 1149 * will result in unsatisfactory results for certain locales. The 1150 * {@link java.text.Collator} class provides locale-sensitive comparison. 1151 * 1152 * @param anotherString 1153 * The {@code String} to compare this {@code String} against 1154 * 1155 * @return {@code true} if the argument is not {@code null} and it 1156 * represents an equivalent {@code String} ignoring case; {@code 1157 * false} otherwise 1158 * 1159 * @see #equals(Object) 1160 */ 1161 public boolean equalsIgnoreCase(String anotherString) { 1162 return (this == anotherString) ? true 1163 : (anotherString != null) 1164 && (anotherString.length() == length()) 1165 && regionMatches(true, 0, anotherString, 0, length()); 1166 } 1167 1168 /** 1169 * Compares two strings lexicographically. 1170 * The comparison is based on the Unicode value of each character in 1171 * the strings. The character sequence represented by this 1172 * {@code String} object is compared lexicographically to the 1173 * character sequence represented by the argument string. The result is 1174 * a negative integer if this {@code String} object 1175 * lexicographically precedes the argument string. The result is a 1176 * positive integer if this {@code String} object lexicographically 1177 * follows the argument string. The result is zero if the strings 1178 * are equal; {@code compareTo} returns {@code 0} exactly when 1179 * the {@link #equals(Object)} method would return {@code true}. 1180 * <p> 1181 * This is the definition of lexicographic ordering. If two strings are 1182 * different, then either they have different characters at some index 1183 * that is a valid index for both strings, or their lengths are different, 1184 * or both. If they have different characters at one or more index 1185 * positions, let <i>k</i> be the smallest such index; then the string 1186 * whose character at position <i>k</i> has the smaller value, as 1187 * determined by using the {@code <} operator, lexicographically precedes the 1188 * other string. In this case, {@code compareTo} returns the 1189 * difference of the two character values at position {@code k} in 1190 * the two string -- that is, the value: 1191 * <blockquote><pre> 1192 * this.charAt(k)-anotherString.charAt(k) 1193 * </pre></blockquote> 1194 * If there is no index position at which they differ, then the shorter 1195 * string lexicographically precedes the longer string. In this case, 1196 * {@code compareTo} returns the difference of the lengths of the 1197 * strings -- that is, the value: 1198 * <blockquote><pre> 1199 * this.length()-anotherString.length() 1200 * </pre></blockquote> 1201 * 1202 * <p>For finer-grained String comparison, refer to 1203 * {@link java.text.Collator}. 1204 * 1205 * @param anotherString the {@code String} to be compared. 1206 * @return the value {@code 0} if the argument string is equal to 1207 * this string; a value less than {@code 0} if this string 1208 * is lexicographically less than the string argument; and a 1209 * value greater than {@code 0} if this string is 1210 * lexicographically greater than the string argument. 1211 */ 1212 public int compareTo(String anotherString) { 1213 byte v1[] = value; 1214 byte v2[] = anotherString.value; 1215 if (coder() == anotherString.coder()) { 1216 return isLatin1() ? StringLatin1.compareTo(v1, v2) 1217 : StringUTF16.compareTo(v1, v2); 1218 } 1219 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2) 1220 : StringUTF16.compareToLatin1(v1, v2); 1221 } 1222 1223 /** 1224 * A Comparator that orders {@code String} objects as by 1225 * {@code compareToIgnoreCase}. This comparator is serializable. 1226 * <p> 1227 * Note that this Comparator does <em>not</em> take locale into account, 1228 * and will result in an unsatisfactory ordering for certain locales. 1229 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1230 * 1231 * @see java.text.Collator 1232 * @since 1.2 1233 */ 1234 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1235 = new CaseInsensitiveComparator(); 1236 private static class CaseInsensitiveComparator 1237 implements Comparator<String>, java.io.Serializable { 1238 // use serialVersionUID from JDK 1.2.2 for interoperability 1239 private static final long serialVersionUID = 8575799808933029326L; 1240 1241 public int compare(String s1, String s2) { 1242 byte v1[] = s1.value; 1243 byte v2[] = s2.value; 1244 if (s1.coder() == s2.coder()) { 1245 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2) 1246 : StringUTF16.compareToCI(v1, v2); 1247 } 1248 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2) 1249 : StringUTF16.compareToCI_Latin1(v1, v2); 1250 } 1251 1252 /** Replaces the de-serialized object. */ 1253 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1254 } 1255 1256 /** 1257 * Compares two strings lexicographically, ignoring case 1258 * differences. This method returns an integer whose sign is that of 1259 * calling {@code compareTo} with normalized versions of the strings 1260 * where case differences have been eliminated by calling 1261 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1262 * each character. 1263 * <p> 1264 * Note that this method does <em>not</em> take locale into account, 1265 * and will result in an unsatisfactory ordering for certain locales. 1266 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1267 * 1268 * @param str the {@code String} to be compared. 1269 * @return a negative integer, zero, or a positive integer as the 1270 * specified String is greater than, equal to, or less 1271 * than this String, ignoring case considerations. 1272 * @see java.text.Collator 1273 * @since 1.2 1274 */ 1275 public int compareToIgnoreCase(String str) { 1276 return CASE_INSENSITIVE_ORDER.compare(this, str); 1277 } 1278 1279 /** 1280 * Tests if two string regions are equal. 1281 * <p> 1282 * A substring of this {@code String} object is compared to a substring 1283 * of the argument other. The result is true if these substrings 1284 * represent identical character sequences. The substring of this 1285 * {@code String} object to be compared begins at index {@code toffset} 1286 * and has length {@code len}. The substring of other to be compared 1287 * begins at index {@code ooffset} and has length {@code len}. The 1288 * result is {@code false} if and only if at least one of the following 1289 * is true: 1290 * <ul><li>{@code toffset} is negative. 1291 * <li>{@code ooffset} is negative. 1292 * <li>{@code toffset+len} is greater than the length of this 1293 * {@code String} object. 1294 * <li>{@code ooffset+len} is greater than the length of the other 1295 * argument. 1296 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1297 * such that: 1298 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1299 * <i>k</i>{@code )} 1300 * </ul> 1301 * 1302 * <p>Note that this method does <em>not</em> take locale into account. The 1303 * {@link java.text.Collator} class provides locale-sensitive comparison. 1304 * 1305 * @param toffset the starting offset of the subregion in this string. 1306 * @param other the string argument. 1307 * @param ooffset the starting offset of the subregion in the string 1308 * argument. 1309 * @param len the number of characters to compare. 1310 * @return {@code true} if the specified subregion of this string 1311 * exactly matches the specified subregion of the string argument; 1312 * {@code false} otherwise. 1313 */ 1314 public boolean regionMatches(int toffset, String other, int ooffset, int len) { 1315 byte tv[] = value; 1316 byte ov[] = other.value; 1317 // Note: toffset, ooffset, or len might be near -1>>>1. 1318 if ((ooffset < 0) || (toffset < 0) || 1319 (toffset > (long)length() - len) || 1320 (ooffset > (long)other.length() - len)) { 1321 return false; 1322 } 1323 if (coder() == other.coder()) { 1324 if (!isLatin1() && (len > 0)) { 1325 toffset = toffset << 1; 1326 ooffset = ooffset << 1; 1327 len = len << 1; 1328 } 1329 while (len-- > 0) { 1330 if (tv[toffset++] != ov[ooffset++]) { 1331 return false; 1332 } 1333 } 1334 } else { 1335 if (coder() == LATIN1) { 1336 while (len-- > 0) { 1337 if (StringLatin1.getChar(tv, toffset++) != 1338 StringUTF16.getChar(ov, ooffset++)) { 1339 return false; 1340 } 1341 } 1342 } else { 1343 while (len-- > 0) { 1344 if (StringUTF16.getChar(tv, toffset++) != 1345 StringLatin1.getChar(ov, ooffset++)) { 1346 return false; 1347 } 1348 } 1349 } 1350 } 1351 return true; 1352 } 1353 1354 /** 1355 * Tests if two string regions are equal. 1356 * <p> 1357 * A substring of this {@code String} object is compared to a substring 1358 * of the argument {@code other}. The result is {@code true} if these 1359 * substrings represent character sequences that are the same, ignoring 1360 * case if and only if {@code ignoreCase} is true. The substring of 1361 * this {@code String} object to be compared begins at index 1362 * {@code toffset} and has length {@code len}. The substring of 1363 * {@code other} to be compared begins at index {@code ooffset} and 1364 * has length {@code len}. The result is {@code false} if and only if 1365 * at least one of the following is true: 1366 * <ul><li>{@code toffset} is negative. 1367 * <li>{@code ooffset} is negative. 1368 * <li>{@code toffset+len} is greater than the length of this 1369 * {@code String} object. 1370 * <li>{@code ooffset+len} is greater than the length of the other 1371 * argument. 1372 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1373 * integer <i>k</i> less than {@code len} such that: 1374 * <blockquote><pre> 1375 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1376 * </pre></blockquote> 1377 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1378 * integer <i>k</i> less than {@code len} such that: 1379 * <blockquote><pre> 1380 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) != 1381 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k))) 1382 * </pre></blockquote> 1383 * </ul> 1384 * 1385 * <p>Note that this method does <em>not</em> take locale into account, 1386 * and will result in unsatisfactory results for certain locales when 1387 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class 1388 * provides locale-sensitive comparison. 1389 * 1390 * @param ignoreCase if {@code true}, ignore case when comparing 1391 * characters. 1392 * @param toffset the starting offset of the subregion in this 1393 * string. 1394 * @param other the string argument. 1395 * @param ooffset the starting offset of the subregion in the string 1396 * argument. 1397 * @param len the number of characters to compare. 1398 * @return {@code true} if the specified subregion of this string 1399 * matches the specified subregion of the string argument; 1400 * {@code false} otherwise. Whether the matching is exact 1401 * or case insensitive depends on the {@code ignoreCase} 1402 * argument. 1403 */ 1404 public boolean regionMatches(boolean ignoreCase, int toffset, 1405 String other, int ooffset, int len) { 1406 if (!ignoreCase) { 1407 return regionMatches(toffset, other, ooffset, len); 1408 } 1409 // Note: toffset, ooffset, or len might be near -1>>>1. 1410 if ((ooffset < 0) || (toffset < 0) 1411 || (toffset > (long)length() - len) 1412 || (ooffset > (long)other.length() - len)) { 1413 return false; 1414 } 1415 byte tv[] = value; 1416 byte ov[] = other.value; 1417 if (coder() == other.coder()) { 1418 return isLatin1() 1419 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len) 1420 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len); 1421 } 1422 return isLatin1() 1423 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len) 1424 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len); 1425 } 1426 1427 /** 1428 * Tests if the substring of this string beginning at the 1429 * specified index starts with the specified prefix. 1430 * 1431 * @param prefix the prefix. 1432 * @param toffset where to begin looking in this string. 1433 * @return {@code true} if the character sequence represented by the 1434 * argument is a prefix of the substring of this object starting 1435 * at index {@code toffset}; {@code false} otherwise. 1436 * The result is {@code false} if {@code toffset} is 1437 * negative or greater than the length of this 1438 * {@code String} object; otherwise the result is the same 1439 * as the result of the expression 1440 * <pre> 1441 * this.substring(toffset).startsWith(prefix) 1442 * </pre> 1443 */ 1444 public boolean startsWith(String prefix, int toffset) { 1445 // Note: toffset might be near -1>>>1. 1446 if (toffset < 0 || toffset > length() - prefix.length()) { 1447 return false; 1448 } 1449 byte ta[] = value; 1450 byte pa[] = prefix.value; 1451 int po = 0; 1452 int pc = pa.length; 1453 if (coder() == prefix.coder()) { 1454 int to = isLatin1() ? toffset : toffset << 1; 1455 while (po < pc) { 1456 if (ta[to++] != pa[po++]) { 1457 return false; 1458 } 1459 } 1460 } else { 1461 if (isLatin1()) { // && pcoder == UTF16 1462 return false; 1463 } 1464 // coder == UTF16 && pcoder == LATIN1) 1465 while (po < pc) { 1466 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) { 1467 return false; 1468 } 1469 } 1470 } 1471 return true; 1472 } 1473 1474 /** 1475 * Tests if this string starts with the specified prefix. 1476 * 1477 * @param prefix the prefix. 1478 * @return {@code true} if the character sequence represented by the 1479 * argument is a prefix of the character sequence represented by 1480 * this string; {@code false} otherwise. 1481 * Note also that {@code true} will be returned if the 1482 * argument is an empty string or is equal to this 1483 * {@code String} object as determined by the 1484 * {@link #equals(Object)} method. 1485 * @since 1.0 1486 */ 1487 public boolean startsWith(String prefix) { 1488 return startsWith(prefix, 0); 1489 } 1490 1491 /** 1492 * Tests if this string ends with the specified suffix. 1493 * 1494 * @param suffix the suffix. 1495 * @return {@code true} if the character sequence represented by the 1496 * argument is a suffix of the character sequence represented by 1497 * this object; {@code false} otherwise. Note that the 1498 * result will be {@code true} if the argument is the 1499 * empty string or is equal to this {@code String} object 1500 * as determined by the {@link #equals(Object)} method. 1501 */ 1502 public boolean endsWith(String suffix) { 1503 return startsWith(suffix, length() - suffix.length()); 1504 } 1505 1506 /** 1507 * Returns a hash code for this string. The hash code for a 1508 * {@code String} object is computed as 1509 * <blockquote><pre> 1510 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1511 * </pre></blockquote> 1512 * using {@code int} arithmetic, where {@code s[i]} is the 1513 * <i>i</i>th character of the string, {@code n} is the length of 1514 * the string, and {@code ^} indicates exponentiation. 1515 * (The hash value of the empty string is zero.) 1516 * 1517 * @return a hash code value for this object. 1518 */ 1519 public int hashCode() { 1520 int h = hash; 1521 if (h == 0 && value.length > 0) { 1522 hash = h = isLatin1() ? StringLatin1.hashCode(value) 1523 : StringUTF16.hashCode(value); 1524 } 1525 return h; 1526 } 1527 1528 /** 1529 * Returns the index within this string of the first occurrence of 1530 * the specified character. If a character with value 1531 * {@code ch} occurs in the character sequence represented by 1532 * this {@code String} object, then the index (in Unicode 1533 * code units) of the first such occurrence is returned. For 1534 * values of {@code ch} in the range from 0 to 0xFFFF 1535 * (inclusive), this is the smallest value <i>k</i> such that: 1536 * <blockquote><pre> 1537 * this.charAt(<i>k</i>) == ch 1538 * </pre></blockquote> 1539 * is true. For other values of {@code ch}, it is the 1540 * smallest value <i>k</i> such that: 1541 * <blockquote><pre> 1542 * this.codePointAt(<i>k</i>) == ch 1543 * </pre></blockquote> 1544 * is true. In either case, if no such character occurs in this 1545 * string, then {@code -1} is returned. 1546 * 1547 * @param ch a character (Unicode code point). 1548 * @return the index of the first occurrence of the character in the 1549 * character sequence represented by this object, or 1550 * {@code -1} if the character does not occur. 1551 */ 1552 public int indexOf(int ch) { 1553 return indexOf(ch, 0); 1554 } 1555 1556 /** 1557 * Returns the index within this string of the first occurrence of the 1558 * specified character, starting the search at the specified index. 1559 * <p> 1560 * If a character with value {@code ch} occurs in the 1561 * character sequence represented by this {@code String} 1562 * object at an index no smaller than {@code fromIndex}, then 1563 * the index of the first such occurrence is returned. For values 1564 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1565 * this is the smallest value <i>k</i> such that: 1566 * <blockquote><pre> 1567 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1568 * </pre></blockquote> 1569 * is true. For other values of {@code ch}, it is the 1570 * smallest value <i>k</i> such that: 1571 * <blockquote><pre> 1572 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1573 * </pre></blockquote> 1574 * is true. In either case, if no such character occurs in this 1575 * string at or after position {@code fromIndex}, then 1576 * {@code -1} is returned. 1577 * 1578 * <p> 1579 * There is no restriction on the value of {@code fromIndex}. If it 1580 * is negative, it has the same effect as if it were zero: this entire 1581 * string may be searched. If it is greater than the length of this 1582 * string, it has the same effect as if it were equal to the length of 1583 * this string: {@code -1} is returned. 1584 * 1585 * <p>All indices are specified in {@code char} values 1586 * (Unicode code units). 1587 * 1588 * @param ch a character (Unicode code point). 1589 * @param fromIndex the index to start the search from. 1590 * @return the index of the first occurrence of the character in the 1591 * character sequence represented by this object that is greater 1592 * than or equal to {@code fromIndex}, or {@code -1} 1593 * if the character does not occur. 1594 */ 1595 public int indexOf(int ch, int fromIndex) { 1596 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex) 1597 : StringUTF16.indexOf(value, ch, fromIndex); 1598 } 1599 1600 /** 1601 * Returns the index within this string of the last occurrence of 1602 * the specified character. For values of {@code ch} in the 1603 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1604 * units) returned is the largest value <i>k</i> such that: 1605 * <blockquote><pre> 1606 * this.charAt(<i>k</i>) == ch 1607 * </pre></blockquote> 1608 * is true. For other values of {@code ch}, it is the 1609 * largest value <i>k</i> such that: 1610 * <blockquote><pre> 1611 * this.codePointAt(<i>k</i>) == ch 1612 * </pre></blockquote> 1613 * is true. In either case, if no such character occurs in this 1614 * string, then {@code -1} is returned. The 1615 * {@code String} is searched backwards starting at the last 1616 * character. 1617 * 1618 * @param ch a character (Unicode code point). 1619 * @return the index of the last occurrence of the character in the 1620 * character sequence represented by this object, or 1621 * {@code -1} if the character does not occur. 1622 */ 1623 public int lastIndexOf(int ch) { 1624 return lastIndexOf(ch, length() - 1); 1625 } 1626 1627 /** 1628 * Returns the index within this string of the last occurrence of 1629 * the specified character, searching backward starting at the 1630 * specified index. For values of {@code ch} in the range 1631 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1632 * value <i>k</i> such that: 1633 * <blockquote><pre> 1634 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1635 * </pre></blockquote> 1636 * is true. For other values of {@code ch}, it is the 1637 * largest value <i>k</i> such that: 1638 * <blockquote><pre> 1639 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1640 * </pre></blockquote> 1641 * is true. In either case, if no such character occurs in this 1642 * string at or before position {@code fromIndex}, then 1643 * {@code -1} is returned. 1644 * 1645 * <p>All indices are specified in {@code char} values 1646 * (Unicode code units). 1647 * 1648 * @param ch a character (Unicode code point). 1649 * @param fromIndex the index to start the search from. There is no 1650 * restriction on the value of {@code fromIndex}. If it is 1651 * greater than or equal to the length of this string, it has 1652 * the same effect as if it were equal to one less than the 1653 * length of this string: this entire string may be searched. 1654 * If it is negative, it has the same effect as if it were -1: 1655 * -1 is returned. 1656 * @return the index of the last occurrence of the character in the 1657 * character sequence represented by this object that is less 1658 * than or equal to {@code fromIndex}, or {@code -1} 1659 * if the character does not occur before that point. 1660 */ 1661 public int lastIndexOf(int ch, int fromIndex) { 1662 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex) 1663 : StringUTF16.lastIndexOf(value, ch, fromIndex); 1664 } 1665 1666 /** 1667 * Returns the index within this string of the first occurrence of the 1668 * specified substring. 1669 * 1670 * <p>The returned index is the smallest value {@code k} for which: 1671 * <pre>{@code 1672 * this.startsWith(str, k) 1673 * }</pre> 1674 * If no such value of {@code k} exists, then {@code -1} is returned. 1675 * 1676 * @param str the substring to search for. 1677 * @return the index of the first occurrence of the specified substring, 1678 * or {@code -1} if there is no such occurrence. 1679 */ 1680 public int indexOf(String str) { 1681 if (coder() == str.coder()) { 1682 return isLatin1() ? StringLatin1.indexOf(value, str.value) 1683 : StringUTF16.indexOf(value, str.value); 1684 } 1685 if (coder() == LATIN1) { // str.coder == UTF16 1686 return -1; 1687 } 1688 return StringUTF16.indexOfLatin1(value, str.value); 1689 } 1690 1691 /** 1692 * Returns the index within this string of the first occurrence of the 1693 * specified substring, starting at the specified index. 1694 * 1695 * <p>The returned index is the smallest value {@code k} for which: 1696 * <pre>{@code 1697 * k >= Math.min(fromIndex, this.length()) && 1698 * this.startsWith(str, k) 1699 * }</pre> 1700 * If no such value of {@code k} exists, then {@code -1} is returned. 1701 * 1702 * @param str the substring to search for. 1703 * @param fromIndex the index from which to start the search. 1704 * @return the index of the first occurrence of the specified substring, 1705 * starting at the specified index, 1706 * or {@code -1} if there is no such occurrence. 1707 */ 1708 public int indexOf(String str, int fromIndex) { 1709 return indexOf(value, coder(), length(), str, fromIndex); 1710 } 1711 1712 /** 1713 * Code shared by String and AbstractStringBuilder to do searches. The 1714 * source is the character array being searched, and the target 1715 * is the string being searched for. 1716 * 1717 * @param src the characters being searched. 1718 * @param srcCoder the coder of the source string. 1719 * @param srcCount length of the source string. 1720 * @param tgtStr the characters being searched for. 1721 * @param fromIndex the index to begin searching from. 1722 */ 1723 static int indexOf(byte[] src, byte srcCoder, int srcCount, 1724 String tgtStr, int fromIndex) { 1725 byte[] tgt = tgtStr.value; 1726 byte tgtCoder = tgtStr.coder(); 1727 int tgtCount = tgtStr.length(); 1728 1729 if (fromIndex >= srcCount) { 1730 return (tgtCount == 0 ? srcCount : -1); 1731 } 1732 if (fromIndex < 0) { 1733 fromIndex = 0; 1734 } 1735 if (tgtCount == 0) { 1736 return fromIndex; 1737 } 1738 if (tgtCount > srcCount) { 1739 return -1; 1740 } 1741 if (srcCoder == tgtCoder) { 1742 return srcCoder == LATIN1 1743 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex) 1744 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex); 1745 } 1746 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1747 return -1; 1748 } 1749 // srcCoder == UTF16 && tgtCoder == LATIN1) { 1750 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex); 1751 } 1752 1753 /** 1754 * Returns the index within this string of the last occurrence of the 1755 * specified substring. The last occurrence of the empty string "" 1756 * is considered to occur at the index value {@code this.length()}. 1757 * 1758 * <p>The returned index is the largest value {@code k} for which: 1759 * <pre>{@code 1760 * this.startsWith(str, k) 1761 * }</pre> 1762 * If no such value of {@code k} exists, then {@code -1} is returned. 1763 * 1764 * @param str the substring to search for. 1765 * @return the index of the last occurrence of the specified substring, 1766 * or {@code -1} if there is no such occurrence. 1767 */ 1768 public int lastIndexOf(String str) { 1769 return lastIndexOf(str, length()); 1770 } 1771 1772 /** 1773 * Returns the index within this string of the last occurrence of the 1774 * specified substring, searching backward starting at the specified index. 1775 * 1776 * <p>The returned index is the largest value {@code k} for which: 1777 * <pre>{@code 1778 * k <= Math.min(fromIndex, this.length()) && 1779 * this.startsWith(str, k) 1780 * }</pre> 1781 * If no such value of {@code k} exists, then {@code -1} is returned. 1782 * 1783 * @param str the substring to search for. 1784 * @param fromIndex the index to start the search from. 1785 * @return the index of the last occurrence of the specified substring, 1786 * searching backward from the specified index, 1787 * or {@code -1} if there is no such occurrence. 1788 */ 1789 public int lastIndexOf(String str, int fromIndex) { 1790 return lastIndexOf(value, coder(), length(), str, fromIndex); 1791 } 1792 1793 /** 1794 * Code shared by String and AbstractStringBuilder to do searches. The 1795 * source is the character array being searched, and the target 1796 * is the string being searched for. 1797 * 1798 * @param src the characters being searched. 1799 * @param srcCoder coder handles the mapping between bytes/chars 1800 * @param srcCount count of the source string. 1801 * @param tgtStr the characters being searched for. 1802 * @param fromIndex the index to begin searching from. 1803 */ 1804 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount, 1805 String tgtStr, int fromIndex) { 1806 byte[] tgt = tgtStr.value; 1807 byte tgtCoder = tgtStr.coder(); 1808 int tgtCount = tgtStr.length(); 1809 /* 1810 * Check arguments; return immediately where possible. For 1811 * consistency, don't check for null str. 1812 */ 1813 int rightIndex = srcCount - tgtCount; 1814 if (fromIndex > rightIndex) { 1815 fromIndex = rightIndex; 1816 } 1817 if (fromIndex < 0) { 1818 return -1; 1819 } 1820 /* Empty string always matches. */ 1821 if (tgtCount == 0) { 1822 return fromIndex; 1823 } 1824 if (srcCoder == tgtCoder) { 1825 return srcCoder == LATIN1 1826 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex) 1827 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex); 1828 } 1829 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1830 return -1; 1831 } 1832 // srcCoder == UTF16 && tgtCoder == LATIN1 1833 int min = tgtCount - 1; 1834 int i = min + fromIndex; 1835 int strLastIndex = tgtCount - 1; 1836 1837 char strLastChar = (char)(tgt[strLastIndex] & 0xff); 1838 startSearchForLastChar: 1839 while (true) { 1840 while (i >= min && StringUTF16.getChar(src, i) != strLastChar) { 1841 i--; 1842 } 1843 if (i < min) { 1844 return -1; 1845 } 1846 int j = i - 1; 1847 int start = j - strLastIndex; 1848 int k = strLastIndex - 1; 1849 while (j > start) { 1850 if (StringUTF16.getChar(src, j--) != (tgt[k--] & 0xff)) { 1851 i--; 1852 continue startSearchForLastChar; 1853 } 1854 } 1855 return start + 1; 1856 } 1857 } 1858 1859 /** 1860 * Returns a string that is a substring of this string. The 1861 * substring begins with the character at the specified index and 1862 * extends to the end of this string. <p> 1863 * Examples: 1864 * <blockquote><pre> 1865 * "unhappy".substring(2) returns "happy" 1866 * "Harbison".substring(3) returns "bison" 1867 * "emptiness".substring(9) returns "" (an empty string) 1868 * </pre></blockquote> 1869 * 1870 * @param beginIndex the beginning index, inclusive. 1871 * @return the specified substring. 1872 * @exception IndexOutOfBoundsException if 1873 * {@code beginIndex} is negative or larger than the 1874 * length of this {@code String} object. 1875 */ 1876 public String substring(int beginIndex) { 1877 if (beginIndex < 0) { 1878 throw new StringIndexOutOfBoundsException(beginIndex); 1879 } 1880 int subLen = length() - beginIndex; 1881 if (subLen < 0) { 1882 throw new StringIndexOutOfBoundsException(subLen); 1883 } 1884 if (beginIndex == 0) { 1885 return this; 1886 } 1887 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1888 : StringUTF16.newString(value, beginIndex, subLen); 1889 } 1890 1891 /** 1892 * Returns a string that is a substring of this string. The 1893 * substring begins at the specified {@code beginIndex} and 1894 * extends to the character at index {@code endIndex - 1}. 1895 * Thus the length of the substring is {@code endIndex-beginIndex}. 1896 * <p> 1897 * Examples: 1898 * <blockquote><pre> 1899 * "hamburger".substring(4, 8) returns "urge" 1900 * "smiles".substring(1, 5) returns "mile" 1901 * </pre></blockquote> 1902 * 1903 * @param beginIndex the beginning index, inclusive. 1904 * @param endIndex the ending index, exclusive. 1905 * @return the specified substring. 1906 * @exception IndexOutOfBoundsException if the 1907 * {@code beginIndex} is negative, or 1908 * {@code endIndex} is larger than the length of 1909 * this {@code String} object, or 1910 * {@code beginIndex} is larger than 1911 * {@code endIndex}. 1912 */ 1913 public String substring(int beginIndex, int endIndex) { 1914 int length = length(); 1915 checkBoundsBeginEnd(beginIndex, endIndex, length); 1916 int subLen = endIndex - beginIndex; 1917 if (beginIndex == 0 && endIndex == length) { 1918 return this; 1919 } 1920 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1921 : StringUTF16.newString(value, beginIndex, subLen); 1922 } 1923 1924 /** 1925 * Returns a character sequence that is a subsequence of this sequence. 1926 * 1927 * <p> An invocation of this method of the form 1928 * 1929 * <blockquote><pre> 1930 * str.subSequence(begin, end)</pre></blockquote> 1931 * 1932 * behaves in exactly the same way as the invocation 1933 * 1934 * <blockquote><pre> 1935 * str.substring(begin, end)</pre></blockquote> 1936 * 1937 * @apiNote 1938 * This method is defined so that the {@code String} class can implement 1939 * the {@link CharSequence} interface. 1940 * 1941 * @param beginIndex the begin index, inclusive. 1942 * @param endIndex the end index, exclusive. 1943 * @return the specified subsequence. 1944 * 1945 * @throws IndexOutOfBoundsException 1946 * if {@code beginIndex} or {@code endIndex} is negative, 1947 * if {@code endIndex} is greater than {@code length()}, 1948 * or if {@code beginIndex} is greater than {@code endIndex} 1949 * 1950 * @since 1.4 1951 * @spec JSR-51 1952 */ 1953 public CharSequence subSequence(int beginIndex, int endIndex) { 1954 return this.substring(beginIndex, endIndex); 1955 } 1956 1957 /** 1958 * Concatenates the specified string to the end of this string. 1959 * <p> 1960 * If the length of the argument string is {@code 0}, then this 1961 * {@code String} object is returned. Otherwise, a 1962 * {@code String} object is returned that represents a character 1963 * sequence that is the concatenation of the character sequence 1964 * represented by this {@code String} object and the character 1965 * sequence represented by the argument string.<p> 1966 * Examples: 1967 * <blockquote><pre> 1968 * "cares".concat("s") returns "caress" 1969 * "to".concat("get").concat("her") returns "together" 1970 * </pre></blockquote> 1971 * 1972 * @param str the {@code String} that is concatenated to the end 1973 * of this {@code String}. 1974 * @return a string that represents the concatenation of this object's 1975 * characters followed by the string argument's characters. 1976 */ 1977 public String concat(String str) { 1978 int olen = str.length(); 1979 if (olen == 0) { 1980 return this; 1981 } 1982 if (coder() == str.coder()) { 1983 byte[] val = this.value; 1984 byte[] oval = str.value; 1985 int len = val.length + oval.length; 1986 byte[] buf = Arrays.copyOf(val, len); 1987 System.arraycopy(oval, 0, buf, val.length, oval.length); 1988 return new String(buf, coder); 1989 } 1990 int len = length(); 1991 byte[] buf = StringUTF16.newBytesFor(len + olen); 1992 getBytes(buf, 0, UTF16); 1993 str.getBytes(buf, len, UTF16); 1994 return new String(buf, UTF16); 1995 } 1996 1997 /** 1998 * Returns a string resulting from replacing all occurrences of 1999 * {@code oldChar} in this string with {@code newChar}. 2000 * <p> 2001 * If the character {@code oldChar} does not occur in the 2002 * character sequence represented by this {@code String} object, 2003 * then a reference to this {@code String} object is returned. 2004 * Otherwise, a {@code String} object is returned that 2005 * represents a character sequence identical to the character sequence 2006 * represented by this {@code String} object, except that every 2007 * occurrence of {@code oldChar} is replaced by an occurrence 2008 * of {@code newChar}. 2009 * <p> 2010 * Examples: 2011 * <blockquote><pre> 2012 * "mesquite in your cellar".replace('e', 'o') 2013 * returns "mosquito in your collar" 2014 * "the war of baronets".replace('r', 'y') 2015 * returns "the way of bayonets" 2016 * "sparring with a purple porpoise".replace('p', 't') 2017 * returns "starring with a turtle tortoise" 2018 * "JonL".replace('q', 'x') returns "JonL" (no change) 2019 * </pre></blockquote> 2020 * 2021 * @param oldChar the old character. 2022 * @param newChar the new character. 2023 * @return a string derived from this string by replacing every 2024 * occurrence of {@code oldChar} with {@code newChar}. 2025 */ 2026 public String replace(char oldChar, char newChar) { 2027 if (oldChar != newChar) { 2028 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar) 2029 : StringUTF16.replace(value, oldChar, newChar); 2030 if (ret != null) { 2031 return ret; 2032 } 2033 } 2034 return this; 2035 } 2036 2037 /** 2038 * Tells whether or not this string matches the given <a 2039 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2040 * 2041 * <p> An invocation of this method of the form 2042 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2043 * same result as the expression 2044 * 2045 * <blockquote> 2046 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2047 * matches(<i>regex</i>, <i>str</i>)} 2048 * </blockquote> 2049 * 2050 * @param regex 2051 * the regular expression to which this string is to be matched 2052 * 2053 * @return {@code true} if, and only if, this string matches the 2054 * given regular expression 2055 * 2056 * @throws PatternSyntaxException 2057 * if the regular expression's syntax is invalid 2058 * 2059 * @see java.util.regex.Pattern 2060 * 2061 * @since 1.4 2062 * @spec JSR-51 2063 */ 2064 public boolean matches(String regex) { 2065 return Pattern.matches(regex, this); 2066 } 2067 2068 /** 2069 * Returns true if and only if this string contains the specified 2070 * sequence of char values. 2071 * 2072 * @param s the sequence to search for 2073 * @return true if this string contains {@code s}, false otherwise 2074 * @since 1.5 2075 */ 2076 public boolean contains(CharSequence s) { 2077 return indexOf(s.toString()) >= 0; 2078 } 2079 2080 /** 2081 * Replaces the first substring of this string that matches the given <a 2082 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2083 * given replacement. 2084 * 2085 * <p> An invocation of this method of the form 2086 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2087 * yields exactly the same result as the expression 2088 * 2089 * <blockquote> 2090 * <code> 2091 * {@link java.util.regex.Pattern}.{@link 2092 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2093 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2094 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>) 2095 * </code> 2096 * </blockquote> 2097 * 2098 *<p> 2099 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2100 * replacement string may cause the results to be different than if it were 2101 * being treated as a literal replacement string; see 2102 * {@link java.util.regex.Matcher#replaceFirst}. 2103 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2104 * meaning of these characters, if desired. 2105 * 2106 * @param regex 2107 * the regular expression to which this string is to be matched 2108 * @param replacement 2109 * the string to be substituted for the first match 2110 * 2111 * @return The resulting {@code String} 2112 * 2113 * @throws PatternSyntaxException 2114 * if the regular expression's syntax is invalid 2115 * 2116 * @see java.util.regex.Pattern 2117 * 2118 * @since 1.4 2119 * @spec JSR-51 2120 */ 2121 public String replaceFirst(String regex, String replacement) { 2122 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2123 } 2124 2125 /** 2126 * Replaces each substring of this string that matches the given <a 2127 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2128 * given replacement. 2129 * 2130 * <p> An invocation of this method of the form 2131 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2132 * yields exactly the same result as the expression 2133 * 2134 * <blockquote> 2135 * <code> 2136 * {@link java.util.regex.Pattern}.{@link 2137 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2138 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2139 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2140 * </code> 2141 * </blockquote> 2142 * 2143 *<p> 2144 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2145 * replacement string may cause the results to be different than if it were 2146 * being treated as a literal replacement string; see 2147 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2148 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2149 * meaning of these characters, if desired. 2150 * 2151 * @param regex 2152 * the regular expression to which this string is to be matched 2153 * @param replacement 2154 * the string to be substituted for each match 2155 * 2156 * @return The resulting {@code String} 2157 * 2158 * @throws PatternSyntaxException 2159 * if the regular expression's syntax is invalid 2160 * 2161 * @see java.util.regex.Pattern 2162 * 2163 * @since 1.4 2164 * @spec JSR-51 2165 */ 2166 public String replaceAll(String regex, String replacement) { 2167 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2168 } 2169 2170 /** 2171 * Replaces each substring of this string that matches the literal target 2172 * sequence with the specified literal replacement sequence. The 2173 * replacement proceeds from the beginning of the string to the end, for 2174 * example, replacing "aa" with "b" in the string "aaa" will result in 2175 * "ba" rather than "ab". 2176 * 2177 * @param target The sequence of char values to be replaced 2178 * @param replacement The replacement sequence of char values 2179 * @return The resulting string 2180 * @since 1.5 2181 */ 2182 public String replace(CharSequence target, CharSequence replacement) { 2183 String tgtStr = target.toString(); 2184 String replStr = replacement.toString(); 2185 int j = indexOf(tgtStr); 2186 if (j < 0) { 2187 return this; 2188 } 2189 int tgtLen = tgtStr.length(); 2190 int tgtLen1 = Math.max(tgtLen, 1); 2191 int thisLen = length(); 2192 2193 int newLenHint = thisLen - tgtLen + replStr.length(); 2194 if (newLenHint < 0) { 2195 throw new OutOfMemoryError(); 2196 } 2197 StringBuilder sb = new StringBuilder(newLenHint); 2198 int i = 0; 2199 do { 2200 sb.append(this, i, j).append(replStr); 2201 i = j + tgtLen; 2202 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0); 2203 return sb.append(this, i, thisLen).toString(); 2204 } 2205 2206 /** 2207 * Splits this string around matches of the given 2208 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2209 * 2210 * <p> The array returned by this method contains each substring of this 2211 * string that is terminated by another substring that matches the given 2212 * expression or is terminated by the end of the string. The substrings in 2213 * the array are in the order in which they occur in this string. If the 2214 * expression does not match any part of the input then the resulting array 2215 * has just one element, namely this string. 2216 * 2217 * <p> When there is a positive-width match at the beginning of this 2218 * string then an empty leading substring is included at the beginning 2219 * of the resulting array. A zero-width match at the beginning however 2220 * never produces such empty leading substring. 2221 * 2222 * <p> The {@code limit} parameter controls the number of times the 2223 * pattern is applied and therefore affects the length of the resulting 2224 * array. If the limit <i>n</i> is greater than zero then the pattern 2225 * will be applied at most <i>n</i> - 1 times, the array's 2226 * length will be no greater than <i>n</i>, and the array's last entry 2227 * will contain all input beyond the last matched delimiter. If <i>n</i> 2228 * is non-positive then the pattern will be applied as many times as 2229 * possible and the array can have any length. If <i>n</i> is zero then 2230 * the pattern will be applied as many times as possible, the array can 2231 * have any length, and trailing empty strings will be discarded. 2232 * 2233 * <p> The string {@code "boo:and:foo"}, for example, yields the 2234 * following results with these parameters: 2235 * 2236 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2237 * <tr> 2238 * <th>Regex</th> 2239 * <th>Limit</th> 2240 * <th>Result</th> 2241 * </tr> 2242 * <tr><td align=center>:</td> 2243 * <td align=center>2</td> 2244 * <td>{@code { "boo", "and:foo" }}</td></tr> 2245 * <tr><td align=center>:</td> 2246 * <td align=center>5</td> 2247 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2248 * <tr><td align=center>:</td> 2249 * <td align=center>-2</td> 2250 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2251 * <tr><td align=center>o</td> 2252 * <td align=center>5</td> 2253 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2254 * <tr><td align=center>o</td> 2255 * <td align=center>-2</td> 2256 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2257 * <tr><td align=center>o</td> 2258 * <td align=center>0</td> 2259 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2260 * </table></blockquote> 2261 * 2262 * <p> An invocation of this method of the form 2263 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2264 * yields the same result as the expression 2265 * 2266 * <blockquote> 2267 * <code> 2268 * {@link java.util.regex.Pattern}.{@link 2269 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2270 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2271 * </code> 2272 * </blockquote> 2273 * 2274 * 2275 * @param regex 2276 * the delimiting regular expression 2277 * 2278 * @param limit 2279 * the result threshold, as described above 2280 * 2281 * @return the array of strings computed by splitting this string 2282 * around matches of the given regular expression 2283 * 2284 * @throws PatternSyntaxException 2285 * if the regular expression's syntax is invalid 2286 * 2287 * @see java.util.regex.Pattern 2288 * 2289 * @since 1.4 2290 * @spec JSR-51 2291 */ 2292 public String[] split(String regex, int limit) { 2293 /* fastpath if the regex is a 2294 (1)one-char String and this character is not one of the 2295 RegEx's meta characters ".$|()[{^?*+\\", or 2296 (2)two-char String and the first char is the backslash and 2297 the second is not the ascii digit or ascii letter. 2298 */ 2299 char ch = 0; 2300 if (((regex.length() == 1 && 2301 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2302 (regex.length() == 2 && 2303 regex.charAt(0) == '\\' && 2304 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2305 ((ch-'a')|('z'-ch)) < 0 && 2306 ((ch-'A')|('Z'-ch)) < 0)) && 2307 (ch < Character.MIN_HIGH_SURROGATE || 2308 ch > Character.MAX_LOW_SURROGATE)) 2309 { 2310 int off = 0; 2311 int next = 0; 2312 boolean limited = limit > 0; 2313 ArrayList<String> list = new ArrayList<>(); 2314 while ((next = indexOf(ch, off)) != -1) { 2315 if (!limited || list.size() < limit - 1) { 2316 list.add(substring(off, next)); 2317 off = next + 1; 2318 } else { // last one 2319 //assert (list.size() == limit - 1); 2320 int last = length(); 2321 list.add(substring(off, last)); 2322 off = last; 2323 break; 2324 } 2325 } 2326 // If no match was found, return this 2327 if (off == 0) 2328 return new String[]{this}; 2329 2330 // Add remaining segment 2331 if (!limited || list.size() < limit) 2332 list.add(substring(off, length())); 2333 2334 // Construct result 2335 int resultSize = list.size(); 2336 if (limit == 0) { 2337 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) { 2338 resultSize--; 2339 } 2340 } 2341 String[] result = new String[resultSize]; 2342 return list.subList(0, resultSize).toArray(result); 2343 } 2344 return Pattern.compile(regex).split(this, limit); 2345 } 2346 2347 /** 2348 * Splits this string around matches of the given <a 2349 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2350 * 2351 * <p> This method works as if by invoking the two-argument {@link 2352 * #split(String, int) split} method with the given expression and a limit 2353 * argument of zero. Trailing empty strings are therefore not included in 2354 * the resulting array. 2355 * 2356 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2357 * results with these expressions: 2358 * 2359 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2360 * <tr> 2361 * <th>Regex</th> 2362 * <th>Result</th> 2363 * </tr> 2364 * <tr><td align=center>:</td> 2365 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2366 * <tr><td align=center>o</td> 2367 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2368 * </table></blockquote> 2369 * 2370 * 2371 * @param regex 2372 * the delimiting regular expression 2373 * 2374 * @return the array of strings computed by splitting this string 2375 * around matches of the given regular expression 2376 * 2377 * @throws PatternSyntaxException 2378 * if the regular expression's syntax is invalid 2379 * 2380 * @see java.util.regex.Pattern 2381 * 2382 * @since 1.4 2383 * @spec JSR-51 2384 */ 2385 public String[] split(String regex) { 2386 return split(regex, 0); 2387 } 2388 2389 /** 2390 * Returns a new String composed of copies of the 2391 * {@code CharSequence elements} joined together with a copy of 2392 * the specified {@code delimiter}. 2393 * 2394 * <blockquote>For example, 2395 * <pre>{@code 2396 * String message = String.join("-", "Java", "is", "cool"); 2397 * // message returned is: "Java-is-cool" 2398 * }</pre></blockquote> 2399 * 2400 * Note that if an element is null, then {@code "null"} is added. 2401 * 2402 * @param delimiter the delimiter that separates each element 2403 * @param elements the elements to join together. 2404 * 2405 * @return a new {@code String} that is composed of the {@code elements} 2406 * separated by the {@code delimiter} 2407 * 2408 * @throws NullPointerException If {@code delimiter} or {@code elements} 2409 * is {@code null} 2410 * 2411 * @see java.util.StringJoiner 2412 * @since 1.8 2413 */ 2414 public static String join(CharSequence delimiter, CharSequence... elements) { 2415 Objects.requireNonNull(delimiter); 2416 Objects.requireNonNull(elements); 2417 // Number of elements not likely worth Arrays.stream overhead. 2418 StringJoiner joiner = new StringJoiner(delimiter); 2419 for (CharSequence cs: elements) { 2420 joiner.add(cs); 2421 } 2422 return joiner.toString(); 2423 } 2424 2425 /** 2426 * Returns a new {@code String} composed of copies of the 2427 * {@code CharSequence elements} joined together with a copy of the 2428 * specified {@code delimiter}. 2429 * 2430 * <blockquote>For example, 2431 * <pre>{@code 2432 * List<String> strings = List.of("Java", "is", "cool"); 2433 * String message = String.join(" ", strings); 2434 * //message returned is: "Java is cool" 2435 * 2436 * Set<String> strings = 2437 * new LinkedHashSet<>(List.of("Java", "is", "very", "cool")); 2438 * String message = String.join("-", strings); 2439 * //message returned is: "Java-is-very-cool" 2440 * }</pre></blockquote> 2441 * 2442 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2443 * 2444 * @param delimiter a sequence of characters that is used to separate each 2445 * of the {@code elements} in the resulting {@code String} 2446 * @param elements an {@code Iterable} that will have its {@code elements} 2447 * joined together. 2448 * 2449 * @return a new {@code String} that is composed from the {@code elements} 2450 * argument 2451 * 2452 * @throws NullPointerException If {@code delimiter} or {@code elements} 2453 * is {@code null} 2454 * 2455 * @see #join(CharSequence,CharSequence...) 2456 * @see java.util.StringJoiner 2457 * @since 1.8 2458 */ 2459 public static String join(CharSequence delimiter, 2460 Iterable<? extends CharSequence> elements) { 2461 Objects.requireNonNull(delimiter); 2462 Objects.requireNonNull(elements); 2463 StringJoiner joiner = new StringJoiner(delimiter); 2464 for (CharSequence cs: elements) { 2465 joiner.add(cs); 2466 } 2467 return joiner.toString(); 2468 } 2469 2470 /** 2471 * Converts all of the characters in this {@code String} to lower 2472 * case using the rules of the given {@code Locale}. Case mapping is based 2473 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2474 * class. Since case mappings are not always 1:1 char mappings, the resulting 2475 * {@code String} may be a different length than the original {@code String}. 2476 * <p> 2477 * Examples of lowercase mappings are in the following table: 2478 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2479 * <tr> 2480 * <th>Language Code of Locale</th> 2481 * <th>Upper Case</th> 2482 * <th>Lower Case</th> 2483 * <th>Description</th> 2484 * </tr> 2485 * <tr> 2486 * <td>tr (Turkish)</td> 2487 * <td>\u0130</td> 2488 * <td>\u0069</td> 2489 * <td>capital letter I with dot above -> small letter i</td> 2490 * </tr> 2491 * <tr> 2492 * <td>tr (Turkish)</td> 2493 * <td>\u0049</td> 2494 * <td>\u0131</td> 2495 * <td>capital letter I -> small letter dotless i </td> 2496 * </tr> 2497 * <tr> 2498 * <td>(all)</td> 2499 * <td>French Fries</td> 2500 * <td>french fries</td> 2501 * <td>lowercased all chars in String</td> 2502 * </tr> 2503 * <tr> 2504 * <td>(all)</td> 2505 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2506 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2507 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2508 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2509 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2510 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2511 * <td>lowercased all chars in String</td> 2512 * </tr> 2513 * </table> 2514 * 2515 * @param locale use the case transformation rules for this locale 2516 * @return the {@code String}, converted to lowercase. 2517 * @see java.lang.String#toLowerCase() 2518 * @see java.lang.String#toUpperCase() 2519 * @see java.lang.String#toUpperCase(Locale) 2520 * @since 1.1 2521 */ 2522 public String toLowerCase(Locale locale) { 2523 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale) 2524 : StringUTF16.toLowerCase(this, value, locale); 2525 } 2526 2527 /** 2528 * Converts all of the characters in this {@code String} to lower 2529 * case using the rules of the default locale. This is equivalent to calling 2530 * {@code toLowerCase(Locale.getDefault())}. 2531 * <p> 2532 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2533 * results if used for strings that are intended to be interpreted locale 2534 * independently. 2535 * Examples are programming language identifiers, protocol keys, and HTML 2536 * tags. 2537 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2538 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2539 * LATIN SMALL LETTER DOTLESS I character. 2540 * To obtain correct results for locale insensitive strings, use 2541 * {@code toLowerCase(Locale.ROOT)}. 2542 * 2543 * @return the {@code String}, converted to lowercase. 2544 * @see java.lang.String#toLowerCase(Locale) 2545 */ 2546 public String toLowerCase() { 2547 return toLowerCase(Locale.getDefault()); 2548 } 2549 2550 /** 2551 * Converts all of the characters in this {@code String} to upper 2552 * case using the rules of the given {@code Locale}. Case mapping is based 2553 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2554 * class. Since case mappings are not always 1:1 char mappings, the resulting 2555 * {@code String} may be a different length than the original {@code String}. 2556 * <p> 2557 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2558 * 2559 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2560 * <tr> 2561 * <th>Language Code of Locale</th> 2562 * <th>Lower Case</th> 2563 * <th>Upper Case</th> 2564 * <th>Description</th> 2565 * </tr> 2566 * <tr> 2567 * <td>tr (Turkish)</td> 2568 * <td>\u0069</td> 2569 * <td>\u0130</td> 2570 * <td>small letter i -> capital letter I with dot above</td> 2571 * </tr> 2572 * <tr> 2573 * <td>tr (Turkish)</td> 2574 * <td>\u0131</td> 2575 * <td>\u0049</td> 2576 * <td>small letter dotless i -> capital letter I</td> 2577 * </tr> 2578 * <tr> 2579 * <td>(all)</td> 2580 * <td>\u00df</td> 2581 * <td>\u0053 \u0053</td> 2582 * <td>small letter sharp s -> two letters: SS</td> 2583 * </tr> 2584 * <tr> 2585 * <td>(all)</td> 2586 * <td>Fahrvergnügen</td> 2587 * <td>FAHRVERGNÜGEN</td> 2588 * <td></td> 2589 * </tr> 2590 * </table> 2591 * @param locale use the case transformation rules for this locale 2592 * @return the {@code String}, converted to uppercase. 2593 * @see java.lang.String#toUpperCase() 2594 * @see java.lang.String#toLowerCase() 2595 * @see java.lang.String#toLowerCase(Locale) 2596 * @since 1.1 2597 */ 2598 public String toUpperCase(Locale locale) { 2599 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale) 2600 : StringUTF16.toUpperCase(this, value, locale); 2601 } 2602 2603 /** 2604 * Converts all of the characters in this {@code String} to upper 2605 * case using the rules of the default locale. This method is equivalent to 2606 * {@code toUpperCase(Locale.getDefault())}. 2607 * <p> 2608 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2609 * results if used for strings that are intended to be interpreted locale 2610 * independently. 2611 * Examples are programming language identifiers, protocol keys, and HTML 2612 * tags. 2613 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2614 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2615 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2616 * To obtain correct results for locale insensitive strings, use 2617 * {@code toUpperCase(Locale.ROOT)}. 2618 * 2619 * @return the {@code String}, converted to uppercase. 2620 * @see java.lang.String#toUpperCase(Locale) 2621 */ 2622 public String toUpperCase() { 2623 return toUpperCase(Locale.getDefault()); 2624 } 2625 2626 /** 2627 * Returns a string whose value is this string, with any leading and trailing 2628 * whitespace removed. 2629 * <p> 2630 * If this {@code String} object represents an empty character 2631 * sequence, or the first and last characters of character sequence 2632 * represented by this {@code String} object both have codes 2633 * greater than {@code '\u005Cu0020'} (the space character), then a 2634 * reference to this {@code String} object is returned. 2635 * <p> 2636 * Otherwise, if there is no character with a code greater than 2637 * {@code '\u005Cu0020'} in the string, then a 2638 * {@code String} object representing an empty string is 2639 * returned. 2640 * <p> 2641 * Otherwise, let <i>k</i> be the index of the first character in the 2642 * string whose code is greater than {@code '\u005Cu0020'}, and let 2643 * <i>m</i> be the index of the last character in the string whose code 2644 * is greater than {@code '\u005Cu0020'}. A {@code String} 2645 * object is returned, representing the substring of this string that 2646 * begins with the character at index <i>k</i> and ends with the 2647 * character at index <i>m</i>-that is, the result of 2648 * {@code this.substring(k, m + 1)}. 2649 * <p> 2650 * This method may be used to trim whitespace (as defined above) from 2651 * the beginning and end of a string. 2652 * 2653 * @return A string whose value is this string, with any leading and trailing white 2654 * space removed, or this string if it has no leading or 2655 * trailing white space. 2656 */ 2657 public String trim() { 2658 String ret = isLatin1() ? StringLatin1.trim(value) 2659 : StringUTF16.trim(value); 2660 return ret == null ? this : ret; 2661 } 2662 2663 /** 2664 * This object (which is already a string!) is itself returned. 2665 * 2666 * @return the string itself. 2667 */ 2668 public String toString() { 2669 return this; 2670 } 2671 2672 /** 2673 * Returns a stream of {@code int} zero-extending the {@code char} values 2674 * from this sequence. Any char which maps to a <a 2675 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code 2676 * point</a> is passed through uninterpreted. 2677 * 2678 * @return an IntStream of char values from this sequence 2679 * @since 9 2680 */ 2681 @Override 2682 public IntStream chars() { 2683 return StreamSupport.intStream( 2684 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2685 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE), 2686 false); 2687 } 2688 2689 2690 /** 2691 * Returns a stream of code point values from this sequence. Any surrogate 2692 * pairs encountered in the sequence are combined as if by {@linkplain 2693 * Character#toCodePoint Character.toCodePoint} and the result is passed 2694 * to the stream. Any other code units, including ordinary BMP characters, 2695 * unpaired surrogates, and undefined code units, are zero-extended to 2696 * {@code int} values which are then passed to the stream. 2697 * 2698 * @return an IntStream of Unicode code points from this sequence 2699 * @since 9 2700 */ 2701 @Override 2702 public IntStream codePoints() { 2703 return StreamSupport.intStream( 2704 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2705 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE), 2706 false); 2707 } 2708 2709 /** 2710 * Converts this string to a new character array. 2711 * 2712 * @return a newly allocated character array whose length is the length 2713 * of this string and whose contents are initialized to contain 2714 * the character sequence represented by this string. 2715 */ 2716 public char[] toCharArray() { 2717 return isLatin1() ? StringLatin1.toChars(value) 2718 : StringUTF16.toChars(value); 2719 } 2720 2721 /** 2722 * Returns a formatted string using the specified format string and 2723 * arguments. 2724 * 2725 * <p> The locale always used is the one returned by {@link 2726 * java.util.Locale#getDefault(java.util.Locale.Category) 2727 * Locale.getDefault(Locale.Category)} with 2728 * {@link java.util.Locale.Category#FORMAT FORMAT} category specified. 2729 * 2730 * @param format 2731 * A <a href="../util/Formatter.html#syntax">format string</a> 2732 * 2733 * @param args 2734 * Arguments referenced by the format specifiers in the format 2735 * string. If there are more arguments than format specifiers, the 2736 * extra arguments are ignored. The number of arguments is 2737 * variable and may be zero. The maximum number of arguments is 2738 * limited by the maximum dimension of a Java array as defined by 2739 * <cite>The Java™ Virtual Machine Specification</cite>. 2740 * The behaviour on a 2741 * {@code null} argument depends on the <a 2742 * href="../util/Formatter.html#syntax">conversion</a>. 2743 * 2744 * @throws java.util.IllegalFormatException 2745 * If a format string contains an illegal syntax, a format 2746 * specifier that is incompatible with the given arguments, 2747 * insufficient arguments given the format string, or other 2748 * illegal conditions. For specification of all possible 2749 * formatting errors, see the <a 2750 * href="../util/Formatter.html#detail">Details</a> section of the 2751 * formatter class specification. 2752 * 2753 * @return A formatted string 2754 * 2755 * @see java.util.Formatter 2756 * @since 1.5 2757 */ 2758 public static String format(String format, Object... args) { 2759 return new Formatter().format(format, args).toString(); 2760 } 2761 2762 /** 2763 * Returns a formatted string using the specified locale, format string, 2764 * and arguments. 2765 * 2766 * @param l 2767 * The {@linkplain java.util.Locale locale} to apply during 2768 * formatting. If {@code l} is {@code null} then no localization 2769 * is applied. 2770 * 2771 * @param format 2772 * A <a href="../util/Formatter.html#syntax">format string</a> 2773 * 2774 * @param args 2775 * Arguments referenced by the format specifiers in the format 2776 * string. If there are more arguments than format specifiers, the 2777 * extra arguments are ignored. The number of arguments is 2778 * variable and may be zero. The maximum number of arguments is 2779 * limited by the maximum dimension of a Java array as defined by 2780 * <cite>The Java™ Virtual Machine Specification</cite>. 2781 * The behaviour on a 2782 * {@code null} argument depends on the 2783 * <a href="../util/Formatter.html#syntax">conversion</a>. 2784 * 2785 * @throws java.util.IllegalFormatException 2786 * If a format string contains an illegal syntax, a format 2787 * specifier that is incompatible with the given arguments, 2788 * insufficient arguments given the format string, or other 2789 * illegal conditions. For specification of all possible 2790 * formatting errors, see the <a 2791 * href="../util/Formatter.html#detail">Details</a> section of the 2792 * formatter class specification 2793 * 2794 * @return A formatted string 2795 * 2796 * @see java.util.Formatter 2797 * @since 1.5 2798 */ 2799 public static String format(Locale l, String format, Object... args) { 2800 return new Formatter(l).format(format, args).toString(); 2801 } 2802 2803 /** 2804 * Returns the string representation of the {@code Object} argument. 2805 * 2806 * @param obj an {@code Object}. 2807 * @return if the argument is {@code null}, then a string equal to 2808 * {@code "null"}; otherwise, the value of 2809 * {@code obj.toString()} is returned. 2810 * @see java.lang.Object#toString() 2811 */ 2812 public static String valueOf(Object obj) { 2813 return (obj == null) ? "null" : obj.toString(); 2814 } 2815 2816 /** 2817 * Returns the string representation of the {@code char} array 2818 * argument. The contents of the character array are copied; subsequent 2819 * modification of the character array does not affect the returned 2820 * string. 2821 * 2822 * @param data the character array. 2823 * @return a {@code String} that contains the characters of the 2824 * character array. 2825 */ 2826 public static String valueOf(char data[]) { 2827 return new String(data); 2828 } 2829 2830 /** 2831 * Returns the string representation of a specific subarray of the 2832 * {@code char} array argument. 2833 * <p> 2834 * The {@code offset} argument is the index of the first 2835 * character of the subarray. The {@code count} argument 2836 * specifies the length of the subarray. The contents of the subarray 2837 * are copied; subsequent modification of the character array does not 2838 * affect the returned string. 2839 * 2840 * @param data the character array. 2841 * @param offset initial offset of the subarray. 2842 * @param count length of the subarray. 2843 * @return a {@code String} that contains the characters of the 2844 * specified subarray of the character array. 2845 * @exception IndexOutOfBoundsException if {@code offset} is 2846 * negative, or {@code count} is negative, or 2847 * {@code offset+count} is larger than 2848 * {@code data.length}. 2849 */ 2850 public static String valueOf(char data[], int offset, int count) { 2851 return new String(data, offset, count); 2852 } 2853 2854 /** 2855 * Equivalent to {@link #valueOf(char[], int, int)}. 2856 * 2857 * @param data the character array. 2858 * @param offset initial offset of the subarray. 2859 * @param count length of the subarray. 2860 * @return a {@code String} that contains the characters of the 2861 * specified subarray of the character array. 2862 * @exception IndexOutOfBoundsException if {@code offset} is 2863 * negative, or {@code count} is negative, or 2864 * {@code offset+count} is larger than 2865 * {@code data.length}. 2866 */ 2867 public static String copyValueOf(char data[], int offset, int count) { 2868 return new String(data, offset, count); 2869 } 2870 2871 /** 2872 * Equivalent to {@link #valueOf(char[])}. 2873 * 2874 * @param data the character array. 2875 * @return a {@code String} that contains the characters of the 2876 * character array. 2877 */ 2878 public static String copyValueOf(char data[]) { 2879 return new String(data); 2880 } 2881 2882 /** 2883 * Returns the string representation of the {@code boolean} argument. 2884 * 2885 * @param b a {@code boolean}. 2886 * @return if the argument is {@code true}, a string equal to 2887 * {@code "true"} is returned; otherwise, a string equal to 2888 * {@code "false"} is returned. 2889 */ 2890 public static String valueOf(boolean b) { 2891 return b ? "true" : "false"; 2892 } 2893 2894 /** 2895 * Returns the string representation of the {@code char} 2896 * argument. 2897 * 2898 * @param c a {@code char}. 2899 * @return a string of length {@code 1} containing 2900 * as its single character the argument {@code c}. 2901 */ 2902 public static String valueOf(char c) { 2903 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) { 2904 return new String(StringLatin1.toBytes(c), LATIN1); 2905 } 2906 return new String(StringUTF16.toBytes(c), UTF16); 2907 } 2908 2909 /** 2910 * Returns the string representation of the {@code int} argument. 2911 * <p> 2912 * The representation is exactly the one returned by the 2913 * {@code Integer.toString} method of one argument. 2914 * 2915 * @param i an {@code int}. 2916 * @return a string representation of the {@code int} argument. 2917 * @see java.lang.Integer#toString(int, int) 2918 */ 2919 public static String valueOf(int i) { 2920 return Integer.toString(i); 2921 } 2922 2923 /** 2924 * Returns the string representation of the {@code long} argument. 2925 * <p> 2926 * The representation is exactly the one returned by the 2927 * {@code Long.toString} method of one argument. 2928 * 2929 * @param l a {@code long}. 2930 * @return a string representation of the {@code long} argument. 2931 * @see java.lang.Long#toString(long) 2932 */ 2933 public static String valueOf(long l) { 2934 return Long.toString(l); 2935 } 2936 2937 /** 2938 * Returns the string representation of the {@code float} argument. 2939 * <p> 2940 * The representation is exactly the one returned by the 2941 * {@code Float.toString} method of one argument. 2942 * 2943 * @param f a {@code float}. 2944 * @return a string representation of the {@code float} argument. 2945 * @see java.lang.Float#toString(float) 2946 */ 2947 public static String valueOf(float f) { 2948 return Float.toString(f); 2949 } 2950 2951 /** 2952 * Returns the string representation of the {@code double} argument. 2953 * <p> 2954 * The representation is exactly the one returned by the 2955 * {@code Double.toString} method of one argument. 2956 * 2957 * @param d a {@code double}. 2958 * @return a string representation of the {@code double} argument. 2959 * @see java.lang.Double#toString(double) 2960 */ 2961 public static String valueOf(double d) { 2962 return Double.toString(d); 2963 } 2964 2965 /** 2966 * Returns a canonical representation for the string object. 2967 * <p> 2968 * A pool of strings, initially empty, is maintained privately by the 2969 * class {@code String}. 2970 * <p> 2971 * When the intern method is invoked, if the pool already contains a 2972 * string equal to this {@code String} object as determined by 2973 * the {@link #equals(Object)} method, then the string from the pool is 2974 * returned. Otherwise, this {@code String} object is added to the 2975 * pool and a reference to this {@code String} object is returned. 2976 * <p> 2977 * It follows that for any two strings {@code s} and {@code t}, 2978 * {@code s.intern() == t.intern()} is {@code true} 2979 * if and only if {@code s.equals(t)} is {@code true}. 2980 * <p> 2981 * All literal strings and string-valued constant expressions are 2982 * interned. String literals are defined in section 3.10.5 of the 2983 * <cite>The Java™ Language Specification</cite>. 2984 * 2985 * @return a string that has the same contents as this string, but is 2986 * guaranteed to be from a pool of unique strings. 2987 * @jls 3.10.5 String Literals 2988 */ 2989 public native String intern(); 2990 2991 //////////////////////////////////////////////////////////////// 2992 2993 /** 2994 * Copy character bytes from this string into dst starting at dstBegin. 2995 * This method doesn't perform any range checking. 2996 * 2997 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two 2998 * coders are different, and dst is big enough (range check) 2999 * 3000 * @param dstBegin the char index, not offset of byte[] 3001 * @param coder the coder of dst[] 3002 */ 3003 void getBytes(byte dst[], int dstBegin, byte coder) { 3004 if (coder() == coder) { 3005 System.arraycopy(value, 0, dst, dstBegin << coder, value.length); 3006 } else { // this.coder == LATIN && coder == UTF16 3007 StringLatin1.inflate(value, 0, dst, dstBegin, value.length); 3008 } 3009 } 3010 3011 /* 3012 * Package private constructor. Trailing Void argument is there for 3013 * disambiguating it against other (public) constructors. 3014 * 3015 * Stores the char[] value into a byte[] that each byte represents 3016 * the8 low-order bits of the corresponding character, if the char[] 3017 * contains only latin1 character. Or a byte[] that stores all 3018 * characters in their byte sequences defined by the {@code StringUTF16}. 3019 */ 3020 String(char[] value, int off, int len, Void sig) { 3021 if (len == 0) { 3022 this.value = "".value; 3023 this.coder = "".coder; 3024 return; 3025 } 3026 if (COMPACT_STRINGS) { 3027 byte[] val = StringUTF16.compress(value, off, len); 3028 if (val != null) { 3029 this.value = val; 3030 this.coder = LATIN1; 3031 return; 3032 } 3033 } 3034 this.coder = UTF16; 3035 this.value = StringUTF16.toBytes(value, off, len); 3036 } 3037 3038 /* 3039 * Package private constructor. Trailing Void argument is there for 3040 * disambiguating it against other (public) constructors. 3041 */ 3042 String(AbstractStringBuilder asb, Void sig) { 3043 byte[] val = asb.getValue(); 3044 int length = asb.length(); 3045 if (asb.isLatin1()) { 3046 this.coder = LATIN1; 3047 this.value = Arrays.copyOfRange(val, 0, length); 3048 } else { 3049 if (COMPACT_STRINGS) { 3050 byte[] buf = StringUTF16.compress(val, 0, length); 3051 if (buf != null) { 3052 this.coder = LATIN1; 3053 this.value = buf; 3054 return; 3055 } 3056 } 3057 this.coder = UTF16; 3058 this.value = Arrays.copyOfRange(val, 0, length << 1); 3059 } 3060 } 3061 3062 /* 3063 * Package private constructor which shares value array for speed. 3064 */ 3065 String(byte[] value, byte coder) { 3066 this.value = value; 3067 this.coder = coder; 3068 } 3069 3070 byte coder() { 3071 return COMPACT_STRINGS ? coder : UTF16; 3072 } 3073 3074 private boolean isLatin1() { 3075 return COMPACT_STRINGS && coder == LATIN1; 3076 } 3077 3078 static final byte LATIN1 = 0; 3079 static final byte UTF16 = 1; 3080 3081 /* 3082 * StringIndexOutOfBoundsException if {@code index} is 3083 * negative or greater than or equal to {@code length}. 3084 */ 3085 static void checkIndex(int index, int length) { 3086 if (index < 0 || index >= length) { 3087 throw new StringIndexOutOfBoundsException("index " + index + 3088 ", length " + length); 3089 } 3090 } 3091 3092 /* 3093 * StringIndexOutOfBoundsException if {@code offset} 3094 * is negative or greater than {@code length}. 3095 */ 3096 static void checkOffset(int offset, int length) { 3097 if (offset < 0 || offset > length) { 3098 throw new StringIndexOutOfBoundsException("offset " + offset + 3099 ",length " + length); 3100 } 3101 } 3102 3103 /* 3104 * Check {@code offset}, {@code count} against {@code 0} and {@code length} 3105 * bounds. 3106 * 3107 * @throws StringIndexOutOfBoundsException 3108 * If {@code offset} is negative, {@code count} is negative, 3109 * or {@code offset} is greater than {@code length - count} 3110 */ 3111 static void checkBoundsOffCount(int offset, int count, int length) { 3112 if (offset < 0 || count < 0 || offset > length - count) { 3113 throw new StringIndexOutOfBoundsException( 3114 "offset " + offset + ", count " + count + ", length " + length); 3115 } 3116 } 3117 3118 /* 3119 * Check {@code begin}, {@code end} against {@code 0} and {@code length} 3120 * bounds. 3121 * 3122 * @throws StringIndexOutOfBoundsException 3123 * If {@code begin} is negative, {@code begin} is greater than 3124 * {@code end}, or {@code end} is greater than {@code length}. 3125 */ 3126 static void checkBoundsBeginEnd(int begin, int end, int length) { 3127 if (begin < 0 || begin > end || end > length) { 3128 throw new StringIndexOutOfBoundsException( 3129 "begin " + begin + ", end " + end + ", length " + length); 3130 } 3131 } 3132 }