1 /* 2 * Copyright (c) 1994, 2019, Oracle and/or its affiliates. All rights reserved. 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4 * 5 * This code is free software; you can redistribute it and/or modify it 6 * under the terms of the GNU General Public License version 2 only, as 7 * published by the Free Software Foundation. Oracle designates this 8 * particular file as subject to the "Classpath" exception as provided 9 * by Oracle in the LICENSE file that accompanied this code. 10 * 11 * This code is distributed in the hope that it will be useful, but WITHOUT 12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 14 * version 2 for more details (a copy is included in the LICENSE file that 15 * accompanied this code). 16 * 17 * You should have received a copy of the GNU General Public License version 18 * 2 along with this work; if not, write to the Free Software Foundation, 19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 20 * 21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 22 * or visit www.oracle.com if you need additional information or have any 23 * questions. 24 */ 25 26 package java.lang; 27 28 import java.io.ObjectStreamField; 29 import java.io.UnsupportedEncodingException; 30 import java.lang.annotation.Native; 31 import java.lang.invoke.MethodHandles; 32 import java.lang.constant.Constable; 33 import java.lang.constant.ConstantDesc; 34 import java.nio.charset.Charset; 35 import java.util.ArrayList; 36 import java.util.Arrays; 37 import java.util.Comparator; 38 import java.util.Formatter; 39 import java.util.Locale; 40 import java.util.Objects; 41 import java.util.Optional; 42 import java.util.Spliterator; 43 import java.util.StringJoiner; 44 import java.util.function.Function; 45 import java.util.regex.Matcher; 46 import java.util.regex.Pattern; 47 import java.util.regex.PatternSyntaxException; 48 import java.util.stream.Collectors; 49 import java.util.stream.IntStream; 50 import java.util.stream.Stream; 51 import java.util.stream.StreamSupport; 52 import jdk.internal.HotSpotIntrinsicCandidate; 53 import jdk.internal.vm.annotation.Stable; 54 55 import static java.util.function.Predicate.not; 56 57 /** 58 * The {@code String} class represents character strings. All 59 * string literals in Java programs, such as {@code "abc"}, are 60 * implemented as instances of this class. 61 * <p> 62 * Strings are constant; their values cannot be changed after they 63 * are created. String buffers support mutable strings. 64 * Because String objects are immutable they can be shared. For example: 65 * <blockquote><pre> 66 * String str = "abc"; 67 * </pre></blockquote><p> 68 * is equivalent to: 69 * <blockquote><pre> 70 * char data[] = {'a', 'b', 'c'}; 71 * String str = new String(data); 72 * </pre></blockquote><p> 73 * Here are some more examples of how strings can be used: 74 * <blockquote><pre> 75 * System.out.println("abc"); 76 * String cde = "cde"; 77 * System.out.println("abc" + cde); 78 * String c = "abc".substring(2,3); 79 * String d = cde.substring(1, 2); 80 * </pre></blockquote> 81 * <p> 82 * The class {@code String} includes methods for examining 83 * individual characters of the sequence, for comparing strings, for 84 * searching strings, for extracting substrings, and for creating a 85 * copy of a string with all characters translated to uppercase or to 86 * lowercase. Case mapping is based on the Unicode Standard version 87 * specified by the {@link java.lang.Character Character} class. 88 * <p> 89 * The Java language provides special support for the string 90 * concatenation operator ( + ), and for conversion of 91 * other objects to strings. For additional information on string 92 * concatenation and conversion, see <i>The Java™ Language Specification</i>. 93 * 94 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor 95 * or method in this class will cause a {@link NullPointerException} to be 96 * thrown. 97 * 98 * <p>A {@code String} represents a string in the UTF-16 format 99 * in which <em>supplementary characters</em> are represented by <em>surrogate 100 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 101 * Character Representations</a> in the {@code Character} class for 102 * more information). 103 * Index values refer to {@code char} code units, so a supplementary 104 * character uses two positions in a {@code String}. 105 * <p>The {@code String} class provides methods for dealing with 106 * Unicode code points (i.e., characters), in addition to those for 107 * dealing with Unicode code units (i.e., {@code char} values). 108 * 109 * <p>Unless otherwise noted, methods for comparing Strings do not take locale 110 * into account. The {@link java.text.Collator} class provides methods for 111 * finer-grain, locale-sensitive String comparison. 112 * 113 * @implNote The implementation of the string concatenation operator is left to 114 * the discretion of a Java compiler, as long as the compiler ultimately conforms 115 * to <i>The Java™ Language Specification</i>. For example, the {@code javac} compiler 116 * may implement the operator with {@code StringBuffer}, {@code StringBuilder}, 117 * or {@code java.lang.invoke.StringConcatFactory} depending on the JDK version. The 118 * implementation of string conversion is typically through the method {@code toString}, 119 * defined by {@code Object} and inherited by all classes in Java. 120 * 121 * @author Lee Boynton 122 * @author Arthur van Hoff 123 * @author Martin Buchholz 124 * @author Ulf Zibis 125 * @see java.lang.Object#toString() 126 * @see java.lang.StringBuffer 127 * @see java.lang.StringBuilder 128 * @see java.nio.charset.Charset 129 * @since 1.0 130 * @jls 15.18.1 String Concatenation Operator + 131 */ 132 133 public final class String 134 implements java.io.Serializable, Comparable<String>, CharSequence, 135 Constable, ConstantDesc { 136 137 /** 138 * The value is used for character storage. 139 * 140 * @implNote This field is trusted by the VM, and is a subject to 141 * constant folding if String instance is constant. Overwriting this 142 * field after construction will cause problems. 143 * 144 * Additionally, it is marked with {@link Stable} to trust the contents 145 * of the array. No other facility in JDK provides this functionality (yet). 146 * {@link Stable} is safe here, because value is never null. 147 */ 148 @Stable 149 private final byte[] value; 150 151 /** 152 * The identifier of the encoding used to encode the bytes in 153 * {@code value}. The supported values in this implementation are 154 * 155 * LATIN1 156 * UTF16 157 * 158 * @implNote This field is trusted by the VM, and is a subject to 159 * constant folding if String instance is constant. Overwriting this 160 * field after construction will cause problems. 161 */ 162 private final byte coder; 163 164 /** Cache the hash code for the string */ 165 private int hash; // Default to 0 166 167 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 168 private static final long serialVersionUID = -6849794470754667710L; 169 170 /** 171 * If String compaction is disabled, the bytes in {@code value} are 172 * always encoded in UTF16. 173 * 174 * For methods with several possible implementation paths, when String 175 * compaction is disabled, only one code path is taken. 176 * 177 * The instance field value is generally opaque to optimizing JIT 178 * compilers. Therefore, in performance-sensitive place, an explicit 179 * check of the static boolean {@code COMPACT_STRINGS} is done first 180 * before checking the {@code coder} field since the static boolean 181 * {@code COMPACT_STRINGS} would be constant folded away by an 182 * optimizing JIT compiler. The idioms for these cases are as follows. 183 * 184 * For code such as: 185 * 186 * if (coder == LATIN1) { ... } 187 * 188 * can be written more optimally as 189 * 190 * if (coder() == LATIN1) { ... } 191 * 192 * or: 193 * 194 * if (COMPACT_STRINGS && coder == LATIN1) { ... } 195 * 196 * An optimizing JIT compiler can fold the above conditional as: 197 * 198 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... } 199 * COMPACT_STRINGS == false => if (false) { ... } 200 * 201 * @implNote 202 * The actual value for this field is injected by JVM. The static 203 * initialization block is used to set the value here to communicate 204 * that this static final field is not statically foldable, and to 205 * avoid any possible circular dependency during vm initialization. 206 */ 207 static final boolean COMPACT_STRINGS; 208 209 static { 210 COMPACT_STRINGS = true; 211 } 212 213 /** 214 * Class String is special cased within the Serialization Stream Protocol. 215 * 216 * A String instance is written into an ObjectOutputStream according to 217 * <a href="{@docRoot}/../specs/serialization/protocol.html#stream-elements"> 218 * Object Serialization Specification, Section 6.2, "Stream Elements"</a> 219 */ 220 private static final ObjectStreamField[] serialPersistentFields = 221 new ObjectStreamField[0]; 222 223 /** 224 * Initializes a newly created {@code String} object so that it represents 225 * an empty character sequence. Note that use of this constructor is 226 * unnecessary since Strings are immutable. 227 */ 228 public String() { 229 this.value = "".value; 230 this.coder = "".coder; 231 } 232 233 /** 234 * Initializes a newly created {@code String} object so that it represents 235 * the same sequence of characters as the argument; in other words, the 236 * newly created string is a copy of the argument string. Unless an 237 * explicit copy of {@code original} is needed, use of this constructor is 238 * unnecessary since Strings are immutable. 239 * 240 * @param original 241 * A {@code String} 242 */ 243 @HotSpotIntrinsicCandidate 244 public String(String original) { 245 this.value = original.value; 246 this.coder = original.coder; 247 this.hash = original.hash; 248 } 249 250 /** 251 * Allocates a new {@code String} so that it represents the sequence of 252 * characters currently contained in the character array argument. The 253 * contents of the character array are copied; subsequent modification of 254 * the character array does not affect the newly created string. 255 * 256 * @param value 257 * The initial value of the string 258 */ 259 public String(char value[]) { 260 this(value, 0, value.length, null); 261 } 262 263 /** 264 * Allocates a new {@code String} that contains characters from a subarray 265 * of the character array argument. The {@code offset} argument is the 266 * index of the first character of the subarray and the {@code count} 267 * argument specifies the length of the subarray. The contents of the 268 * subarray are copied; subsequent modification of the character array does 269 * not affect the newly created string. 270 * 271 * @param value 272 * Array that is the source of characters 273 * 274 * @param offset 275 * The initial offset 276 * 277 * @param count 278 * The length 279 * 280 * @throws IndexOutOfBoundsException 281 * If {@code offset} is negative, {@code count} is negative, or 282 * {@code offset} is greater than {@code value.length - count} 283 */ 284 public String(char value[], int offset, int count) { 285 this(value, offset, count, rangeCheck(value, offset, count)); 286 } 287 288 private static Void rangeCheck(char[] value, int offset, int count) { 289 checkBoundsOffCount(offset, count, value.length); 290 return null; 291 } 292 293 /** 294 * Allocates a new {@code String} that contains characters from a subarray 295 * of the <a href="Character.html#unicode">Unicode code point</a> array 296 * argument. The {@code offset} argument is the index of the first code 297 * point of the subarray and the {@code count} argument specifies the 298 * length of the subarray. The contents of the subarray are converted to 299 * {@code char}s; subsequent modification of the {@code int} array does not 300 * affect the newly created string. 301 * 302 * @param codePoints 303 * Array that is the source of Unicode code points 304 * 305 * @param offset 306 * The initial offset 307 * 308 * @param count 309 * The length 310 * 311 * @throws IllegalArgumentException 312 * If any invalid Unicode code point is found in {@code 313 * codePoints} 314 * 315 * @throws IndexOutOfBoundsException 316 * If {@code offset} is negative, {@code count} is negative, or 317 * {@code offset} is greater than {@code codePoints.length - count} 318 * 319 * @since 1.5 320 */ 321 public String(int[] codePoints, int offset, int count) { 322 checkBoundsOffCount(offset, count, codePoints.length); 323 if (count == 0) { 324 this.value = "".value; 325 this.coder = "".coder; 326 return; 327 } 328 if (COMPACT_STRINGS) { 329 byte[] val = StringLatin1.toBytes(codePoints, offset, count); 330 if (val != null) { 331 this.coder = LATIN1; 332 this.value = val; 333 return; 334 } 335 } 336 this.coder = UTF16; 337 this.value = StringUTF16.toBytes(codePoints, offset, count); 338 } 339 340 /** 341 * Allocates a new {@code String} constructed from a subarray of an array 342 * of 8-bit integer values. 343 * 344 * <p> The {@code offset} argument is the index of the first byte of the 345 * subarray, and the {@code count} argument specifies the length of the 346 * subarray. 347 * 348 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 349 * specified in the {@link #String(byte[],int) String(byte[],int)} constructor. 350 * 351 * @deprecated This method does not properly convert bytes into characters. 352 * As of JDK 1.1, the preferred way to do this is via the 353 * {@code String} constructors that take a {@link 354 * java.nio.charset.Charset}, charset name, or that use the platform's 355 * default charset. 356 * 357 * @param ascii 358 * The bytes to be converted to characters 359 * 360 * @param hibyte 361 * The top 8 bits of each 16-bit Unicode code unit 362 * 363 * @param offset 364 * The initial offset 365 * @param count 366 * The length 367 * 368 * @throws IndexOutOfBoundsException 369 * If {@code offset} is negative, {@code count} is negative, or 370 * {@code offset} is greater than {@code ascii.length - count} 371 * 372 * @see #String(byte[], int) 373 * @see #String(byte[], int, int, java.lang.String) 374 * @see #String(byte[], int, int, java.nio.charset.Charset) 375 * @see #String(byte[], int, int) 376 * @see #String(byte[], java.lang.String) 377 * @see #String(byte[], java.nio.charset.Charset) 378 * @see #String(byte[]) 379 */ 380 @Deprecated(since="1.1") 381 public String(byte ascii[], int hibyte, int offset, int count) { 382 checkBoundsOffCount(offset, count, ascii.length); 383 if (count == 0) { 384 this.value = "".value; 385 this.coder = "".coder; 386 return; 387 } 388 if (COMPACT_STRINGS && (byte)hibyte == 0) { 389 this.value = Arrays.copyOfRange(ascii, offset, offset + count); 390 this.coder = LATIN1; 391 } else { 392 hibyte <<= 8; 393 byte[] val = StringUTF16.newBytesFor(count); 394 for (int i = 0; i < count; i++) { 395 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff)); 396 } 397 this.value = val; 398 this.coder = UTF16; 399 } 400 } 401 402 /** 403 * Allocates a new {@code String} containing characters constructed from 404 * an array of 8-bit integer values. Each character <i>c</i> in the 405 * resulting string is constructed from the corresponding component 406 * <i>b</i> in the byte array such that: 407 * 408 * <blockquote><pre> 409 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 410 * | (<b><i>b</i></b> & 0xff)) 411 * </pre></blockquote> 412 * 413 * @deprecated This method does not properly convert bytes into 414 * characters. As of JDK 1.1, the preferred way to do this is via the 415 * {@code String} constructors that take a {@link 416 * java.nio.charset.Charset}, charset name, or that use the platform's 417 * default charset. 418 * 419 * @param ascii 420 * The bytes to be converted to characters 421 * 422 * @param hibyte 423 * The top 8 bits of each 16-bit Unicode code unit 424 * 425 * @see #String(byte[], int, int, java.lang.String) 426 * @see #String(byte[], int, int, java.nio.charset.Charset) 427 * @see #String(byte[], int, int) 428 * @see #String(byte[], java.lang.String) 429 * @see #String(byte[], java.nio.charset.Charset) 430 * @see #String(byte[]) 431 */ 432 @Deprecated(since="1.1") 433 public String(byte ascii[], int hibyte) { 434 this(ascii, hibyte, 0, ascii.length); 435 } 436 437 /** 438 * Constructs a new {@code String} by decoding the specified subarray of 439 * bytes using the specified charset. The length of the new {@code String} 440 * is a function of the charset, and hence may not be equal to the length 441 * of the subarray. 442 * 443 * <p> The behavior of this constructor when the given bytes are not valid 444 * in the given charset is unspecified. The {@link 445 * java.nio.charset.CharsetDecoder} class should be used when more control 446 * over the decoding process is required. 447 * 448 * @param bytes 449 * The bytes to be decoded into characters 450 * 451 * @param offset 452 * The index of the first byte to decode 453 * 454 * @param length 455 * The number of bytes to decode 456 457 * @param charsetName 458 * The name of a supported {@linkplain java.nio.charset.Charset 459 * charset} 460 * 461 * @throws UnsupportedEncodingException 462 * If the named charset is not supported 463 * 464 * @throws IndexOutOfBoundsException 465 * If {@code offset} is negative, {@code length} is negative, or 466 * {@code offset} is greater than {@code bytes.length - length} 467 * 468 * @since 1.1 469 */ 470 public String(byte bytes[], int offset, int length, String charsetName) 471 throws UnsupportedEncodingException { 472 if (charsetName == null) 473 throw new NullPointerException("charsetName"); 474 checkBoundsOffCount(offset, length, bytes.length); 475 StringCoding.Result ret = 476 StringCoding.decode(charsetName, bytes, offset, length); 477 this.value = ret.value; 478 this.coder = ret.coder; 479 } 480 481 /** 482 * Constructs a new {@code String} by decoding the specified subarray of 483 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 484 * The length of the new {@code String} is a function of the charset, and 485 * hence may not be equal to the length of the subarray. 486 * 487 * <p> This method always replaces malformed-input and unmappable-character 488 * sequences with this charset's default replacement string. The {@link 489 * java.nio.charset.CharsetDecoder} class should be used when more control 490 * over the decoding process is required. 491 * 492 * @param bytes 493 * The bytes to be decoded into characters 494 * 495 * @param offset 496 * The index of the first byte to decode 497 * 498 * @param length 499 * The number of bytes to decode 500 * 501 * @param charset 502 * The {@linkplain java.nio.charset.Charset charset} to be used to 503 * decode the {@code bytes} 504 * 505 * @throws IndexOutOfBoundsException 506 * If {@code offset} is negative, {@code length} is negative, or 507 * {@code offset} is greater than {@code bytes.length - length} 508 * 509 * @since 1.6 510 */ 511 public String(byte bytes[], int offset, int length, Charset charset) { 512 if (charset == null) 513 throw new NullPointerException("charset"); 514 checkBoundsOffCount(offset, length, bytes.length); 515 StringCoding.Result ret = 516 StringCoding.decode(charset, bytes, offset, length); 517 this.value = ret.value; 518 this.coder = ret.coder; 519 } 520 521 /** 522 * Constructs a new {@code String} by decoding the specified array of bytes 523 * using the specified {@linkplain java.nio.charset.Charset charset}. The 524 * length of the new {@code String} is a function of the charset, and hence 525 * may not be equal to the length of the byte array. 526 * 527 * <p> The behavior of this constructor when the given bytes are not valid 528 * in the given charset is unspecified. The {@link 529 * java.nio.charset.CharsetDecoder} class should be used when more control 530 * over the decoding process is required. 531 * 532 * @param bytes 533 * The bytes to be decoded into characters 534 * 535 * @param charsetName 536 * The name of a supported {@linkplain java.nio.charset.Charset 537 * charset} 538 * 539 * @throws UnsupportedEncodingException 540 * If the named charset is not supported 541 * 542 * @since 1.1 543 */ 544 public String(byte bytes[], String charsetName) 545 throws UnsupportedEncodingException { 546 this(bytes, 0, bytes.length, charsetName); 547 } 548 549 /** 550 * Constructs a new {@code String} by decoding the specified array of 551 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 552 * The length of the new {@code String} is a function of the charset, and 553 * hence may not be equal to the length of the byte array. 554 * 555 * <p> This method always replaces malformed-input and unmappable-character 556 * sequences with this charset's default replacement string. The {@link 557 * java.nio.charset.CharsetDecoder} class should be used when more control 558 * over the decoding process is required. 559 * 560 * @param bytes 561 * The bytes to be decoded into characters 562 * 563 * @param charset 564 * The {@linkplain java.nio.charset.Charset charset} to be used to 565 * decode the {@code bytes} 566 * 567 * @since 1.6 568 */ 569 public String(byte bytes[], Charset charset) { 570 this(bytes, 0, bytes.length, charset); 571 } 572 573 /** 574 * Constructs a new {@code String} by decoding the specified subarray of 575 * bytes using the platform's default charset. The length of the new 576 * {@code String} is a function of the charset, and hence may not be equal 577 * to the length of the subarray. 578 * 579 * <p> The behavior of this constructor when the given bytes are not valid 580 * in the default charset is unspecified. The {@link 581 * java.nio.charset.CharsetDecoder} class should be used when more control 582 * over the decoding process is required. 583 * 584 * @param bytes 585 * The bytes to be decoded into characters 586 * 587 * @param offset 588 * The index of the first byte to decode 589 * 590 * @param length 591 * The number of bytes to decode 592 * 593 * @throws IndexOutOfBoundsException 594 * If {@code offset} is negative, {@code length} is negative, or 595 * {@code offset} is greater than {@code bytes.length - length} 596 * 597 * @since 1.1 598 */ 599 public String(byte bytes[], int offset, int length) { 600 checkBoundsOffCount(offset, length, bytes.length); 601 StringCoding.Result ret = StringCoding.decode(bytes, offset, length); 602 this.value = ret.value; 603 this.coder = ret.coder; 604 } 605 606 /** 607 * Constructs a new {@code String} by decoding the specified array of bytes 608 * using the platform's default charset. The length of the new {@code 609 * String} is a function of the charset, and hence may not be equal to the 610 * length of the byte array. 611 * 612 * <p> The behavior of this constructor when the given bytes are not valid 613 * in the default charset is unspecified. The {@link 614 * java.nio.charset.CharsetDecoder} class should be used when more control 615 * over the decoding process is required. 616 * 617 * @param bytes 618 * The bytes to be decoded into characters 619 * 620 * @since 1.1 621 */ 622 public String(byte[] bytes) { 623 this(bytes, 0, bytes.length); 624 } 625 626 /** 627 * Allocates a new string that contains the sequence of characters 628 * currently contained in the string buffer argument. The contents of the 629 * string buffer are copied; subsequent modification of the string buffer 630 * does not affect the newly created string. 631 * 632 * @param buffer 633 * A {@code StringBuffer} 634 */ 635 public String(StringBuffer buffer) { 636 this(buffer.toString()); 637 } 638 639 /** 640 * Allocates a new string that contains the sequence of characters 641 * currently contained in the string builder argument. The contents of the 642 * string builder are copied; subsequent modification of the string builder 643 * does not affect the newly created string. 644 * 645 * <p> This constructor is provided to ease migration to {@code 646 * StringBuilder}. Obtaining a string from a string builder via the {@code 647 * toString} method is likely to run faster and is generally preferred. 648 * 649 * @param builder 650 * A {@code StringBuilder} 651 * 652 * @since 1.5 653 */ 654 public String(StringBuilder builder) { 655 this(builder, null); 656 } 657 658 /** 659 * Returns the length of this string. 660 * The length is equal to the number of <a href="Character.html#unicode">Unicode 661 * code units</a> in the string. 662 * 663 * @return the length of the sequence of characters represented by this 664 * object. 665 */ 666 public int length() { 667 return value.length >> coder(); 668 } 669 670 /** 671 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 672 * 673 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 674 * {@code false} 675 * 676 * @since 1.6 677 */ 678 public boolean isEmpty() { 679 return value.length == 0; 680 } 681 682 /** 683 * Returns the {@code char} value at the 684 * specified index. An index ranges from {@code 0} to 685 * {@code length() - 1}. The first {@code char} value of the sequence 686 * is at index {@code 0}, the next at index {@code 1}, 687 * and so on, as for array indexing. 688 * 689 * <p>If the {@code char} value specified by the index is a 690 * <a href="Character.html#unicode">surrogate</a>, the surrogate 691 * value is returned. 692 * 693 * @param index the index of the {@code char} value. 694 * @return the {@code char} value at the specified index of this string. 695 * The first {@code char} value is at index {@code 0}. 696 * @exception IndexOutOfBoundsException if the {@code index} 697 * argument is negative or not less than the length of this 698 * string. 699 */ 700 public char charAt(int index) { 701 if (isLatin1()) { 702 return StringLatin1.charAt(value, index); 703 } else { 704 return StringUTF16.charAt(value, index); 705 } 706 } 707 708 /** 709 * Returns the character (Unicode code point) at the specified 710 * index. The index refers to {@code char} values 711 * (Unicode code units) and ranges from {@code 0} to 712 * {@link #length()}{@code - 1}. 713 * 714 * <p> If the {@code char} value specified at the given index 715 * is in the high-surrogate range, the following index is less 716 * than the length of this {@code String}, and the 717 * {@code char} value at the following index is in the 718 * low-surrogate range, then the supplementary code point 719 * corresponding to this surrogate pair is returned. Otherwise, 720 * the {@code char} value at the given index is returned. 721 * 722 * @param index the index to the {@code char} values 723 * @return the code point value of the character at the 724 * {@code index} 725 * @exception IndexOutOfBoundsException if the {@code index} 726 * argument is negative or not less than the length of this 727 * string. 728 * @since 1.5 729 */ 730 public int codePointAt(int index) { 731 if (isLatin1()) { 732 checkIndex(index, value.length); 733 return value[index] & 0xff; 734 } 735 int length = value.length >> 1; 736 checkIndex(index, length); 737 return StringUTF16.codePointAt(value, index, length); 738 } 739 740 /** 741 * Returns the character (Unicode code point) before the specified 742 * index. The index refers to {@code char} values 743 * (Unicode code units) and ranges from {@code 1} to {@link 744 * CharSequence#length() length}. 745 * 746 * <p> If the {@code char} value at {@code (index - 1)} 747 * is in the low-surrogate range, {@code (index - 2)} is not 748 * negative, and the {@code char} value at {@code (index - 749 * 2)} is in the high-surrogate range, then the 750 * supplementary code point value of the surrogate pair is 751 * returned. If the {@code char} value at {@code index - 752 * 1} is an unpaired low-surrogate or a high-surrogate, the 753 * surrogate value is returned. 754 * 755 * @param index the index following the code point that should be returned 756 * @return the Unicode code point value before the given index. 757 * @exception IndexOutOfBoundsException if the {@code index} 758 * argument is less than 1 or greater than the length 759 * of this string. 760 * @since 1.5 761 */ 762 public int codePointBefore(int index) { 763 int i = index - 1; 764 if (i < 0 || i >= length()) { 765 throw new StringIndexOutOfBoundsException(index); 766 } 767 if (isLatin1()) { 768 return (value[i] & 0xff); 769 } 770 return StringUTF16.codePointBefore(value, index); 771 } 772 773 /** 774 * Returns the number of Unicode code points in the specified text 775 * range of this {@code String}. The text range begins at the 776 * specified {@code beginIndex} and extends to the 777 * {@code char} at index {@code endIndex - 1}. Thus the 778 * length (in {@code char}s) of the text range is 779 * {@code endIndex-beginIndex}. Unpaired surrogates within 780 * the text range count as one code point each. 781 * 782 * @param beginIndex the index to the first {@code char} of 783 * the text range. 784 * @param endIndex the index after the last {@code char} of 785 * the text range. 786 * @return the number of Unicode code points in the specified text 787 * range 788 * @exception IndexOutOfBoundsException if the 789 * {@code beginIndex} is negative, or {@code endIndex} 790 * is larger than the length of this {@code String}, or 791 * {@code beginIndex} is larger than {@code endIndex}. 792 * @since 1.5 793 */ 794 public int codePointCount(int beginIndex, int endIndex) { 795 if (beginIndex < 0 || beginIndex > endIndex || 796 endIndex > length()) { 797 throw new IndexOutOfBoundsException(); 798 } 799 if (isLatin1()) { 800 return endIndex - beginIndex; 801 } 802 return StringUTF16.codePointCount(value, beginIndex, endIndex); 803 } 804 805 /** 806 * Returns the index within this {@code String} that is 807 * offset from the given {@code index} by 808 * {@code codePointOffset} code points. Unpaired surrogates 809 * within the text range given by {@code index} and 810 * {@code codePointOffset} count as one code point each. 811 * 812 * @param index the index to be offset 813 * @param codePointOffset the offset in code points 814 * @return the index within this {@code String} 815 * @exception IndexOutOfBoundsException if {@code index} 816 * is negative or larger then the length of this 817 * {@code String}, or if {@code codePointOffset} is positive 818 * and the substring starting with {@code index} has fewer 819 * than {@code codePointOffset} code points, 820 * or if {@code codePointOffset} is negative and the substring 821 * before {@code index} has fewer than the absolute value 822 * of {@code codePointOffset} code points. 823 * @since 1.5 824 */ 825 public int offsetByCodePoints(int index, int codePointOffset) { 826 if (index < 0 || index > length()) { 827 throw new IndexOutOfBoundsException(); 828 } 829 return Character.offsetByCodePoints(this, index, codePointOffset); 830 } 831 832 /** 833 * Copies characters from this string into the destination character 834 * array. 835 * <p> 836 * The first character to be copied is at index {@code srcBegin}; 837 * the last character to be copied is at index {@code srcEnd-1} 838 * (thus the total number of characters to be copied is 839 * {@code srcEnd-srcBegin}). The characters are copied into the 840 * subarray of {@code dst} starting at index {@code dstBegin} 841 * and ending at index: 842 * <blockquote><pre> 843 * dstBegin + (srcEnd-srcBegin) - 1 844 * </pre></blockquote> 845 * 846 * @param srcBegin index of the first character in the string 847 * to copy. 848 * @param srcEnd index after the last character in the string 849 * to copy. 850 * @param dst the destination array. 851 * @param dstBegin the start offset in the destination array. 852 * @exception IndexOutOfBoundsException If any of the following 853 * is true: 854 * <ul><li>{@code srcBegin} is negative. 855 * <li>{@code srcBegin} is greater than {@code srcEnd} 856 * <li>{@code srcEnd} is greater than the length of this 857 * string 858 * <li>{@code dstBegin} is negative 859 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 860 * {@code dst.length}</ul> 861 */ 862 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 863 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 864 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 865 if (isLatin1()) { 866 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin); 867 } else { 868 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin); 869 } 870 } 871 872 /** 873 * Copies characters from this string into the destination byte array. Each 874 * byte receives the 8 low-order bits of the corresponding character. The 875 * eight high-order bits of each character are not copied and do not 876 * participate in the transfer in any way. 877 * 878 * <p> The first character to be copied is at index {@code srcBegin}; the 879 * last character to be copied is at index {@code srcEnd-1}. The total 880 * number of characters to be copied is {@code srcEnd-srcBegin}. The 881 * characters, converted to bytes, are copied into the subarray of {@code 882 * dst} starting at index {@code dstBegin} and ending at index: 883 * 884 * <blockquote><pre> 885 * dstBegin + (srcEnd-srcBegin) - 1 886 * </pre></blockquote> 887 * 888 * @deprecated This method does not properly convert characters into 889 * bytes. As of JDK 1.1, the preferred way to do this is via the 890 * {@link #getBytes()} method, which uses the platform's default charset. 891 * 892 * @param srcBegin 893 * Index of the first character in the string to copy 894 * 895 * @param srcEnd 896 * Index after the last character in the string to copy 897 * 898 * @param dst 899 * The destination array 900 * 901 * @param dstBegin 902 * The start offset in the destination array 903 * 904 * @throws IndexOutOfBoundsException 905 * If any of the following is true: 906 * <ul> 907 * <li> {@code srcBegin} is negative 908 * <li> {@code srcBegin} is greater than {@code srcEnd} 909 * <li> {@code srcEnd} is greater than the length of this String 910 * <li> {@code dstBegin} is negative 911 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 912 * dst.length} 913 * </ul> 914 */ 915 @Deprecated(since="1.1") 916 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 917 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 918 Objects.requireNonNull(dst); 919 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 920 if (isLatin1()) { 921 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 922 } else { 923 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 924 } 925 } 926 927 /** 928 * Encodes this {@code String} into a sequence of bytes using the named 929 * charset, storing the result into a new byte array. 930 * 931 * <p> The behavior of this method when this string cannot be encoded in 932 * the given charset is unspecified. The {@link 933 * java.nio.charset.CharsetEncoder} class should be used when more control 934 * over the encoding process is required. 935 * 936 * @param charsetName 937 * The name of a supported {@linkplain java.nio.charset.Charset 938 * charset} 939 * 940 * @return The resultant byte array 941 * 942 * @throws UnsupportedEncodingException 943 * If the named charset is not supported 944 * 945 * @since 1.1 946 */ 947 public byte[] getBytes(String charsetName) 948 throws UnsupportedEncodingException { 949 if (charsetName == null) throw new NullPointerException(); 950 return StringCoding.encode(charsetName, coder(), value); 951 } 952 953 /** 954 * Encodes this {@code String} into a sequence of bytes using the given 955 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 956 * new byte array. 957 * 958 * <p> This method always replaces malformed-input and unmappable-character 959 * sequences with this charset's default replacement byte array. The 960 * {@link java.nio.charset.CharsetEncoder} class should be used when more 961 * control over the encoding process is required. 962 * 963 * @param charset 964 * The {@linkplain java.nio.charset.Charset} to be used to encode 965 * the {@code String} 966 * 967 * @return The resultant byte array 968 * 969 * @since 1.6 970 */ 971 public byte[] getBytes(Charset charset) { 972 if (charset == null) throw new NullPointerException(); 973 return StringCoding.encode(charset, coder(), value); 974 } 975 976 /** 977 * Encodes this {@code String} into a sequence of bytes using the 978 * platform's default charset, storing the result into a new byte array. 979 * 980 * <p> The behavior of this method when this string cannot be encoded in 981 * the default charset is unspecified. The {@link 982 * java.nio.charset.CharsetEncoder} class should be used when more control 983 * over the encoding process is required. 984 * 985 * @return The resultant byte array 986 * 987 * @since 1.1 988 */ 989 public byte[] getBytes() { 990 return StringCoding.encode(coder(), value); 991 } 992 993 /** 994 * Compares this string to the specified object. The result is {@code 995 * true} if and only if the argument is not {@code null} and is a {@code 996 * String} object that represents the same sequence of characters as this 997 * object. 998 * 999 * <p>For finer-grained String comparison, refer to 1000 * {@link java.text.Collator}. 1001 * 1002 * @param anObject 1003 * The object to compare this {@code String} against 1004 * 1005 * @return {@code true} if the given object represents a {@code String} 1006 * equivalent to this string, {@code false} otherwise 1007 * 1008 * @see #compareTo(String) 1009 * @see #equalsIgnoreCase(String) 1010 */ 1011 public boolean equals(Object anObject) { 1012 if (this == anObject) { 1013 return true; 1014 } 1015 if (anObject instanceof String) { 1016 String aString = (String)anObject; 1017 if (coder() == aString.coder()) { 1018 return isLatin1() ? StringLatin1.equals(value, aString.value) 1019 : StringUTF16.equals(value, aString.value); 1020 } 1021 } 1022 return false; 1023 } 1024 1025 /** 1026 * Compares this string to the specified {@code StringBuffer}. The result 1027 * is {@code true} if and only if this {@code String} represents the same 1028 * sequence of characters as the specified {@code StringBuffer}. This method 1029 * synchronizes on the {@code StringBuffer}. 1030 * 1031 * <p>For finer-grained String comparison, refer to 1032 * {@link java.text.Collator}. 1033 * 1034 * @param sb 1035 * The {@code StringBuffer} to compare this {@code String} against 1036 * 1037 * @return {@code true} if this {@code String} represents the same 1038 * sequence of characters as the specified {@code StringBuffer}, 1039 * {@code false} otherwise 1040 * 1041 * @since 1.4 1042 */ 1043 public boolean contentEquals(StringBuffer sb) { 1044 return contentEquals((CharSequence)sb); 1045 } 1046 1047 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1048 int len = length(); 1049 if (len != sb.length()) { 1050 return false; 1051 } 1052 byte v1[] = value; 1053 byte v2[] = sb.getValue(); 1054 if (coder() == sb.getCoder()) { 1055 int n = v1.length; 1056 for (int i = 0; i < n; i++) { 1057 if (v1[i] != v2[i]) { 1058 return false; 1059 } 1060 } 1061 } else { 1062 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal" 1063 return false; 1064 } 1065 return StringUTF16.contentEquals(v1, v2, len); 1066 } 1067 return true; 1068 } 1069 1070 /** 1071 * Compares this string to the specified {@code CharSequence}. The 1072 * result is {@code true} if and only if this {@code String} represents the 1073 * same sequence of char values as the specified sequence. Note that if the 1074 * {@code CharSequence} is a {@code StringBuffer} then the method 1075 * synchronizes on it. 1076 * 1077 * <p>For finer-grained String comparison, refer to 1078 * {@link java.text.Collator}. 1079 * 1080 * @param cs 1081 * The sequence to compare this {@code String} against 1082 * 1083 * @return {@code true} if this {@code String} represents the same 1084 * sequence of char values as the specified sequence, {@code 1085 * false} otherwise 1086 * 1087 * @since 1.5 1088 */ 1089 public boolean contentEquals(CharSequence cs) { 1090 // Argument is a StringBuffer, StringBuilder 1091 if (cs instanceof AbstractStringBuilder) { 1092 if (cs instanceof StringBuffer) { 1093 synchronized(cs) { 1094 return nonSyncContentEquals((AbstractStringBuilder)cs); 1095 } 1096 } else { 1097 return nonSyncContentEquals((AbstractStringBuilder)cs); 1098 } 1099 } 1100 // Argument is a String 1101 if (cs instanceof String) { 1102 return equals(cs); 1103 } 1104 // Argument is a generic CharSequence 1105 int n = cs.length(); 1106 if (n != length()) { 1107 return false; 1108 } 1109 byte[] val = this.value; 1110 if (isLatin1()) { 1111 for (int i = 0; i < n; i++) { 1112 if ((val[i] & 0xff) != cs.charAt(i)) { 1113 return false; 1114 } 1115 } 1116 } else { 1117 if (!StringUTF16.contentEquals(val, cs, n)) { 1118 return false; 1119 } 1120 } 1121 return true; 1122 } 1123 1124 /** 1125 * Compares this {@code String} to another {@code String}, ignoring case 1126 * considerations. Two strings are considered equal ignoring case if they 1127 * are of the same length and corresponding characters in the two strings 1128 * are equal ignoring case. 1129 * 1130 * <p> Two characters {@code c1} and {@code c2} are considered the same 1131 * ignoring case if at least one of the following is true: 1132 * <ul> 1133 * <li> The two characters are the same (as compared by the 1134 * {@code ==} operator) 1135 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))} 1136 * on each character produces the same result 1137 * </ul> 1138 * 1139 * <p>Note that this method does <em>not</em> take locale into account, and 1140 * will result in unsatisfactory results for certain locales. The 1141 * {@link java.text.Collator} class provides locale-sensitive comparison. 1142 * 1143 * @param anotherString 1144 * The {@code String} to compare this {@code String} against 1145 * 1146 * @return {@code true} if the argument is not {@code null} and it 1147 * represents an equivalent {@code String} ignoring case; {@code 1148 * false} otherwise 1149 * 1150 * @see #equals(Object) 1151 */ 1152 public boolean equalsIgnoreCase(String anotherString) { 1153 return (this == anotherString) ? true 1154 : (anotherString != null) 1155 && (anotherString.length() == length()) 1156 && regionMatches(true, 0, anotherString, 0, length()); 1157 } 1158 1159 /** 1160 * Compares two strings lexicographically. 1161 * The comparison is based on the Unicode value of each character in 1162 * the strings. The character sequence represented by this 1163 * {@code String} object is compared lexicographically to the 1164 * character sequence represented by the argument string. The result is 1165 * a negative integer if this {@code String} object 1166 * lexicographically precedes the argument string. The result is a 1167 * positive integer if this {@code String} object lexicographically 1168 * follows the argument string. The result is zero if the strings 1169 * are equal; {@code compareTo} returns {@code 0} exactly when 1170 * the {@link #equals(Object)} method would return {@code true}. 1171 * <p> 1172 * This is the definition of lexicographic ordering. If two strings are 1173 * different, then either they have different characters at some index 1174 * that is a valid index for both strings, or their lengths are different, 1175 * or both. If they have different characters at one or more index 1176 * positions, let <i>k</i> be the smallest such index; then the string 1177 * whose character at position <i>k</i> has the smaller value, as 1178 * determined by using the {@code <} operator, lexicographically precedes the 1179 * other string. In this case, {@code compareTo} returns the 1180 * difference of the two character values at position {@code k} in 1181 * the two string -- that is, the value: 1182 * <blockquote><pre> 1183 * this.charAt(k)-anotherString.charAt(k) 1184 * </pre></blockquote> 1185 * If there is no index position at which they differ, then the shorter 1186 * string lexicographically precedes the longer string. In this case, 1187 * {@code compareTo} returns the difference of the lengths of the 1188 * strings -- that is, the value: 1189 * <blockquote><pre> 1190 * this.length()-anotherString.length() 1191 * </pre></blockquote> 1192 * 1193 * <p>For finer-grained String comparison, refer to 1194 * {@link java.text.Collator}. 1195 * 1196 * @param anotherString the {@code String} to be compared. 1197 * @return the value {@code 0} if the argument string is equal to 1198 * this string; a value less than {@code 0} if this string 1199 * is lexicographically less than the string argument; and a 1200 * value greater than {@code 0} if this string is 1201 * lexicographically greater than the string argument. 1202 */ 1203 public int compareTo(String anotherString) { 1204 byte v1[] = value; 1205 byte v2[] = anotherString.value; 1206 if (coder() == anotherString.coder()) { 1207 return isLatin1() ? StringLatin1.compareTo(v1, v2) 1208 : StringUTF16.compareTo(v1, v2); 1209 } 1210 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2) 1211 : StringUTF16.compareToLatin1(v1, v2); 1212 } 1213 1214 /** 1215 * A Comparator that orders {@code String} objects as by 1216 * {@code compareToIgnoreCase}. This comparator is serializable. 1217 * <p> 1218 * Note that this Comparator does <em>not</em> take locale into account, 1219 * and will result in an unsatisfactory ordering for certain locales. 1220 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1221 * 1222 * @see java.text.Collator 1223 * @since 1.2 1224 */ 1225 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1226 = new CaseInsensitiveComparator(); 1227 private static class CaseInsensitiveComparator 1228 implements Comparator<String>, java.io.Serializable { 1229 // use serialVersionUID from JDK 1.2.2 for interoperability 1230 private static final long serialVersionUID = 8575799808933029326L; 1231 1232 public int compare(String s1, String s2) { 1233 byte v1[] = s1.value; 1234 byte v2[] = s2.value; 1235 if (s1.coder() == s2.coder()) { 1236 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2) 1237 : StringUTF16.compareToCI(v1, v2); 1238 } 1239 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2) 1240 : StringUTF16.compareToCI_Latin1(v1, v2); 1241 } 1242 1243 /** Replaces the de-serialized object. */ 1244 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1245 } 1246 1247 /** 1248 * Compares two strings lexicographically, ignoring case 1249 * differences. This method returns an integer whose sign is that of 1250 * calling {@code compareTo} with normalized versions of the strings 1251 * where case differences have been eliminated by calling 1252 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1253 * each character. 1254 * <p> 1255 * Note that this method does <em>not</em> take locale into account, 1256 * and will result in an unsatisfactory ordering for certain locales. 1257 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1258 * 1259 * @param str the {@code String} to be compared. 1260 * @return a negative integer, zero, or a positive integer as the 1261 * specified String is greater than, equal to, or less 1262 * than this String, ignoring case considerations. 1263 * @see java.text.Collator 1264 * @since 1.2 1265 */ 1266 public int compareToIgnoreCase(String str) { 1267 return CASE_INSENSITIVE_ORDER.compare(this, str); 1268 } 1269 1270 /** 1271 * Tests if two string regions are equal. 1272 * <p> 1273 * A substring of this {@code String} object is compared to a substring 1274 * of the argument other. The result is true if these substrings 1275 * represent identical character sequences. The substring of this 1276 * {@code String} object to be compared begins at index {@code toffset} 1277 * and has length {@code len}. The substring of other to be compared 1278 * begins at index {@code ooffset} and has length {@code len}. The 1279 * result is {@code false} if and only if at least one of the following 1280 * is true: 1281 * <ul><li>{@code toffset} is negative. 1282 * <li>{@code ooffset} is negative. 1283 * <li>{@code toffset+len} is greater than the length of this 1284 * {@code String} object. 1285 * <li>{@code ooffset+len} is greater than the length of the other 1286 * argument. 1287 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1288 * such that: 1289 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1290 * <i>k</i>{@code )} 1291 * </ul> 1292 * 1293 * <p>Note that this method does <em>not</em> take locale into account. The 1294 * {@link java.text.Collator} class provides locale-sensitive comparison. 1295 * 1296 * @param toffset the starting offset of the subregion in this string. 1297 * @param other the string argument. 1298 * @param ooffset the starting offset of the subregion in the string 1299 * argument. 1300 * @param len the number of characters to compare. 1301 * @return {@code true} if the specified subregion of this string 1302 * exactly matches the specified subregion of the string argument; 1303 * {@code false} otherwise. 1304 */ 1305 public boolean regionMatches(int toffset, String other, int ooffset, int len) { 1306 byte tv[] = value; 1307 byte ov[] = other.value; 1308 // Note: toffset, ooffset, or len might be near -1>>>1. 1309 if ((ooffset < 0) || (toffset < 0) || 1310 (toffset > (long)length() - len) || 1311 (ooffset > (long)other.length() - len)) { 1312 return false; 1313 } 1314 if (coder() == other.coder()) { 1315 if (!isLatin1() && (len > 0)) { 1316 toffset = toffset << 1; 1317 ooffset = ooffset << 1; 1318 len = len << 1; 1319 } 1320 while (len-- > 0) { 1321 if (tv[toffset++] != ov[ooffset++]) { 1322 return false; 1323 } 1324 } 1325 } else { 1326 if (coder() == LATIN1) { 1327 while (len-- > 0) { 1328 if (StringLatin1.getChar(tv, toffset++) != 1329 StringUTF16.getChar(ov, ooffset++)) { 1330 return false; 1331 } 1332 } 1333 } else { 1334 while (len-- > 0) { 1335 if (StringUTF16.getChar(tv, toffset++) != 1336 StringLatin1.getChar(ov, ooffset++)) { 1337 return false; 1338 } 1339 } 1340 } 1341 } 1342 return true; 1343 } 1344 1345 /** 1346 * Tests if two string regions are equal. 1347 * <p> 1348 * A substring of this {@code String} object is compared to a substring 1349 * of the argument {@code other}. The result is {@code true} if these 1350 * substrings represent character sequences that are the same, ignoring 1351 * case if and only if {@code ignoreCase} is true. The substring of 1352 * this {@code String} object to be compared begins at index 1353 * {@code toffset} and has length {@code len}. The substring of 1354 * {@code other} to be compared begins at index {@code ooffset} and 1355 * has length {@code len}. The result is {@code false} if and only if 1356 * at least one of the following is true: 1357 * <ul><li>{@code toffset} is negative. 1358 * <li>{@code ooffset} is negative. 1359 * <li>{@code toffset+len} is greater than the length of this 1360 * {@code String} object. 1361 * <li>{@code ooffset+len} is greater than the length of the other 1362 * argument. 1363 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1364 * integer <i>k</i> less than {@code len} such that: 1365 * <blockquote><pre> 1366 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1367 * </pre></blockquote> 1368 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1369 * integer <i>k</i> less than {@code len} such that: 1370 * <blockquote><pre> 1371 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) != 1372 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k))) 1373 * </pre></blockquote> 1374 * </ul> 1375 * 1376 * <p>Note that this method does <em>not</em> take locale into account, 1377 * and will result in unsatisfactory results for certain locales when 1378 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class 1379 * provides locale-sensitive comparison. 1380 * 1381 * @param ignoreCase if {@code true}, ignore case when comparing 1382 * characters. 1383 * @param toffset the starting offset of the subregion in this 1384 * string. 1385 * @param other the string argument. 1386 * @param ooffset the starting offset of the subregion in the string 1387 * argument. 1388 * @param len the number of characters to compare. 1389 * @return {@code true} if the specified subregion of this string 1390 * matches the specified subregion of the string argument; 1391 * {@code false} otherwise. Whether the matching is exact 1392 * or case insensitive depends on the {@code ignoreCase} 1393 * argument. 1394 */ 1395 public boolean regionMatches(boolean ignoreCase, int toffset, 1396 String other, int ooffset, int len) { 1397 if (!ignoreCase) { 1398 return regionMatches(toffset, other, ooffset, len); 1399 } 1400 // Note: toffset, ooffset, or len might be near -1>>>1. 1401 if ((ooffset < 0) || (toffset < 0) 1402 || (toffset > (long)length() - len) 1403 || (ooffset > (long)other.length() - len)) { 1404 return false; 1405 } 1406 byte tv[] = value; 1407 byte ov[] = other.value; 1408 if (coder() == other.coder()) { 1409 return isLatin1() 1410 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len) 1411 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len); 1412 } 1413 return isLatin1() 1414 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len) 1415 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len); 1416 } 1417 1418 /** 1419 * Tests if the substring of this string beginning at the 1420 * specified index starts with the specified prefix. 1421 * 1422 * @param prefix the prefix. 1423 * @param toffset where to begin looking in this string. 1424 * @return {@code true} if the character sequence represented by the 1425 * argument is a prefix of the substring of this object starting 1426 * at index {@code toffset}; {@code false} otherwise. 1427 * The result is {@code false} if {@code toffset} is 1428 * negative or greater than the length of this 1429 * {@code String} object; otherwise the result is the same 1430 * as the result of the expression 1431 * <pre> 1432 * this.substring(toffset).startsWith(prefix) 1433 * </pre> 1434 */ 1435 public boolean startsWith(String prefix, int toffset) { 1436 // Note: toffset might be near -1>>>1. 1437 if (toffset < 0 || toffset > length() - prefix.length()) { 1438 return false; 1439 } 1440 byte ta[] = value; 1441 byte pa[] = prefix.value; 1442 int po = 0; 1443 int pc = pa.length; 1444 if (coder() == prefix.coder()) { 1445 int to = isLatin1() ? toffset : toffset << 1; 1446 while (po < pc) { 1447 if (ta[to++] != pa[po++]) { 1448 return false; 1449 } 1450 } 1451 } else { 1452 if (isLatin1()) { // && pcoder == UTF16 1453 return false; 1454 } 1455 // coder == UTF16 && pcoder == LATIN1) 1456 while (po < pc) { 1457 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) { 1458 return false; 1459 } 1460 } 1461 } 1462 return true; 1463 } 1464 1465 /** 1466 * Tests if this string starts with the specified prefix. 1467 * 1468 * @param prefix the prefix. 1469 * @return {@code true} if the character sequence represented by the 1470 * argument is a prefix of the character sequence represented by 1471 * this string; {@code false} otherwise. 1472 * Note also that {@code true} will be returned if the 1473 * argument is an empty string or is equal to this 1474 * {@code String} object as determined by the 1475 * {@link #equals(Object)} method. 1476 * @since 1.0 1477 */ 1478 public boolean startsWith(String prefix) { 1479 return startsWith(prefix, 0); 1480 } 1481 1482 /** 1483 * Tests if this string ends with the specified suffix. 1484 * 1485 * @param suffix the suffix. 1486 * @return {@code true} if the character sequence represented by the 1487 * argument is a suffix of the character sequence represented by 1488 * this object; {@code false} otherwise. Note that the 1489 * result will be {@code true} if the argument is the 1490 * empty string or is equal to this {@code String} object 1491 * as determined by the {@link #equals(Object)} method. 1492 */ 1493 public boolean endsWith(String suffix) { 1494 return startsWith(suffix, length() - suffix.length()); 1495 } 1496 1497 /** 1498 * Returns a hash code for this string. The hash code for a 1499 * {@code String} object is computed as 1500 * <blockquote><pre> 1501 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1502 * </pre></blockquote> 1503 * using {@code int} arithmetic, where {@code s[i]} is the 1504 * <i>i</i>th character of the string, {@code n} is the length of 1505 * the string, and {@code ^} indicates exponentiation. 1506 * (The hash value of the empty string is zero.) 1507 * 1508 * @return a hash code value for this object. 1509 */ 1510 public int hashCode() { 1511 int h = hash; 1512 if (h == 0 && value.length > 0) { 1513 h = isLatin1() ? StringLatin1.hashCode(value) 1514 : StringUTF16.hashCode(value); 1515 // Avoid issuing a store if the calculated value is also zero: 1516 // in addition to a minor performance benefit, this allows storing 1517 // Strings with zero hash code in read-only memory. 1518 if (h != 0) { 1519 hash = h; 1520 } 1521 } 1522 return h; 1523 } 1524 1525 /** 1526 * Returns the index within this string of the first occurrence of 1527 * the specified character. If a character with value 1528 * {@code ch} occurs in the character sequence represented by 1529 * this {@code String} object, then the index (in Unicode 1530 * code units) of the first such occurrence is returned. For 1531 * values of {@code ch} in the range from 0 to 0xFFFF 1532 * (inclusive), this is the smallest value <i>k</i> such that: 1533 * <blockquote><pre> 1534 * this.charAt(<i>k</i>) == ch 1535 * </pre></blockquote> 1536 * is true. For other values of {@code ch}, it is the 1537 * smallest value <i>k</i> such that: 1538 * <blockquote><pre> 1539 * this.codePointAt(<i>k</i>) == ch 1540 * </pre></blockquote> 1541 * is true. In either case, if no such character occurs in this 1542 * string, then {@code -1} is returned. 1543 * 1544 * @param ch a character (Unicode code point). 1545 * @return the index of the first occurrence of the character in the 1546 * character sequence represented by this object, or 1547 * {@code -1} if the character does not occur. 1548 */ 1549 public int indexOf(int ch) { 1550 return indexOf(ch, 0); 1551 } 1552 1553 /** 1554 * Returns the index within this string of the first occurrence of the 1555 * specified character, starting the search at the specified index. 1556 * <p> 1557 * If a character with value {@code ch} occurs in the 1558 * character sequence represented by this {@code String} 1559 * object at an index no smaller than {@code fromIndex}, then 1560 * the index of the first such occurrence is returned. For values 1561 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1562 * this is the smallest value <i>k</i> such that: 1563 * <blockquote><pre> 1564 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1565 * </pre></blockquote> 1566 * is true. For other values of {@code ch}, it is the 1567 * smallest value <i>k</i> such that: 1568 * <blockquote><pre> 1569 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1570 * </pre></blockquote> 1571 * is true. In either case, if no such character occurs in this 1572 * string at or after position {@code fromIndex}, then 1573 * {@code -1} is returned. 1574 * 1575 * <p> 1576 * There is no restriction on the value of {@code fromIndex}. If it 1577 * is negative, it has the same effect as if it were zero: this entire 1578 * string may be searched. If it is greater than the length of this 1579 * string, it has the same effect as if it were equal to the length of 1580 * this string: {@code -1} is returned. 1581 * 1582 * <p>All indices are specified in {@code char} values 1583 * (Unicode code units). 1584 * 1585 * @param ch a character (Unicode code point). 1586 * @param fromIndex the index to start the search from. 1587 * @return the index of the first occurrence of the character in the 1588 * character sequence represented by this object that is greater 1589 * than or equal to {@code fromIndex}, or {@code -1} 1590 * if the character does not occur. 1591 */ 1592 public int indexOf(int ch, int fromIndex) { 1593 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex) 1594 : StringUTF16.indexOf(value, ch, fromIndex); 1595 } 1596 1597 /** 1598 * Returns the index within this string of the last occurrence of 1599 * the specified character. For values of {@code ch} in the 1600 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1601 * units) returned is the largest value <i>k</i> such that: 1602 * <blockquote><pre> 1603 * this.charAt(<i>k</i>) == ch 1604 * </pre></blockquote> 1605 * is true. For other values of {@code ch}, it is the 1606 * largest value <i>k</i> such that: 1607 * <blockquote><pre> 1608 * this.codePointAt(<i>k</i>) == ch 1609 * </pre></blockquote> 1610 * is true. In either case, if no such character occurs in this 1611 * string, then {@code -1} is returned. The 1612 * {@code String} is searched backwards starting at the last 1613 * character. 1614 * 1615 * @param ch a character (Unicode code point). 1616 * @return the index of the last occurrence of the character in the 1617 * character sequence represented by this object, or 1618 * {@code -1} if the character does not occur. 1619 */ 1620 public int lastIndexOf(int ch) { 1621 return lastIndexOf(ch, length() - 1); 1622 } 1623 1624 /** 1625 * Returns the index within this string of the last occurrence of 1626 * the specified character, searching backward starting at the 1627 * specified index. For values of {@code ch} in the range 1628 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1629 * value <i>k</i> such that: 1630 * <blockquote><pre> 1631 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1632 * </pre></blockquote> 1633 * is true. For other values of {@code ch}, it is the 1634 * largest value <i>k</i> such that: 1635 * <blockquote><pre> 1636 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1637 * </pre></blockquote> 1638 * is true. In either case, if no such character occurs in this 1639 * string at or before position {@code fromIndex}, then 1640 * {@code -1} is returned. 1641 * 1642 * <p>All indices are specified in {@code char} values 1643 * (Unicode code units). 1644 * 1645 * @param ch a character (Unicode code point). 1646 * @param fromIndex the index to start the search from. There is no 1647 * restriction on the value of {@code fromIndex}. If it is 1648 * greater than or equal to the length of this string, it has 1649 * the same effect as if it were equal to one less than the 1650 * length of this string: this entire string may be searched. 1651 * If it is negative, it has the same effect as if it were -1: 1652 * -1 is returned. 1653 * @return the index of the last occurrence of the character in the 1654 * character sequence represented by this object that is less 1655 * than or equal to {@code fromIndex}, or {@code -1} 1656 * if the character does not occur before that point. 1657 */ 1658 public int lastIndexOf(int ch, int fromIndex) { 1659 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex) 1660 : StringUTF16.lastIndexOf(value, ch, fromIndex); 1661 } 1662 1663 /** 1664 * Returns the index within this string of the first occurrence of the 1665 * specified substring. 1666 * 1667 * <p>The returned index is the smallest value {@code k} for which: 1668 * <pre>{@code 1669 * this.startsWith(str, k) 1670 * }</pre> 1671 * If no such value of {@code k} exists, then {@code -1} is returned. 1672 * 1673 * @param str the substring to search for. 1674 * @return the index of the first occurrence of the specified substring, 1675 * or {@code -1} if there is no such occurrence. 1676 */ 1677 public int indexOf(String str) { 1678 if (coder() == str.coder()) { 1679 return isLatin1() ? StringLatin1.indexOf(value, str.value) 1680 : StringUTF16.indexOf(value, str.value); 1681 } 1682 if (coder() == LATIN1) { // str.coder == UTF16 1683 return -1; 1684 } 1685 return StringUTF16.indexOfLatin1(value, str.value); 1686 } 1687 1688 /** 1689 * Returns the index within this string of the first occurrence of the 1690 * specified substring, starting at the specified index. 1691 * 1692 * <p>The returned index is the smallest value {@code k} for which: 1693 * <pre>{@code 1694 * k >= Math.min(fromIndex, this.length()) && 1695 * this.startsWith(str, k) 1696 * }</pre> 1697 * If no such value of {@code k} exists, then {@code -1} is returned. 1698 * 1699 * @param str the substring to search for. 1700 * @param fromIndex the index from which to start the search. 1701 * @return the index of the first occurrence of the specified substring, 1702 * starting at the specified index, 1703 * or {@code -1} if there is no such occurrence. 1704 */ 1705 public int indexOf(String str, int fromIndex) { 1706 return indexOf(value, coder(), length(), str, fromIndex); 1707 } 1708 1709 /** 1710 * Code shared by String and AbstractStringBuilder to do searches. The 1711 * source is the character array being searched, and the target 1712 * is the string being searched for. 1713 * 1714 * @param src the characters being searched. 1715 * @param srcCoder the coder of the source string. 1716 * @param srcCount length of the source string. 1717 * @param tgtStr the characters being searched for. 1718 * @param fromIndex the index to begin searching from. 1719 */ 1720 static int indexOf(byte[] src, byte srcCoder, int srcCount, 1721 String tgtStr, int fromIndex) { 1722 byte[] tgt = tgtStr.value; 1723 byte tgtCoder = tgtStr.coder(); 1724 int tgtCount = tgtStr.length(); 1725 1726 if (fromIndex >= srcCount) { 1727 return (tgtCount == 0 ? srcCount : -1); 1728 } 1729 if (fromIndex < 0) { 1730 fromIndex = 0; 1731 } 1732 if (tgtCount == 0) { 1733 return fromIndex; 1734 } 1735 if (tgtCount > srcCount) { 1736 return -1; 1737 } 1738 if (srcCoder == tgtCoder) { 1739 return srcCoder == LATIN1 1740 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex) 1741 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex); 1742 } 1743 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1744 return -1; 1745 } 1746 // srcCoder == UTF16 && tgtCoder == LATIN1) { 1747 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex); 1748 } 1749 1750 /** 1751 * Returns the index within this string of the last occurrence of the 1752 * specified substring. The last occurrence of the empty string "" 1753 * is considered to occur at the index value {@code this.length()}. 1754 * 1755 * <p>The returned index is the largest value {@code k} for which: 1756 * <pre>{@code 1757 * this.startsWith(str, k) 1758 * }</pre> 1759 * If no such value of {@code k} exists, then {@code -1} is returned. 1760 * 1761 * @param str the substring to search for. 1762 * @return the index of the last occurrence of the specified substring, 1763 * or {@code -1} if there is no such occurrence. 1764 */ 1765 public int lastIndexOf(String str) { 1766 return lastIndexOf(str, length()); 1767 } 1768 1769 /** 1770 * Returns the index within this string of the last occurrence of the 1771 * specified substring, searching backward starting at the specified index. 1772 * 1773 * <p>The returned index is the largest value {@code k} for which: 1774 * <pre>{@code 1775 * k <= Math.min(fromIndex, this.length()) && 1776 * this.startsWith(str, k) 1777 * }</pre> 1778 * If no such value of {@code k} exists, then {@code -1} is returned. 1779 * 1780 * @param str the substring to search for. 1781 * @param fromIndex the index to start the search from. 1782 * @return the index of the last occurrence of the specified substring, 1783 * searching backward from the specified index, 1784 * or {@code -1} if there is no such occurrence. 1785 */ 1786 public int lastIndexOf(String str, int fromIndex) { 1787 return lastIndexOf(value, coder(), length(), str, fromIndex); 1788 } 1789 1790 /** 1791 * Code shared by String and AbstractStringBuilder to do searches. The 1792 * source is the character array being searched, and the target 1793 * is the string being searched for. 1794 * 1795 * @param src the characters being searched. 1796 * @param srcCoder coder handles the mapping between bytes/chars 1797 * @param srcCount count of the source string. 1798 * @param tgt the characters being searched for. 1799 * @param fromIndex the index to begin searching from. 1800 */ 1801 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount, 1802 String tgtStr, int fromIndex) { 1803 byte[] tgt = tgtStr.value; 1804 byte tgtCoder = tgtStr.coder(); 1805 int tgtCount = tgtStr.length(); 1806 /* 1807 * Check arguments; return immediately where possible. For 1808 * consistency, don't check for null str. 1809 */ 1810 int rightIndex = srcCount - tgtCount; 1811 if (fromIndex > rightIndex) { 1812 fromIndex = rightIndex; 1813 } 1814 if (fromIndex < 0) { 1815 return -1; 1816 } 1817 /* Empty string always matches. */ 1818 if (tgtCount == 0) { 1819 return fromIndex; 1820 } 1821 if (srcCoder == tgtCoder) { 1822 return srcCoder == LATIN1 1823 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex) 1824 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex); 1825 } 1826 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1827 return -1; 1828 } 1829 // srcCoder == UTF16 && tgtCoder == LATIN1 1830 return StringUTF16.lastIndexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex); 1831 } 1832 1833 /** 1834 * Returns a string that is a substring of this string. The 1835 * substring begins with the character at the specified index and 1836 * extends to the end of this string. <p> 1837 * Examples: 1838 * <blockquote><pre> 1839 * "unhappy".substring(2) returns "happy" 1840 * "Harbison".substring(3) returns "bison" 1841 * "emptiness".substring(9) returns "" (an empty string) 1842 * </pre></blockquote> 1843 * 1844 * @param beginIndex the beginning index, inclusive. 1845 * @return the specified substring. 1846 * @exception IndexOutOfBoundsException if 1847 * {@code beginIndex} is negative or larger than the 1848 * length of this {@code String} object. 1849 */ 1850 public String substring(int beginIndex) { 1851 if (beginIndex < 0) { 1852 throw new StringIndexOutOfBoundsException(beginIndex); 1853 } 1854 int subLen = length() - beginIndex; 1855 if (subLen < 0) { 1856 throw new StringIndexOutOfBoundsException(subLen); 1857 } 1858 if (beginIndex == 0) { 1859 return this; 1860 } 1861 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1862 : StringUTF16.newString(value, beginIndex, subLen); 1863 } 1864 1865 /** 1866 * Returns a string that is a substring of this string. The 1867 * substring begins at the specified {@code beginIndex} and 1868 * extends to the character at index {@code endIndex - 1}. 1869 * Thus the length of the substring is {@code endIndex-beginIndex}. 1870 * <p> 1871 * Examples: 1872 * <blockquote><pre> 1873 * "hamburger".substring(4, 8) returns "urge" 1874 * "smiles".substring(1, 5) returns "mile" 1875 * </pre></blockquote> 1876 * 1877 * @param beginIndex the beginning index, inclusive. 1878 * @param endIndex the ending index, exclusive. 1879 * @return the specified substring. 1880 * @exception IndexOutOfBoundsException if the 1881 * {@code beginIndex} is negative, or 1882 * {@code endIndex} is larger than the length of 1883 * this {@code String} object, or 1884 * {@code beginIndex} is larger than 1885 * {@code endIndex}. 1886 */ 1887 public String substring(int beginIndex, int endIndex) { 1888 int length = length(); 1889 checkBoundsBeginEnd(beginIndex, endIndex, length); 1890 int subLen = endIndex - beginIndex; 1891 if (beginIndex == 0 && endIndex == length) { 1892 return this; 1893 } 1894 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1895 : StringUTF16.newString(value, beginIndex, subLen); 1896 } 1897 1898 /** 1899 * Returns a character sequence that is a subsequence of this sequence. 1900 * 1901 * <p> An invocation of this method of the form 1902 * 1903 * <blockquote><pre> 1904 * str.subSequence(begin, end)</pre></blockquote> 1905 * 1906 * behaves in exactly the same way as the invocation 1907 * 1908 * <blockquote><pre> 1909 * str.substring(begin, end)</pre></blockquote> 1910 * 1911 * @apiNote 1912 * This method is defined so that the {@code String} class can implement 1913 * the {@link CharSequence} interface. 1914 * 1915 * @param beginIndex the begin index, inclusive. 1916 * @param endIndex the end index, exclusive. 1917 * @return the specified subsequence. 1918 * 1919 * @throws IndexOutOfBoundsException 1920 * if {@code beginIndex} or {@code endIndex} is negative, 1921 * if {@code endIndex} is greater than {@code length()}, 1922 * or if {@code beginIndex} is greater than {@code endIndex} 1923 * 1924 * @since 1.4 1925 * @spec JSR-51 1926 */ 1927 public CharSequence subSequence(int beginIndex, int endIndex) { 1928 return this.substring(beginIndex, endIndex); 1929 } 1930 1931 /** 1932 * Concatenates the specified string to the end of this string. 1933 * <p> 1934 * If the length of the argument string is {@code 0}, then this 1935 * {@code String} object is returned. Otherwise, a 1936 * {@code String} object is returned that represents a character 1937 * sequence that is the concatenation of the character sequence 1938 * represented by this {@code String} object and the character 1939 * sequence represented by the argument string.<p> 1940 * Examples: 1941 * <blockquote><pre> 1942 * "cares".concat("s") returns "caress" 1943 * "to".concat("get").concat("her") returns "together" 1944 * </pre></blockquote> 1945 * 1946 * @param str the {@code String} that is concatenated to the end 1947 * of this {@code String}. 1948 * @return a string that represents the concatenation of this object's 1949 * characters followed by the string argument's characters. 1950 */ 1951 public String concat(String str) { 1952 if (str.isEmpty()) { 1953 return this; 1954 } 1955 if (coder() == str.coder()) { 1956 byte[] val = this.value; 1957 byte[] oval = str.value; 1958 int len = val.length + oval.length; 1959 byte[] buf = Arrays.copyOf(val, len); 1960 System.arraycopy(oval, 0, buf, val.length, oval.length); 1961 return new String(buf, coder); 1962 } 1963 int len = length(); 1964 int olen = str.length(); 1965 byte[] buf = StringUTF16.newBytesFor(len + olen); 1966 getBytes(buf, 0, UTF16); 1967 str.getBytes(buf, len, UTF16); 1968 return new String(buf, UTF16); 1969 } 1970 1971 /** 1972 * Returns a string resulting from replacing all occurrences of 1973 * {@code oldChar} in this string with {@code newChar}. 1974 * <p> 1975 * If the character {@code oldChar} does not occur in the 1976 * character sequence represented by this {@code String} object, 1977 * then a reference to this {@code String} object is returned. 1978 * Otherwise, a {@code String} object is returned that 1979 * represents a character sequence identical to the character sequence 1980 * represented by this {@code String} object, except that every 1981 * occurrence of {@code oldChar} is replaced by an occurrence 1982 * of {@code newChar}. 1983 * <p> 1984 * Examples: 1985 * <blockquote><pre> 1986 * "mesquite in your cellar".replace('e', 'o') 1987 * returns "mosquito in your collar" 1988 * "the war of baronets".replace('r', 'y') 1989 * returns "the way of bayonets" 1990 * "sparring with a purple porpoise".replace('p', 't') 1991 * returns "starring with a turtle tortoise" 1992 * "JonL".replace('q', 'x') returns "JonL" (no change) 1993 * </pre></blockquote> 1994 * 1995 * @param oldChar the old character. 1996 * @param newChar the new character. 1997 * @return a string derived from this string by replacing every 1998 * occurrence of {@code oldChar} with {@code newChar}. 1999 */ 2000 public String replace(char oldChar, char newChar) { 2001 if (oldChar != newChar) { 2002 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar) 2003 : StringUTF16.replace(value, oldChar, newChar); 2004 if (ret != null) { 2005 return ret; 2006 } 2007 } 2008 return this; 2009 } 2010 2011 /** 2012 * Tells whether or not this string matches the given <a 2013 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2014 * 2015 * <p> An invocation of this method of the form 2016 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2017 * same result as the expression 2018 * 2019 * <blockquote> 2020 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2021 * matches(<i>regex</i>, <i>str</i>)} 2022 * </blockquote> 2023 * 2024 * @param regex 2025 * the regular expression to which this string is to be matched 2026 * 2027 * @return {@code true} if, and only if, this string matches the 2028 * given regular expression 2029 * 2030 * @throws PatternSyntaxException 2031 * if the regular expression's syntax is invalid 2032 * 2033 * @see java.util.regex.Pattern 2034 * 2035 * @since 1.4 2036 * @spec JSR-51 2037 */ 2038 public boolean matches(String regex) { 2039 return Pattern.matches(regex, this); 2040 } 2041 2042 /** 2043 * Returns true if and only if this string contains the specified 2044 * sequence of char values. 2045 * 2046 * @param s the sequence to search for 2047 * @return true if this string contains {@code s}, false otherwise 2048 * @since 1.5 2049 */ 2050 public boolean contains(CharSequence s) { 2051 return indexOf(s.toString()) >= 0; 2052 } 2053 2054 /** 2055 * Replaces the first substring of this string that matches the given <a 2056 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2057 * given replacement. 2058 * 2059 * <p> An invocation of this method of the form 2060 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2061 * yields exactly the same result as the expression 2062 * 2063 * <blockquote> 2064 * <code> 2065 * {@link java.util.regex.Pattern}.{@link 2066 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2067 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2068 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>) 2069 * </code> 2070 * </blockquote> 2071 * 2072 *<p> 2073 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2074 * replacement string may cause the results to be different than if it were 2075 * being treated as a literal replacement string; see 2076 * {@link java.util.regex.Matcher#replaceFirst}. 2077 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2078 * meaning of these characters, if desired. 2079 * 2080 * @param regex 2081 * the regular expression to which this string is to be matched 2082 * @param replacement 2083 * the string to be substituted for the first match 2084 * 2085 * @return The resulting {@code String} 2086 * 2087 * @throws PatternSyntaxException 2088 * if the regular expression's syntax is invalid 2089 * 2090 * @see java.util.regex.Pattern 2091 * 2092 * @since 1.4 2093 * @spec JSR-51 2094 */ 2095 public String replaceFirst(String regex, String replacement) { 2096 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2097 } 2098 2099 /** 2100 * Replaces each substring of this string that matches the given <a 2101 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2102 * given replacement. 2103 * 2104 * <p> An invocation of this method of the form 2105 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2106 * yields exactly the same result as the expression 2107 * 2108 * <blockquote> 2109 * <code> 2110 * {@link java.util.regex.Pattern}.{@link 2111 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2112 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2113 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2114 * </code> 2115 * </blockquote> 2116 * 2117 *<p> 2118 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2119 * replacement string may cause the results to be different than if it were 2120 * being treated as a literal replacement string; see 2121 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2122 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2123 * meaning of these characters, if desired. 2124 * 2125 * @param regex 2126 * the regular expression to which this string is to be matched 2127 * @param replacement 2128 * the string to be substituted for each match 2129 * 2130 * @return The resulting {@code String} 2131 * 2132 * @throws PatternSyntaxException 2133 * if the regular expression's syntax is invalid 2134 * 2135 * @see java.util.regex.Pattern 2136 * 2137 * @since 1.4 2138 * @spec JSR-51 2139 */ 2140 public String replaceAll(String regex, String replacement) { 2141 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2142 } 2143 2144 /** 2145 * Replaces each substring of this string that matches the literal target 2146 * sequence with the specified literal replacement sequence. The 2147 * replacement proceeds from the beginning of the string to the end, for 2148 * example, replacing "aa" with "b" in the string "aaa" will result in 2149 * "ba" rather than "ab". 2150 * 2151 * @param target The sequence of char values to be replaced 2152 * @param replacement The replacement sequence of char values 2153 * @return The resulting string 2154 * @since 1.5 2155 */ 2156 public String replace(CharSequence target, CharSequence replacement) { 2157 String tgtStr = target.toString(); 2158 String replStr = replacement.toString(); 2159 int j = indexOf(tgtStr); 2160 if (j < 0) { 2161 return this; 2162 } 2163 int tgtLen = tgtStr.length(); 2164 int tgtLen1 = Math.max(tgtLen, 1); 2165 int thisLen = length(); 2166 2167 int newLenHint = thisLen - tgtLen + replStr.length(); 2168 if (newLenHint < 0) { 2169 throw new OutOfMemoryError(); 2170 } 2171 StringBuilder sb = new StringBuilder(newLenHint); 2172 int i = 0; 2173 do { 2174 sb.append(this, i, j).append(replStr); 2175 i = j + tgtLen; 2176 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0); 2177 return sb.append(this, i, thisLen).toString(); 2178 } 2179 2180 /** 2181 * Splits this string around matches of the given 2182 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2183 * 2184 * <p> The array returned by this method contains each substring of this 2185 * string that is terminated by another substring that matches the given 2186 * expression or is terminated by the end of the string. The substrings in 2187 * the array are in the order in which they occur in this string. If the 2188 * expression does not match any part of the input then the resulting array 2189 * has just one element, namely this string. 2190 * 2191 * <p> When there is a positive-width match at the beginning of this 2192 * string then an empty leading substring is included at the beginning 2193 * of the resulting array. A zero-width match at the beginning however 2194 * never produces such empty leading substring. 2195 * 2196 * <p> The {@code limit} parameter controls the number of times the 2197 * pattern is applied and therefore affects the length of the resulting 2198 * array. 2199 * <ul> 2200 * <li><p> 2201 * If the <i>limit</i> is positive then the pattern will be applied 2202 * at most <i>limit</i> - 1 times, the array's length will be 2203 * no greater than <i>limit</i>, and the array's last entry will contain 2204 * all input beyond the last matched delimiter.</p></li> 2205 * 2206 * <li><p> 2207 * If the <i>limit</i> is zero then the pattern will be applied as 2208 * many times as possible, the array can have any length, and trailing 2209 * empty strings will be discarded.</p></li> 2210 * 2211 * <li><p> 2212 * If the <i>limit</i> is negative then the pattern will be applied 2213 * as many times as possible and the array can have any length.</p></li> 2214 * </ul> 2215 * 2216 * <p> The string {@code "boo:and:foo"}, for example, yields the 2217 * following results with these parameters: 2218 * 2219 * <blockquote><table class="plain"> 2220 * <caption style="display:none">Split example showing regex, limit, and result</caption> 2221 * <thead> 2222 * <tr> 2223 * <th scope="col">Regex</th> 2224 * <th scope="col">Limit</th> 2225 * <th scope="col">Result</th> 2226 * </tr> 2227 * </thead> 2228 * <tbody> 2229 * <tr><th scope="row" rowspan="3" style="font-weight:normal">:</th> 2230 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">2</th> 2231 * <td>{@code { "boo", "and:foo" }}</td></tr> 2232 * <tr><!-- : --> 2233 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th> 2234 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2235 * <tr><!-- : --> 2236 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th> 2237 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2238 * <tr><th scope="row" rowspan="3" style="font-weight:normal">o</th> 2239 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th> 2240 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2241 * <tr><!-- o --> 2242 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th> 2243 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2244 * <tr><!-- o --> 2245 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">0</th> 2246 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2247 * </tbody> 2248 * </table></blockquote> 2249 * 2250 * <p> An invocation of this method of the form 2251 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2252 * yields the same result as the expression 2253 * 2254 * <blockquote> 2255 * <code> 2256 * {@link java.util.regex.Pattern}.{@link 2257 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2258 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2259 * </code> 2260 * </blockquote> 2261 * 2262 * 2263 * @param regex 2264 * the delimiting regular expression 2265 * 2266 * @param limit 2267 * the result threshold, as described above 2268 * 2269 * @return the array of strings computed by splitting this string 2270 * around matches of the given regular expression 2271 * 2272 * @throws PatternSyntaxException 2273 * if the regular expression's syntax is invalid 2274 * 2275 * @see java.util.regex.Pattern 2276 * 2277 * @since 1.4 2278 * @spec JSR-51 2279 */ 2280 public String[] split(String regex, int limit) { 2281 /* fastpath if the regex is a 2282 (1)one-char String and this character is not one of the 2283 RegEx's meta characters ".$|()[{^?*+\\", or 2284 (2)two-char String and the first char is the backslash and 2285 the second is not the ascii digit or ascii letter. 2286 */ 2287 char ch = 0; 2288 if (((regex.length() == 1 && 2289 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2290 (regex.length() == 2 && 2291 regex.charAt(0) == '\\' && 2292 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2293 ((ch-'a')|('z'-ch)) < 0 && 2294 ((ch-'A')|('Z'-ch)) < 0)) && 2295 (ch < Character.MIN_HIGH_SURROGATE || 2296 ch > Character.MAX_LOW_SURROGATE)) 2297 { 2298 int off = 0; 2299 int next = 0; 2300 boolean limited = limit > 0; 2301 ArrayList<String> list = new ArrayList<>(); 2302 while ((next = indexOf(ch, off)) != -1) { 2303 if (!limited || list.size() < limit - 1) { 2304 list.add(substring(off, next)); 2305 off = next + 1; 2306 } else { // last one 2307 //assert (list.size() == limit - 1); 2308 int last = length(); 2309 list.add(substring(off, last)); 2310 off = last; 2311 break; 2312 } 2313 } 2314 // If no match was found, return this 2315 if (off == 0) 2316 return new String[]{this}; 2317 2318 // Add remaining segment 2319 if (!limited || list.size() < limit) 2320 list.add(substring(off, length())); 2321 2322 // Construct result 2323 int resultSize = list.size(); 2324 if (limit == 0) { 2325 while (resultSize > 0 && list.get(resultSize - 1).isEmpty()) { 2326 resultSize--; 2327 } 2328 } 2329 String[] result = new String[resultSize]; 2330 return list.subList(0, resultSize).toArray(result); 2331 } 2332 return Pattern.compile(regex).split(this, limit); 2333 } 2334 2335 /** 2336 * Splits this string around matches of the given <a 2337 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2338 * 2339 * <p> This method works as if by invoking the two-argument {@link 2340 * #split(String, int) split} method with the given expression and a limit 2341 * argument of zero. Trailing empty strings are therefore not included in 2342 * the resulting array. 2343 * 2344 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2345 * results with these expressions: 2346 * 2347 * <blockquote><table class="plain"> 2348 * <caption style="display:none">Split examples showing regex and result</caption> 2349 * <thead> 2350 * <tr> 2351 * <th scope="col">Regex</th> 2352 * <th scope="col">Result</th> 2353 * </tr> 2354 * </thead> 2355 * <tbody> 2356 * <tr><th scope="row" style="text-weight:normal">:</th> 2357 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2358 * <tr><th scope="row" style="text-weight:normal">o</th> 2359 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2360 * </tbody> 2361 * </table></blockquote> 2362 * 2363 * 2364 * @param regex 2365 * the delimiting regular expression 2366 * 2367 * @return the array of strings computed by splitting this string 2368 * around matches of the given regular expression 2369 * 2370 * @throws PatternSyntaxException 2371 * if the regular expression's syntax is invalid 2372 * 2373 * @see java.util.regex.Pattern 2374 * 2375 * @since 1.4 2376 * @spec JSR-51 2377 */ 2378 public String[] split(String regex) { 2379 return split(regex, 0); 2380 } 2381 2382 /** 2383 * Returns a new String composed of copies of the 2384 * {@code CharSequence elements} joined together with a copy of 2385 * the specified {@code delimiter}. 2386 * 2387 * <blockquote>For example, 2388 * <pre>{@code 2389 * String message = String.join("-", "Java", "is", "cool"); 2390 * // message returned is: "Java-is-cool" 2391 * }</pre></blockquote> 2392 * 2393 * Note that if an element is null, then {@code "null"} is added. 2394 * 2395 * @param delimiter the delimiter that separates each element 2396 * @param elements the elements to join together. 2397 * 2398 * @return a new {@code String} that is composed of the {@code elements} 2399 * separated by the {@code delimiter} 2400 * 2401 * @throws NullPointerException If {@code delimiter} or {@code elements} 2402 * is {@code null} 2403 * 2404 * @see java.util.StringJoiner 2405 * @since 1.8 2406 */ 2407 public static String join(CharSequence delimiter, CharSequence... elements) { 2408 Objects.requireNonNull(delimiter); 2409 Objects.requireNonNull(elements); 2410 // Number of elements not likely worth Arrays.stream overhead. 2411 StringJoiner joiner = new StringJoiner(delimiter); 2412 for (CharSequence cs: elements) { 2413 joiner.add(cs); 2414 } 2415 return joiner.toString(); 2416 } 2417 2418 /** 2419 * Returns a new {@code String} composed of copies of the 2420 * {@code CharSequence elements} joined together with a copy of the 2421 * specified {@code delimiter}. 2422 * 2423 * <blockquote>For example, 2424 * <pre>{@code 2425 * List<String> strings = List.of("Java", "is", "cool"); 2426 * String message = String.join(" ", strings); 2427 * //message returned is: "Java is cool" 2428 * 2429 * Set<String> strings = 2430 * new LinkedHashSet<>(List.of("Java", "is", "very", "cool")); 2431 * String message = String.join("-", strings); 2432 * //message returned is: "Java-is-very-cool" 2433 * }</pre></blockquote> 2434 * 2435 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2436 * 2437 * @param delimiter a sequence of characters that is used to separate each 2438 * of the {@code elements} in the resulting {@code String} 2439 * @param elements an {@code Iterable} that will have its {@code elements} 2440 * joined together. 2441 * 2442 * @return a new {@code String} that is composed from the {@code elements} 2443 * argument 2444 * 2445 * @throws NullPointerException If {@code delimiter} or {@code elements} 2446 * is {@code null} 2447 * 2448 * @see #join(CharSequence,CharSequence...) 2449 * @see java.util.StringJoiner 2450 * @since 1.8 2451 */ 2452 public static String join(CharSequence delimiter, 2453 Iterable<? extends CharSequence> elements) { 2454 Objects.requireNonNull(delimiter); 2455 Objects.requireNonNull(elements); 2456 StringJoiner joiner = new StringJoiner(delimiter); 2457 for (CharSequence cs: elements) { 2458 joiner.add(cs); 2459 } 2460 return joiner.toString(); 2461 } 2462 2463 /** 2464 * Converts all of the characters in this {@code String} to lower 2465 * case using the rules of the given {@code Locale}. Case mapping is based 2466 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2467 * class. Since case mappings are not always 1:1 char mappings, the resulting 2468 * {@code String} may be a different length than the original {@code String}. 2469 * <p> 2470 * Examples of lowercase mappings are in the following table: 2471 * <table class="plain"> 2472 * <caption style="display:none">Lowercase mapping examples showing language code of locale, upper case, lower case, and description</caption> 2473 * <thead> 2474 * <tr> 2475 * <th scope="col">Language Code of Locale</th> 2476 * <th scope="col">Upper Case</th> 2477 * <th scope="col">Lower Case</th> 2478 * <th scope="col">Description</th> 2479 * </tr> 2480 * </thead> 2481 * <tbody> 2482 * <tr> 2483 * <td>tr (Turkish)</td> 2484 * <th scope="row" style="font-weight:normal; text-align:left">\u0130</th> 2485 * <td>\u0069</td> 2486 * <td>capital letter I with dot above -> small letter i</td> 2487 * </tr> 2488 * <tr> 2489 * <td>tr (Turkish)</td> 2490 * <th scope="row" style="font-weight:normal; text-align:left">\u0049</th> 2491 * <td>\u0131</td> 2492 * <td>capital letter I -> small letter dotless i </td> 2493 * </tr> 2494 * <tr> 2495 * <td>(all)</td> 2496 * <th scope="row" style="font-weight:normal; text-align:left">French Fries</th> 2497 * <td>french fries</td> 2498 * <td>lowercased all chars in String</td> 2499 * </tr> 2500 * <tr> 2501 * <td>(all)</td> 2502 * <th scope="row" style="font-weight:normal; text-align:left"> 2503 * ΙΧΘΥΣ</th> 2504 * <td>ιχθυσ</td> 2505 * <td>lowercased all chars in String</td> 2506 * </tr> 2507 * </tbody> 2508 * </table> 2509 * 2510 * @param locale use the case transformation rules for this locale 2511 * @return the {@code String}, converted to lowercase. 2512 * @see java.lang.String#toLowerCase() 2513 * @see java.lang.String#toUpperCase() 2514 * @see java.lang.String#toUpperCase(Locale) 2515 * @since 1.1 2516 */ 2517 public String toLowerCase(Locale locale) { 2518 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale) 2519 : StringUTF16.toLowerCase(this, value, locale); 2520 } 2521 2522 /** 2523 * Converts all of the characters in this {@code String} to lower 2524 * case using the rules of the default locale. This is equivalent to calling 2525 * {@code toLowerCase(Locale.getDefault())}. 2526 * <p> 2527 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2528 * results if used for strings that are intended to be interpreted locale 2529 * independently. 2530 * Examples are programming language identifiers, protocol keys, and HTML 2531 * tags. 2532 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2533 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2534 * LATIN SMALL LETTER DOTLESS I character. 2535 * To obtain correct results for locale insensitive strings, use 2536 * {@code toLowerCase(Locale.ROOT)}. 2537 * 2538 * @return the {@code String}, converted to lowercase. 2539 * @see java.lang.String#toLowerCase(Locale) 2540 */ 2541 public String toLowerCase() { 2542 return toLowerCase(Locale.getDefault()); 2543 } 2544 2545 /** 2546 * Converts all of the characters in this {@code String} to upper 2547 * case using the rules of the given {@code Locale}. Case mapping is based 2548 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2549 * class. Since case mappings are not always 1:1 char mappings, the resulting 2550 * {@code String} may be a different length than the original {@code String}. 2551 * <p> 2552 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2553 * 2554 * <table class="plain"> 2555 * <caption style="display:none">Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.</caption> 2556 * <thead> 2557 * <tr> 2558 * <th scope="col">Language Code of Locale</th> 2559 * <th scope="col">Lower Case</th> 2560 * <th scope="col">Upper Case</th> 2561 * <th scope="col">Description</th> 2562 * </tr> 2563 * </thead> 2564 * <tbody> 2565 * <tr> 2566 * <td>tr (Turkish)</td> 2567 * <th scope="row" style="font-weight:normal; text-align:left">\u0069</th> 2568 * <td>\u0130</td> 2569 * <td>small letter i -> capital letter I with dot above</td> 2570 * </tr> 2571 * <tr> 2572 * <td>tr (Turkish)</td> 2573 * <th scope="row" style="font-weight:normal; text-align:left">\u0131</th> 2574 * <td>\u0049</td> 2575 * <td>small letter dotless i -> capital letter I</td> 2576 * </tr> 2577 * <tr> 2578 * <td>(all)</td> 2579 * <th scope="row" style="font-weight:normal; text-align:left">\u00df</th> 2580 * <td>\u0053 \u0053</td> 2581 * <td>small letter sharp s -> two letters: SS</td> 2582 * </tr> 2583 * <tr> 2584 * <td>(all)</td> 2585 * <th scope="row" style="font-weight:normal; text-align:left">Fahrvergnügen</th> 2586 * <td>FAHRVERGNÜGEN</td> 2587 * <td></td> 2588 * </tr> 2589 * </tbody> 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 all leading 2628 * and trailing space removed, where space is defined 2629 * as any character whose codepoint is less than or equal to 2630 * {@code 'U+0020'} (the space character). 2631 * <p> 2632 * If this {@code String} object represents an empty character 2633 * sequence, or the first and last characters of character sequence 2634 * represented by this {@code String} object both have codes 2635 * that are not space (as defined above), then a 2636 * reference to this {@code String} object is returned. 2637 * <p> 2638 * Otherwise, if all characters in this string are space (as 2639 * defined above), then a {@code String} object representing an 2640 * empty string is returned. 2641 * <p> 2642 * Otherwise, let <i>k</i> be the index of the first character in the 2643 * string whose code is not a space (as defined above) and let 2644 * <i>m</i> be the index of the last character in the string whose code 2645 * is not a space (as defined above). A {@code String} 2646 * object is returned, representing the substring of this string that 2647 * begins with the character at index <i>k</i> and ends with the 2648 * character at index <i>m</i>-that is, the result of 2649 * {@code this.substring(k, m + 1)}. 2650 * <p> 2651 * This method may be used to trim space (as defined above) from 2652 * the beginning and end of a string. 2653 * 2654 * @return a string whose value is this string, with all leading 2655 * and trailing space removed, or this string if it 2656 * has no leading or trailing space. 2657 */ 2658 public String trim() { 2659 String ret = isLatin1() ? StringLatin1.trim(value) 2660 : StringUTF16.trim(value); 2661 return ret == null ? this : ret; 2662 } 2663 2664 /** 2665 * Returns a string whose value is this string, with all leading 2666 * and trailing {@link Character#isWhitespace(int) white space} 2667 * removed. 2668 * <p> 2669 * If this {@code String} object represents an empty string, 2670 * or if all code points in this string are 2671 * {@link Character#isWhitespace(int) white space}, then an empty string 2672 * is returned. 2673 * <p> 2674 * Otherwise, returns a substring of this string beginning with the first 2675 * code point that is not a {@link Character#isWhitespace(int) white space} 2676 * up to and including the last code point that is not a 2677 * {@link Character#isWhitespace(int) white space}. 2678 * <p> 2679 * This method may be used to strip 2680 * {@link Character#isWhitespace(int) white space} from 2681 * the beginning and end of a string. 2682 * 2683 * @return a string whose value is this string, with all leading 2684 * and trailing white space removed 2685 * 2686 * @see Character#isWhitespace(int) 2687 * 2688 * @since 11 2689 */ 2690 public String strip() { 2691 String ret = isLatin1() ? StringLatin1.strip(value) 2692 : StringUTF16.strip(value); 2693 return ret == null ? this : ret; 2694 } 2695 2696 /** 2697 * Returns a string whose value is this string, with all leading 2698 * {@link Character#isWhitespace(int) white space} removed. 2699 * <p> 2700 * If this {@code String} object represents an empty string, 2701 * or if all code points in this string are 2702 * {@link Character#isWhitespace(int) white space}, then an empty string 2703 * is returned. 2704 * <p> 2705 * Otherwise, returns a substring of this string beginning with the first 2706 * code point that is not a {@link Character#isWhitespace(int) white space} 2707 * up to and including the last code point of this string. 2708 * <p> 2709 * This method may be used to trim 2710 * {@link Character#isWhitespace(int) white space} from 2711 * the beginning of a string. 2712 * 2713 * @return a string whose value is this string, with all leading white 2714 * space removed 2715 * 2716 * @see Character#isWhitespace(int) 2717 * 2718 * @since 11 2719 */ 2720 public String stripLeading() { 2721 String ret = isLatin1() ? StringLatin1.stripLeading(value) 2722 : StringUTF16.stripLeading(value); 2723 return ret == null ? this : ret; 2724 } 2725 2726 /** 2727 * Returns a string whose value is this string, with all trailing 2728 * {@link Character#isWhitespace(int) white space} removed. 2729 * <p> 2730 * If this {@code String} object represents an empty string, 2731 * or if all characters in this string are 2732 * {@link Character#isWhitespace(int) white space}, then an empty string 2733 * is returned. 2734 * <p> 2735 * Otherwise, returns a substring of this string beginning with the first 2736 * code point of this string up to and including the last code point 2737 * that is not a {@link Character#isWhitespace(int) white space}. 2738 * <p> 2739 * This method may be used to trim 2740 * {@link Character#isWhitespace(int) white space} from 2741 * the end of a string. 2742 * 2743 * @return a string whose value is this string, with all trailing white 2744 * space removed 2745 * 2746 * @see Character#isWhitespace(int) 2747 * 2748 * @since 11 2749 */ 2750 public String stripTrailing() { 2751 String ret = isLatin1() ? StringLatin1.stripTrailing(value) 2752 : StringUTF16.stripTrailing(value); 2753 return ret == null ? this : ret; 2754 } 2755 2756 /** 2757 * Returns {@code true} if the string is empty or contains only 2758 * {@link Character#isWhitespace(int) white space} codepoints, 2759 * otherwise {@code false}. 2760 * 2761 * @return {@code true} if the string is empty or contains only 2762 * {@link Character#isWhitespace(int) white space} codepoints, 2763 * otherwise {@code false} 2764 * 2765 * @see Character#isWhitespace(int) 2766 * 2767 * @since 11 2768 */ 2769 public boolean isBlank() { 2770 return indexOfNonWhitespace() == length(); 2771 } 2772 2773 private Stream<String> lines(int maxLeading, int maxTrailing) { 2774 return isLatin1() ? StringLatin1.lines(value, maxLeading, maxTrailing) 2775 : StringUTF16.lines(value, maxLeading, maxTrailing); 2776 } 2777 2778 /** 2779 * Returns a stream of lines extracted from this string, 2780 * separated by line terminators. 2781 * <p> 2782 * A <i>line terminator</i> is one of the following: 2783 * a line feed character {@code "\n"} (U+000A), 2784 * a carriage return character {@code "\r"} (U+000D), 2785 * or a carriage return followed immediately by a line feed 2786 * {@code "\r\n"} (U+000D U+000A). 2787 * <p> 2788 * A <i>line</i> is either a sequence of zero or more characters 2789 * followed by a line terminator, or it is a sequence of one or 2790 * more characters followed by the end of the string. A 2791 * line does not include the line terminator. 2792 * <p> 2793 * The stream returned by this method contains the lines from 2794 * this string in the order in which they occur. 2795 * 2796 * @apiNote This definition of <i>line</i> implies that an empty 2797 * string has zero lines and that there is no empty line 2798 * following a line terminator at the end of a string. 2799 * 2800 * @implNote This method provides better performance than 2801 * split("\R") by supplying elements lazily and 2802 * by faster search of new line terminators. 2803 * 2804 * @return the stream of lines extracted from this string 2805 * 2806 * @since 11 2807 */ 2808 public Stream<String> lines() { 2809 return lines(0, 0); 2810 } 2811 2812 /** 2813 * Adjusts the indentation of each line of this string based on the value of 2814 * {@code n}, and normalizes line termination characters. 2815 * <p> 2816 * This string is conceptually separated into lines using 2817 * {@link String#lines()}. Each line is then adjusted as described below 2818 * and then suffixed with a line feed {@code "\n"} (U+000A). The resulting 2819 * lines are then concatenated and returned. 2820 * <p> 2821 * If {@code n > 0} then {@code n} spaces (U+0020) are inserted at the 2822 * beginning of each line. 2823 * <p> 2824 * If {@code n < 0} then up to {@code n} 2825 * {@link Character#isWhitespace(int) white space characters} are removed 2826 * from the beginning of each line. If a given line does not contain 2827 * sufficient white space then all leading 2828 * {@link Character#isWhitespace(int) white space characters} are removed. 2829 * Each white space character is treated as a single character. In 2830 * particular, the tab character {@code "\t"} (U+0009) is considered a 2831 * single character; it is not expanded. 2832 * <p> 2833 * If {@code n == 0} then the line remains unchanged. However, line 2834 * terminators are still normalized. 2835 * 2836 * @param n number of leading 2837 * {@link Character#isWhitespace(int) white space characters} 2838 * to add or remove 2839 * 2840 * @return string with indentation adjusted and line endings normalized 2841 * 2842 * @see String#lines() 2843 * @see String#isBlank() 2844 * @see Character#isWhitespace(int) 2845 * 2846 * @since 12 2847 */ 2848 public String indent(int n) { 2849 return isEmpty() ? "" : indent(n, false); 2850 } 2851 2852 private String indent(int n, boolean removeBlanks) { 2853 Stream<String> stream = removeBlanks ? lines(Integer.MAX_VALUE, Integer.MAX_VALUE) 2854 : lines(); 2855 if (n > 0) { 2856 final String spaces = " ".repeat(n); 2857 stream = stream.map(s -> spaces + s); 2858 } else if (n == Integer.MIN_VALUE) { 2859 stream = stream.map(s -> s.stripLeading()); 2860 } else if (n < 0) { 2861 stream = stream.map(s -> s.substring(Math.min(-n, s.indexOfNonWhitespace()))); 2862 } 2863 return stream.collect(Collectors.joining("\n", "", "\n")); 2864 } 2865 2866 private int indexOfNonWhitespace() { 2867 return isLatin1() ? StringLatin1.indexOfNonWhitespace(value) 2868 : StringUTF16.indexOfNonWhitespace(value); 2869 } 2870 2871 private int lastIndexOfNonWhitespace() { 2872 return isLatin1() ? StringLatin1.lastIndexOfNonWhitespace(value) 2873 : StringUTF16.lastIndexOfNonWhitespace(value); 2874 } 2875 2876 /** 2877 * This method allows the application of a function to {@code this} 2878 * string. The function should expect a single String argument 2879 * and produce an {@code R} result. 2880 * <p> 2881 * Any exception thrown by {@code f()} will be propagated to the 2882 * caller. 2883 * 2884 * @param f functional interface to a apply 2885 * 2886 * @param <R> class of the result 2887 * 2888 * @return the result of applying the function to this string 2889 * 2890 * @see java.util.function.Function 2891 * 2892 * @since 12 2893 */ 2894 public <R> R transform(Function<? super String, ? extends R> f) { 2895 return f.apply(this); 2896 } 2897 2898 /** 2899 * This object (which is already a string!) is itself returned. 2900 * 2901 * @return the string itself. 2902 */ 2903 public String toString() { 2904 return this; 2905 } 2906 2907 /** 2908 * Returns a stream of {@code int} zero-extending the {@code char} values 2909 * from this sequence. Any char which maps to a <a 2910 * href="{@docRoot}/java.base/java/lang/Character.html#unicode">surrogate code 2911 * point</a> is passed through uninterpreted. 2912 * 2913 * @return an IntStream of char values from this sequence 2914 * @since 9 2915 */ 2916 @Override 2917 public IntStream chars() { 2918 return StreamSupport.intStream( 2919 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2920 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE), 2921 false); 2922 } 2923 2924 2925 /** 2926 * Returns a stream of code point values from this sequence. Any surrogate 2927 * pairs encountered in the sequence are combined as if by {@linkplain 2928 * Character#toCodePoint Character.toCodePoint} and the result is passed 2929 * to the stream. Any other code units, including ordinary BMP characters, 2930 * unpaired surrogates, and undefined code units, are zero-extended to 2931 * {@code int} values which are then passed to the stream. 2932 * 2933 * @return an IntStream of Unicode code points from this sequence 2934 * @since 9 2935 */ 2936 @Override 2937 public IntStream codePoints() { 2938 return StreamSupport.intStream( 2939 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2940 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE), 2941 false); 2942 } 2943 2944 /** 2945 * Converts this string to a new character array. 2946 * 2947 * @return a newly allocated character array whose length is the length 2948 * of this string and whose contents are initialized to contain 2949 * the character sequence represented by this string. 2950 */ 2951 public char[] toCharArray() { 2952 return isLatin1() ? StringLatin1.toChars(value) 2953 : StringUTF16.toChars(value); 2954 } 2955 2956 /** 2957 * Returns a formatted string using the specified format string and 2958 * arguments. 2959 * 2960 * <p> The locale always used is the one returned by {@link 2961 * java.util.Locale#getDefault(java.util.Locale.Category) 2962 * Locale.getDefault(Locale.Category)} with 2963 * {@link java.util.Locale.Category#FORMAT FORMAT} category specified. 2964 * 2965 * @param format 2966 * A <a href="../util/Formatter.html#syntax">format string</a> 2967 * 2968 * @param args 2969 * Arguments referenced by the format specifiers in the format 2970 * string. If there are more arguments than format specifiers, the 2971 * extra arguments are ignored. The number of arguments is 2972 * variable and may be zero. The maximum number of arguments is 2973 * limited by the maximum dimension of a Java array as defined by 2974 * <cite>The Java™ Virtual Machine Specification</cite>. 2975 * The behaviour on a 2976 * {@code null} argument depends on the <a 2977 * href="../util/Formatter.html#syntax">conversion</a>. 2978 * 2979 * @throws java.util.IllegalFormatException 2980 * If a format string contains an illegal syntax, a format 2981 * specifier that is incompatible with the given arguments, 2982 * insufficient arguments given the format string, or other 2983 * illegal conditions. For specification of all possible 2984 * formatting errors, see the <a 2985 * href="../util/Formatter.html#detail">Details</a> section of the 2986 * formatter class specification. 2987 * 2988 * @return A formatted string 2989 * 2990 * @see java.util.Formatter 2991 * @since 1.5 2992 */ 2993 public static String format(String format, Object... args) { 2994 return new Formatter().format(format, args).toString(); 2995 } 2996 2997 /** 2998 * Returns a formatted string using the specified locale, format string, 2999 * and arguments. 3000 * 3001 * @param l 3002 * The {@linkplain java.util.Locale locale} to apply during 3003 * formatting. If {@code l} is {@code null} then no localization 3004 * is applied. 3005 * 3006 * @param format 3007 * A <a href="../util/Formatter.html#syntax">format string</a> 3008 * 3009 * @param args 3010 * Arguments referenced by the format specifiers in the format 3011 * string. If there are more arguments than format specifiers, the 3012 * extra arguments are ignored. The number of arguments is 3013 * variable and may be zero. The maximum number of arguments is 3014 * limited by the maximum dimension of a Java array as defined by 3015 * <cite>The Java™ Virtual Machine Specification</cite>. 3016 * The behaviour on a 3017 * {@code null} argument depends on the 3018 * <a href="../util/Formatter.html#syntax">conversion</a>. 3019 * 3020 * @throws java.util.IllegalFormatException 3021 * If a format string contains an illegal syntax, a format 3022 * specifier that is incompatible with the given arguments, 3023 * insufficient arguments given the format string, or other 3024 * illegal conditions. For specification of all possible 3025 * formatting errors, see the <a 3026 * href="../util/Formatter.html#detail">Details</a> section of the 3027 * formatter class specification 3028 * 3029 * @return A formatted string 3030 * 3031 * @see java.util.Formatter 3032 * @since 1.5 3033 */ 3034 public static String format(Locale l, String format, Object... args) { 3035 return new Formatter(l).format(format, args).toString(); 3036 } 3037 3038 /** 3039 * Returns the string representation of the {@code Object} argument. 3040 * 3041 * @param obj an {@code Object}. 3042 * @return if the argument is {@code null}, then a string equal to 3043 * {@code "null"}; otherwise, the value of 3044 * {@code obj.toString()} is returned. 3045 * @see java.lang.Object#toString() 3046 */ 3047 public static String valueOf(Object obj) { 3048 return (obj == null) ? "null" : obj.toString(); 3049 } 3050 3051 /** 3052 * Returns the string representation of the {@code char} array 3053 * argument. The contents of the character array are copied; subsequent 3054 * modification of the character array does not affect the returned 3055 * string. 3056 * 3057 * @param data the character array. 3058 * @return a {@code String} that contains the characters of the 3059 * character array. 3060 */ 3061 public static String valueOf(char data[]) { 3062 return new String(data); 3063 } 3064 3065 /** 3066 * Returns the string representation of a specific subarray of the 3067 * {@code char} array argument. 3068 * <p> 3069 * The {@code offset} argument is the index of the first 3070 * character of the subarray. The {@code count} argument 3071 * specifies the length of the subarray. The contents of the subarray 3072 * are copied; subsequent modification of the character array does not 3073 * affect the returned string. 3074 * 3075 * @param data the character array. 3076 * @param offset initial offset of the subarray. 3077 * @param count length of the subarray. 3078 * @return a {@code String} that contains the characters of the 3079 * specified subarray of the character array. 3080 * @exception IndexOutOfBoundsException if {@code offset} is 3081 * negative, or {@code count} is negative, or 3082 * {@code offset+count} is larger than 3083 * {@code data.length}. 3084 */ 3085 public static String valueOf(char data[], int offset, int count) { 3086 return new String(data, offset, count); 3087 } 3088 3089 /** 3090 * Equivalent to {@link #valueOf(char[], int, int)}. 3091 * 3092 * @param data the character array. 3093 * @param offset initial offset of the subarray. 3094 * @param count length of the subarray. 3095 * @return a {@code String} that contains the characters of the 3096 * specified subarray of the character array. 3097 * @exception IndexOutOfBoundsException if {@code offset} is 3098 * negative, or {@code count} is negative, or 3099 * {@code offset+count} is larger than 3100 * {@code data.length}. 3101 */ 3102 public static String copyValueOf(char data[], int offset, int count) { 3103 return new String(data, offset, count); 3104 } 3105 3106 /** 3107 * Equivalent to {@link #valueOf(char[])}. 3108 * 3109 * @param data the character array. 3110 * @return a {@code String} that contains the characters of the 3111 * character array. 3112 */ 3113 public static String copyValueOf(char data[]) { 3114 return new String(data); 3115 } 3116 3117 /** 3118 * Returns the string representation of the {@code boolean} argument. 3119 * 3120 * @param b a {@code boolean}. 3121 * @return if the argument is {@code true}, a string equal to 3122 * {@code "true"} is returned; otherwise, a string equal to 3123 * {@code "false"} is returned. 3124 */ 3125 public static String valueOf(boolean b) { 3126 return b ? "true" : "false"; 3127 } 3128 3129 /** 3130 * Returns the string representation of the {@code char} 3131 * argument. 3132 * 3133 * @param c a {@code char}. 3134 * @return a string of length {@code 1} containing 3135 * as its single character the argument {@code c}. 3136 */ 3137 public static String valueOf(char c) { 3138 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) { 3139 return new String(StringLatin1.toBytes(c), LATIN1); 3140 } 3141 return new String(StringUTF16.toBytes(c), UTF16); 3142 } 3143 3144 /** 3145 * Returns the string representation of the {@code int} argument. 3146 * <p> 3147 * The representation is exactly the one returned by the 3148 * {@code Integer.toString} method of one argument. 3149 * 3150 * @param i an {@code int}. 3151 * @return a string representation of the {@code int} argument. 3152 * @see java.lang.Integer#toString(int, int) 3153 */ 3154 public static String valueOf(int i) { 3155 return Integer.toString(i); 3156 } 3157 3158 /** 3159 * Returns the string representation of the {@code long} argument. 3160 * <p> 3161 * The representation is exactly the one returned by the 3162 * {@code Long.toString} method of one argument. 3163 * 3164 * @param l a {@code long}. 3165 * @return a string representation of the {@code long} argument. 3166 * @see java.lang.Long#toString(long) 3167 */ 3168 public static String valueOf(long l) { 3169 return Long.toString(l); 3170 } 3171 3172 /** 3173 * Returns the string representation of the {@code float} argument. 3174 * <p> 3175 * The representation is exactly the one returned by the 3176 * {@code Float.toString} method of one argument. 3177 * 3178 * @param f a {@code float}. 3179 * @return a string representation of the {@code float} argument. 3180 * @see java.lang.Float#toString(float) 3181 */ 3182 public static String valueOf(float f) { 3183 return Float.toString(f); 3184 } 3185 3186 /** 3187 * Returns the string representation of the {@code double} argument. 3188 * <p> 3189 * The representation is exactly the one returned by the 3190 * {@code Double.toString} method of one argument. 3191 * 3192 * @param d a {@code double}. 3193 * @return a string representation of the {@code double} argument. 3194 * @see java.lang.Double#toString(double) 3195 */ 3196 public static String valueOf(double d) { 3197 return Double.toString(d); 3198 } 3199 3200 /** 3201 * Returns a canonical representation for the string object. 3202 * <p> 3203 * A pool of strings, initially empty, is maintained privately by the 3204 * class {@code String}. 3205 * <p> 3206 * When the intern method is invoked, if the pool already contains a 3207 * string equal to this {@code String} object as determined by 3208 * the {@link #equals(Object)} method, then the string from the pool is 3209 * returned. Otherwise, this {@code String} object is added to the 3210 * pool and a reference to this {@code String} object is returned. 3211 * <p> 3212 * It follows that for any two strings {@code s} and {@code t}, 3213 * {@code s.intern() == t.intern()} is {@code true} 3214 * if and only if {@code s.equals(t)} is {@code true}. 3215 * <p> 3216 * All literal strings and string-valued constant expressions are 3217 * interned. String literals are defined in section 3.10.5 of the 3218 * <cite>The Java™ Language Specification</cite>. 3219 * 3220 * @return a string that has the same contents as this string, but is 3221 * guaranteed to be from a pool of unique strings. 3222 * @jls 3.10.5 String Literals 3223 */ 3224 public native String intern(); 3225 3226 /** 3227 * Returns a string whose value is the concatenation of this 3228 * string repeated {@code count} times. 3229 * <p> 3230 * If this string is empty or count is zero then the empty 3231 * string is returned. 3232 * 3233 * @param count number of times to repeat 3234 * 3235 * @return A string composed of this string repeated 3236 * {@code count} times or the empty string if this 3237 * string is empty or count is zero 3238 * 3239 * @throws IllegalArgumentException if the {@code count} is 3240 * negative. 3241 * 3242 * @since 11 3243 */ 3244 public String repeat(int count) { 3245 if (count < 0) { 3246 throw new IllegalArgumentException("count is negative: " + count); 3247 } 3248 if (count == 1) { 3249 return this; 3250 } 3251 final int len = value.length; 3252 if (len == 0 || count == 0) { 3253 return ""; 3254 } 3255 if (len == 1) { 3256 final byte[] single = new byte[count]; 3257 Arrays.fill(single, value[0]); 3258 return new String(single, coder); 3259 } 3260 if (Integer.MAX_VALUE / count < len) { 3261 throw new OutOfMemoryError("Repeating " + len + " bytes String " + count + 3262 " times will produce a String exceeding maximum size."); 3263 } 3264 final int limit = len * count; 3265 final byte[] multiple = new byte[limit]; 3266 System.arraycopy(value, 0, multiple, 0, len); 3267 int copied = len; 3268 for (; copied < limit - copied; copied <<= 1) { 3269 System.arraycopy(multiple, 0, multiple, copied, copied); 3270 } 3271 System.arraycopy(multiple, 0, multiple, copied, limit - copied); 3272 return new String(multiple, coder); 3273 } 3274 3275 //////////////////////////////////////////////////////////////// 3276 3277 /** 3278 * Copy character bytes from this string into dst starting at dstBegin. 3279 * This method doesn't perform any range checking. 3280 * 3281 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two 3282 * coders are different, and dst is big enough (range check) 3283 * 3284 * @param dstBegin the char index, not offset of byte[] 3285 * @param coder the coder of dst[] 3286 */ 3287 void getBytes(byte dst[], int dstBegin, byte coder) { 3288 if (coder() == coder) { 3289 System.arraycopy(value, 0, dst, dstBegin << coder, value.length); 3290 } else { // this.coder == LATIN && coder == UTF16 3291 StringLatin1.inflate(value, 0, dst, dstBegin, value.length); 3292 } 3293 } 3294 3295 /* 3296 * Package private constructor. Trailing Void argument is there for 3297 * disambiguating it against other (public) constructors. 3298 * 3299 * Stores the char[] value into a byte[] that each byte represents 3300 * the8 low-order bits of the corresponding character, if the char[] 3301 * contains only latin1 character. Or a byte[] that stores all 3302 * characters in their byte sequences defined by the {@code StringUTF16}. 3303 */ 3304 String(char[] value, int off, int len, Void sig) { 3305 if (len == 0) { 3306 this.value = "".value; 3307 this.coder = "".coder; 3308 return; 3309 } 3310 if (COMPACT_STRINGS) { 3311 byte[] val = StringUTF16.compress(value, off, len); 3312 if (val != null) { 3313 this.value = val; 3314 this.coder = LATIN1; 3315 return; 3316 } 3317 } 3318 this.coder = UTF16; 3319 this.value = StringUTF16.toBytes(value, off, len); 3320 } 3321 3322 /* 3323 * Package private constructor. Trailing Void argument is there for 3324 * disambiguating it against other (public) constructors. 3325 */ 3326 String(AbstractStringBuilder asb, Void sig) { 3327 byte[] val = asb.getValue(); 3328 int length = asb.length(); 3329 if (asb.isLatin1()) { 3330 this.coder = LATIN1; 3331 this.value = Arrays.copyOfRange(val, 0, length); 3332 } else { 3333 if (COMPACT_STRINGS) { 3334 byte[] buf = StringUTF16.compress(val, 0, length); 3335 if (buf != null) { 3336 this.coder = LATIN1; 3337 this.value = buf; 3338 return; 3339 } 3340 } 3341 this.coder = UTF16; 3342 this.value = Arrays.copyOfRange(val, 0, length << 1); 3343 } 3344 } 3345 3346 /* 3347 * Package private constructor which shares value array for speed. 3348 */ 3349 String(byte[] value, byte coder) { 3350 this.value = value; 3351 this.coder = coder; 3352 } 3353 3354 byte coder() { 3355 return COMPACT_STRINGS ? coder : UTF16; 3356 } 3357 3358 byte[] value() { 3359 return value; 3360 } 3361 3362 private boolean isLatin1() { 3363 return COMPACT_STRINGS && coder == LATIN1; 3364 } 3365 3366 @Native static final byte LATIN1 = 0; 3367 @Native static final byte UTF16 = 1; 3368 3369 /* 3370 * StringIndexOutOfBoundsException if {@code index} is 3371 * negative or greater than or equal to {@code length}. 3372 */ 3373 static void checkIndex(int index, int length) { 3374 if (index < 0 || index >= length) { 3375 throw new StringIndexOutOfBoundsException("index " + index + 3376 ",length " + length); 3377 } 3378 } 3379 3380 /* 3381 * StringIndexOutOfBoundsException if {@code offset} 3382 * is negative or greater than {@code length}. 3383 */ 3384 static void checkOffset(int offset, int length) { 3385 if (offset < 0 || offset > length) { 3386 throw new StringIndexOutOfBoundsException("offset " + offset + 3387 ",length " + length); 3388 } 3389 } 3390 3391 /* 3392 * Check {@code offset}, {@code count} against {@code 0} and {@code length} 3393 * bounds. 3394 * 3395 * @throws StringIndexOutOfBoundsException 3396 * If {@code offset} is negative, {@code count} is negative, 3397 * or {@code offset} is greater than {@code length - count} 3398 */ 3399 static void checkBoundsOffCount(int offset, int count, int length) { 3400 if (offset < 0 || count < 0 || offset > length - count) { 3401 throw new StringIndexOutOfBoundsException( 3402 "offset " + offset + ", count " + count + ", length " + length); 3403 } 3404 } 3405 3406 /* 3407 * Check {@code begin}, {@code end} against {@code 0} and {@code length} 3408 * bounds. 3409 * 3410 * @throws StringIndexOutOfBoundsException 3411 * If {@code begin} is negative, {@code begin} is greater than 3412 * {@code end}, or {@code end} is greater than {@code length}. 3413 */ 3414 static void checkBoundsBeginEnd(int begin, int end, int length) { 3415 if (begin < 0 || begin > end || end > length) { 3416 throw new StringIndexOutOfBoundsException( 3417 "begin " + begin + ", end " + end + ", length " + length); 3418 } 3419 } 3420 3421 /** 3422 * Returns the string representation of the {@code codePoint} 3423 * argument. 3424 * 3425 * @param codePoint a {@code codePoint}. 3426 * @return a string of length {@code 1} or {@code 2} containing 3427 * as its single character the argument {@code codePoint}. 3428 * @throws IllegalArgumentException if the specified 3429 * {@code codePoint} is not a {@linkplain Character#isValidCodePoint 3430 * valid Unicode code point}. 3431 */ 3432 static String valueOfCodePoint(int codePoint) { 3433 if (COMPACT_STRINGS && StringLatin1.canEncode(codePoint)) { 3434 return new String(StringLatin1.toBytes((char)codePoint), LATIN1); 3435 } else if (Character.isBmpCodePoint(codePoint)) { 3436 return new String(StringUTF16.toBytes((char)codePoint), UTF16); 3437 } else if (Character.isSupplementaryCodePoint(codePoint)) { 3438 return new String(StringUTF16.toBytesSupplementary(codePoint), UTF16); 3439 } 3440 3441 throw new IllegalArgumentException( 3442 format("Not a valid Unicode code point: 0x%X", codePoint)); 3443 } 3444 3445 /** 3446 * Returns an {@link Optional} containing the nominal descriptor for this 3447 * instance, which is the instance itself. 3448 * 3449 * @return an {@link Optional} describing the {@linkplain String} instance 3450 * @since 12 3451 */ 3452 @Override 3453 public Optional<String> describeConstable() { 3454 return Optional.of(this); 3455 } 3456 3457 /** 3458 * Resolves this instance as a {@link ConstantDesc}, the result of which is 3459 * the instance itself. 3460 * 3461 * @param lookup ignored 3462 * @return the {@linkplain String} instance 3463 * @since 12 3464 */ 3465 @Override 3466 public String resolveConstantDesc(MethodHandles.Lookup lookup) { 3467 return this; 3468 } 3469 3470 }