1 /* 2 * Copyright (c) 1994, 2015, Oracle and/or its affiliates. All rights reserved. 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4 * 5 * This code is free software; you can redistribute it and/or modify it 6 * under the terms of the GNU General Public License version 2 only, as 7 * published by the Free Software Foundation. Oracle designates this 8 * particular file as subject to the "Classpath" exception as provided 9 * by Oracle in the LICENSE file that accompanied this code. 10 * 11 * This code is distributed in the hope that it will be useful, but WITHOUT 12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 14 * version 2 for more details (a copy is included in the LICENSE file that 15 * accompanied this code). 16 * 17 * You should have received a copy of the GNU General Public License version 18 * 2 along with this work; if not, write to the Free Software Foundation, 19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 20 * 21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 22 * or visit www.oracle.com if you need additional information or have any 23 * questions. 24 */ 25 26 package java.lang; 27 28 import java.io.ObjectStreamField; 29 import java.io.UnsupportedEncodingException; 30 import java.nio.charset.Charset; 31 import java.util.ArrayList; 32 import java.util.Arrays; 33 import java.util.Comparator; 34 import java.util.Formatter; 35 import java.util.Locale; 36 import java.util.Objects; 37 import java.util.Spliterator; 38 import java.util.StringJoiner; 39 import java.util.regex.Matcher; 40 import java.util.regex.Pattern; 41 import java.util.regex.PatternSyntaxException; 42 import java.util.stream.IntStream; 43 import java.util.stream.StreamSupport; 44 import jdk.internal.HotSpotIntrinsicCandidate; 45 46 /** 47 * The {@code String} class represents character strings. All 48 * string literals in Java programs, such as {@code "abc"}, are 49 * implemented as instances of this class. 50 * <p> 51 * Strings are constant; their values cannot be changed after they 52 * are created. String buffers support mutable strings. 53 * Because String objects are immutable they can be shared. For example: 54 * <blockquote><pre> 55 * String str = "abc"; 56 * </pre></blockquote><p> 57 * is equivalent to: 58 * <blockquote><pre> 59 * char data[] = {'a', 'b', 'c'}; 60 * String str = new String(data); 61 * </pre></blockquote><p> 62 * Here are some more examples of how strings can be used: 63 * <blockquote><pre> 64 * System.out.println("abc"); 65 * String cde = "cde"; 66 * System.out.println("abc" + cde); 67 * String c = "abc".substring(2,3); 68 * String d = cde.substring(1, 2); 69 * </pre></blockquote> 70 * <p> 71 * The class {@code String} includes methods for examining 72 * individual characters of the sequence, for comparing strings, for 73 * searching strings, for extracting substrings, and for creating a 74 * copy of a string with all characters translated to uppercase or to 75 * lowercase. Case mapping is based on the Unicode Standard version 76 * specified by the {@link java.lang.Character Character} class. 77 * <p> 78 * The Java language provides special support for the string 79 * concatenation operator ( + ), and for conversion of 80 * other objects to strings. String concatenation is implemented 81 * through the {@code StringBuilder}(or {@code StringBuffer}) 82 * class and its {@code append} method. 83 * String conversions are implemented through the method 84 * {@code toString}, defined by {@code Object} and 85 * inherited by all classes in Java. For additional information on 86 * string concatenation and conversion, see Gosling, Joy, and Steele, 87 * <i>The Java Language Specification</i>. 88 * 89 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor 90 * or method in this class will cause a {@link NullPointerException} to be 91 * thrown. 92 * 93 * <p>A {@code String} represents a string in the UTF-16 format 94 * in which <em>supplementary characters</em> are represented by <em>surrogate 95 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 96 * Character Representations</a> in the {@code Character} class for 97 * more information). 98 * Index values refer to {@code char} code units, so a supplementary 99 * character uses two positions in a {@code String}. 100 * <p>The {@code String} class provides methods for dealing with 101 * Unicode code points (i.e., characters), in addition to those for 102 * dealing with Unicode code units (i.e., {@code char} values). 103 * 104 * <p>Unless otherwise noted, methods for comparing Strings do not take locale 105 * into account. The {@link java.text.Collator} class provides methods for 106 * finer-grain, locale-sensitive String comparison. 107 * 108 * @author Lee Boynton 109 * @author Arthur van Hoff 110 * @author Martin Buchholz 111 * @author Ulf Zibis 112 * @see java.lang.Object#toString() 113 * @see java.lang.StringBuffer 114 * @see java.lang.StringBuilder 115 * @see java.nio.charset.Charset 116 * @since 1.0 117 */ 118 119 public final class String 120 implements java.io.Serializable, Comparable<String>, CharSequence { 121 122 /** The value is used for character storage. */ 123 private final byte[] value; 124 125 /** 126 * The identifier of the encoding used to encode the bytes in 127 * {@code value}. The supported values in this implementation are 128 * 129 * LATIN1 130 * UTF16 131 * 132 */ 133 private final byte coder; 134 135 /** Cache the hash code for the string */ 136 private int hash; // Default to 0 137 138 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 139 private static final long serialVersionUID = -6849794470754667710L; 140 141 /** 142 * If String compaction is disabled, the bytes in {@code value} are 143 * always encoded in UTF16. 144 * 145 * For methods with several possible implementation paths, when String 146 * compaction is disabled, only one code path is taken. 147 * 148 * The instance field value is generally opaque to optimizing JIT 149 * compilers. Therefore, in performance-sensitive place, an explicit 150 * check of the static boolean {@code COMPACT_STRINGS} is done first 151 * before checking the {@code coder} field since the static boolean 152 * {@code COMPACT_STRINGS} would be constant folded away by an 153 * optimizing JIT compiler. The idioms for these cases are as follows. 154 * 155 * For code such as: 156 * 157 * if (coder == LATIN1) { ... } 158 * 159 * can be written more optimally as 160 * 161 * if (coder() == LATIN1) { ... } 162 * 163 * or: 164 * 165 * if (COMPACT_STRINGS && coder == LATIN1) { ... } 166 * 167 * An optimizing JIT compiler can fold the above conditional as: 168 * 169 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... } 170 * COMPACT_STRINGS == false => if (false) { ... } 171 * 172 * @implNote 173 * The actual value for this field is injected by JVM. The static 174 * initialization block is used to set the value here to communicate 175 * that this static final field is not statically foldable, and to 176 * avoid any possible circular dependency during vm initialization. 177 */ 178 static final boolean COMPACT_STRINGS; 179 180 static { 181 COMPACT_STRINGS = true; 182 } 183 184 /** 185 * Class String is special cased within the Serialization Stream Protocol. 186 * 187 * A String instance is written into an ObjectOutputStream according to 188 * <a href="{@docRoot}/../platform/serialization/spec/output.html"> 189 * Object Serialization Specification, Section 6.2, "Stream Elements"</a> 190 */ 191 private static final ObjectStreamField[] serialPersistentFields = 192 new ObjectStreamField[0]; 193 194 /** 195 * Initializes a newly created {@code String} object so that it represents 196 * an empty character sequence. Note that use of this constructor is 197 * unnecessary since Strings are immutable. 198 */ 199 public String() { 200 this.value = "".value; 201 this.coder = "".coder; 202 } 203 204 /** 205 * Initializes a newly created {@code String} object so that it represents 206 * the same sequence of characters as the argument; in other words, the 207 * newly created string is a copy of the argument string. Unless an 208 * explicit copy of {@code original} is needed, use of this constructor is 209 * unnecessary since Strings are immutable. 210 * 211 * @param original 212 * A {@code String} 213 */ 214 @HotSpotIntrinsicCandidate 215 public String(String original) { 216 this.value = original.value; 217 this.coder = original.coder; 218 this.hash = original.hash; 219 } 220 221 /** 222 * Allocates a new {@code String} so that it represents the sequence of 223 * characters currently contained in the character array argument. The 224 * contents of the character array are copied; subsequent modification of 225 * the character array does not affect the newly created string. 226 * 227 * @param value 228 * The initial value of the string 229 */ 230 public String(char value[]) { 231 this(value, 0, value.length, null); 232 } 233 234 /** 235 * Allocates a new {@code String} that contains characters from a subarray 236 * of the character array argument. The {@code offset} argument is the 237 * index of the first character of the subarray and the {@code count} 238 * argument specifies the length of the subarray. The contents of the 239 * subarray are copied; subsequent modification of the character array does 240 * not affect the newly created string. 241 * 242 * @param value 243 * Array that is the source of characters 244 * 245 * @param offset 246 * The initial offset 247 * 248 * @param count 249 * The length 250 * 251 * @throws IndexOutOfBoundsException 252 * If {@code offset} is negative, {@code count} is negative, or 253 * {@code offset} is greater than {@code value.length - count} 254 */ 255 public String(char value[], int offset, int count) { 256 this(value, offset, count, rangeCheck(value, offset, count)); 257 } 258 259 private static Void rangeCheck(char[] value, int offset, int count) { 260 checkBoundsOffCount(offset, count, value.length); 261 return null; 262 } 263 264 /** 265 * Allocates a new {@code String} that contains characters from a subarray 266 * of the <a href="Character.html#unicode">Unicode code point</a> array 267 * argument. The {@code offset} argument is the index of the first code 268 * point of the subarray and the {@code count} argument specifies the 269 * length of the subarray. The contents of the subarray are converted to 270 * {@code char}s; subsequent modification of the {@code int} array does not 271 * affect the newly created string. 272 * 273 * @param codePoints 274 * Array that is the source of Unicode code points 275 * 276 * @param offset 277 * The initial offset 278 * 279 * @param count 280 * The length 281 * 282 * @throws IllegalArgumentException 283 * If any invalid Unicode code point is found in {@code 284 * codePoints} 285 * 286 * @throws IndexOutOfBoundsException 287 * If {@code offset} is negative, {@code count} is negative, or 288 * {@code offset} is greater than {@code codePoints.length - count} 289 * 290 * @since 1.5 291 */ 292 public String(int[] codePoints, int offset, int count) { 293 checkBoundsOffCount(offset, count, codePoints.length); 294 if (count == 0) { 295 this.value = "".value; 296 this.coder = "".coder; 297 return; 298 } 299 if (COMPACT_STRINGS) { 300 byte[] val = StringLatin1.toBytes(codePoints, offset, count); 301 if (val != null) { 302 this.coder = LATIN1; 303 this.value = val; 304 return; 305 } 306 } 307 this.coder = UTF16; 308 this.value = StringUTF16.toBytes(codePoints, offset, count); 309 } 310 311 /** 312 * Allocates a new {@code String} constructed from a subarray of an array 313 * of 8-bit integer values. 314 * 315 * <p> The {@code offset} argument is the index of the first byte of the 316 * subarray, and the {@code count} argument specifies the length of the 317 * subarray. 318 * 319 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 320 * specified in the method above. 321 * 322 * @deprecated This method does not properly convert bytes into characters. 323 * As of JDK 1.1, the preferred way to do this is via the 324 * {@code String} constructors that take a {@link 325 * java.nio.charset.Charset}, charset name, or that use the platform's 326 * default charset. 327 * 328 * @param ascii 329 * The bytes to be converted to characters 330 * 331 * @param hibyte 332 * The top 8 bits of each 16-bit Unicode code unit 333 * 334 * @param offset 335 * The initial offset 336 * @param count 337 * The length 338 * 339 * @throws IndexOutOfBoundsException 340 * If {@code offset} is negative, {@code count} is negative, or 341 * {@code offset} is greater than {@code ascii.length - count} 342 * 343 * @see #String(byte[], int) 344 * @see #String(byte[], int, int, java.lang.String) 345 * @see #String(byte[], int, int, java.nio.charset.Charset) 346 * @see #String(byte[], int, int) 347 * @see #String(byte[], java.lang.String) 348 * @see #String(byte[], java.nio.charset.Charset) 349 * @see #String(byte[]) 350 */ 351 @Deprecated 352 public String(byte ascii[], int hibyte, int offset, int count) { 353 checkBoundsOffCount(offset, count, ascii.length); 354 if (count == 0) { 355 this.value = "".value; 356 this.coder = "".coder; 357 return; 358 } 359 if (COMPACT_STRINGS && (byte)hibyte == 0) { 360 this.value = Arrays.copyOfRange(ascii, offset, offset + count); 361 this.coder = LATIN1; 362 } else { 363 hibyte <<= 8; 364 byte[] val = StringUTF16.newBytesFor(count); 365 for (int i = 0; i < count; i++) { 366 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff)); 367 } 368 this.value = val; 369 this.coder = UTF16; 370 } 371 } 372 373 /** 374 * Allocates a new {@code String} containing characters constructed from 375 * an array of 8-bit integer values. Each character <i>c</i>in the 376 * resulting string is constructed from the corresponding component 377 * <i>b</i> in the byte array such that: 378 * 379 * <blockquote><pre> 380 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 381 * | (<b><i>b</i></b> & 0xff)) 382 * </pre></blockquote> 383 * 384 * @deprecated This method does not properly convert bytes into 385 * characters. As of JDK 1.1, the preferred way to do this is via the 386 * {@code String} constructors that take a {@link 387 * java.nio.charset.Charset}, charset name, or that use the platform's 388 * default charset. 389 * 390 * @param ascii 391 * The bytes to be converted to characters 392 * 393 * @param hibyte 394 * The top 8 bits of each 16-bit Unicode code unit 395 * 396 * @see #String(byte[], int, int, java.lang.String) 397 * @see #String(byte[], int, int, java.nio.charset.Charset) 398 * @see #String(byte[], int, int) 399 * @see #String(byte[], java.lang.String) 400 * @see #String(byte[], java.nio.charset.Charset) 401 * @see #String(byte[]) 402 */ 403 @Deprecated 404 public String(byte ascii[], int hibyte) { 405 this(ascii, hibyte, 0, ascii.length); 406 } 407 408 /** 409 * Constructs a new {@code String} by decoding the specified subarray of 410 * bytes using the specified charset. The length of the new {@code String} 411 * is a function of the charset, and hence may not be equal to the length 412 * of the subarray. 413 * 414 * <p> The behavior of this constructor when the given bytes are not valid 415 * in the given charset is unspecified. The {@link 416 * java.nio.charset.CharsetDecoder} class should be used when more control 417 * over the decoding process is required. 418 * 419 * @param bytes 420 * The bytes to be decoded into characters 421 * 422 * @param offset 423 * The index of the first byte to decode 424 * 425 * @param length 426 * The number of bytes to decode 427 428 * @param charsetName 429 * The name of a supported {@linkplain java.nio.charset.Charset 430 * charset} 431 * 432 * @throws UnsupportedEncodingException 433 * If the named charset is not supported 434 * 435 * @throws IndexOutOfBoundsException 436 * If {@code offset} is negative, {@code length} is negative, or 437 * {@code offset} is greater than {@code bytes.length - length} 438 * 439 * @since 1.1 440 */ 441 public String(byte bytes[], int offset, int length, String charsetName) 442 throws UnsupportedEncodingException { 443 if (charsetName == null) 444 throw new NullPointerException("charsetName"); 445 checkBoundsOffCount(offset, length, bytes.length); 446 StringCoding.Result ret = 447 StringCoding.decode(charsetName, bytes, offset, length); 448 this.value = ret.value; 449 this.coder = ret.coder; 450 } 451 452 /** 453 * Constructs a new {@code String} by decoding the specified subarray of 454 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 455 * The length of the new {@code String} is a function of the charset, and 456 * hence may not be equal to the length of the subarray. 457 * 458 * <p> This method always replaces malformed-input and unmappable-character 459 * sequences with this charset's default replacement string. The {@link 460 * java.nio.charset.CharsetDecoder} class should be used when more control 461 * over the decoding process is required. 462 * 463 * @param bytes 464 * The bytes to be decoded into characters 465 * 466 * @param offset 467 * The index of the first byte to decode 468 * 469 * @param length 470 * The number of bytes to decode 471 * 472 * @param charset 473 * The {@linkplain java.nio.charset.Charset charset} to be used to 474 * decode the {@code bytes} 475 * 476 * @throws IndexOutOfBoundsException 477 * If {@code offset} is negative, {@code length} is negative, or 478 * {@code offset} is greater than {@code bytes.length - length} 479 * 480 * @since 1.6 481 */ 482 public String(byte bytes[], int offset, int length, Charset charset) { 483 if (charset == null) 484 throw new NullPointerException("charset"); 485 checkBoundsOffCount(offset, length, bytes.length); 486 StringCoding.Result ret = 487 StringCoding.decode(charset, bytes, offset, length); 488 this.value = ret.value; 489 this.coder = ret.coder; 490 } 491 492 /** 493 * Constructs a new {@code String} by decoding the specified array of bytes 494 * using the specified {@linkplain java.nio.charset.Charset charset}. The 495 * length of the new {@code String} is a function of the charset, and hence 496 * may not be equal to the length of the byte array. 497 * 498 * <p> The behavior of this constructor when the given bytes are not valid 499 * in the given charset is unspecified. The {@link 500 * java.nio.charset.CharsetDecoder} class should be used when more control 501 * over the decoding process is required. 502 * 503 * @param bytes 504 * The bytes to be decoded into characters 505 * 506 * @param charsetName 507 * The name of a supported {@linkplain java.nio.charset.Charset 508 * charset} 509 * 510 * @throws UnsupportedEncodingException 511 * If the named charset is not supported 512 * 513 * @since 1.1 514 */ 515 public String(byte bytes[], String charsetName) 516 throws UnsupportedEncodingException { 517 this(bytes, 0, bytes.length, charsetName); 518 } 519 520 /** 521 * Constructs a new {@code String} by decoding the specified array of 522 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 523 * The length of the new {@code String} is a function of the charset, and 524 * hence may not be equal to the length of the byte array. 525 * 526 * <p> This method always replaces malformed-input and unmappable-character 527 * sequences with this charset's default replacement string. The {@link 528 * java.nio.charset.CharsetDecoder} class should be used when more control 529 * over the decoding process is required. 530 * 531 * @param bytes 532 * The bytes to be decoded into characters 533 * 534 * @param charset 535 * The {@linkplain java.nio.charset.Charset charset} to be used to 536 * decode the {@code bytes} 537 * 538 * @since 1.6 539 */ 540 public String(byte bytes[], Charset charset) { 541 this(bytes, 0, bytes.length, charset); 542 } 543 544 /** 545 * Constructs a new {@code String} by decoding the specified subarray of 546 * bytes using the platform's default charset. The length of the new 547 * {@code String} is a function of the charset, and hence may not be equal 548 * to the length of the subarray. 549 * 550 * <p> The behavior of this constructor when the given bytes are not valid 551 * in the default charset is unspecified. The {@link 552 * java.nio.charset.CharsetDecoder} class should be used when more control 553 * over the decoding process is required. 554 * 555 * @param bytes 556 * The bytes to be decoded into characters 557 * 558 * @param offset 559 * The index of the first byte to decode 560 * 561 * @param length 562 * The number of bytes to decode 563 * 564 * @throws IndexOutOfBoundsException 565 * If {@code offset} is negative, {@code length} is negative, or 566 * {@code offset} is greater than {@code bytes.length - length} 567 * 568 * @since 1.1 569 */ 570 public String(byte bytes[], int offset, int length) { 571 checkBoundsOffCount(offset, length, bytes.length); 572 StringCoding.Result ret = StringCoding.decode(bytes, offset, length); 573 this.value = ret.value; 574 this.coder = ret.coder; 575 } 576 577 /** 578 * Constructs a new {@code String} by decoding the specified array of bytes 579 * using the platform's default charset. The length of the new {@code 580 * String} is a function of the charset, and hence may not be equal to the 581 * length of the byte array. 582 * 583 * <p> The behavior of this constructor when the given bytes are not valid 584 * in the default charset is unspecified. The {@link 585 * java.nio.charset.CharsetDecoder} class should be used when more control 586 * over the decoding process is required. 587 * 588 * @param bytes 589 * The bytes to be decoded into characters 590 * 591 * @since 1.1 592 */ 593 public String(byte[] bytes) { 594 this(bytes, 0, bytes.length); 595 } 596 597 /** 598 * Allocates a new string that contains the sequence of characters 599 * currently contained in the string buffer argument. The contents of the 600 * string buffer are copied; subsequent modification of the string buffer 601 * does not affect the newly created string. 602 * 603 * @param buffer 604 * A {@code StringBuffer} 605 */ 606 public String(StringBuffer buffer) { 607 this(buffer.toString()); 608 } 609 610 /** 611 * Allocates a new string that contains the sequence of characters 612 * currently contained in the string builder argument. The contents of the 613 * string builder are copied; subsequent modification of the string builder 614 * does not affect the newly created string. 615 * 616 * <p> This constructor is provided to ease migration to {@code 617 * StringBuilder}. Obtaining a string from a string builder via the {@code 618 * toString} method is likely to run faster and is generally preferred. 619 * 620 * @param builder 621 * A {@code StringBuilder} 622 * 623 * @since 1.5 624 */ 625 public String(StringBuilder builder) { 626 this(builder, null); 627 } 628 629 /* 630 * Package private constructor which shares value array for speed. 631 * this constructor is always expected to be called with share==true. 632 * a separate constructor is needed because we already have a public 633 * String(char[]) constructor that makes a copy of the given char[]. 634 */ 635 // TBD: this is kept for package internal use (Thread/System), 636 // should be removed if they all have a byte[] version 637 String(char[] val, boolean share) { 638 // assert share : "unshared not supported"; 639 this(val, 0, val.length, null); 640 } 641 642 /** 643 * Returns the length of this string. 644 * The length is equal to the number of <a href="Character.html#unicode">Unicode 645 * code units</a> in the string. 646 * 647 * @return the length of the sequence of characters represented by this 648 * object. 649 */ 650 public int length() { 651 return value.length >> coder(); 652 } 653 654 /** 655 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 656 * 657 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 658 * {@code false} 659 * 660 * @since 1.6 661 */ 662 public boolean isEmpty() { 663 return value.length == 0; 664 } 665 666 /** 667 * Returns the {@code char} value at the 668 * specified index. An index ranges from {@code 0} to 669 * {@code length() - 1}. The first {@code char} value of the sequence 670 * is at index {@code 0}, the next at index {@code 1}, 671 * and so on, as for array indexing. 672 * 673 * <p>If the {@code char} value specified by the index is a 674 * <a href="Character.html#unicode">surrogate</a>, the surrogate 675 * value is returned. 676 * 677 * @param index the index of the {@code char} value. 678 * @return the {@code char} value at the specified index of this string. 679 * The first {@code char} value is at index {@code 0}. 680 * @exception IndexOutOfBoundsException if the {@code index} 681 * argument is negative or not less than the length of this 682 * string. 683 */ 684 public char charAt(int index) { 685 if (isLatin1()) { 686 return StringLatin1.charAt(value, index); 687 } else { 688 return StringUTF16.charAt(value, index); 689 } 690 } 691 692 /** 693 * Returns the character (Unicode code point) at the specified 694 * index. The index refers to {@code char} values 695 * (Unicode code units) and ranges from {@code 0} to 696 * {@link #length()}{@code - 1}. 697 * 698 * <p> If the {@code char} value specified at the given index 699 * is in the high-surrogate range, the following index is less 700 * than the length of this {@code String}, and the 701 * {@code char} value at the following index is in the 702 * low-surrogate range, then the supplementary code point 703 * corresponding to this surrogate pair is returned. Otherwise, 704 * the {@code char} value at the given index is returned. 705 * 706 * @param index the index to the {@code char} values 707 * @return the code point value of the character at the 708 * {@code index} 709 * @exception IndexOutOfBoundsException if the {@code index} 710 * argument is negative or not less than the length of this 711 * string. 712 * @since 1.5 713 */ 714 public int codePointAt(int index) { 715 if (isLatin1()) { 716 checkIndex(index, value.length); 717 return value[index] & 0xff; 718 } 719 int length = value.length >> 1; 720 checkIndex(index, length); 721 return StringUTF16.codePointAt(value, index, length); 722 } 723 724 /** 725 * Returns the character (Unicode code point) before the specified 726 * index. The index refers to {@code char} values 727 * (Unicode code units) and ranges from {@code 1} to {@link 728 * CharSequence#length() length}. 729 * 730 * <p> If the {@code char} value at {@code (index - 1)} 731 * is in the low-surrogate range, {@code (index - 2)} is not 732 * negative, and the {@code char} value at {@code (index - 733 * 2)} is in the high-surrogate range, then the 734 * supplementary code point value of the surrogate pair is 735 * returned. If the {@code char} value at {@code index - 736 * 1} is an unpaired low-surrogate or a high-surrogate, the 737 * surrogate value is returned. 738 * 739 * @param index the index following the code point that should be returned 740 * @return the Unicode code point value before the given index. 741 * @exception IndexOutOfBoundsException if the {@code index} 742 * argument is less than 1 or greater than the length 743 * of this string. 744 * @since 1.5 745 */ 746 public int codePointBefore(int index) { 747 int i = index - 1; 748 if (i < 0 || i >= length()) { 749 throw new StringIndexOutOfBoundsException(index); 750 } 751 if (isLatin1()) { 752 return (value[i] & 0xff); 753 } 754 return StringUTF16.codePointBefore(value, index); 755 } 756 757 /** 758 * Returns the number of Unicode code points in the specified text 759 * range of this {@code String}. The text range begins at the 760 * specified {@code beginIndex} and extends to the 761 * {@code char} at index {@code endIndex - 1}. Thus the 762 * length (in {@code char}s) of the text range is 763 * {@code endIndex-beginIndex}. Unpaired surrogates within 764 * the text range count as one code point each. 765 * 766 * @param beginIndex the index to the first {@code char} of 767 * the text range. 768 * @param endIndex the index after the last {@code char} of 769 * the text range. 770 * @return the number of Unicode code points in the specified text 771 * range 772 * @exception IndexOutOfBoundsException if the 773 * {@code beginIndex} is negative, or {@code endIndex} 774 * is larger than the length of this {@code String}, or 775 * {@code beginIndex} is larger than {@code endIndex}. 776 * @since 1.5 777 */ 778 public int codePointCount(int beginIndex, int endIndex) { 779 if (beginIndex < 0 || beginIndex > endIndex || 780 endIndex > length()) { 781 throw new IndexOutOfBoundsException(); 782 } 783 if (isLatin1()) { 784 return endIndex - beginIndex; 785 } 786 return StringUTF16.codePointCount(value, beginIndex, endIndex); 787 } 788 789 /** 790 * Returns the index within this {@code String} that is 791 * offset from the given {@code index} by 792 * {@code codePointOffset} code points. Unpaired surrogates 793 * within the text range given by {@code index} and 794 * {@code codePointOffset} count as one code point each. 795 * 796 * @param index the index to be offset 797 * @param codePointOffset the offset in code points 798 * @return the index within this {@code String} 799 * @exception IndexOutOfBoundsException if {@code index} 800 * is negative or larger then the length of this 801 * {@code String}, or if {@code codePointOffset} is positive 802 * and the substring starting with {@code index} has fewer 803 * than {@code codePointOffset} code points, 804 * or if {@code codePointOffset} is negative and the substring 805 * before {@code index} has fewer than the absolute value 806 * of {@code codePointOffset} code points. 807 * @since 1.5 808 */ 809 public int offsetByCodePoints(int index, int codePointOffset) { 810 if (index < 0 || index > length()) { 811 throw new IndexOutOfBoundsException(); 812 } 813 return Character.offsetByCodePoints(this, index, codePointOffset); 814 } 815 816 /** 817 * Copies characters from this string into the destination character 818 * array. 819 * <p> 820 * The first character to be copied is at index {@code srcBegin}; 821 * the last character to be copied is at index {@code srcEnd-1} 822 * (thus the total number of characters to be copied is 823 * {@code srcEnd-srcBegin}). The characters are copied into the 824 * subarray of {@code dst} starting at index {@code dstBegin} 825 * and ending at index: 826 * <blockquote><pre> 827 * dstBegin + (srcEnd-srcBegin) - 1 828 * </pre></blockquote> 829 * 830 * @param srcBegin index of the first character in the string 831 * to copy. 832 * @param srcEnd index after the last character in the string 833 * to copy. 834 * @param dst the destination array. 835 * @param dstBegin the start offset in the destination array. 836 * @exception IndexOutOfBoundsException If any of the following 837 * is true: 838 * <ul><li>{@code srcBegin} is negative. 839 * <li>{@code srcBegin} is greater than {@code srcEnd} 840 * <li>{@code srcEnd} is greater than the length of this 841 * string 842 * <li>{@code dstBegin} is negative 843 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 844 * {@code dst.length}</ul> 845 */ 846 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 847 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 848 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 849 if (isLatin1()) { 850 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin); 851 } else { 852 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin); 853 } 854 } 855 856 /** 857 * Copies characters from this string into the destination byte array. Each 858 * byte receives the 8 low-order bits of the corresponding character. The 859 * eight high-order bits of each character are not copied and do not 860 * participate in the transfer in any way. 861 * 862 * <p> The first character to be copied is at index {@code srcBegin}; the 863 * last character to be copied is at index {@code srcEnd-1}. The total 864 * number of characters to be copied is {@code srcEnd-srcBegin}. The 865 * characters, converted to bytes, are copied into the subarray of {@code 866 * dst} starting at index {@code dstBegin} and ending at index: 867 * 868 * <blockquote><pre> 869 * dstBegin + (srcEnd-srcBegin) - 1 870 * </pre></blockquote> 871 * 872 * @deprecated This method does not properly convert characters into 873 * bytes. As of JDK 1.1, the preferred way to do this is via the 874 * {@link #getBytes()} method, which uses the platform's default charset. 875 * 876 * @param srcBegin 877 * Index of the first character in the string to copy 878 * 879 * @param srcEnd 880 * Index after the last character in the string to copy 881 * 882 * @param dst 883 * The destination array 884 * 885 * @param dstBegin 886 * The start offset in the destination array 887 * 888 * @throws IndexOutOfBoundsException 889 * If any of the following is true: 890 * <ul> 891 * <li> {@code srcBegin} is negative 892 * <li> {@code srcBegin} is greater than {@code srcEnd} 893 * <li> {@code srcEnd} is greater than the length of this String 894 * <li> {@code dstBegin} is negative 895 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 896 * dst.length} 897 * </ul> 898 */ 899 @Deprecated 900 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 901 checkBoundsBeginEnd(srcBegin, srcEnd, length()); 902 Objects.requireNonNull(dst); 903 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length); 904 if (isLatin1()) { 905 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 906 } else { 907 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin); 908 } 909 } 910 911 /** 912 * Encodes this {@code String} into a sequence of bytes using the named 913 * charset, storing the result into a new byte array. 914 * 915 * <p> The behavior of this method when this string cannot be encoded in 916 * the given charset is unspecified. The {@link 917 * java.nio.charset.CharsetEncoder} class should be used when more control 918 * over the encoding process is required. 919 * 920 * @param charsetName 921 * The name of a supported {@linkplain java.nio.charset.Charset 922 * charset} 923 * 924 * @return The resultant byte array 925 * 926 * @throws UnsupportedEncodingException 927 * If the named charset is not supported 928 * 929 * @since 1.1 930 */ 931 public byte[] getBytes(String charsetName) 932 throws UnsupportedEncodingException { 933 if (charsetName == null) throw new NullPointerException(); 934 return StringCoding.encode(charsetName, coder(), value); 935 } 936 937 /** 938 * Encodes this {@code String} into a sequence of bytes using the given 939 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 940 * new byte array. 941 * 942 * <p> This method always replaces malformed-input and unmappable-character 943 * sequences with this charset's default replacement byte array. The 944 * {@link java.nio.charset.CharsetEncoder} class should be used when more 945 * control over the encoding process is required. 946 * 947 * @param charset 948 * The {@linkplain java.nio.charset.Charset} to be used to encode 949 * the {@code String} 950 * 951 * @return The resultant byte array 952 * 953 * @since 1.6 954 */ 955 public byte[] getBytes(Charset charset) { 956 if (charset == null) throw new NullPointerException(); 957 return StringCoding.encode(charset, coder(), value); 958 } 959 960 /** 961 * Encodes this {@code String} into a sequence of bytes using the 962 * platform's default charset, storing the result into a new byte array. 963 * 964 * <p> The behavior of this method when this string cannot be encoded in 965 * the default charset is unspecified. The {@link 966 * java.nio.charset.CharsetEncoder} class should be used when more control 967 * over the encoding process is required. 968 * 969 * @return The resultant byte array 970 * 971 * @since 1.1 972 */ 973 public byte[] getBytes() { 974 return StringCoding.encode(coder(), value); 975 } 976 977 /** 978 * Compares this string to the specified object. The result is {@code 979 * true} if and only if the argument is not {@code null} and is a {@code 980 * String} object that represents the same sequence of characters as this 981 * object. 982 * 983 * <p>For finer-grained String comparison, refer to 984 * {@link java.text.Collator}. 985 * 986 * @param anObject 987 * The object to compare this {@code String} against 988 * 989 * @return {@code true} if the given object represents a {@code String} 990 * equivalent to this string, {@code false} otherwise 991 * 992 * @see #compareTo(String) 993 * @see #equalsIgnoreCase(String) 994 */ 995 public boolean equals(Object anObject) { 996 if (this == anObject) { 997 return true; 998 } 999 if (anObject instanceof String) { 1000 String aString = (String)anObject; 1001 if (coder() == aString.coder()) { 1002 return isLatin1() ? StringLatin1.equals(value, aString.value) 1003 : StringUTF16.equals(value, aString.value); 1004 } 1005 } 1006 return false; 1007 } 1008 1009 /** 1010 * Compares this string to the specified {@code StringBuffer}. The result 1011 * is {@code true} if and only if this {@code String} represents the same 1012 * sequence of characters as the specified {@code StringBuffer}. This method 1013 * synchronizes on the {@code StringBuffer}. 1014 * 1015 * <p>For finer-grained String comparison, refer to 1016 * {@link java.text.Collator}. 1017 * 1018 * @param sb 1019 * The {@code StringBuffer} to compare this {@code String} against 1020 * 1021 * @return {@code true} if this {@code String} represents the same 1022 * sequence of characters as the specified {@code StringBuffer}, 1023 * {@code false} otherwise 1024 * 1025 * @since 1.4 1026 */ 1027 public boolean contentEquals(StringBuffer sb) { 1028 return contentEquals((CharSequence)sb); 1029 } 1030 1031 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1032 int len = length(); 1033 if (len != sb.length()) { 1034 return false; 1035 } 1036 byte v1[] = value; 1037 byte v2[] = sb.getValue(); 1038 if (coder() == sb.getCoder()) { 1039 int n = v1.length; 1040 for (int i = 0; i < n; i++) { 1041 if (v1[i] != v2[i]) { 1042 return false; 1043 } 1044 } 1045 } else { 1046 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal" 1047 return false; 1048 } 1049 for (int i = 0; i < len; i++) { 1050 if ((char)(v1[i] & 0xff) != StringUTF16.getChar(v2, i)) { 1051 return false; 1052 } 1053 } 1054 } 1055 return true; 1056 } 1057 1058 /** 1059 * Compares this string to the specified {@code CharSequence}. The 1060 * result is {@code true} if and only if this {@code String} represents the 1061 * same sequence of char values as the specified sequence. Note that if the 1062 * {@code CharSequence} is a {@code StringBuffer} then the method 1063 * synchronizes on it. 1064 * 1065 * <p>For finer-grained String comparison, refer to 1066 * {@link java.text.Collator}. 1067 * 1068 * @param cs 1069 * The sequence to compare this {@code String} against 1070 * 1071 * @return {@code true} if this {@code String} represents the same 1072 * sequence of char values as the specified sequence, {@code 1073 * false} otherwise 1074 * 1075 * @since 1.5 1076 */ 1077 public boolean contentEquals(CharSequence cs) { 1078 // Argument is a StringBuffer, StringBuilder 1079 if (cs instanceof AbstractStringBuilder) { 1080 if (cs instanceof StringBuffer) { 1081 synchronized(cs) { 1082 return nonSyncContentEquals((AbstractStringBuilder)cs); 1083 } 1084 } else { 1085 return nonSyncContentEquals((AbstractStringBuilder)cs); 1086 } 1087 } 1088 // Argument is a String 1089 if (cs instanceof String) { 1090 return equals(cs); 1091 } 1092 // Argument is a generic CharSequence 1093 int n = cs.length(); 1094 if (n != length()) { 1095 return false; 1096 } 1097 byte[] val = this.value; 1098 if (isLatin1()) { 1099 for (int i = 0; i < n; i++) { 1100 if ((val[i] & 0xff) != cs.charAt(i)) { 1101 return false; 1102 } 1103 } 1104 } else { 1105 for (int i = 0; i < n; i++) { 1106 if (StringUTF16.getChar(val, i) != cs.charAt(i)) { 1107 return false; 1108 } 1109 } 1110 } 1111 return true; 1112 } 1113 1114 /** 1115 * Compares this {@code String} to another {@code String}, ignoring case 1116 * considerations. Two strings are considered equal ignoring case if they 1117 * are of the same length and corresponding characters in the two strings 1118 * are equal ignoring case. 1119 * 1120 * <p> Two characters {@code c1} and {@code c2} are considered the same 1121 * ignoring case if at least one of the following is true: 1122 * <ul> 1123 * <li> The two characters are the same (as compared by the 1124 * {@code ==} operator) 1125 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))} 1126 * on each character produces the same result 1127 * </ul> 1128 * 1129 * <p>Note that this method does <em>not</em> take locale into account, and 1130 * will result in unsatisfactory results for certain locales. The 1131 * {@link java.text.Collator} class provides locale-sensitive comparison. 1132 * 1133 * @param anotherString 1134 * The {@code String} to compare this {@code String} against 1135 * 1136 * @return {@code true} if the argument is not {@code null} and it 1137 * represents an equivalent {@code String} ignoring case; {@code 1138 * false} otherwise 1139 * 1140 * @see #equals(Object) 1141 */ 1142 public boolean equalsIgnoreCase(String anotherString) { 1143 return (this == anotherString) ? true 1144 : (anotherString != null) 1145 && (anotherString.length() == length()) 1146 && regionMatches(true, 0, anotherString, 0, length()); 1147 } 1148 1149 /** 1150 * Compares two strings lexicographically. 1151 * The comparison is based on the Unicode value of each character in 1152 * the strings. The character sequence represented by this 1153 * {@code String} object is compared lexicographically to the 1154 * character sequence represented by the argument string. The result is 1155 * a negative integer if this {@code String} object 1156 * lexicographically precedes the argument string. The result is a 1157 * positive integer if this {@code String} object lexicographically 1158 * follows the argument string. The result is zero if the strings 1159 * are equal; {@code compareTo} returns {@code 0} exactly when 1160 * the {@link #equals(Object)} method would return {@code true}. 1161 * <p> 1162 * This is the definition of lexicographic ordering. If two strings are 1163 * different, then either they have different characters at some index 1164 * that is a valid index for both strings, or their lengths are different, 1165 * or both. If they have different characters at one or more index 1166 * positions, let <i>k</i> be the smallest such index; then the string 1167 * whose character at position <i>k</i> has the smaller value, as 1168 * determined by using the {@code <} operator, lexicographically precedes the 1169 * other string. In this case, {@code compareTo} returns the 1170 * difference of the two character values at position {@code k} in 1171 * the two string -- that is, the value: 1172 * <blockquote><pre> 1173 * this.charAt(k)-anotherString.charAt(k) 1174 * </pre></blockquote> 1175 * If there is no index position at which they differ, then the shorter 1176 * string lexicographically precedes the longer string. In this case, 1177 * {@code compareTo} returns the difference of the lengths of the 1178 * strings -- that is, the value: 1179 * <blockquote><pre> 1180 * this.length()-anotherString.length() 1181 * </pre></blockquote> 1182 * 1183 * <p>For finer-grained String comparison, refer to 1184 * {@link java.text.Collator}. 1185 * 1186 * @param anotherString the {@code String} to be compared. 1187 * @return the value {@code 0} if the argument string is equal to 1188 * this string; a value less than {@code 0} if this string 1189 * is lexicographically less than the string argument; and a 1190 * value greater than {@code 0} if this string is 1191 * lexicographically greater than the string argument. 1192 */ 1193 public int compareTo(String anotherString) { 1194 byte v1[] = value; 1195 byte v2[] = anotherString.value; 1196 if (coder() == anotherString.coder()) { 1197 return isLatin1() ? StringLatin1.compareTo(v1, v2) 1198 : StringUTF16.compareTo(v1, v2); 1199 } 1200 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2) 1201 : StringUTF16.compareToLatin1(v1, v2); 1202 } 1203 1204 /** 1205 * A Comparator that orders {@code String} objects as by 1206 * {@code compareToIgnoreCase}. This comparator is serializable. 1207 * <p> 1208 * Note that this Comparator does <em>not</em> take locale into account, 1209 * and will result in an unsatisfactory ordering for certain locales. 1210 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1211 * 1212 * @see java.text.Collator 1213 * @since 1.2 1214 */ 1215 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1216 = new CaseInsensitiveComparator(); 1217 private static class CaseInsensitiveComparator 1218 implements Comparator<String>, java.io.Serializable { 1219 // use serialVersionUID from JDK 1.2.2 for interoperability 1220 private static final long serialVersionUID = 8575799808933029326L; 1221 1222 public int compare(String s1, String s2) { 1223 byte v1[] = s1.value; 1224 byte v2[] = s2.value; 1225 int n1 = s1.length(); 1226 int n2 = s2.length(); 1227 boolean s1IsLatin1 = s1.isLatin1(); 1228 boolean s2IsLatin1 = s2.isLatin1(); 1229 int min = Math.min(n1, n2); 1230 for (int i = 0; i < min; i++) { 1231 char c1 = s1IsLatin1 ? StringLatin1.getChar(v1, i) 1232 : StringUTF16.getChar(v1, i); 1233 char c2 = s2IsLatin1 ? StringLatin1.getChar(v2, i) 1234 : StringUTF16.getChar(v2, i); 1235 if (c1 != c2) { 1236 c1 = Character.toUpperCase(c1); 1237 c2 = Character.toUpperCase(c2); 1238 if (c1 != c2) { 1239 c1 = Character.toLowerCase(c1); 1240 c2 = Character.toLowerCase(c2); 1241 if (c1 != c2) { 1242 // No overflow because of numeric promotion 1243 return c1 - c2; 1244 } 1245 } 1246 } 1247 } 1248 return n1 - n2; 1249 } 1250 1251 /** Replaces the de-serialized object. */ 1252 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1253 } 1254 1255 /** 1256 * Compares two strings lexicographically, ignoring case 1257 * differences. This method returns an integer whose sign is that of 1258 * calling {@code compareTo} with normalized versions of the strings 1259 * where case differences have been eliminated by calling 1260 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1261 * each character. 1262 * <p> 1263 * Note that this method does <em>not</em> take locale into account, 1264 * and will result in an unsatisfactory ordering for certain locales. 1265 * The {@link java.text.Collator} class provides locale-sensitive comparison. 1266 * 1267 * @param str the {@code String} to be compared. 1268 * @return a negative integer, zero, or a positive integer as the 1269 * specified String is greater than, equal to, or less 1270 * than this String, ignoring case considerations. 1271 * @see java.text.Collator 1272 * @since 1.2 1273 */ 1274 public int compareToIgnoreCase(String str) { 1275 return CASE_INSENSITIVE_ORDER.compare(this, str); 1276 } 1277 1278 /** 1279 * Tests if two string regions are equal. 1280 * <p> 1281 * A substring of this {@code String} object is compared to a substring 1282 * of the argument other. The result is true if these substrings 1283 * represent identical character sequences. The substring of this 1284 * {@code String} object to be compared begins at index {@code toffset} 1285 * and has length {@code len}. The substring of other to be compared 1286 * begins at index {@code ooffset} and has length {@code len}. The 1287 * result is {@code false} if and only if at least one of the following 1288 * is true: 1289 * <ul><li>{@code toffset} is negative. 1290 * <li>{@code ooffset} is negative. 1291 * <li>{@code toffset+len} is greater than the length of this 1292 * {@code String} object. 1293 * <li>{@code ooffset+len} is greater than the length of the other 1294 * argument. 1295 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1296 * such that: 1297 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1298 * <i>k</i>{@code )} 1299 * </ul> 1300 * 1301 * <p>Note that this method does <em>not</em> take locale into account. The 1302 * {@link java.text.Collator} class provides locale-sensitive comparison. 1303 * 1304 * @param toffset the starting offset of the subregion in this string. 1305 * @param other the string argument. 1306 * @param ooffset the starting offset of the subregion in the string 1307 * argument. 1308 * @param len the number of characters to compare. 1309 * @return {@code true} if the specified subregion of this string 1310 * exactly matches the specified subregion of the string argument; 1311 * {@code false} otherwise. 1312 */ 1313 public boolean regionMatches(int toffset, String other, int ooffset, int len) { 1314 byte tv[] = value; 1315 byte ov[] = other.value; 1316 // Note: toffset, ooffset, or len might be near -1>>>1. 1317 if ((ooffset < 0) || (toffset < 0) || 1318 (toffset > (long)length() - len) || 1319 (ooffset > (long)other.length() - len)) { 1320 return false; 1321 } 1322 if (coder() == other.coder()) { 1323 if (!isLatin1() && (len > 0)) { 1324 toffset = toffset << 1; 1325 ooffset = ooffset << 1; 1326 len = len << 1; 1327 } 1328 while (len-- > 0) { 1329 if (tv[toffset++] != ov[ooffset++]) { 1330 return false; 1331 } 1332 } 1333 } else { 1334 if (coder() == LATIN1) { 1335 while (len-- > 0) { 1336 if (StringLatin1.getChar(tv, toffset++) != 1337 StringUTF16.getChar(ov, ooffset++)) { 1338 return false; 1339 } 1340 } 1341 } else { 1342 while (len-- > 0) { 1343 if (StringUTF16.getChar(tv, toffset++) != 1344 StringLatin1.getChar(ov, ooffset++)) { 1345 return false; 1346 } 1347 } 1348 } 1349 } 1350 return true; 1351 } 1352 1353 /** 1354 * Tests if two string regions are equal. 1355 * <p> 1356 * A substring of this {@code String} object is compared to a substring 1357 * of the argument {@code other}. The result is {@code true} if these 1358 * substrings represent character sequences that are the same, ignoring 1359 * case if and only if {@code ignoreCase} is true. The substring of 1360 * this {@code String} object to be compared begins at index 1361 * {@code toffset} and has length {@code len}. The substring of 1362 * {@code other} to be compared begins at index {@code ooffset} and 1363 * has length {@code len}. The result is {@code false} if and only if 1364 * at least one of the following is true: 1365 * <ul><li>{@code toffset} is negative. 1366 * <li>{@code ooffset} is negative. 1367 * <li>{@code toffset+len} is greater than the length of this 1368 * {@code String} object. 1369 * <li>{@code ooffset+len} is greater than the length of the other 1370 * argument. 1371 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1372 * integer <i>k</i> less than {@code len} such that: 1373 * <blockquote><pre> 1374 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1375 * </pre></blockquote> 1376 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1377 * integer <i>k</i> less than {@code len} such that: 1378 * <blockquote><pre> 1379 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) != 1380 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k))) 1381 * </pre></blockquote> 1382 * </ul> 1383 * 1384 * <p>Note that this method does <em>not</em> take locale into account, 1385 * and will result in unsatisfactory results for certain locales when 1386 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class 1387 * provides locale-sensitive comparison. 1388 * 1389 * @param ignoreCase if {@code true}, ignore case when comparing 1390 * characters. 1391 * @param toffset the starting offset of the subregion in this 1392 * string. 1393 * @param other the string argument. 1394 * @param ooffset the starting offset of the subregion in the string 1395 * argument. 1396 * @param len the number of characters to compare. 1397 * @return {@code true} if the specified subregion of this string 1398 * matches the specified subregion of the string argument; 1399 * {@code false} otherwise. Whether the matching is exact 1400 * or case insensitive depends on the {@code ignoreCase} 1401 * argument. 1402 */ 1403 public boolean regionMatches(boolean ignoreCase, int toffset, 1404 String other, int ooffset, int len) { 1405 if (!ignoreCase) { 1406 return regionMatches(toffset, other, ooffset, len); 1407 } 1408 // Note: toffset, ooffset, or len might be near -1>>>1. 1409 if ((ooffset < 0) || (toffset < 0) 1410 || (toffset > (long)length() - len) 1411 || (ooffset > (long)other.length() - len)) { 1412 return false; 1413 } 1414 byte tv[] = value; 1415 byte ov[] = other.value; 1416 if (coder() == other.coder()) { 1417 return isLatin1() 1418 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len) 1419 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len); 1420 } 1421 return isLatin1() 1422 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len) 1423 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len); 1424 } 1425 1426 /** 1427 * Tests if the substring of this string beginning at the 1428 * specified index starts with the specified prefix. 1429 * 1430 * @param prefix the prefix. 1431 * @param toffset where to begin looking in this string. 1432 * @return {@code true} if the character sequence represented by the 1433 * argument is a prefix of the substring of this object starting 1434 * at index {@code toffset}; {@code false} otherwise. 1435 * The result is {@code false} if {@code toffset} is 1436 * negative or greater than the length of this 1437 * {@code String} object; otherwise the result is the same 1438 * as the result of the expression 1439 * <pre> 1440 * this.substring(toffset).startsWith(prefix) 1441 * </pre> 1442 */ 1443 public boolean startsWith(String prefix, int toffset) { 1444 // Note: toffset might be near -1>>>1. 1445 if (toffset < 0 || toffset > length() - prefix.length()) { 1446 return false; 1447 } 1448 byte ta[] = value; 1449 byte pa[] = prefix.value; 1450 int po = 0; 1451 int pc = pa.length; 1452 if (coder() == prefix.coder()) { 1453 int to = isLatin1() ? toffset : toffset << 1; 1454 while (po < pc) { 1455 if (ta[to++] != pa[po++]) { 1456 return false; 1457 } 1458 } 1459 } else { 1460 if (isLatin1()) { // && pcoder == UTF16 1461 return false; 1462 } 1463 // coder == UTF16 && pcoder == LATIN1) 1464 while (po < pc) { 1465 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) { 1466 return false; 1467 } 1468 } 1469 } 1470 return true; 1471 } 1472 1473 /** 1474 * Tests if this string starts with the specified prefix. 1475 * 1476 * @param prefix the prefix. 1477 * @return {@code true} if the character sequence represented by the 1478 * argument is a prefix of the character sequence represented by 1479 * this string; {@code false} otherwise. 1480 * Note also that {@code true} will be returned if the 1481 * argument is an empty string or is equal to this 1482 * {@code String} object as determined by the 1483 * {@link #equals(Object)} method. 1484 * @since 1.0 1485 */ 1486 public boolean startsWith(String prefix) { 1487 return startsWith(prefix, 0); 1488 } 1489 1490 /** 1491 * Tests if this string ends with the specified suffix. 1492 * 1493 * @param suffix the suffix. 1494 * @return {@code true} if the character sequence represented by the 1495 * argument is a suffix of the character sequence represented by 1496 * this object; {@code false} otherwise. Note that the 1497 * result will be {@code true} if the argument is the 1498 * empty string or is equal to this {@code String} object 1499 * as determined by the {@link #equals(Object)} method. 1500 */ 1501 public boolean endsWith(String suffix) { 1502 return startsWith(suffix, length() - suffix.length()); 1503 } 1504 1505 /** 1506 * Returns a hash code for this string. The hash code for a 1507 * {@code String} object is computed as 1508 * <blockquote><pre> 1509 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1510 * </pre></blockquote> 1511 * using {@code int} arithmetic, where {@code s[i]} is the 1512 * <i>i</i>th character of the string, {@code n} is the length of 1513 * the string, and {@code ^} indicates exponentiation. 1514 * (The hash value of the empty string is zero.) 1515 * 1516 * @return a hash code value for this object. 1517 */ 1518 public int hashCode() { 1519 if (hash == 0 && value.length > 0) { 1520 hash = isLatin1() ? StringLatin1.hashCode(value) 1521 : StringUTF16.hashCode(value); 1522 } 1523 return hash; 1524 } 1525 1526 /** 1527 * Returns the index within this string of the first occurrence of 1528 * the specified character. If a character with value 1529 * {@code ch} occurs in the character sequence represented by 1530 * this {@code String} object, then the index (in Unicode 1531 * code units) of the first such occurrence is returned. For 1532 * values of {@code ch} in the range from 0 to 0xFFFF 1533 * (inclusive), this is the smallest value <i>k</i> such that: 1534 * <blockquote><pre> 1535 * this.charAt(<i>k</i>) == ch 1536 * </pre></blockquote> 1537 * is true. For other values of {@code ch}, it is the 1538 * smallest value <i>k</i> such that: 1539 * <blockquote><pre> 1540 * this.codePointAt(<i>k</i>) == ch 1541 * </pre></blockquote> 1542 * is true. In either case, if no such character occurs in this 1543 * string, then {@code -1} is returned. 1544 * 1545 * @param ch a character (Unicode code point). 1546 * @return the index of the first occurrence of the character in the 1547 * character sequence represented by this object, or 1548 * {@code -1} if the character does not occur. 1549 */ 1550 public int indexOf(int ch) { 1551 return indexOf(ch, 0); 1552 } 1553 1554 /** 1555 * Returns the index within this string of the first occurrence of the 1556 * specified character, starting the search at the specified index. 1557 * <p> 1558 * If a character with value {@code ch} occurs in the 1559 * character sequence represented by this {@code String} 1560 * object at an index no smaller than {@code fromIndex}, then 1561 * the index of the first such occurrence is returned. For values 1562 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1563 * this is the smallest value <i>k</i> such that: 1564 * <blockquote><pre> 1565 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1566 * </pre></blockquote> 1567 * is true. For other values of {@code ch}, it is the 1568 * smallest value <i>k</i> such that: 1569 * <blockquote><pre> 1570 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1571 * </pre></blockquote> 1572 * is true. In either case, if no such character occurs in this 1573 * string at or after position {@code fromIndex}, then 1574 * {@code -1} is returned. 1575 * 1576 * <p> 1577 * There is no restriction on the value of {@code fromIndex}. If it 1578 * is negative, it has the same effect as if it were zero: this entire 1579 * string may be searched. If it is greater than the length of this 1580 * string, it has the same effect as if it were equal to the length of 1581 * this string: {@code -1} is returned. 1582 * 1583 * <p>All indices are specified in {@code char} values 1584 * (Unicode code units). 1585 * 1586 * @param ch a character (Unicode code point). 1587 * @param fromIndex the index to start the search from. 1588 * @return the index of the first occurrence of the character in the 1589 * character sequence represented by this object that is greater 1590 * than or equal to {@code fromIndex}, or {@code -1} 1591 * if the character does not occur. 1592 */ 1593 public int indexOf(int ch, int fromIndex) { 1594 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex) 1595 : StringUTF16.indexOf(value, ch, fromIndex); 1596 } 1597 1598 /** 1599 * Returns the index within this string of the last occurrence of 1600 * the specified character. For values of {@code ch} in the 1601 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1602 * units) returned is the largest value <i>k</i> such that: 1603 * <blockquote><pre> 1604 * this.charAt(<i>k</i>) == ch 1605 * </pre></blockquote> 1606 * is true. For other values of {@code ch}, it is the 1607 * largest value <i>k</i> such that: 1608 * <blockquote><pre> 1609 * this.codePointAt(<i>k</i>) == ch 1610 * </pre></blockquote> 1611 * is true. In either case, if no such character occurs in this 1612 * string, then {@code -1} is returned. The 1613 * {@code String} is searched backwards starting at the last 1614 * character. 1615 * 1616 * @param ch a character (Unicode code point). 1617 * @return the index of the last occurrence of the character in the 1618 * character sequence represented by this object, or 1619 * {@code -1} if the character does not occur. 1620 */ 1621 public int lastIndexOf(int ch) { 1622 return lastIndexOf(ch, length() - 1); 1623 } 1624 1625 /** 1626 * Returns the index within this string of the last occurrence of 1627 * the specified character, searching backward starting at the 1628 * specified index. For values of {@code ch} in the range 1629 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1630 * value <i>k</i> such that: 1631 * <blockquote><pre> 1632 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1633 * </pre></blockquote> 1634 * is true. For other values of {@code ch}, it is the 1635 * largest value <i>k</i> such that: 1636 * <blockquote><pre> 1637 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1638 * </pre></blockquote> 1639 * is true. In either case, if no such character occurs in this 1640 * string at or before position {@code fromIndex}, then 1641 * {@code -1} is returned. 1642 * 1643 * <p>All indices are specified in {@code char} values 1644 * (Unicode code units). 1645 * 1646 * @param ch a character (Unicode code point). 1647 * @param fromIndex the index to start the search from. There is no 1648 * restriction on the value of {@code fromIndex}. If it is 1649 * greater than or equal to the length of this string, it has 1650 * the same effect as if it were equal to one less than the 1651 * length of this string: this entire string may be searched. 1652 * If it is negative, it has the same effect as if it were -1: 1653 * -1 is returned. 1654 * @return the index of the last occurrence of the character in the 1655 * character sequence represented by this object that is less 1656 * than or equal to {@code fromIndex}, or {@code -1} 1657 * if the character does not occur before that point. 1658 */ 1659 public int lastIndexOf(int ch, int fromIndex) { 1660 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex) 1661 : StringUTF16.lastIndexOf(value, ch, fromIndex); 1662 } 1663 1664 /** 1665 * Returns the index within this string of the first occurrence of the 1666 * specified substring. 1667 * 1668 * <p>The returned index is the smallest value {@code k} for which: 1669 * <pre>{@code 1670 * this.startsWith(str, k) 1671 * }</pre> 1672 * If no such value of {@code k} exists, then {@code -1} is returned. 1673 * 1674 * @param str the substring to search for. 1675 * @return the index of the first occurrence of the specified substring, 1676 * or {@code -1} if there is no such occurrence. 1677 */ 1678 public int indexOf(String str) { 1679 if (coder() == str.coder()) { 1680 return isLatin1() ? StringLatin1.indexOf(value, str.value) 1681 : StringUTF16.indexOf(value, str.value); 1682 } 1683 if (coder() == LATIN1) { // str.coder == UTF16 1684 return -1; 1685 } 1686 return StringUTF16.indexOfLatin1(value, str.value); 1687 } 1688 1689 /** 1690 * Returns the index within this string of the first occurrence of the 1691 * specified substring, starting at the specified index. 1692 * 1693 * <p>The returned index is the smallest value {@code k} for which: 1694 * <pre>{@code 1695 * k >= Math.min(fromIndex, this.length()) && 1696 * this.startsWith(str, k) 1697 * }</pre> 1698 * If no such value of {@code k} exists, then {@code -1} is returned. 1699 * 1700 * @param str the substring to search for. 1701 * @param fromIndex the index from which to start the search. 1702 * @return the index of the first occurrence of the specified substring, 1703 * starting at the specified index, 1704 * or {@code -1} if there is no such occurrence. 1705 */ 1706 public int indexOf(String str, int fromIndex) { 1707 return indexOf(value, coder(), length(), str, fromIndex); 1708 } 1709 1710 /** 1711 * Code shared by String and AbstractStringBuilder to do searches. The 1712 * source is the character array being searched, and the target 1713 * is the string being searched for. 1714 * 1715 * @param src the characters being searched. 1716 * @param srcCoder the coder of the source string. 1717 * @param srcCount length of the source string. 1718 * @param tgtStr the characters being searched for. 1719 * @param fromIndex the index to begin searching from. 1720 */ 1721 static int indexOf(byte[] src, byte srcCoder, int srcCount, 1722 String tgtStr, int fromIndex) { 1723 byte[] tgt = tgtStr.value; 1724 byte tgtCoder = tgtStr.coder(); 1725 int tgtCount = tgtStr.length(); 1726 1727 if (fromIndex >= srcCount) { 1728 return (tgtCount == 0 ? srcCount : -1); 1729 } 1730 if (fromIndex < 0) { 1731 fromIndex = 0; 1732 } 1733 if (tgtCount == 0) { 1734 return fromIndex; 1735 } 1736 if (srcCoder == tgtCoder) { 1737 return srcCoder == LATIN1 1738 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex) 1739 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex); 1740 } 1741 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1742 return -1; 1743 } 1744 // srcCoder == UTF16 && tgtCoder == LATIN1) { 1745 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex); 1746 } 1747 1748 /** 1749 * Returns the index within this string of the last occurrence of the 1750 * specified substring. The last occurrence of the empty string "" 1751 * is considered to occur at the index value {@code this.length()}. 1752 * 1753 * <p>The returned index is the largest value {@code k} for which: 1754 * <pre>{@code 1755 * this.startsWith(str, k) 1756 * }</pre> 1757 * If no such value of {@code k} exists, then {@code -1} is returned. 1758 * 1759 * @param str the substring to search for. 1760 * @return the index of the last occurrence of the specified substring, 1761 * or {@code -1} if there is no such occurrence. 1762 */ 1763 public int lastIndexOf(String str) { 1764 return lastIndexOf(str, length()); 1765 } 1766 1767 /** 1768 * Returns the index within this string of the last occurrence of the 1769 * specified substring, searching backward starting at the specified index. 1770 * 1771 * <p>The returned index is the largest value {@code k} for which: 1772 * <pre>{@code 1773 * k <= Math.min(fromIndex, this.length()) && 1774 * this.startsWith(str, k) 1775 * }</pre> 1776 * If no such value of {@code k} exists, then {@code -1} is returned. 1777 * 1778 * @param str the substring to search for. 1779 * @param fromIndex the index to start the search from. 1780 * @return the index of the last occurrence of the specified substring, 1781 * searching backward from the specified index, 1782 * or {@code -1} if there is no such occurrence. 1783 */ 1784 public int lastIndexOf(String str, int fromIndex) { 1785 return lastIndexOf(value, coder(), length(), str, fromIndex); 1786 } 1787 1788 /** 1789 * Code shared by String and AbstractStringBuilder to do searches. The 1790 * source is the character array being searched, and the target 1791 * is the string being searched for. 1792 * 1793 * @param src the characters being searched. 1794 * @param srcCoder coder handles the mapping between bytes/chars 1795 * @param srcCount count of the source string. 1796 * @param tgt the characters being searched for. 1797 * @param fromIndex the index to begin searching from. 1798 */ 1799 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount, 1800 String tgtStr, int fromIndex) { 1801 byte[] tgt = tgtStr.value; 1802 byte tgtCoder = tgtStr.coder(); 1803 int tgtCount = tgtStr.length(); 1804 /* 1805 * Check arguments; return immediately where possible. For 1806 * consistency, don't check for null str. 1807 */ 1808 int rightIndex = srcCount - tgtCount; 1809 if (fromIndex < 0) { 1810 return -1; 1811 } 1812 if (fromIndex > rightIndex) { 1813 fromIndex = rightIndex; 1814 } 1815 /* Empty string always matches. */ 1816 if (tgtCount == 0) { 1817 return fromIndex; 1818 } 1819 if (srcCoder == tgtCoder) { 1820 return srcCoder == LATIN1 1821 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex) 1822 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex); 1823 } 1824 if (srcCoder == LATIN1) { // && tgtCoder == UTF16 1825 return -1; 1826 } 1827 // srcCoder == UTF16 && tgtCoder == LATIN1 1828 int min = tgtCount - 1; 1829 int i = min + fromIndex; 1830 int strLastIndex = tgtCount - 1; 1831 1832 char strLastChar = (char)(tgt[strLastIndex] & 0xff); 1833 startSearchForLastChar: 1834 while (true) { 1835 while (i >= min && StringUTF16.getChar(src, i) != strLastChar) { 1836 i--; 1837 } 1838 if (i < min) { 1839 return -1; 1840 } 1841 int j = i - 1; 1842 int start = j - strLastIndex; 1843 int k = strLastIndex - 1; 1844 while (j > start) { 1845 if (StringUTF16.getChar(src, j--) != (tgt[k--] & 0xff)) { 1846 i--; 1847 continue startSearchForLastChar; 1848 } 1849 } 1850 return start + 1; 1851 } 1852 } 1853 1854 /** 1855 * Returns a string that is a substring of this string. The 1856 * substring begins with the character at the specified index and 1857 * extends to the end of this string. <p> 1858 * Examples: 1859 * <blockquote><pre> 1860 * "unhappy".substring(2) returns "happy" 1861 * "Harbison".substring(3) returns "bison" 1862 * "emptiness".substring(9) returns "" (an empty string) 1863 * </pre></blockquote> 1864 * 1865 * @param beginIndex the beginning index, inclusive. 1866 * @return the specified substring. 1867 * @exception IndexOutOfBoundsException if 1868 * {@code beginIndex} is negative or larger than the 1869 * length of this {@code String} object. 1870 */ 1871 public String substring(int beginIndex) { 1872 if (beginIndex < 0) { 1873 throw new StringIndexOutOfBoundsException(beginIndex); 1874 } 1875 int subLen = length() - beginIndex; 1876 if (subLen < 0) { 1877 throw new StringIndexOutOfBoundsException(subLen); 1878 } 1879 if (beginIndex == 0) { 1880 return this; 1881 } 1882 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1883 : StringUTF16.newString(value, beginIndex, subLen); 1884 } 1885 1886 /** 1887 * Returns a string that is a substring of this string. The 1888 * substring begins at the specified {@code beginIndex} and 1889 * extends to the character at index {@code endIndex - 1}. 1890 * Thus the length of the substring is {@code endIndex-beginIndex}. 1891 * <p> 1892 * Examples: 1893 * <blockquote><pre> 1894 * "hamburger".substring(4, 8) returns "urge" 1895 * "smiles".substring(1, 5) returns "mile" 1896 * </pre></blockquote> 1897 * 1898 * @param beginIndex the beginning index, inclusive. 1899 * @param endIndex the ending index, exclusive. 1900 * @return the specified substring. 1901 * @exception IndexOutOfBoundsException if the 1902 * {@code beginIndex} is negative, or 1903 * {@code endIndex} is larger than the length of 1904 * this {@code String} object, or 1905 * {@code beginIndex} is larger than 1906 * {@code endIndex}. 1907 */ 1908 public String substring(int beginIndex, int endIndex) { 1909 int length = length(); 1910 checkBoundsBeginEnd(beginIndex, endIndex, length); 1911 int subLen = endIndex - beginIndex; 1912 if (beginIndex == 0 && endIndex == length) { 1913 return this; 1914 } 1915 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen) 1916 : StringUTF16.newString(value, beginIndex, subLen); 1917 } 1918 1919 /** 1920 * Returns a character sequence that is a subsequence of this sequence. 1921 * 1922 * <p> An invocation of this method of the form 1923 * 1924 * <blockquote><pre> 1925 * str.subSequence(begin, end)</pre></blockquote> 1926 * 1927 * behaves in exactly the same way as the invocation 1928 * 1929 * <blockquote><pre> 1930 * str.substring(begin, end)</pre></blockquote> 1931 * 1932 * @apiNote 1933 * This method is defined so that the {@code String} class can implement 1934 * the {@link CharSequence} interface. 1935 * 1936 * @param beginIndex the begin index, inclusive. 1937 * @param endIndex the end index, exclusive. 1938 * @return the specified subsequence. 1939 * 1940 * @throws IndexOutOfBoundsException 1941 * if {@code beginIndex} or {@code endIndex} is negative, 1942 * if {@code endIndex} is greater than {@code length()}, 1943 * or if {@code beginIndex} is greater than {@code endIndex} 1944 * 1945 * @since 1.4 1946 * @spec JSR-51 1947 */ 1948 public CharSequence subSequence(int beginIndex, int endIndex) { 1949 return this.substring(beginIndex, endIndex); 1950 } 1951 1952 /** 1953 * Concatenates the specified string to the end of this string. 1954 * <p> 1955 * If the length of the argument string is {@code 0}, then this 1956 * {@code String} object is returned. Otherwise, a 1957 * {@code String} object is returned that represents a character 1958 * sequence that is the concatenation of the character sequence 1959 * represented by this {@code String} object and the character 1960 * sequence represented by the argument string.<p> 1961 * Examples: 1962 * <blockquote><pre> 1963 * "cares".concat("s") returns "caress" 1964 * "to".concat("get").concat("her") returns "together" 1965 * </pre></blockquote> 1966 * 1967 * @param str the {@code String} that is concatenated to the end 1968 * of this {@code String}. 1969 * @return a string that represents the concatenation of this object's 1970 * characters followed by the string argument's characters. 1971 */ 1972 public String concat(String str) { 1973 int olen = str.length(); 1974 if (olen == 0) { 1975 return this; 1976 } 1977 if (coder() == str.coder()) { 1978 byte[] val = this.value; 1979 byte[] oval = str.value; 1980 int len = val.length + oval.length; 1981 byte[] buf = Arrays.copyOf(val, len); 1982 System.arraycopy(oval, 0, buf, val.length, oval.length); 1983 return new String(buf, coder); 1984 } 1985 int len = length(); 1986 byte[] buf = StringUTF16.newBytesFor(len + olen); 1987 getBytes(buf, 0, UTF16); 1988 str.getBytes(buf, len, UTF16); 1989 return new String(buf, UTF16); 1990 } 1991 1992 /** 1993 * Returns a string resulting from replacing all occurrences of 1994 * {@code oldChar} in this string with {@code newChar}. 1995 * <p> 1996 * If the character {@code oldChar} does not occur in the 1997 * character sequence represented by this {@code String} object, 1998 * then a reference to this {@code String} object is returned. 1999 * Otherwise, a {@code String} object is returned that 2000 * represents a character sequence identical to the character sequence 2001 * represented by this {@code String} object, except that every 2002 * occurrence of {@code oldChar} is replaced by an occurrence 2003 * of {@code newChar}. 2004 * <p> 2005 * Examples: 2006 * <blockquote><pre> 2007 * "mesquite in your cellar".replace('e', 'o') 2008 * returns "mosquito in your collar" 2009 * "the war of baronets".replace('r', 'y') 2010 * returns "the way of bayonets" 2011 * "sparring with a purple porpoise".replace('p', 't') 2012 * returns "starring with a turtle tortoise" 2013 * "JonL".replace('q', 'x') returns "JonL" (no change) 2014 * </pre></blockquote> 2015 * 2016 * @param oldChar the old character. 2017 * @param newChar the new character. 2018 * @return a string derived from this string by replacing every 2019 * occurrence of {@code oldChar} with {@code newChar}. 2020 */ 2021 public String replace(char oldChar, char newChar) { 2022 if (oldChar != newChar) { 2023 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar) 2024 : StringUTF16.replace(value, oldChar, newChar); 2025 if (ret != null) { 2026 return ret; 2027 } 2028 } 2029 return this; 2030 } 2031 2032 /** 2033 * Tells whether or not this string matches the given <a 2034 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2035 * 2036 * <p> An invocation of this method of the form 2037 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2038 * same result as the expression 2039 * 2040 * <blockquote> 2041 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2042 * matches(<i>regex</i>, <i>str</i>)} 2043 * </blockquote> 2044 * 2045 * @param regex 2046 * the regular expression to which this string is to be matched 2047 * 2048 * @return {@code true} if, and only if, this string matches the 2049 * given regular expression 2050 * 2051 * @throws PatternSyntaxException 2052 * if the regular expression's syntax is invalid 2053 * 2054 * @see java.util.regex.Pattern 2055 * 2056 * @since 1.4 2057 * @spec JSR-51 2058 */ 2059 public boolean matches(String regex) { 2060 return Pattern.matches(regex, this); 2061 } 2062 2063 /** 2064 * Returns true if and only if this string contains the specified 2065 * sequence of char values. 2066 * 2067 * @param s the sequence to search for 2068 * @return true if this string contains {@code s}, false otherwise 2069 * @since 1.5 2070 */ 2071 public boolean contains(CharSequence s) { 2072 return indexOf(s.toString()) >= 0; 2073 } 2074 2075 /** 2076 * Replaces the first substring of this string that matches the given <a 2077 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2078 * given replacement. 2079 * 2080 * <p> An invocation of this method of the form 2081 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2082 * yields exactly the same result as the expression 2083 * 2084 * <blockquote> 2085 * <code> 2086 * {@link java.util.regex.Pattern}.{@link 2087 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2088 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2089 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>) 2090 * </code> 2091 * </blockquote> 2092 * 2093 *<p> 2094 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2095 * replacement string may cause the results to be different than if it were 2096 * being treated as a literal replacement string; see 2097 * {@link java.util.regex.Matcher#replaceFirst}. 2098 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2099 * meaning of these characters, if desired. 2100 * 2101 * @param regex 2102 * the regular expression to which this string is to be matched 2103 * @param replacement 2104 * the string to be substituted for the first match 2105 * 2106 * @return The resulting {@code String} 2107 * 2108 * @throws PatternSyntaxException 2109 * if the regular expression's syntax is invalid 2110 * 2111 * @see java.util.regex.Pattern 2112 * 2113 * @since 1.4 2114 * @spec JSR-51 2115 */ 2116 public String replaceFirst(String regex, String replacement) { 2117 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2118 } 2119 2120 /** 2121 * Replaces each substring of this string that matches the given <a 2122 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2123 * given replacement. 2124 * 2125 * <p> An invocation of this method of the form 2126 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2127 * yields exactly the same result as the expression 2128 * 2129 * <blockquote> 2130 * <code> 2131 * {@link java.util.regex.Pattern}.{@link 2132 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2133 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2134 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2135 * </code> 2136 * </blockquote> 2137 * 2138 *<p> 2139 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2140 * replacement string may cause the results to be different than if it were 2141 * being treated as a literal replacement string; see 2142 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2143 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2144 * meaning of these characters, if desired. 2145 * 2146 * @param regex 2147 * the regular expression to which this string is to be matched 2148 * @param replacement 2149 * the string to be substituted for each match 2150 * 2151 * @return The resulting {@code String} 2152 * 2153 * @throws PatternSyntaxException 2154 * if the regular expression's syntax is invalid 2155 * 2156 * @see java.util.regex.Pattern 2157 * 2158 * @since 1.4 2159 * @spec JSR-51 2160 */ 2161 public String replaceAll(String regex, String replacement) { 2162 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2163 } 2164 2165 /** 2166 * Replaces each substring of this string that matches the literal target 2167 * sequence with the specified literal replacement sequence. The 2168 * replacement proceeds from the beginning of the string to the end, for 2169 * example, replacing "aa" with "b" in the string "aaa" will result in 2170 * "ba" rather than "ab". 2171 * 2172 * @param target The sequence of char values to be replaced 2173 * @param replacement The replacement sequence of char values 2174 * @return The resulting string 2175 * @since 1.5 2176 */ 2177 public String replace(CharSequence target, CharSequence replacement) { 2178 String tgtStr = target.toString(); 2179 String replStr = replacement.toString(); 2180 int j = indexOf(tgtStr); 2181 if (j < 0) { 2182 return this; 2183 } 2184 int tgtLen = tgtStr.length(); 2185 int tgtLen1 = Math.max(tgtLen, 1); 2186 int thisLen = length(); 2187 2188 int newLenHint = thisLen - tgtLen + replStr.length(); 2189 if (newLenHint < 0) { 2190 throw new OutOfMemoryError(); 2191 } 2192 StringBuilder sb = new StringBuilder(newLenHint); 2193 int i = 0; 2194 do { 2195 sb.append(this, i, j).append(replStr); 2196 i = j + tgtLen; 2197 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0); 2198 return sb.append(this, i, thisLen).toString(); 2199 } 2200 2201 /** 2202 * Splits this string around matches of the given 2203 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2204 * 2205 * <p> The array returned by this method contains each substring of this 2206 * string that is terminated by another substring that matches the given 2207 * expression or is terminated by the end of the string. The substrings in 2208 * the array are in the order in which they occur in this string. If the 2209 * expression does not match any part of the input then the resulting array 2210 * has just one element, namely this string. 2211 * 2212 * <p> When there is a positive-width match at the beginning of this 2213 * string then an empty leading substring is included at the beginning 2214 * of the resulting array. A zero-width match at the beginning however 2215 * never produces such empty leading substring. 2216 * 2217 * <p> The {@code limit} parameter controls the number of times the 2218 * pattern is applied and therefore affects the length of the resulting 2219 * array. If the limit <i>n</i> is greater than zero then the pattern 2220 * will be applied at most <i>n</i> - 1 times, the array's 2221 * length will be no greater than <i>n</i>, and the array's last entry 2222 * will contain all input beyond the last matched delimiter. If <i>n</i> 2223 * is non-positive then the pattern will be applied as many times as 2224 * possible and the array can have any length. If <i>n</i> is zero then 2225 * the pattern will be applied as many times as possible, the array can 2226 * have any length, and trailing empty strings will be discarded. 2227 * 2228 * <p> The string {@code "boo:and:foo"}, for example, yields the 2229 * following results with these parameters: 2230 * 2231 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2232 * <tr> 2233 * <th>Regex</th> 2234 * <th>Limit</th> 2235 * <th>Result</th> 2236 * </tr> 2237 * <tr><td align=center>:</td> 2238 * <td align=center>2</td> 2239 * <td>{@code { "boo", "and:foo" }}</td></tr> 2240 * <tr><td align=center>:</td> 2241 * <td align=center>5</td> 2242 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2243 * <tr><td align=center>:</td> 2244 * <td align=center>-2</td> 2245 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2246 * <tr><td align=center>o</td> 2247 * <td align=center>5</td> 2248 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2249 * <tr><td align=center>o</td> 2250 * <td align=center>-2</td> 2251 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2252 * <tr><td align=center>o</td> 2253 * <td align=center>0</td> 2254 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2255 * </table></blockquote> 2256 * 2257 * <p> An invocation of this method of the form 2258 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2259 * yields the same result as the expression 2260 * 2261 * <blockquote> 2262 * <code> 2263 * {@link java.util.regex.Pattern}.{@link 2264 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2265 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2266 * </code> 2267 * </blockquote> 2268 * 2269 * 2270 * @param regex 2271 * the delimiting regular expression 2272 * 2273 * @param limit 2274 * the result threshold, as described above 2275 * 2276 * @return the array of strings computed by splitting this string 2277 * around matches of the given regular expression 2278 * 2279 * @throws PatternSyntaxException 2280 * if the regular expression's syntax is invalid 2281 * 2282 * @see java.util.regex.Pattern 2283 * 2284 * @since 1.4 2285 * @spec JSR-51 2286 */ 2287 public String[] split(String regex, int limit) { 2288 /* fastpath if the regex is a 2289 (1)one-char String and this character is not one of the 2290 RegEx's meta characters ".$|()[{^?*+\\", or 2291 (2)two-char String and the first char is the backslash and 2292 the second is not the ascii digit or ascii letter. 2293 */ 2294 char ch = 0; 2295 if (((regex.length() == 1 && 2296 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2297 (regex.length() == 2 && 2298 regex.charAt(0) == '\\' && 2299 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2300 ((ch-'a')|('z'-ch)) < 0 && 2301 ((ch-'A')|('Z'-ch)) < 0)) && 2302 (ch < Character.MIN_HIGH_SURROGATE || 2303 ch > Character.MAX_LOW_SURROGATE)) 2304 { 2305 int off = 0; 2306 int next = 0; 2307 boolean limited = limit > 0; 2308 ArrayList<String> list = new ArrayList<>(); 2309 while ((next = indexOf(ch, off)) != -1) { 2310 if (!limited || list.size() < limit - 1) { 2311 list.add(substring(off, next)); 2312 off = next + 1; 2313 } else { // last one 2314 //assert (list.size() == limit - 1); 2315 int last = length(); 2316 list.add(substring(off, last)); 2317 off = last; 2318 break; 2319 } 2320 } 2321 // If no match was found, return this 2322 if (off == 0) 2323 return new String[]{this}; 2324 2325 // Add remaining segment 2326 if (!limited || list.size() < limit) 2327 list.add(substring(off, length())); 2328 2329 // Construct result 2330 int resultSize = list.size(); 2331 if (limit == 0) { 2332 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) { 2333 resultSize--; 2334 } 2335 } 2336 String[] result = new String[resultSize]; 2337 return list.subList(0, resultSize).toArray(result); 2338 } 2339 return Pattern.compile(regex).split(this, limit); 2340 } 2341 2342 /** 2343 * Splits this string around matches of the given <a 2344 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2345 * 2346 * <p> This method works as if by invoking the two-argument {@link 2347 * #split(String, int) split} method with the given expression and a limit 2348 * argument of zero. Trailing empty strings are therefore not included in 2349 * the resulting array. 2350 * 2351 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2352 * results with these expressions: 2353 * 2354 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2355 * <tr> 2356 * <th>Regex</th> 2357 * <th>Result</th> 2358 * </tr> 2359 * <tr><td align=center>:</td> 2360 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2361 * <tr><td align=center>o</td> 2362 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2363 * </table></blockquote> 2364 * 2365 * 2366 * @param regex 2367 * the delimiting regular expression 2368 * 2369 * @return the array of strings computed by splitting this string 2370 * around matches of the given regular expression 2371 * 2372 * @throws PatternSyntaxException 2373 * if the regular expression's syntax is invalid 2374 * 2375 * @see java.util.regex.Pattern 2376 * 2377 * @since 1.4 2378 * @spec JSR-51 2379 */ 2380 public String[] split(String regex) { 2381 return split(regex, 0); 2382 } 2383 2384 /** 2385 * Returns a new String composed of copies of the 2386 * {@code CharSequence elements} joined together with a copy of 2387 * the specified {@code delimiter}. 2388 * 2389 * <blockquote>For example, 2390 * <pre>{@code 2391 * String message = String.join("-", "Java", "is", "cool"); 2392 * // message returned is: "Java-is-cool" 2393 * }</pre></blockquote> 2394 * 2395 * Note that if an element is null, then {@code "null"} is added. 2396 * 2397 * @param delimiter the delimiter that separates each element 2398 * @param elements the elements to join together. 2399 * 2400 * @return a new {@code String} that is composed of the {@code elements} 2401 * separated by the {@code delimiter} 2402 * 2403 * @throws NullPointerException If {@code delimiter} or {@code elements} 2404 * is {@code null} 2405 * 2406 * @see java.util.StringJoiner 2407 * @since 1.8 2408 */ 2409 public static String join(CharSequence delimiter, CharSequence... elements) { 2410 Objects.requireNonNull(delimiter); 2411 Objects.requireNonNull(elements); 2412 // Number of elements not likely worth Arrays.stream overhead. 2413 StringJoiner joiner = new StringJoiner(delimiter); 2414 for (CharSequence cs: elements) { 2415 joiner.add(cs); 2416 } 2417 return joiner.toString(); 2418 } 2419 2420 /** 2421 * Returns a new {@code String} composed of copies of the 2422 * {@code CharSequence elements} joined together with a copy of the 2423 * specified {@code delimiter}. 2424 * 2425 * <blockquote>For example, 2426 * <pre>{@code 2427 * List<String> strings = new LinkedList<>(); 2428 * strings.add("Java");strings.add("is"); 2429 * strings.add("cool"); 2430 * String message = String.join(" ", strings); 2431 * //message returned is: "Java is cool" 2432 * 2433 * Set<String> strings = new LinkedHashSet<>(); 2434 * strings.add("Java"); strings.add("is"); 2435 * strings.add("very"); strings.add("cool"); 2436 * String message = String.join("-", strings); 2437 * //message returned is: "Java-is-very-cool" 2438 * }</pre></blockquote> 2439 * 2440 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2441 * 2442 * @param delimiter a sequence of characters that is used to separate each 2443 * of the {@code elements} in the resulting {@code String} 2444 * @param elements an {@code Iterable} that will have its {@code elements} 2445 * joined together. 2446 * 2447 * @return a new {@code String} that is composed from the {@code elements} 2448 * argument 2449 * 2450 * @throws NullPointerException If {@code delimiter} or {@code elements} 2451 * is {@code null} 2452 * 2453 * @see #join(CharSequence,CharSequence...) 2454 * @see java.util.StringJoiner 2455 * @since 1.8 2456 */ 2457 public static String join(CharSequence delimiter, 2458 Iterable<? extends CharSequence> elements) { 2459 Objects.requireNonNull(delimiter); 2460 Objects.requireNonNull(elements); 2461 StringJoiner joiner = new StringJoiner(delimiter); 2462 for (CharSequence cs: elements) { 2463 joiner.add(cs); 2464 } 2465 return joiner.toString(); 2466 } 2467 2468 /** 2469 * Converts all of the characters in this {@code String} to lower 2470 * case using the rules of the given {@code Locale}. Case mapping is based 2471 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2472 * class. Since case mappings are not always 1:1 char mappings, the resulting 2473 * {@code String} may be a different length than the original {@code String}. 2474 * <p> 2475 * Examples of lowercase mappings are in the following table: 2476 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2477 * <tr> 2478 * <th>Language Code of Locale</th> 2479 * <th>Upper Case</th> 2480 * <th>Lower Case</th> 2481 * <th>Description</th> 2482 * </tr> 2483 * <tr> 2484 * <td>tr (Turkish)</td> 2485 * <td>\u0130</td> 2486 * <td>\u0069</td> 2487 * <td>capital letter I with dot above -> small letter i</td> 2488 * </tr> 2489 * <tr> 2490 * <td>tr (Turkish)</td> 2491 * <td>\u0049</td> 2492 * <td>\u0131</td> 2493 * <td>capital letter I -> small letter dotless i </td> 2494 * </tr> 2495 * <tr> 2496 * <td>(all)</td> 2497 * <td>French Fries</td> 2498 * <td>french fries</td> 2499 * <td>lowercased all chars in String</td> 2500 * </tr> 2501 * <tr> 2502 * <td>(all)</td> 2503 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2504 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2505 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2506 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2507 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2508 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2509 * <td>lowercased all chars in String</td> 2510 * </tr> 2511 * </table> 2512 * 2513 * @param locale use the case transformation rules for this locale 2514 * @return the {@code String}, converted to lowercase. 2515 * @see java.lang.String#toLowerCase() 2516 * @see java.lang.String#toUpperCase() 2517 * @see java.lang.String#toUpperCase(Locale) 2518 * @since 1.1 2519 */ 2520 public String toLowerCase(Locale locale) { 2521 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale) 2522 : StringUTF16.toLowerCase(this, value, locale); 2523 } 2524 2525 /** 2526 * Converts all of the characters in this {@code String} to lower 2527 * case using the rules of the default locale. This is equivalent to calling 2528 * {@code toLowerCase(Locale.getDefault())}. 2529 * <p> 2530 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2531 * results if used for strings that are intended to be interpreted locale 2532 * independently. 2533 * Examples are programming language identifiers, protocol keys, and HTML 2534 * tags. 2535 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2536 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2537 * LATIN SMALL LETTER DOTLESS I character. 2538 * To obtain correct results for locale insensitive strings, use 2539 * {@code toLowerCase(Locale.ROOT)}. 2540 * 2541 * @return the {@code String}, converted to lowercase. 2542 * @see java.lang.String#toLowerCase(Locale) 2543 */ 2544 public String toLowerCase() { 2545 return toLowerCase(Locale.getDefault()); 2546 } 2547 2548 /** 2549 * Converts all of the characters in this {@code String} to upper 2550 * case using the rules of the given {@code Locale}. Case mapping is based 2551 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2552 * class. Since case mappings are not always 1:1 char mappings, the resulting 2553 * {@code String} may be a different length than the original {@code String}. 2554 * <p> 2555 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2556 * 2557 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2558 * <tr> 2559 * <th>Language Code of Locale</th> 2560 * <th>Lower Case</th> 2561 * <th>Upper Case</th> 2562 * <th>Description</th> 2563 * </tr> 2564 * <tr> 2565 * <td>tr (Turkish)</td> 2566 * <td>\u0069</td> 2567 * <td>\u0130</td> 2568 * <td>small letter i -> capital letter I with dot above</td> 2569 * </tr> 2570 * <tr> 2571 * <td>tr (Turkish)</td> 2572 * <td>\u0131</td> 2573 * <td>\u0049</td> 2574 * <td>small letter dotless i -> capital letter I</td> 2575 * </tr> 2576 * <tr> 2577 * <td>(all)</td> 2578 * <td>\u00df</td> 2579 * <td>\u0053 \u0053</td> 2580 * <td>small letter sharp s -> two letters: SS</td> 2581 * </tr> 2582 * <tr> 2583 * <td>(all)</td> 2584 * <td>Fahrvergnügen</td> 2585 * <td>FAHRVERGNÜGEN</td> 2586 * <td></td> 2587 * </tr> 2588 * </table> 2589 * @param locale use the case transformation rules for this locale 2590 * @return the {@code String}, converted to uppercase. 2591 * @see java.lang.String#toUpperCase() 2592 * @see java.lang.String#toLowerCase() 2593 * @see java.lang.String#toLowerCase(Locale) 2594 * @since 1.1 2595 */ 2596 public String toUpperCase(Locale locale) { 2597 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale) 2598 : StringUTF16.toUpperCase(this, value, locale); 2599 } 2600 2601 /** 2602 * Converts all of the characters in this {@code String} to upper 2603 * case using the rules of the default locale. This method is equivalent to 2604 * {@code toUpperCase(Locale.getDefault())}. 2605 * <p> 2606 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2607 * results if used for strings that are intended to be interpreted locale 2608 * independently. 2609 * Examples are programming language identifiers, protocol keys, and HTML 2610 * tags. 2611 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2612 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2613 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2614 * To obtain correct results for locale insensitive strings, use 2615 * {@code toUpperCase(Locale.ROOT)}. 2616 * 2617 * @return the {@code String}, converted to uppercase. 2618 * @see java.lang.String#toUpperCase(Locale) 2619 */ 2620 public String toUpperCase() { 2621 return toUpperCase(Locale.getDefault()); 2622 } 2623 2624 /** 2625 * Returns a string whose value is this string, with any leading and trailing 2626 * whitespace removed. 2627 * <p> 2628 * If this {@code String} object represents an empty character 2629 * sequence, or the first and last characters of character sequence 2630 * represented by this {@code String} object both have codes 2631 * greater than {@code '\u005Cu0020'} (the space character), then a 2632 * reference to this {@code String} object is returned. 2633 * <p> 2634 * Otherwise, if there is no character with a code greater than 2635 * {@code '\u005Cu0020'} in the string, then a 2636 * {@code String} object representing an empty string is 2637 * returned. 2638 * <p> 2639 * Otherwise, let <i>k</i> be the index of the first character in the 2640 * string whose code is greater than {@code '\u005Cu0020'}, and let 2641 * <i>m</i> be the index of the last character in the string whose code 2642 * is greater than {@code '\u005Cu0020'}. A {@code String} 2643 * object is returned, representing the substring of this string that 2644 * begins with the character at index <i>k</i> and ends with the 2645 * character at index <i>m</i>-that is, the result of 2646 * {@code this.substring(k, m + 1)}. 2647 * <p> 2648 * This method may be used to trim whitespace (as defined above) from 2649 * the beginning and end of a string. 2650 * 2651 * @return A string whose value is this string, with any leading and trailing white 2652 * space removed, or this string if it has no leading or 2653 * trailing white space. 2654 */ 2655 public String trim() { 2656 String ret = isLatin1() ? StringLatin1.trim(value) 2657 : StringUTF16.trim(value); 2658 return ret == null ? this : ret; 2659 } 2660 2661 /** 2662 * This object (which is already a string!) is itself returned. 2663 * 2664 * @return the string itself. 2665 */ 2666 public String toString() { 2667 return this; 2668 } 2669 2670 /** 2671 * Returns a stream of {@code int} zero-extending the {@code char} values 2672 * from this sequence. Any char which maps to a <a 2673 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code 2674 * point</a> is passed through uninterpreted. 2675 * 2676 * @return an IntStream of char values from this sequence 2677 * @since 1.9 2678 */ 2679 @Override 2680 public IntStream chars() { 2681 return StreamSupport.intStream( 2682 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2683 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE), 2684 false); 2685 } 2686 2687 2688 /** 2689 * Returns a stream of code point values from this sequence. Any surrogate 2690 * pairs encountered in the sequence are combined as if by {@linkplain 2691 * Character#toCodePoint Character.toCodePoint} and the result is passed 2692 * to the stream. Any other code units, including ordinary BMP characters, 2693 * unpaired surrogates, and undefined code units, are zero-extended to 2694 * {@code int} values which are then passed to the stream. 2695 * 2696 * @return an IntStream of Unicode code points from this sequence 2697 * @since 1.9 2698 */ 2699 @Override 2700 public IntStream codePoints() { 2701 return StreamSupport.intStream( 2702 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE) 2703 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE), 2704 false); 2705 } 2706 2707 /** 2708 * Converts this string to a new character array. 2709 * 2710 * @return a newly allocated character array whose length is the length 2711 * of this string and whose contents are initialized to contain 2712 * the character sequence represented by this string. 2713 */ 2714 public char[] toCharArray() { 2715 return isLatin1() ? StringLatin1.toChars(value) 2716 : StringUTF16.toChars(value); 2717 } 2718 2719 /** 2720 * Returns a formatted string using the specified format string and 2721 * arguments. 2722 * 2723 * <p> The locale always used is the one returned by {@link 2724 * java.util.Locale#getDefault() Locale.getDefault()}. 2725 * 2726 * @param format 2727 * A <a href="../util/Formatter.html#syntax">format string</a> 2728 * 2729 * @param args 2730 * Arguments referenced by the format specifiers in the format 2731 * string. If there are more arguments than format specifiers, the 2732 * extra arguments are ignored. The number of arguments is 2733 * variable and may be zero. The maximum number of arguments is 2734 * limited by the maximum dimension of a Java array as defined by 2735 * <cite>The Java™ Virtual Machine Specification</cite>. 2736 * The behaviour on a 2737 * {@code null} argument depends on the <a 2738 * href="../util/Formatter.html#syntax">conversion</a>. 2739 * 2740 * @throws java.util.IllegalFormatException 2741 * If a format string contains an illegal syntax, a format 2742 * specifier that is incompatible with the given arguments, 2743 * insufficient arguments given the format string, or other 2744 * illegal conditions. For specification of all possible 2745 * formatting errors, see the <a 2746 * href="../util/Formatter.html#detail">Details</a> section of the 2747 * formatter class specification. 2748 * 2749 * @return A formatted string 2750 * 2751 * @see java.util.Formatter 2752 * @since 1.5 2753 */ 2754 public static String format(String format, Object... args) { 2755 return new Formatter().format(format, args).toString(); 2756 } 2757 2758 /** 2759 * Returns a formatted string using the specified locale, format string, 2760 * and arguments. 2761 * 2762 * @param l 2763 * The {@linkplain java.util.Locale locale} to apply during 2764 * formatting. If {@code l} is {@code null} then no localization 2765 * is applied. 2766 * 2767 * @param format 2768 * A <a href="../util/Formatter.html#syntax">format string</a> 2769 * 2770 * @param args 2771 * Arguments referenced by the format specifiers in the format 2772 * string. If there are more arguments than format specifiers, the 2773 * extra arguments are ignored. The number of arguments is 2774 * variable and may be zero. The maximum number of arguments is 2775 * limited by the maximum dimension of a Java array as defined by 2776 * <cite>The Java™ Virtual Machine Specification</cite>. 2777 * The behaviour on a 2778 * {@code null} argument depends on the 2779 * <a href="../util/Formatter.html#syntax">conversion</a>. 2780 * 2781 * @throws java.util.IllegalFormatException 2782 * If a format string contains an illegal syntax, a format 2783 * specifier that is incompatible with the given arguments, 2784 * insufficient arguments given the format string, or other 2785 * illegal conditions. For specification of all possible 2786 * formatting errors, see the <a 2787 * href="../util/Formatter.html#detail">Details</a> section of the 2788 * formatter class specification 2789 * 2790 * @return A formatted string 2791 * 2792 * @see java.util.Formatter 2793 * @since 1.5 2794 */ 2795 public static String format(Locale l, String format, Object... args) { 2796 return new Formatter(l).format(format, args).toString(); 2797 } 2798 2799 /** 2800 * Returns the string representation of the {@code Object} argument. 2801 * 2802 * @param obj an {@code Object}. 2803 * @return if the argument is {@code null}, then a string equal to 2804 * {@code "null"}; otherwise, the value of 2805 * {@code obj.toString()} is returned. 2806 * @see java.lang.Object#toString() 2807 */ 2808 public static String valueOf(Object obj) { 2809 return (obj == null) ? "null" : obj.toString(); 2810 } 2811 2812 /** 2813 * Returns the string representation of the {@code char} array 2814 * argument. The contents of the character array are copied; subsequent 2815 * modification of the character array does not affect the returned 2816 * string. 2817 * 2818 * @param data the character array. 2819 * @return a {@code String} that contains the characters of the 2820 * character array. 2821 */ 2822 public static String valueOf(char data[]) { 2823 return new String(data); 2824 } 2825 2826 /** 2827 * Returns the string representation of a specific subarray of the 2828 * {@code char} array argument. 2829 * <p> 2830 * The {@code offset} argument is the index of the first 2831 * character of the subarray. The {@code count} argument 2832 * specifies the length of the subarray. The contents of the subarray 2833 * are copied; subsequent modification of the character array does not 2834 * affect the returned string. 2835 * 2836 * @param data the character array. 2837 * @param offset initial offset of the subarray. 2838 * @param count length of the subarray. 2839 * @return a {@code String} that contains the characters of the 2840 * specified subarray of the character array. 2841 * @exception IndexOutOfBoundsException if {@code offset} is 2842 * negative, or {@code count} is negative, or 2843 * {@code offset+count} is larger than 2844 * {@code data.length}. 2845 */ 2846 public static String valueOf(char data[], int offset, int count) { 2847 return new String(data, offset, count); 2848 } 2849 2850 /** 2851 * Equivalent to {@link #valueOf(char[], int, int)}. 2852 * 2853 * @param data the character array. 2854 * @param offset initial offset of the subarray. 2855 * @param count length of the subarray. 2856 * @return a {@code String} that contains the characters of the 2857 * specified subarray of the character array. 2858 * @exception IndexOutOfBoundsException if {@code offset} is 2859 * negative, or {@code count} is negative, or 2860 * {@code offset+count} is larger than 2861 * {@code data.length}. 2862 */ 2863 public static String copyValueOf(char data[], int offset, int count) { 2864 return new String(data, offset, count); 2865 } 2866 2867 /** 2868 * Equivalent to {@link #valueOf(char[])}. 2869 * 2870 * @param data the character array. 2871 * @return a {@code String} that contains the characters of the 2872 * character array. 2873 */ 2874 public static String copyValueOf(char data[]) { 2875 return new String(data); 2876 } 2877 2878 /** 2879 * Returns the string representation of the {@code boolean} argument. 2880 * 2881 * @param b a {@code boolean}. 2882 * @return if the argument is {@code true}, a string equal to 2883 * {@code "true"} is returned; otherwise, a string equal to 2884 * {@code "false"} is returned. 2885 */ 2886 public static String valueOf(boolean b) { 2887 return b ? "true" : "false"; 2888 } 2889 2890 /** 2891 * Returns the string representation of the {@code char} 2892 * argument. 2893 * 2894 * @param c a {@code char}. 2895 * @return a string of length {@code 1} containing 2896 * as its single character the argument {@code c}. 2897 */ 2898 public static String valueOf(char c) { 2899 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) { 2900 return new String(StringLatin1.toBytes(c), LATIN1); 2901 } 2902 return new String(StringUTF16.toBytes(c), UTF16); 2903 } 2904 2905 /** 2906 * Returns the string representation of the {@code int} argument. 2907 * <p> 2908 * The representation is exactly the one returned by the 2909 * {@code Integer.toString} method of one argument. 2910 * 2911 * @param i an {@code int}. 2912 * @return a string representation of the {@code int} argument. 2913 * @see java.lang.Integer#toString(int, int) 2914 */ 2915 public static String valueOf(int i) { 2916 return Integer.toString(i); 2917 } 2918 2919 /** 2920 * Returns the string representation of the {@code long} argument. 2921 * <p> 2922 * The representation is exactly the one returned by the 2923 * {@code Long.toString} method of one argument. 2924 * 2925 * @param l a {@code long}. 2926 * @return a string representation of the {@code long} argument. 2927 * @see java.lang.Long#toString(long) 2928 */ 2929 public static String valueOf(long l) { 2930 return Long.toString(l); 2931 } 2932 2933 /** 2934 * Returns the string representation of the {@code float} argument. 2935 * <p> 2936 * The representation is exactly the one returned by the 2937 * {@code Float.toString} method of one argument. 2938 * 2939 * @param f a {@code float}. 2940 * @return a string representation of the {@code float} argument. 2941 * @see java.lang.Float#toString(float) 2942 */ 2943 public static String valueOf(float f) { 2944 return Float.toString(f); 2945 } 2946 2947 /** 2948 * Returns the string representation of the {@code double} argument. 2949 * <p> 2950 * The representation is exactly the one returned by the 2951 * {@code Double.toString} method of one argument. 2952 * 2953 * @param d a {@code double}. 2954 * @return a string representation of the {@code double} argument. 2955 * @see java.lang.Double#toString(double) 2956 */ 2957 public static String valueOf(double d) { 2958 return Double.toString(d); 2959 } 2960 2961 /** 2962 * Returns a canonical representation for the string object. 2963 * <p> 2964 * A pool of strings, initially empty, is maintained privately by the 2965 * class {@code String}. 2966 * <p> 2967 * When the intern method is invoked, if the pool already contains a 2968 * string equal to this {@code String} object as determined by 2969 * the {@link #equals(Object)} method, then the string from the pool is 2970 * returned. Otherwise, this {@code String} object is added to the 2971 * pool and a reference to this {@code String} object is returned. 2972 * <p> 2973 * It follows that for any two strings {@code s} and {@code t}, 2974 * {@code s.intern() == t.intern()} is {@code true} 2975 * if and only if {@code s.equals(t)} is {@code true}. 2976 * <p> 2977 * All literal strings and string-valued constant expressions are 2978 * interned. String literals are defined in section 3.10.5 of the 2979 * <cite>The Java™ Language Specification</cite>. 2980 * 2981 * @return a string that has the same contents as this string, but is 2982 * guaranteed to be from a pool of unique strings. 2983 */ 2984 public native String intern(); 2985 2986 //////////////////////////////////////////////////////////////// 2987 2988 /** 2989 * Copy character bytes from this string into dst starting at dstBegin. 2990 * This method doesn't perform any range checking. 2991 * 2992 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two 2993 * coders are different, and dst is big enough (range check) 2994 * 2995 * @param dstBegin the char index, not offset of byte[] 2996 * @param coder the coder of dst[] 2997 */ 2998 void getBytes(byte dst[], int dstBegin, byte coder) { 2999 if (coder() == coder) { 3000 System.arraycopy(value, 0, dst, dstBegin << coder, value.length); 3001 } else { // this.coder == LATIN && coder == UTF16 3002 StringLatin1.inflate(value, 0, dst, dstBegin, value.length); 3003 } 3004 } 3005 3006 /* 3007 * Package private constructor. Trailing Void argument is there for 3008 * disambiguating it against other (public) constructors. 3009 * 3010 * Stores the char[] value into a byte[] that each byte represents 3011 * the8 low-order bits of the corresponding character, if the char[] 3012 * contains only latin1 character. Or a byte[] that stores all 3013 * characters in their byte sequences defined by the {@code StringUTF16}. 3014 */ 3015 String(char[] value, int off, int len, Void sig) { 3016 if (len == 0) { 3017 this.value = "".value; 3018 this.coder = "".coder; 3019 return; 3020 } 3021 if (COMPACT_STRINGS) { 3022 byte[] val = StringUTF16.compress(value, off, len); 3023 if (val != null) { 3024 this.value = val; 3025 this.coder = LATIN1; 3026 return; 3027 } 3028 } 3029 this.coder = UTF16; 3030 this.value = StringUTF16.toBytes(value, off, len); 3031 } 3032 3033 /* 3034 * Package private constructor. Trailing Void argument is there for 3035 * disambiguating it against other (public) constructors. 3036 */ 3037 String(AbstractStringBuilder asb, Void sig) { 3038 byte[] val = asb.getValue(); 3039 int length = asb.length(); 3040 if (asb.isLatin1()) { 3041 this.coder = LATIN1; 3042 this.value = Arrays.copyOfRange(val, 0, length); 3043 } else { 3044 if (COMPACT_STRINGS) { 3045 byte[] buf = StringUTF16.compress(val, 0, length); 3046 if (buf != null) { 3047 this.coder = LATIN1; 3048 this.value = buf; 3049 return; 3050 } 3051 } 3052 this.coder = UTF16; 3053 this.value = Arrays.copyOfRange(val, 0, length << 1); 3054 } 3055 } 3056 3057 /* 3058 * Package private constructor which shares value array for speed. 3059 */ 3060 String(byte[] value, byte coder) { 3061 this.value = value; 3062 this.coder = coder; 3063 } 3064 3065 byte coder() { 3066 return COMPACT_STRINGS ? coder : UTF16; 3067 } 3068 3069 private boolean isLatin1() { 3070 return COMPACT_STRINGS && coder == LATIN1; 3071 } 3072 3073 static final byte LATIN1 = 0; 3074 static final byte UTF16 = 1; 3075 3076 /* 3077 * StringIndexOutOfBoundsException if {@code index} is 3078 * negative or greater than or equal to {@code length}. 3079 */ 3080 static void checkIndex(int index, int length) { 3081 if (index < 0 || index >= length) { 3082 throw new StringIndexOutOfBoundsException("index " + index); 3083 } 3084 } 3085 3086 /* 3087 * StringIndexOutOfBoundsException if {@code offset} 3088 * is negative or greater than {@code length}. 3089 */ 3090 static void checkOffset(int offset, int length) { 3091 if (offset < 0 || offset > length) { 3092 throw new StringIndexOutOfBoundsException("offset " + offset + 3093 ",length " + length); 3094 } 3095 } 3096 3097 /* 3098 * Check {@code offset}, {@code count} against {@code 0} and {@code length} 3099 * bounds. 3100 * 3101 * @throws StringIndexOutOfBoundsException 3102 * If {@code offset} is negative, {@code count} is negative, 3103 * or {@code offset} is greater than {@code length - count} 3104 */ 3105 static void checkBoundsOffCount(int offset, int count, int length) { 3106 if (offset < 0 || count < 0 || offset > length - count) { 3107 throw new StringIndexOutOfBoundsException( 3108 "offset " + offset + ", count " + count + ", length " + length); 3109 } 3110 } 3111 3112 /* 3113 * Check {@code begin}, {@code end} against {@code 0} and {@code length} 3114 * bounds. 3115 * 3116 * @throws StringIndexOutOfBoundsException 3117 * If {@code begin} is negative, {@code begin} is greater than 3118 * {@code end}, or {@code end} is greater than {@code length}. 3119 */ 3120 private static void checkBoundsBeginEnd(int begin, int end, int length) { 3121 if (begin < 0 || begin > end || end > length) { 3122 throw new StringIndexOutOfBoundsException( 3123 "begin " + begin + ", end " + end + ", length " + length); 3124 } 3125 } 3126 }