1 /* 2 * Copyright (c) 1994, 2010, 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.regex.Matcher; 37 import java.util.regex.Pattern; 38 import java.util.regex.PatternSyntaxException; 39 40 /** 41 * The {@code String} class represents character strings. All 42 * string literals in Java programs, such as {@code "abc"}, are 43 * implemented as instances of this class. 44 * <p> 45 * Strings are constant; their values cannot be changed after they 46 * are created. String buffers support mutable strings. 47 * Because String objects are immutable they can be shared. For example: 48 * <p><blockquote><pre> 49 * String str = "abc"; 50 * </pre></blockquote><p> 51 * is equivalent to: 52 * <p><blockquote><pre> 53 * char data[] = {'a', 'b', 'c'}; 54 * String str = new String(data); 55 * </pre></blockquote><p> 56 * Here are some more examples of how strings can be used: 57 * <p><blockquote><pre> 58 * System.out.println("abc"); 59 * String cde = "cde"; 60 * System.out.println("abc" + cde); 61 * String c = "abc".substring(2,3); 62 * String d = cde.substring(1, 2); 63 * </pre></blockquote> 64 * <p> 65 * The class {@code String} includes methods for examining 66 * individual characters of the sequence, for comparing strings, for 67 * searching strings, for extracting substrings, and for creating a 68 * copy of a string with all characters translated to uppercase or to 69 * lowercase. Case mapping is based on the Unicode Standard version 70 * specified by the {@link java.lang.Character Character} class. 71 * <p> 72 * The Java language provides special support for the string 73 * concatenation operator ( + ), and for conversion of 74 * other objects to strings. String concatenation is implemented 75 * through the {@code StringBuilder}(or {@code StringBuffer}) 76 * class and its {@code append} method. 77 * String conversions are implemented through the method 78 * {@code toString}, defined by {@code Object} and 79 * inherited by all classes in Java. For additional information on 80 * string concatenation and conversion, see Gosling, Joy, and Steele, 81 * <i>The Java Language Specification</i>. 82 * 83 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor 84 * or method in this class will cause a {@link NullPointerException} to be 85 * thrown. 86 * 87 * <p>A {@code String} represents a string in the UTF-16 format 88 * in which <em>supplementary characters</em> are represented by <em>surrogate 89 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 90 * Character Representations</a> in the {@code Character} class for 91 * more information). 92 * Index values refer to {@code char} code units, so a supplementary 93 * character uses two positions in a {@code String}. 94 * <p>The {@code String} class provides methods for dealing with 95 * Unicode code points (i.e., characters), in addition to those for 96 * dealing with Unicode code units (i.e., {@code char} values). 97 * 98 * @author Lee Boynton 99 * @author Arthur van Hoff 100 * @author Martin Buchholz 101 * @author Ulf Zibis 102 * @see java.lang.Object#toString() 103 * @see java.lang.StringBuffer 104 * @see java.lang.StringBuilder 105 * @see java.nio.charset.Charset 106 * @since JDK1.0 107 */ 108 109 public final class String 110 implements java.io.Serializable, Comparable<String>, CharSequence { 111 /** The value is used for character storage. */ 112 private final char value[]; 113 114 /** The offset is the first index of the storage that is used. */ 115 private final int offset; 116 117 /** The count is the number of characters in the String. */ 118 private final int count; 119 120 /** Cache the hash code for the string */ 121 private int hash; // Default to 0 122 123 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 124 private static final long serialVersionUID = -6849794470754667710L; 125 126 /** 127 * Class String is special cased within the Serialization Stream Protocol. 128 * 129 * A String instance is written initially into an ObjectOutputStream in the 130 * following format: 131 * <pre> 132 * {@code TC_STRING} (utf String) 133 * </pre> 134 * The String is written by method {@code DataOutput.writeUTF}. 135 * A new handle is generated to refer to all future references to the 136 * string instance within the stream. 137 */ 138 private static final ObjectStreamField[] serialPersistentFields = 139 new ObjectStreamField[0]; 140 141 /** 142 * Initializes a newly created {@code String} object so that it represents 143 * an empty character sequence. Note that use of this constructor is 144 * unnecessary since Strings are immutable. 145 */ 146 public String() { 147 this.offset = 0; 148 this.count = 0; 149 this.value = new char[0]; 150 } 151 152 /** 153 * Initializes a newly created {@code String} object so that it represents 154 * the same sequence of characters as the argument; in other words, the 155 * newly created string is a copy of the argument string. Unless an 156 * explicit copy of {@code original} is needed, use of this constructor is 157 * unnecessary since Strings are immutable. 158 * 159 * @param original 160 * A {@code String} 161 */ 162 public String(String original) { 163 int size = original.count; 164 char[] originalValue = original.value; 165 char[] v; 166 if (originalValue.length > size) { 167 // The array representing the String is bigger than the new 168 // String itself. Perhaps this constructor is being called 169 // in order to trim the baggage, so make a copy of the array. 170 int off = original.offset; 171 v = Arrays.copyOfRange(originalValue, off, off+size); 172 } else { 173 // The array representing the String is the same 174 // size as the String, so no point in making a copy. 175 v = originalValue; 176 } 177 this.offset = 0; 178 this.count = size; 179 this.value = v; 180 } 181 182 /** 183 * Allocates a new {@code String} so that it represents the sequence of 184 * characters currently contained in the character array argument. The 185 * contents of the character array are copied; subsequent modification of 186 * the character array does not affect the newly created string. 187 * 188 * @param value 189 * The initial value of the string 190 */ 191 public String(char value[]) { 192 int size = value.length; 193 this.offset = 0; 194 this.count = size; 195 this.value = Arrays.copyOf(value, size); 196 } 197 198 /** 199 * Allocates a new {@code String} that contains characters from a subarray 200 * of the character array argument. The {@code offset} argument is the 201 * index of the first character of the subarray and the {@code count} 202 * argument specifies the length of the subarray. The contents of the 203 * subarray are copied; subsequent modification of the character array does 204 * not affect the newly created string. 205 * 206 * @param value 207 * Array that is the source of characters 208 * 209 * @param offset 210 * The initial offset 211 * 212 * @param count 213 * The length 214 * 215 * @throws IndexOutOfBoundsException 216 * If the {@code offset} and {@code count} arguments index 217 * characters outside the bounds of the {@code value} array 218 */ 219 public String(char value[], int offset, int count) { 220 if (offset < 0) { 221 throw new StringIndexOutOfBoundsException(offset); 222 } 223 if (count < 0) { 224 throw new StringIndexOutOfBoundsException(count); 225 } 226 // Note: offset or count might be near -1>>>1. 227 if (offset > value.length - count) { 228 throw new StringIndexOutOfBoundsException(offset + count); 229 } 230 this.offset = 0; 231 this.count = count; 232 this.value = Arrays.copyOfRange(value, offset, offset+count); 233 } 234 235 /** 236 * Allocates a new {@code String} that contains characters from a subarray 237 * of the <a href="Character.html#unicode">Unicode code point</a> array 238 * argument. The {@code offset} argument is the index of the first code 239 * point of the subarray and the {@code count} argument specifies the 240 * length of the subarray. The contents of the subarray are converted to 241 * {@code char}s; subsequent modification of the {@code int} array does not 242 * affect the newly created string. 243 * 244 * @param codePoints 245 * Array that is the source of Unicode code points 246 * 247 * @param offset 248 * The initial offset 249 * 250 * @param count 251 * The length 252 * 253 * @throws IllegalArgumentException 254 * If any invalid Unicode code point is found in {@code 255 * codePoints} 256 * 257 * @throws IndexOutOfBoundsException 258 * If the {@code offset} and {@code count} arguments index 259 * characters outside the bounds of the {@code codePoints} array 260 * 261 * @since 1.5 262 */ 263 public String(int[] codePoints, int offset, int count) { 264 if (offset < 0) { 265 throw new StringIndexOutOfBoundsException(offset); 266 } 267 if (count < 0) { 268 throw new StringIndexOutOfBoundsException(count); 269 } 270 // Note: offset or count might be near -1>>>1. 271 if (offset > codePoints.length - count) { 272 throw new StringIndexOutOfBoundsException(offset + count); 273 } 274 275 final int end = offset + count; 276 277 // Pass 1: Compute precise size of char[] 278 int n = count; 279 for (int i = offset; i < end; i++) { 280 int c = codePoints[i]; 281 if (Character.isBmpCodePoint(c)) 282 continue; 283 else if (Character.isValidCodePoint(c)) 284 n++; 285 else throw new IllegalArgumentException(Integer.toString(c)); 286 } 287 288 // Pass 2: Allocate and fill in char[] 289 final char[] v = new char[n]; 290 291 for (int i = offset, j = 0; i < end; i++, j++) { 292 int c = codePoints[i]; 293 if (Character.isBmpCodePoint(c)) 294 v[j] = (char) c; 295 else 296 Character.toSurrogates(c, v, j++); 297 } 298 299 this.value = v; 300 this.count = n; 301 this.offset = 0; 302 } 303 304 /** 305 * Allocates a new {@code String} constructed from a subarray of an array 306 * of 8-bit integer values. 307 * 308 * <p> The {@code offset} argument is the index of the first byte of the 309 * subarray, and the {@code count} argument specifies the length of the 310 * subarray. 311 * 312 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 313 * specified in the method above. 314 * 315 * @deprecated This method does not properly convert bytes into characters. 316 * As of JDK 1.1, the preferred way to do this is via the 317 * {@code String} constructors that take a {@link 318 * java.nio.charset.Charset}, charset name, or that use the platform's 319 * default charset. 320 * 321 * @param ascii 322 * The bytes to be converted to characters 323 * 324 * @param hibyte 325 * The top 8 bits of each 16-bit Unicode code unit 326 * 327 * @param offset 328 * The initial offset 329 * @param count 330 * The length 331 * 332 * @throws IndexOutOfBoundsException 333 * If the {@code offset} or {@code count} argument is invalid 334 * 335 * @see #String(byte[], int) 336 * @see #String(byte[], int, int, java.lang.String) 337 * @see #String(byte[], int, int, java.nio.charset.Charset) 338 * @see #String(byte[], int, int) 339 * @see #String(byte[], java.lang.String) 340 * @see #String(byte[], java.nio.charset.Charset) 341 * @see #String(byte[]) 342 */ 343 @Deprecated 344 public String(byte ascii[], int hibyte, int offset, int count) { 345 checkBounds(ascii, offset, count); 346 char value[] = new char[count]; 347 348 if (hibyte == 0) { 349 for (int i = count ; i-- > 0 ;) { 350 value[i] = (char) (ascii[i + offset] & 0xff); 351 } 352 } else { 353 hibyte <<= 8; 354 for (int i = count ; i-- > 0 ;) { 355 value[i] = (char) (hibyte | (ascii[i + offset] & 0xff)); 356 } 357 } 358 this.offset = 0; 359 this.count = count; 360 this.value = value; 361 } 362 363 /** 364 * Allocates a new {@code String} containing characters constructed from 365 * an array of 8-bit integer values. Each character <i>c</i>in the 366 * resulting string is constructed from the corresponding component 367 * <i>b</i> in the byte array such that: 368 * 369 * <blockquote><pre> 370 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 371 * | (<b><i>b</i></b> & 0xff)) 372 * </pre></blockquote> 373 * 374 * @deprecated This method does not properly convert bytes into 375 * characters. As of JDK 1.1, the preferred way to do this is via the 376 * {@code String} constructors that take a {@link 377 * java.nio.charset.Charset}, charset name, or that use the platform's 378 * default charset. 379 * 380 * @param ascii 381 * The bytes to be converted to characters 382 * 383 * @param hibyte 384 * The top 8 bits of each 16-bit Unicode code unit 385 * 386 * @see #String(byte[], int, int, java.lang.String) 387 * @see #String(byte[], int, int, java.nio.charset.Charset) 388 * @see #String(byte[], int, int) 389 * @see #String(byte[], java.lang.String) 390 * @see #String(byte[], java.nio.charset.Charset) 391 * @see #String(byte[]) 392 */ 393 @Deprecated 394 public String(byte ascii[], int hibyte) { 395 this(ascii, hibyte, 0, ascii.length); 396 } 397 398 /* Common private utility method used to bounds check the byte array 399 * and requested offset & length values used by the String(byte[],..) 400 * constructors. 401 */ 402 private static void checkBounds(byte[] bytes, int offset, int length) { 403 if (length < 0) 404 throw new StringIndexOutOfBoundsException(length); 405 if (offset < 0) 406 throw new StringIndexOutOfBoundsException(offset); 407 if (offset > bytes.length - length) 408 throw new StringIndexOutOfBoundsException(offset + length); 409 } 410 411 /** 412 * Constructs a new {@code String} by decoding the specified subarray of 413 * bytes using the specified charset. The length of the new {@code String} 414 * is a function of the charset, and hence may not be equal to the length 415 * of the subarray. 416 * 417 * <p> The behavior of this constructor when the given bytes are not valid 418 * in the given charset is unspecified. The {@link 419 * java.nio.charset.CharsetDecoder} class should be used when more control 420 * over the decoding process is required. 421 * 422 * @param bytes 423 * The bytes to be decoded into characters 424 * 425 * @param offset 426 * The index of the first byte to decode 427 * 428 * @param length 429 * The number of bytes to decode 430 431 * @param charsetName 432 * The name of a supported {@linkplain java.nio.charset.Charset 433 * charset} 434 * 435 * @throws UnsupportedEncodingException 436 * If the named charset is not supported 437 * 438 * @throws IndexOutOfBoundsException 439 * If the {@code offset} and {@code length} arguments index 440 * characters outside the bounds of the {@code bytes} array 441 * 442 * @since JDK1.1 443 */ 444 public String(byte bytes[], int offset, int length, String charsetName) 445 throws UnsupportedEncodingException 446 { 447 if (charsetName == null) 448 throw new NullPointerException("charsetName"); 449 checkBounds(bytes, offset, length); 450 char[] v = StringCoding.decode(charsetName, bytes, offset, length); 451 this.offset = 0; 452 this.count = v.length; 453 this.value = v; 454 } 455 456 /** 457 * Constructs a new {@code String} by decoding the specified subarray of 458 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 459 * The length of the new {@code String} is a function of the charset, and 460 * hence may not be equal to the length of the subarray. 461 * 462 * <p> This method always replaces malformed-input and unmappable-character 463 * sequences with this charset's default replacement string. The {@link 464 * java.nio.charset.CharsetDecoder} class should be used when more control 465 * over the decoding process is required. 466 * 467 * @param bytes 468 * The bytes to be decoded into characters 469 * 470 * @param offset 471 * The index of the first byte to decode 472 * 473 * @param length 474 * The number of bytes to decode 475 * 476 * @param charset 477 * The {@linkplain java.nio.charset.Charset charset} to be used to 478 * decode the {@code bytes} 479 * 480 * @throws IndexOutOfBoundsException 481 * If the {@code offset} and {@code length} arguments index 482 * characters outside the bounds of the {@code bytes} array 483 * 484 * @since 1.6 485 */ 486 public String(byte bytes[], int offset, int length, Charset charset) { 487 if (charset == null) 488 throw new NullPointerException("charset"); 489 checkBounds(bytes, offset, length); 490 char[] v = StringCoding.decode(charset, bytes, offset, length); 491 this.offset = 0; 492 this.count = v.length; 493 this.value = v; 494 } 495 496 /** 497 * Constructs a new {@code String} by decoding the specified array of bytes 498 * using the specified {@linkplain java.nio.charset.Charset charset}. The 499 * length of the new {@code String} is a function of the charset, and hence 500 * may not be equal to the length of the byte array. 501 * 502 * <p> The behavior of this constructor when the given bytes are not valid 503 * in the given charset is unspecified. The {@link 504 * java.nio.charset.CharsetDecoder} class should be used when more control 505 * over the decoding process is required. 506 * 507 * @param bytes 508 * The bytes to be decoded into characters 509 * 510 * @param charsetName 511 * The name of a supported {@linkplain java.nio.charset.Charset 512 * charset} 513 * 514 * @throws UnsupportedEncodingException 515 * If the named charset is not supported 516 * 517 * @since JDK1.1 518 */ 519 public String(byte bytes[], String charsetName) 520 throws UnsupportedEncodingException 521 { 522 this(bytes, 0, bytes.length, charsetName); 523 } 524 525 /** 526 * Constructs a new {@code String} by decoding the specified array of 527 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 528 * The length of the new {@code String} is a function of the charset, and 529 * hence may not be equal to the length of the byte array. 530 * 531 * <p> This method always replaces malformed-input and unmappable-character 532 * sequences with this charset's default replacement string. The {@link 533 * java.nio.charset.CharsetDecoder} class should be used when more control 534 * over the decoding process is required. 535 * 536 * @param bytes 537 * The bytes to be decoded into characters 538 * 539 * @param charset 540 * The {@linkplain java.nio.charset.Charset charset} to be used to 541 * decode the {@code bytes} 542 * 543 * @since 1.6 544 */ 545 public String(byte bytes[], Charset charset) { 546 this(bytes, 0, bytes.length, charset); 547 } 548 549 /** 550 * Constructs a new {@code String} by decoding the specified subarray of 551 * bytes using the platform's default charset. The length of the new 552 * {@code String} is a function of the charset, and hence may not be equal 553 * to the length of the subarray. 554 * 555 * <p> The behavior of this constructor when the given bytes are not valid 556 * in the default charset is unspecified. The {@link 557 * java.nio.charset.CharsetDecoder} class should be used when more control 558 * over the decoding process is required. 559 * 560 * @param bytes 561 * The bytes to be decoded into characters 562 * 563 * @param offset 564 * The index of the first byte to decode 565 * 566 * @param length 567 * The number of bytes to decode 568 * 569 * @throws IndexOutOfBoundsException 570 * If the {@code offset} and the {@code length} arguments index 571 * characters outside the bounds of the {@code bytes} array 572 * 573 * @since JDK1.1 574 */ 575 public String(byte bytes[], int offset, int length) { 576 checkBounds(bytes, offset, length); 577 char[] v = StringCoding.decode(bytes, offset, length); 578 this.offset = 0; 579 this.count = v.length; 580 this.value = v; 581 } 582 583 /** 584 * Constructs a new {@code String} by decoding the specified array of bytes 585 * using the platform's default charset. The length of the new {@code 586 * String} is a function of the charset, and hence may not be equal to the 587 * length of the byte array. 588 * 589 * <p> The behavior of this constructor when the given bytes are not valid 590 * in the default charset is unspecified. The {@link 591 * java.nio.charset.CharsetDecoder} class should be used when more control 592 * over the decoding process is required. 593 * 594 * @param bytes 595 * The bytes to be decoded into characters 596 * 597 * @since JDK1.1 598 */ 599 public String(byte bytes[]) { 600 this(bytes, 0, bytes.length); 601 } 602 603 /** 604 * Allocates a new string that contains the sequence of characters 605 * currently contained in the string buffer argument. The contents of the 606 * string buffer are copied; subsequent modification of the string buffer 607 * does not affect the newly created string. 608 * 609 * @param buffer 610 * A {@code StringBuffer} 611 */ 612 public String(StringBuffer buffer) { 613 String result = buffer.toString(); 614 this.value = result.value; 615 this.count = result.count; 616 this.offset = result.offset; 617 } 618 619 /** 620 * Allocates a new string that contains the sequence of characters 621 * currently contained in the string builder argument. The contents of the 622 * string builder are copied; subsequent modification of the string builder 623 * does not affect the newly created string. 624 * 625 * <p> This constructor is provided to ease migration to {@code 626 * StringBuilder}. Obtaining a string from a string builder via the {@code 627 * toString} method is likely to run faster and is generally preferred. 628 * 629 * @param builder 630 * A {@code StringBuilder} 631 * 632 * @since 1.5 633 */ 634 public String(StringBuilder builder) { 635 String result = builder.toString(); 636 this.value = result.value; 637 this.count = result.count; 638 this.offset = result.offset; 639 } 640 641 642 // Package private constructor which shares value array for speed. 643 String(int offset, int count, char value[]) { 644 this.value = value; 645 this.offset = offset; 646 this.count = count; 647 } 648 649 /** 650 * Returns the length of this string. 651 * The length is equal to the number of <a href="Character.html#unicode">Unicode 652 * code units</a> in the string. 653 * 654 * @return the length of the sequence of characters represented by this 655 * object. 656 */ 657 public int length() { 658 return count; 659 } 660 661 /** 662 * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>. 663 * 664 * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise 665 * <tt>false</tt> 666 * 667 * @since 1.6 668 */ 669 public boolean isEmpty() { 670 return count == 0; 671 } 672 673 /** 674 * Returns the {@code char} value at the 675 * specified index. An index ranges from {@code 0} to 676 * {@code length() - 1}. The first {@code char} value of the sequence 677 * is at index {@code 0}, the next at index {@code 1}, 678 * and so on, as for array indexing. 679 * 680 * <p>If the {@code char} value specified by the index is a 681 * <a href="Character.html#unicode">surrogate</a>, the surrogate 682 * value is returned. 683 * 684 * @param index the index of the {@code char} value. 685 * @return the {@code char} value at the specified index of this string. 686 * The first {@code char} value is at index {@code 0}. 687 * @exception IndexOutOfBoundsException if the {@code index} 688 * argument is negative or not less than the length of this 689 * string. 690 */ 691 public char charAt(int index) { 692 if ((index < 0) || (index >= count)) { 693 throw new StringIndexOutOfBoundsException(index); 694 } 695 return value[index + offset]; 696 } 697 698 /** 699 * Returns the character (Unicode code point) at the specified 700 * index. The index refers to {@code char} values 701 * (Unicode code units) and ranges from {@code 0} to 702 * {@link #length()}{@code - 1}. 703 * 704 * <p> If the {@code char} value specified at the given index 705 * is in the high-surrogate range, the following index is less 706 * than the length of this {@code String}, and the 707 * {@code char} value at the following index is in the 708 * low-surrogate range, then the supplementary code point 709 * corresponding to this surrogate pair is returned. Otherwise, 710 * the {@code char} value at the given index is returned. 711 * 712 * @param index the index to the {@code char} values 713 * @return the code point value of the character at the 714 * {@code index} 715 * @exception IndexOutOfBoundsException if the {@code index} 716 * argument is negative or not less than the length of this 717 * string. 718 * @since 1.5 719 */ 720 public int codePointAt(int index) { 721 if ((index < 0) || (index >= count)) { 722 throw new StringIndexOutOfBoundsException(index); 723 } 724 return Character.codePointAtImpl(value, offset + index, offset + count); 725 } 726 727 /** 728 * Returns the character (Unicode code point) before the specified 729 * index. The index refers to {@code char} values 730 * (Unicode code units) and ranges from {@code 1} to {@link 731 * CharSequence#length() length}. 732 * 733 * <p> If the {@code char} value at {@code (index - 1)} 734 * is in the low-surrogate range, {@code (index - 2)} is not 735 * negative, and the {@code char} value at {@code (index - 736 * 2)} is in the high-surrogate range, then the 737 * supplementary code point value of the surrogate pair is 738 * returned. If the {@code char} value at {@code index - 739 * 1} is an unpaired low-surrogate or a high-surrogate, the 740 * surrogate value is returned. 741 * 742 * @param index the index following the code point that should be returned 743 * @return the Unicode code point value before the given index. 744 * @exception IndexOutOfBoundsException if the {@code index} 745 * argument is less than 1 or greater than the length 746 * of this string. 747 * @since 1.5 748 */ 749 public int codePointBefore(int index) { 750 int i = index - 1; 751 if ((i < 0) || (i >= count)) { 752 throw new StringIndexOutOfBoundsException(index); 753 } 754 return Character.codePointBeforeImpl(value, offset + index, offset); 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 || endIndex > count || beginIndex > endIndex) { 780 throw new IndexOutOfBoundsException(); 781 } 782 return Character.codePointCountImpl(value, offset+beginIndex, endIndex-beginIndex); 783 } 784 785 /** 786 * Returns the index within this {@code String} that is 787 * offset from the given {@code index} by 788 * {@code codePointOffset} code points. Unpaired surrogates 789 * within the text range given by {@code index} and 790 * {@code codePointOffset} count as one code point each. 791 * 792 * @param index the index to be offset 793 * @param codePointOffset the offset in code points 794 * @return the index within this {@code String} 795 * @exception IndexOutOfBoundsException if {@code index} 796 * is negative or larger then the length of this 797 * {@code String}, or if {@code codePointOffset} is positive 798 * and the substring starting with {@code index} has fewer 799 * than {@code codePointOffset} code points, 800 * or if {@code codePointOffset} is negative and the substring 801 * before {@code index} has fewer than the absolute value 802 * of {@code codePointOffset} code points. 803 * @since 1.5 804 */ 805 public int offsetByCodePoints(int index, int codePointOffset) { 806 if (index < 0 || index > count) { 807 throw new IndexOutOfBoundsException(); 808 } 809 return Character.offsetByCodePointsImpl(value, offset, count, 810 offset+index, codePointOffset) - offset; 811 } 812 813 /** 814 * Copy characters from this string into dst starting at dstBegin. 815 * This method doesn't perform any range checking. 816 */ 817 void getChars(char dst[], int dstBegin) { 818 System.arraycopy(value, offset, dst, dstBegin, count); 819 } 820 821 /** 822 * Copies characters from this string into the destination character 823 * array. 824 * <p> 825 * The first character to be copied is at index {@code srcBegin}; 826 * the last character to be copied is at index {@code srcEnd-1} 827 * (thus the total number of characters to be copied is 828 * {@code srcEnd-srcBegin}). The characters are copied into the 829 * subarray of {@code dst} starting at index {@code dstBegin} 830 * and ending at index: 831 * <p><blockquote><pre> 832 * dstbegin + (srcEnd-srcBegin) - 1 833 * </pre></blockquote> 834 * 835 * @param srcBegin index of the first character in the string 836 * to copy. 837 * @param srcEnd index after the last character in the string 838 * to copy. 839 * @param dst the destination array. 840 * @param dstBegin the start offset in the destination array. 841 * @exception IndexOutOfBoundsException If any of the following 842 * is true: 843 * <ul><li>{@code srcBegin} is negative. 844 * <li>{@code srcBegin} is greater than {@code srcEnd} 845 * <li>{@code srcEnd} is greater than the length of this 846 * string 847 * <li>{@code dstBegin} is negative 848 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 849 * {@code dst.length}</ul> 850 */ 851 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 852 if (srcBegin < 0) { 853 throw new StringIndexOutOfBoundsException(srcBegin); 854 } 855 if (srcEnd > count) { 856 throw new StringIndexOutOfBoundsException(srcEnd); 857 } 858 if (srcBegin > srcEnd) { 859 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 860 } 861 System.arraycopy(value, offset + srcBegin, dst, dstBegin, 862 srcEnd - srcBegin); 863 } 864 865 /** 866 * Copies characters from this string into the destination byte array. Each 867 * byte receives the 8 low-order bits of the corresponding character. The 868 * eight high-order bits of each character are not copied and do not 869 * participate in the transfer in any way. 870 * 871 * <p> The first character to be copied is at index {@code srcBegin}; the 872 * last character to be copied is at index {@code srcEnd-1}. The total 873 * number of characters to be copied is {@code srcEnd-srcBegin}. The 874 * characters, converted to bytes, are copied into the subarray of {@code 875 * dst} starting at index {@code dstBegin} and ending at index: 876 * 877 * <blockquote><pre> 878 * dstbegin + (srcEnd-srcBegin) - 1 879 * </pre></blockquote> 880 * 881 * @deprecated This method does not properly convert characters into 882 * bytes. As of JDK 1.1, the preferred way to do this is via the 883 * {@link #getBytes()} method, which uses the platform's default charset. 884 * 885 * @param srcBegin 886 * Index of the first character in the string to copy 887 * 888 * @param srcEnd 889 * Index after the last character in the string to copy 890 * 891 * @param dst 892 * The destination array 893 * 894 * @param dstBegin 895 * The start offset in the destination array 896 * 897 * @throws IndexOutOfBoundsException 898 * If any of the following is true: 899 * <ul> 900 * <li> {@code srcBegin} is negative 901 * <li> {@code srcBegin} is greater than {@code srcEnd} 902 * <li> {@code srcEnd} is greater than the length of this String 903 * <li> {@code dstBegin} is negative 904 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 905 * dst.length} 906 * </ul> 907 */ 908 @Deprecated 909 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 910 if (srcBegin < 0) { 911 throw new StringIndexOutOfBoundsException(srcBegin); 912 } 913 if (srcEnd > count) { 914 throw new StringIndexOutOfBoundsException(srcEnd); 915 } 916 if (srcBegin > srcEnd) { 917 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 918 } 919 int j = dstBegin; 920 int n = offset + srcEnd; 921 int i = offset + srcBegin; 922 char[] val = value; /* avoid getfield opcode */ 923 924 while (i < n) { 925 dst[j++] = (byte)val[i++]; 926 } 927 } 928 929 /** 930 * Encodes this {@code String} into a sequence of bytes using the named 931 * charset, storing the result into a new byte array. 932 * 933 * <p> The behavior of this method when this string cannot be encoded in 934 * the given charset is unspecified. The {@link 935 * java.nio.charset.CharsetEncoder} class should be used when more control 936 * over the encoding process is required. 937 * 938 * @param charsetName 939 * The name of a supported {@linkplain java.nio.charset.Charset 940 * charset} 941 * 942 * @return The resultant byte array 943 * 944 * @throws UnsupportedEncodingException 945 * If the named charset is not supported 946 * 947 * @since JDK1.1 948 */ 949 public byte[] getBytes(String charsetName) 950 throws UnsupportedEncodingException 951 { 952 if (charsetName == null) throw new NullPointerException(); 953 return StringCoding.encode(charsetName, value, offset, count); 954 } 955 956 /** 957 * Encodes this {@code String} into a sequence of bytes using the given 958 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 959 * new byte array. 960 * 961 * <p> This method always replaces malformed-input and unmappable-character 962 * sequences with this charset's default replacement byte array. The 963 * {@link java.nio.charset.CharsetEncoder} class should be used when more 964 * control over the encoding process is required. 965 * 966 * @param charset 967 * The {@linkplain java.nio.charset.Charset} to be used to encode 968 * the {@code String} 969 * 970 * @return The resultant byte array 971 * 972 * @since 1.6 973 */ 974 public byte[] getBytes(Charset charset) { 975 if (charset == null) throw new NullPointerException(); 976 return StringCoding.encode(charset, value, offset, count); 977 } 978 979 /** 980 * Encodes this {@code String} into a sequence of bytes using the 981 * platform's default charset, storing the result into a new byte array. 982 * 983 * <p> The behavior of this method when this string cannot be encoded in 984 * the default charset is unspecified. The {@link 985 * java.nio.charset.CharsetEncoder} class should be used when more control 986 * over the encoding process is required. 987 * 988 * @return The resultant byte array 989 * 990 * @since JDK1.1 991 */ 992 public byte[] getBytes() { 993 return StringCoding.encode(value, offset, count); 994 } 995 996 /** 997 * Compares this string to the specified object. The result is {@code 998 * true} if and only if the argument is not {@code null} and is a {@code 999 * String} object that represents the same sequence of characters as this 1000 * object. 1001 * 1002 * @param anObject 1003 * The object to compare this {@code String} against 1004 * 1005 * @return {@code true} if the given object represents a {@code String} 1006 * equivalent to this string, {@code false} otherwise 1007 * 1008 * @see #compareTo(String) 1009 * @see #equalsIgnoreCase(String) 1010 */ 1011 public boolean equals(Object anObject) { 1012 if (this == anObject) { 1013 return true; 1014 } 1015 if (anObject instanceof String) { 1016 String anotherString = (String)anObject; 1017 int n = count; 1018 if (n == anotherString.count) { 1019 char v1[] = value; 1020 char v2[] = anotherString.value; 1021 int i = offset; 1022 int j = anotherString.offset; 1023 while (n-- != 0) { 1024 if (v1[i++] != v2[j++]) 1025 return false; 1026 } 1027 return true; 1028 } 1029 } 1030 return false; 1031 } 1032 1033 /** 1034 * Compares this string to the specified {@code StringBuffer}. The result 1035 * is {@code true} if and only if this {@code String} represents the same 1036 * sequence of characters as the specified {@code StringBuffer}. 1037 * 1038 * @param sb 1039 * The {@code StringBuffer} to compare this {@code String} against 1040 * 1041 * @return {@code true} if this {@code String} represents the same 1042 * sequence of characters as the specified {@code StringBuffer}, 1043 * {@code false} otherwise 1044 * 1045 * @since 1.4 1046 */ 1047 public boolean contentEquals(StringBuffer sb) { 1048 synchronized(sb) { 1049 return contentEquals((CharSequence)sb); 1050 } 1051 } 1052 1053 /** 1054 * Compares this string to the specified {@code CharSequence}. The result 1055 * is {@code true} if and only if this {@code String} represents the same 1056 * sequence of char values as the specified sequence. 1057 * 1058 * @param cs 1059 * The sequence to compare this {@code String} against 1060 * 1061 * @return {@code true} if this {@code String} represents the same 1062 * sequence of char values as the specified sequence, {@code 1063 * false} otherwise 1064 * 1065 * @since 1.5 1066 */ 1067 public boolean contentEquals(CharSequence cs) { 1068 if (count != cs.length()) 1069 return false; 1070 // Argument is a StringBuffer, StringBuilder 1071 if (cs instanceof AbstractStringBuilder) { 1072 char v1[] = value; 1073 char v2[] = ((AbstractStringBuilder)cs).getValue(); 1074 int i = offset; 1075 int j = 0; 1076 int n = count; 1077 while (n-- != 0) { 1078 if (v1[i++] != v2[j++]) 1079 return false; 1080 } 1081 return true; 1082 } 1083 // Argument is a String 1084 if (cs.equals(this)) 1085 return true; 1086 // Argument is a generic CharSequence 1087 char v1[] = value; 1088 int i = offset; 1089 int j = 0; 1090 int n = count; 1091 while (n-- != 0) { 1092 if (v1[i++] != cs.charAt(j++)) 1093 return false; 1094 } 1095 return true; 1096 } 1097 1098 /** 1099 * Compares this {@code String} to another {@code String}, ignoring case 1100 * considerations. Two strings are considered equal ignoring case if they 1101 * are of the same length and corresponding characters in the two strings 1102 * are equal ignoring case. 1103 * 1104 * <p> Two characters {@code c1} and {@code c2} are considered the same 1105 * ignoring case if at least one of the following is true: 1106 * <ul> 1107 * <li> The two characters are the same (as compared by the 1108 * {@code ==} operator) 1109 * <li> Applying the method {@link 1110 * java.lang.Character#toUpperCase(char)} to each character 1111 * produces the same result 1112 * <li> Applying the method {@link 1113 * java.lang.Character#toLowerCase(char)} to each character 1114 * produces the same result 1115 * </ul> 1116 * 1117 * @param anotherString 1118 * The {@code String} to compare this {@code String} against 1119 * 1120 * @return {@code true} if the argument is not {@code null} and it 1121 * represents an equivalent {@code String} ignoring case; {@code 1122 * false} otherwise 1123 * 1124 * @see #equals(Object) 1125 */ 1126 public boolean equalsIgnoreCase(String anotherString) { 1127 return (this == anotherString) ? true : 1128 (anotherString != null) && (anotherString.count == count) && 1129 regionMatches(true, 0, anotherString, 0, count); 1130 } 1131 1132 /** 1133 * Compares two strings lexicographically. 1134 * The comparison is based on the Unicode value of each character in 1135 * the strings. The character sequence represented by this 1136 * {@code String} object is compared lexicographically to the 1137 * character sequence represented by the argument string. The result is 1138 * a negative integer if this {@code String} object 1139 * lexicographically precedes the argument string. The result is a 1140 * positive integer if this {@code String} object lexicographically 1141 * follows the argument string. The result is zero if the strings 1142 * are equal; {@code compareTo} returns {@code 0} exactly when 1143 * the {@link #equals(Object)} method would return {@code true}. 1144 * <p> 1145 * This is the definition of lexicographic ordering. If two strings are 1146 * different, then either they have different characters at some index 1147 * that is a valid index for both strings, or their lengths are different, 1148 * or both. If they have different characters at one or more index 1149 * positions, let <i>k</i> be the smallest such index; then the string 1150 * whose character at position <i>k</i> has the smaller value, as 1151 * determined by using the < operator, lexicographically precedes the 1152 * other string. In this case, {@code compareTo} returns the 1153 * difference of the two character values at position {@code k} in 1154 * the two string -- that is, the value: 1155 * <blockquote><pre> 1156 * this.charAt(k)-anotherString.charAt(k) 1157 * </pre></blockquote> 1158 * If there is no index position at which they differ, then the shorter 1159 * string lexicographically precedes the longer string. In this case, 1160 * {@code compareTo} returns the difference of the lengths of the 1161 * strings -- that is, the value: 1162 * <blockquote><pre> 1163 * this.length()-anotherString.length() 1164 * </pre></blockquote> 1165 * 1166 * @param anotherString the {@code String} to be compared. 1167 * @return the value {@code 0} if the argument string is equal to 1168 * this string; a value less than {@code 0} if this string 1169 * is lexicographically less than the string argument; and a 1170 * value greater than {@code 0} if this string is 1171 * lexicographically greater than the string argument. 1172 */ 1173 public int compareTo(String anotherString) { 1174 int len1 = count; 1175 int len2 = anotherString.count; 1176 int n = Math.min(len1, len2); 1177 char v1[] = value; 1178 char v2[] = anotherString.value; 1179 int i = offset; 1180 int j = anotherString.offset; 1181 1182 if (i == j) { 1183 int k = i; 1184 int lim = n + i; 1185 while (k < lim) { 1186 char c1 = v1[k]; 1187 char c2 = v2[k]; 1188 if (c1 != c2) { 1189 return c1 - c2; 1190 } 1191 k++; 1192 } 1193 } else { 1194 while (n-- != 0) { 1195 char c1 = v1[i++]; 1196 char c2 = v2[j++]; 1197 if (c1 != c2) { 1198 return c1 - c2; 1199 } 1200 } 1201 } 1202 return len1 - len2; 1203 } 1204 1205 /** 1206 * A Comparator that orders {@code String} objects as by 1207 * {@code compareToIgnoreCase}. This comparator is serializable. 1208 * <p> 1209 * Note that this Comparator does <em>not</em> take locale into account, 1210 * and will result in an unsatisfactory ordering for certain locales. 1211 * The java.text package provides <em>Collators</em> to allow 1212 * locale-sensitive ordering. 1213 * 1214 * @see java.text.Collator#compare(String, String) 1215 * @since 1.2 1216 */ 1217 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1218 = new CaseInsensitiveComparator(); 1219 private static class CaseInsensitiveComparator 1220 implements Comparator<String>, java.io.Serializable { 1221 // use serialVersionUID from JDK 1.2.2 for interoperability 1222 private static final long serialVersionUID = 8575799808933029326L; 1223 1224 public int compare(String s1, String s2) { 1225 int n1 = s1.length(); 1226 int n2 = s2.length(); 1227 int min = Math.min(n1, n2); 1228 for (int i = 0; i < min; i++) { 1229 char c1 = s1.charAt(i); 1230 char c2 = s2.charAt(i); 1231 if (c1 != c2) { 1232 c1 = Character.toUpperCase(c1); 1233 c2 = Character.toUpperCase(c2); 1234 if (c1 != c2) { 1235 c1 = Character.toLowerCase(c1); 1236 c2 = Character.toLowerCase(c2); 1237 if (c1 != c2) { 1238 // No overflow because of numeric promotion 1239 return c1 - c2; 1240 } 1241 } 1242 } 1243 } 1244 return n1 - n2; 1245 } 1246 1247 /** Replaces the de-serialized object. */ 1248 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1249 } 1250 1251 /** 1252 * Compares two strings lexicographically, ignoring case 1253 * differences. This method returns an integer whose sign is that of 1254 * calling {@code compareTo} with normalized versions of the strings 1255 * where case differences have been eliminated by calling 1256 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1257 * each character. 1258 * <p> 1259 * Note that this method does <em>not</em> take locale into account, 1260 * and will result in an unsatisfactory ordering for certain locales. 1261 * The java.text package provides <em>collators</em> to allow 1262 * locale-sensitive ordering. 1263 * 1264 * @param str the {@code String} to be compared. 1265 * @return a negative integer, zero, or a positive integer as the 1266 * specified String is greater than, equal to, or less 1267 * than this String, ignoring case considerations. 1268 * @see java.text.Collator#compare(String, String) 1269 * @since 1.2 1270 */ 1271 public int compareToIgnoreCase(String str) { 1272 return CASE_INSENSITIVE_ORDER.compare(this, str); 1273 } 1274 1275 /** 1276 * Tests if two string regions are equal. 1277 * <p> 1278 * A substring of this <tt>String</tt> object is compared to a substring 1279 * of the argument other. The result is true if these substrings 1280 * represent identical character sequences. The substring of this 1281 * <tt>String</tt> object to be compared begins at index <tt>toffset</tt> 1282 * and has length <tt>len</tt>. The substring of other to be compared 1283 * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The 1284 * result is <tt>false</tt> if and only if at least one of the following 1285 * is true: 1286 * <ul><li><tt>toffset</tt> is negative. 1287 * <li><tt>ooffset</tt> is negative. 1288 * <li><tt>toffset+len</tt> is greater than the length of this 1289 * <tt>String</tt> object. 1290 * <li><tt>ooffset+len</tt> is greater than the length of the other 1291 * argument. 1292 * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt> 1293 * such that: 1294 * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt> 1295 * </ul> 1296 * 1297 * @param toffset the starting offset of the subregion in this string. 1298 * @param other the string argument. 1299 * @param ooffset the starting offset of the subregion in the string 1300 * argument. 1301 * @param len the number of characters to compare. 1302 * @return {@code true} if the specified subregion of this string 1303 * exactly matches the specified subregion of the string argument; 1304 * {@code false} otherwise. 1305 */ 1306 public boolean regionMatches(int toffset, String other, int ooffset, 1307 int len) { 1308 char ta[] = value; 1309 int to = offset + toffset; 1310 char pa[] = other.value; 1311 int po = other.offset + ooffset; 1312 // Note: toffset, ooffset, or len might be near -1>>>1. 1313 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) 1314 || (ooffset > (long)other.count - len)) { 1315 return false; 1316 } 1317 while (len-- > 0) { 1318 if (ta[to++] != pa[po++]) { 1319 return false; 1320 } 1321 } 1322 return true; 1323 } 1324 1325 /** 1326 * Tests if two string regions are equal. 1327 * <p> 1328 * A substring of this <tt>String</tt> object is compared to a substring 1329 * of the argument <tt>other</tt>. The result is <tt>true</tt> if these 1330 * substrings represent character sequences that are the same, ignoring 1331 * case if and only if <tt>ignoreCase</tt> is true. The substring of 1332 * this <tt>String</tt> object to be compared begins at index 1333 * <tt>toffset</tt> and has length <tt>len</tt>. The substring of 1334 * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and 1335 * has length <tt>len</tt>. The result is <tt>false</tt> if and only if 1336 * at least one of the following is true: 1337 * <ul><li><tt>toffset</tt> is negative. 1338 * <li><tt>ooffset</tt> is negative. 1339 * <li><tt>toffset+len</tt> is greater than the length of this 1340 * <tt>String</tt> object. 1341 * <li><tt>ooffset+len</tt> is greater than the length of the other 1342 * argument. 1343 * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative 1344 * integer <i>k</i> less than <tt>len</tt> such that: 1345 * <blockquote><pre> 1346 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1347 * </pre></blockquote> 1348 * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative 1349 * integer <i>k</i> less than <tt>len</tt> such that: 1350 * <blockquote><pre> 1351 * Character.toLowerCase(this.charAt(toffset+k)) != 1352 Character.toLowerCase(other.charAt(ooffset+k)) 1353 * </pre></blockquote> 1354 * and: 1355 * <blockquote><pre> 1356 * Character.toUpperCase(this.charAt(toffset+k)) != 1357 * Character.toUpperCase(other.charAt(ooffset+k)) 1358 * </pre></blockquote> 1359 * </ul> 1360 * 1361 * @param ignoreCase if {@code true}, ignore case when comparing 1362 * characters. 1363 * @param toffset the starting offset of the subregion in this 1364 * string. 1365 * @param other the string argument. 1366 * @param ooffset the starting offset of the subregion in the string 1367 * argument. 1368 * @param len the number of characters to compare. 1369 * @return {@code true} if the specified subregion of this string 1370 * matches the specified subregion of the string argument; 1371 * {@code false} otherwise. Whether the matching is exact 1372 * or case insensitive depends on the {@code ignoreCase} 1373 * argument. 1374 */ 1375 public boolean regionMatches(boolean ignoreCase, int toffset, 1376 String other, int ooffset, int len) { 1377 char ta[] = value; 1378 int to = offset + toffset; 1379 char pa[] = other.value; 1380 int po = other.offset + ooffset; 1381 // Note: toffset, ooffset, or len might be near -1>>>1. 1382 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) || 1383 (ooffset > (long)other.count - len)) { 1384 return false; 1385 } 1386 while (len-- > 0) { 1387 char c1 = ta[to++]; 1388 char c2 = pa[po++]; 1389 if (c1 == c2) { 1390 continue; 1391 } 1392 if (ignoreCase) { 1393 // If characters don't match but case may be ignored, 1394 // try converting both characters to uppercase. 1395 // If the results match, then the comparison scan should 1396 // continue. 1397 char u1 = Character.toUpperCase(c1); 1398 char u2 = Character.toUpperCase(c2); 1399 if (u1 == u2) { 1400 continue; 1401 } 1402 // Unfortunately, conversion to uppercase does not work properly 1403 // for the Georgian alphabet, which has strange rules about case 1404 // conversion. So we need to make one last check before 1405 // exiting. 1406 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) { 1407 continue; 1408 } 1409 } 1410 return false; 1411 } 1412 return true; 1413 } 1414 1415 /** 1416 * Tests if the substring of this string beginning at the 1417 * specified index starts with the specified prefix. 1418 * 1419 * @param prefix the prefix. 1420 * @param toffset where to begin looking in this string. 1421 * @return {@code true} if the character sequence represented by the 1422 * argument is a prefix of the substring of this object starting 1423 * at index {@code toffset}; {@code false} otherwise. 1424 * The result is {@code false} if {@code toffset} is 1425 * negative or greater than the length of this 1426 * {@code String} object; otherwise the result is the same 1427 * as the result of the expression 1428 * <pre> 1429 * this.substring(toffset).startsWith(prefix) 1430 * </pre> 1431 */ 1432 public boolean startsWith(String prefix, int toffset) { 1433 char ta[] = value; 1434 int to = offset + toffset; 1435 char pa[] = prefix.value; 1436 int po = prefix.offset; 1437 int pc = prefix.count; 1438 // Note: toffset might be near -1>>>1. 1439 if ((toffset < 0) || (toffset > count - pc)) { 1440 return false; 1441 } 1442 while (--pc >= 0) { 1443 if (ta[to++] != pa[po++]) { 1444 return false; 1445 } 1446 } 1447 return true; 1448 } 1449 1450 /** 1451 * Tests if this string starts with the specified prefix. 1452 * 1453 * @param prefix the prefix. 1454 * @return {@code true} if the character sequence represented by the 1455 * argument is a prefix of the character sequence represented by 1456 * this string; {@code false} otherwise. 1457 * Note also that {@code true} will be returned if the 1458 * argument is an empty string or is equal to this 1459 * {@code String} object as determined by the 1460 * {@link #equals(Object)} method. 1461 * @since 1. 0 1462 */ 1463 public boolean startsWith(String prefix) { 1464 return startsWith(prefix, 0); 1465 } 1466 1467 /** 1468 * Tests if this string ends with the specified suffix. 1469 * 1470 * @param suffix the suffix. 1471 * @return {@code true} if the character sequence represented by the 1472 * argument is a suffix of the character sequence represented by 1473 * this object; {@code false} otherwise. Note that the 1474 * result will be {@code true} if the argument is the 1475 * empty string or is equal to this {@code String} object 1476 * as determined by the {@link #equals(Object)} method. 1477 */ 1478 public boolean endsWith(String suffix) { 1479 return startsWith(suffix, count - suffix.count); 1480 } 1481 1482 /** 1483 * Returns a hash code for this string. The hash code for a 1484 * {@code String} object is computed as 1485 * <blockquote><pre> 1486 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1487 * </pre></blockquote> 1488 * using {@code int} arithmetic, where {@code s[i]} is the 1489 * <i>i</i>th character of the string, {@code n} is the length of 1490 * the string, and {@code ^} indicates exponentiation. 1491 * (The hash value of the empty string is zero.) 1492 * 1493 * @return a hash code value for this object. 1494 */ 1495 public int hashCode() { 1496 int h = hash; 1497 if (h == 0 && count > 0) { 1498 int off = offset; 1499 char val[] = value; 1500 int len = count; 1501 1502 for (int i = 0; i < len; i++) { 1503 h = 31*h + val[off++]; 1504 } 1505 hash = h; 1506 } 1507 return h; 1508 } 1509 1510 /** 1511 * Returns the index within this string of the first occurrence of 1512 * the specified character. If a character with value 1513 * {@code ch} occurs in the character sequence represented by 1514 * this {@code String} object, then the index (in Unicode 1515 * code units) of the first such occurrence is returned. For 1516 * values of {@code ch} in the range from 0 to 0xFFFF 1517 * (inclusive), this is the smallest value <i>k</i> such that: 1518 * <blockquote><pre> 1519 * this.charAt(<i>k</i>) == ch 1520 * </pre></blockquote> 1521 * is true. For other values of {@code ch}, it is the 1522 * smallest value <i>k</i> such that: 1523 * <blockquote><pre> 1524 * this.codePointAt(<i>k</i>) == ch 1525 * </pre></blockquote> 1526 * is true. In either case, if no such character occurs in this 1527 * string, then {@code -1} is returned. 1528 * 1529 * @param ch a character (Unicode code point). 1530 * @return the index of the first occurrence of the character in the 1531 * character sequence represented by this object, or 1532 * {@code -1} if the character does not occur. 1533 */ 1534 public int indexOf(int ch) { 1535 return indexOf(ch, 0); 1536 } 1537 1538 /** 1539 * Returns the index within this string of the first occurrence of the 1540 * specified character, starting the search at the specified index. 1541 * <p> 1542 * If a character with value {@code ch} occurs in the 1543 * character sequence represented by this {@code String} 1544 * object at an index no smaller than {@code fromIndex}, then 1545 * the index of the first such occurrence is returned. For values 1546 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1547 * this is the smallest value <i>k</i> such that: 1548 * <blockquote><pre> 1549 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex) 1550 * </pre></blockquote> 1551 * is true. For other values of {@code ch}, it is the 1552 * smallest value <i>k</i> such that: 1553 * <blockquote><pre> 1554 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex) 1555 * </pre></blockquote> 1556 * is true. In either case, if no such character occurs in this 1557 * string at or after position {@code fromIndex}, then 1558 * {@code -1} is returned. 1559 * 1560 * <p> 1561 * There is no restriction on the value of {@code fromIndex}. If it 1562 * is negative, it has the same effect as if it were zero: this entire 1563 * string may be searched. If it is greater than the length of this 1564 * string, it has the same effect as if it were equal to the length of 1565 * this string: {@code -1} is returned. 1566 * 1567 * <p>All indices are specified in {@code char} values 1568 * (Unicode code units). 1569 * 1570 * @param ch a character (Unicode code point). 1571 * @param fromIndex the index to start the search from. 1572 * @return the index of the first occurrence of the character in the 1573 * character sequence represented by this object that is greater 1574 * than or equal to {@code fromIndex}, or {@code -1} 1575 * if the character does not occur. 1576 */ 1577 public int indexOf(int ch, int fromIndex) { 1578 if (fromIndex < 0) { 1579 fromIndex = 0; 1580 } else if (fromIndex >= count) { 1581 // Note: fromIndex might be near -1>>>1. 1582 return -1; 1583 } 1584 1585 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1586 // handle most cases here (ch is a BMP code point or a 1587 // negative value (invalid code point)) 1588 final char[] value = this.value; 1589 final int offset = this.offset; 1590 final int max = offset + count; 1591 for (int i = offset + fromIndex; i < max ; i++) { 1592 if (value[i] == ch) { 1593 return i - offset; 1594 } 1595 } 1596 return -1; 1597 } else { 1598 return indexOfSupplementary(ch, fromIndex); 1599 } 1600 } 1601 1602 /** 1603 * Handles (rare) calls of indexOf with a supplementary character. 1604 */ 1605 private int indexOfSupplementary(int ch, int fromIndex) { 1606 if (Character.isValidCodePoint(ch)) { 1607 final char[] value = this.value; 1608 final int offset = this.offset; 1609 final char hi = Character.highSurrogate(ch); 1610 final char lo = Character.lowSurrogate(ch); 1611 final int max = offset + count - 1; 1612 for (int i = offset + fromIndex; i < max; i++) { 1613 if (value[i] == hi && value[i+1] == lo) { 1614 return i - offset; 1615 } 1616 } 1617 } 1618 return -1; 1619 } 1620 1621 /** 1622 * Returns the index within this string of the last occurrence of 1623 * the specified character. For values of {@code ch} in the 1624 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1625 * units) returned is the largest value <i>k</i> such that: 1626 * <blockquote><pre> 1627 * this.charAt(<i>k</i>) == ch 1628 * </pre></blockquote> 1629 * is true. For other values of {@code ch}, it is the 1630 * largest value <i>k</i> such that: 1631 * <blockquote><pre> 1632 * this.codePointAt(<i>k</i>) == ch 1633 * </pre></blockquote> 1634 * is true. In either case, if no such character occurs in this 1635 * string, then {@code -1} is returned. The 1636 * {@code String} is searched backwards starting at the last 1637 * character. 1638 * 1639 * @param ch a character (Unicode code point). 1640 * @return the index of the last occurrence of the character in the 1641 * character sequence represented by this object, or 1642 * {@code -1} if the character does not occur. 1643 */ 1644 public int lastIndexOf(int ch) { 1645 return lastIndexOf(ch, count - 1); 1646 } 1647 1648 /** 1649 * Returns the index within this string of the last occurrence of 1650 * the specified character, searching backward starting at the 1651 * specified index. For values of {@code ch} in the range 1652 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1653 * value <i>k</i> such that: 1654 * <blockquote><pre> 1655 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex) 1656 * </pre></blockquote> 1657 * is true. For other values of {@code ch}, it is the 1658 * largest value <i>k</i> such that: 1659 * <blockquote><pre> 1660 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex) 1661 * </pre></blockquote> 1662 * is true. In either case, if no such character occurs in this 1663 * string at or before position {@code fromIndex}, then 1664 * {@code -1} is returned. 1665 * 1666 * <p>All indices are specified in {@code char} values 1667 * (Unicode code units). 1668 * 1669 * @param ch a character (Unicode code point). 1670 * @param fromIndex the index to start the search from. There is no 1671 * restriction on the value of {@code fromIndex}. If it is 1672 * greater than or equal to the length of this string, it has 1673 * the same effect as if it were equal to one less than the 1674 * length of this string: this entire string may be searched. 1675 * If it is negative, it has the same effect as if it were -1: 1676 * -1 is returned. 1677 * @return the index of the last occurrence of the character in the 1678 * character sequence represented by this object that is less 1679 * than or equal to {@code fromIndex}, or {@code -1} 1680 * if the character does not occur before that point. 1681 */ 1682 public int lastIndexOf(int ch, int fromIndex) { 1683 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1684 // handle most cases here (ch is a BMP code point or a 1685 // negative value (invalid code point)) 1686 final char[] value = this.value; 1687 final int offset = this.offset; 1688 int i = offset + Math.min(fromIndex, count - 1); 1689 for (; i >= offset ; i--) { 1690 if (value[i] == ch) { 1691 return i - offset; 1692 } 1693 } 1694 return -1; 1695 } else { 1696 return lastIndexOfSupplementary(ch, fromIndex); 1697 } 1698 } 1699 1700 /** 1701 * Handles (rare) calls of lastIndexOf with a supplementary character. 1702 */ 1703 private int lastIndexOfSupplementary(int ch, int fromIndex) { 1704 if (Character.isValidCodePoint(ch)) { 1705 final char[] value = this.value; 1706 final int offset = this.offset; 1707 char hi = Character.highSurrogate(ch); 1708 char lo = Character.lowSurrogate(ch); 1709 int i = offset + Math.min(fromIndex, count - 2); 1710 for (; i >= offset; i--) { 1711 if (value[i] == hi && value[i+1] == lo) { 1712 return i - offset; 1713 } 1714 } 1715 } 1716 return -1; 1717 } 1718 1719 /** 1720 * Returns the index within this string of the first occurrence of the 1721 * specified substring. 1722 * 1723 * <p>The returned index is the smallest value <i>k</i> for which: 1724 * <blockquote><pre> 1725 * this.startsWith(str, <i>k</i>) 1726 * </pre></blockquote> 1727 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1728 * 1729 * @param str the substring to search for. 1730 * @return the index of the first occurrence of the specified substring, 1731 * or {@code -1} if there is no such occurrence. 1732 */ 1733 public int indexOf(String str) { 1734 return indexOf(str, 0); 1735 } 1736 1737 /** 1738 * Returns the index within this string of the first occurrence of the 1739 * specified substring, starting at the specified index. 1740 * 1741 * <p>The returned index is the smallest value <i>k</i> for which: 1742 * <blockquote><pre> 1743 * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>) 1744 * </pre></blockquote> 1745 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1746 * 1747 * @param str the substring to search for. 1748 * @param fromIndex the index from which to start the search. 1749 * @return the index of the first occurrence of the specified substring, 1750 * starting at the specified index, 1751 * or {@code -1} if there is no such occurrence. 1752 */ 1753 public int indexOf(String str, int fromIndex) { 1754 return indexOf(value, offset, count, 1755 str.value, str.offset, str.count, fromIndex); 1756 } 1757 1758 /** 1759 * Code shared by String and StringBuffer to do searches. The 1760 * source is the character array being searched, and the target 1761 * is the string being searched for. 1762 * 1763 * @param source the characters being searched. 1764 * @param sourceOffset offset of the source string. 1765 * @param sourceCount count of the source string. 1766 * @param target the characters being searched for. 1767 * @param targetOffset offset of the target string. 1768 * @param targetCount count of the target string. 1769 * @param fromIndex the index to begin searching from. 1770 */ 1771 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1772 char[] target, int targetOffset, int targetCount, 1773 int fromIndex) { 1774 if (fromIndex >= sourceCount) { 1775 return (targetCount == 0 ? sourceCount : -1); 1776 } 1777 if (fromIndex < 0) { 1778 fromIndex = 0; 1779 } 1780 if (targetCount == 0) { 1781 return fromIndex; 1782 } 1783 1784 char first = target[targetOffset]; 1785 int max = sourceOffset + (sourceCount - targetCount); 1786 1787 for (int i = sourceOffset + fromIndex; i <= max; i++) { 1788 /* Look for first character. */ 1789 if (source[i] != first) { 1790 while (++i <= max && source[i] != first); 1791 } 1792 1793 /* Found first character, now look at the rest of v2 */ 1794 if (i <= max) { 1795 int j = i + 1; 1796 int end = j + targetCount - 1; 1797 for (int k = targetOffset + 1; j < end && source[j] == 1798 target[k]; j++, k++); 1799 1800 if (j == end) { 1801 /* Found whole string. */ 1802 return i - sourceOffset; 1803 } 1804 } 1805 } 1806 return -1; 1807 } 1808 1809 /** 1810 * Returns the index within this string of the last occurrence of the 1811 * specified substring. The last occurrence of the empty string "" 1812 * is considered to occur at the index value {@code this.length()}. 1813 * 1814 * <p>The returned index is the largest value <i>k</i> for which: 1815 * <blockquote><pre> 1816 * this.startsWith(str, <i>k</i>) 1817 * </pre></blockquote> 1818 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1819 * 1820 * @param str the substring to search for. 1821 * @return the index of the last occurrence of the specified substring, 1822 * or {@code -1} if there is no such occurrence. 1823 */ 1824 public int lastIndexOf(String str) { 1825 return lastIndexOf(str, count); 1826 } 1827 1828 /** 1829 * Returns the index within this string of the last occurrence of the 1830 * specified substring, searching backward starting at the specified index. 1831 * 1832 * <p>The returned index is the largest value <i>k</i> for which: 1833 * <blockquote><pre> 1834 * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>) 1835 * </pre></blockquote> 1836 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1837 * 1838 * @param str the substring to search for. 1839 * @param fromIndex the index to start the search from. 1840 * @return the index of the last occurrence of the specified substring, 1841 * searching backward from the specified index, 1842 * or {@code -1} if there is no such occurrence. 1843 */ 1844 public int lastIndexOf(String str, int fromIndex) { 1845 return lastIndexOf(value, offset, count, 1846 str.value, str.offset, str.count, fromIndex); 1847 } 1848 1849 /** 1850 * Code shared by String and StringBuffer to do searches. The 1851 * source is the character array being searched, and the target 1852 * is the string being searched for. 1853 * 1854 * @param source the characters being searched. 1855 * @param sourceOffset offset of the source string. 1856 * @param sourceCount count of the source string. 1857 * @param target the characters being searched for. 1858 * @param targetOffset offset of the target string. 1859 * @param targetCount count of the target string. 1860 * @param fromIndex the index to begin searching from. 1861 */ 1862 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1863 char[] target, int targetOffset, int targetCount, 1864 int fromIndex) { 1865 /* 1866 * Check arguments; return immediately where possible. For 1867 * consistency, don't check for null str. 1868 */ 1869 int rightIndex = sourceCount - targetCount; 1870 if (fromIndex < 0) { 1871 return -1; 1872 } 1873 if (fromIndex > rightIndex) { 1874 fromIndex = rightIndex; 1875 } 1876 /* Empty string always matches. */ 1877 if (targetCount == 0) { 1878 return fromIndex; 1879 } 1880 1881 int strLastIndex = targetOffset + targetCount - 1; 1882 char strLastChar = target[strLastIndex]; 1883 int min = sourceOffset + targetCount - 1; 1884 int i = min + fromIndex; 1885 1886 startSearchForLastChar: 1887 while (true) { 1888 while (i >= min && source[i] != strLastChar) { 1889 i--; 1890 } 1891 if (i < min) { 1892 return -1; 1893 } 1894 int j = i - 1; 1895 int start = j - (targetCount - 1); 1896 int k = strLastIndex - 1; 1897 1898 while (j > start) { 1899 if (source[j--] != target[k--]) { 1900 i--; 1901 continue startSearchForLastChar; 1902 } 1903 } 1904 return start - sourceOffset + 1; 1905 } 1906 } 1907 1908 /** 1909 * Returns a new string that is a substring of this string. The 1910 * substring begins with the character at the specified index and 1911 * extends to the end of this string. <p> 1912 * Examples: 1913 * <blockquote><pre> 1914 * "unhappy".substring(2) returns "happy" 1915 * "Harbison".substring(3) returns "bison" 1916 * "emptiness".substring(9) returns "" (an empty string) 1917 * </pre></blockquote> 1918 * 1919 * @param beginIndex the beginning index, inclusive. 1920 * @return the specified substring. 1921 * @exception IndexOutOfBoundsException if 1922 * {@code beginIndex} is negative or larger than the 1923 * length of this {@code String} object. 1924 */ 1925 public String substring(int beginIndex) { 1926 return substring(beginIndex, count); 1927 } 1928 1929 /** 1930 * Returns a new string that is a substring of this string. The 1931 * substring begins at the specified {@code beginIndex} and 1932 * extends to the character at index {@code endIndex - 1}. 1933 * Thus the length of the substring is {@code endIndex-beginIndex}. 1934 * <p> 1935 * Examples: 1936 * <blockquote><pre> 1937 * "hamburger".substring(4, 8) returns "urge" 1938 * "smiles".substring(1, 5) returns "mile" 1939 * </pre></blockquote> 1940 * 1941 * @param beginIndex the beginning index, inclusive. 1942 * @param endIndex the ending index, exclusive. 1943 * @return the specified substring. 1944 * @exception IndexOutOfBoundsException if the 1945 * {@code beginIndex} is negative, or 1946 * {@code endIndex} is larger than the length of 1947 * this {@code String} object, or 1948 * {@code beginIndex} is larger than 1949 * {@code endIndex}. 1950 */ 1951 public String substring(int beginIndex, int endIndex) { 1952 if (beginIndex < 0) { 1953 throw new StringIndexOutOfBoundsException(beginIndex); 1954 } 1955 if (endIndex > count) { 1956 throw new StringIndexOutOfBoundsException(endIndex); 1957 } 1958 if (beginIndex > endIndex) { 1959 throw new StringIndexOutOfBoundsException(endIndex - beginIndex); 1960 } 1961 return ((beginIndex == 0) && (endIndex == count)) ? this : 1962 new String(offset + beginIndex, endIndex - beginIndex, value); 1963 } 1964 1965 /** 1966 * Returns a new character sequence that is a subsequence of this sequence. 1967 * 1968 * <p> An invocation of this method of the form 1969 * 1970 * <blockquote><pre> 1971 * str.subSequence(begin, end)</pre></blockquote> 1972 * 1973 * behaves in exactly the same way as the invocation 1974 * 1975 * <blockquote><pre> 1976 * str.substring(begin, end)</pre></blockquote> 1977 * 1978 * This method is defined so that the <tt>String</tt> class can implement 1979 * the {@link CharSequence} interface. </p> 1980 * 1981 * @param beginIndex the begin index, inclusive. 1982 * @param endIndex the end index, exclusive. 1983 * @return the specified subsequence. 1984 * 1985 * @throws IndexOutOfBoundsException 1986 * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative, 1987 * if <tt>endIndex</tt> is greater than <tt>length()</tt>, 1988 * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt> 1989 * 1990 * @since 1.4 1991 * @spec JSR-51 1992 */ 1993 public CharSequence subSequence(int beginIndex, int endIndex) { 1994 return this.substring(beginIndex, endIndex); 1995 } 1996 1997 /** 1998 * Concatenates the specified string to the end of this string. 1999 * <p> 2000 * If the length of the argument string is {@code 0}, then this 2001 * {@code String} object is returned. Otherwise, a new 2002 * {@code String} object is created, representing a character 2003 * sequence that is the concatenation of the character sequence 2004 * represented by this {@code String} object and the character 2005 * sequence represented by the argument string.<p> 2006 * Examples: 2007 * <blockquote><pre> 2008 * "cares".concat("s") returns "caress" 2009 * "to".concat("get").concat("her") returns "together" 2010 * </pre></blockquote> 2011 * 2012 * @param str the {@code String} that is concatenated to the end 2013 * of this {@code String}. 2014 * @return a string that represents the concatenation of this object's 2015 * characters followed by the string argument's characters. 2016 */ 2017 public String concat(String str) { 2018 int otherLen = str.length(); 2019 if (otherLen == 0) { 2020 return this; 2021 } 2022 char buf[] = new char[count + otherLen]; 2023 getChars(0, count, buf, 0); 2024 str.getChars(0, otherLen, buf, count); 2025 return new String(0, count + otherLen, buf); 2026 } 2027 2028 /** 2029 * Returns a new string resulting from replacing all occurrences of 2030 * {@code oldChar} in this string with {@code newChar}. 2031 * <p> 2032 * If the character {@code oldChar} does not occur in the 2033 * character sequence represented by this {@code String} object, 2034 * then a reference to this {@code String} object is returned. 2035 * Otherwise, a new {@code String} object is created that 2036 * represents a character sequence identical to the character sequence 2037 * represented by this {@code String} object, except that every 2038 * occurrence of {@code oldChar} is replaced by an occurrence 2039 * of {@code newChar}. 2040 * <p> 2041 * Examples: 2042 * <blockquote><pre> 2043 * "mesquite in your cellar".replace('e', 'o') 2044 * returns "mosquito in your collar" 2045 * "the war of baronets".replace('r', 'y') 2046 * returns "the way of bayonets" 2047 * "sparring with a purple porpoise".replace('p', 't') 2048 * returns "starring with a turtle tortoise" 2049 * "JonL".replace('q', 'x') returns "JonL" (no change) 2050 * </pre></blockquote> 2051 * 2052 * @param oldChar the old character. 2053 * @param newChar the new character. 2054 * @return a string derived from this string by replacing every 2055 * occurrence of {@code oldChar} with {@code newChar}. 2056 */ 2057 public String replace(char oldChar, char newChar) { 2058 if (oldChar != newChar) { 2059 int len = count; 2060 int i = -1; 2061 char[] val = value; /* avoid getfield opcode */ 2062 int off = offset; /* avoid getfield opcode */ 2063 2064 while (++i < len) { 2065 if (val[off + i] == oldChar) { 2066 break; 2067 } 2068 } 2069 if (i < len) { 2070 char buf[] = new char[len]; 2071 for (int j = 0 ; j < i ; j++) { 2072 buf[j] = val[off+j]; 2073 } 2074 while (i < len) { 2075 char c = val[off + i]; 2076 buf[i] = (c == oldChar) ? newChar : c; 2077 i++; 2078 } 2079 return new String(0, len, buf); 2080 } 2081 } 2082 return this; 2083 } 2084 2085 /** 2086 * Tells whether or not this string matches the given <a 2087 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2088 * 2089 * <p> An invocation of this method of the form 2090 * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the 2091 * same result as the expression 2092 * 2093 * <blockquote><tt> {@link java.util.regex.Pattern}.{@link 2094 * java.util.regex.Pattern#matches(String,CharSequence) 2095 * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote> 2096 * 2097 * @param regex 2098 * the regular expression to which this string is to be matched 2099 * 2100 * @return <tt>true</tt> if, and only if, this string matches the 2101 * given regular expression 2102 * 2103 * @throws PatternSyntaxException 2104 * if the regular expression's syntax is invalid 2105 * 2106 * @see java.util.regex.Pattern 2107 * 2108 * @since 1.4 2109 * @spec JSR-51 2110 */ 2111 public boolean matches(String regex) { 2112 return Pattern.matches(regex, this); 2113 } 2114 2115 /** 2116 * Returns true if and only if this string contains the specified 2117 * sequence of char values. 2118 * 2119 * @param s the sequence to search for 2120 * @return true if this string contains {@code s}, false otherwise 2121 * @throws NullPointerException if {@code s} is {@code null} 2122 * @since 1.5 2123 */ 2124 public boolean contains(CharSequence s) { 2125 return indexOf(s.toString()) > -1; 2126 } 2127 2128 /** 2129 * Replaces the first substring of this string that matches the given <a 2130 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2131 * given replacement. 2132 * 2133 * <p> An invocation of this method of the form 2134 * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt> 2135 * yields exactly the same result as the expression 2136 * 2137 * <blockquote><tt> 2138 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile 2139 * compile}(</tt><i>regex</i><tt>).{@link 2140 * java.util.regex.Pattern#matcher(java.lang.CharSequence) 2141 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst 2142 * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote> 2143 * 2144 *<p> 2145 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the 2146 * replacement string may cause the results to be different than if it were 2147 * being treated as a literal replacement string; see 2148 * {@link java.util.regex.Matcher#replaceFirst}. 2149 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2150 * meaning of these characters, if desired. 2151 * 2152 * @param regex 2153 * the regular expression to which this string is to be matched 2154 * @param replacement 2155 * the string to be substituted for the first match 2156 * 2157 * @return The resulting <tt>String</tt> 2158 * 2159 * @throws PatternSyntaxException 2160 * if the regular expression's syntax is invalid 2161 * 2162 * @see java.util.regex.Pattern 2163 * 2164 * @since 1.4 2165 * @spec JSR-51 2166 */ 2167 public String replaceFirst(String regex, String replacement) { 2168 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2169 } 2170 2171 /** 2172 * Replaces each substring of this string that matches the given <a 2173 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2174 * given replacement. 2175 * 2176 * <p> An invocation of this method of the form 2177 * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt> 2178 * yields exactly the same result as the expression 2179 * 2180 * <blockquote><tt> 2181 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile 2182 * compile}(</tt><i>regex</i><tt>).{@link 2183 * java.util.regex.Pattern#matcher(java.lang.CharSequence) 2184 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll 2185 * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote> 2186 * 2187 *<p> 2188 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the 2189 * replacement string may cause the results to be different than if it were 2190 * being treated as a literal replacement string; see 2191 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2192 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2193 * meaning of these characters, if desired. 2194 * 2195 * @param regex 2196 * the regular expression to which this string is to be matched 2197 * @param replacement 2198 * the string to be substituted for each match 2199 * 2200 * @return The resulting <tt>String</tt> 2201 * 2202 * @throws PatternSyntaxException 2203 * if the regular expression's syntax is invalid 2204 * 2205 * @see java.util.regex.Pattern 2206 * 2207 * @since 1.4 2208 * @spec JSR-51 2209 */ 2210 public String replaceAll(String regex, String replacement) { 2211 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2212 } 2213 2214 /** 2215 * Replaces each substring of this string that matches the literal target 2216 * sequence with the specified literal replacement sequence. The 2217 * replacement proceeds from the beginning of the string to the end, for 2218 * example, replacing "aa" with "b" in the string "aaa" will result in 2219 * "ba" rather than "ab". 2220 * 2221 * @param target The sequence of char values to be replaced 2222 * @param replacement The replacement sequence of char values 2223 * @return The resulting string 2224 * @throws NullPointerException if {@code target} or 2225 * {@code replacement} is {@code null}. 2226 * @since 1.5 2227 */ 2228 public String replace(CharSequence target, CharSequence replacement) { 2229 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher( 2230 this).replaceAll(Matcher.quoteReplacement(replacement.toString())); 2231 } 2232 2233 /** 2234 * Splits this string around matches of the given 2235 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2236 * 2237 * <p> The array returned by this method contains each substring of this 2238 * string that is terminated by another substring that matches the given 2239 * expression or is terminated by the end of the string. The substrings in 2240 * the array are in the order in which they occur in this string. If the 2241 * expression does not match any part of the input then the resulting array 2242 * has just one element, namely this string. 2243 * 2244 * <p> The <tt>limit</tt> parameter controls the number of times the 2245 * pattern is applied and therefore affects the length of the resulting 2246 * array. If the limit <i>n</i> is greater than zero then the pattern 2247 * will be applied at most <i>n</i> - 1 times, the array's 2248 * length will be no greater than <i>n</i>, and the array's last entry 2249 * will contain all input beyond the last matched delimiter. If <i>n</i> 2250 * is non-positive then the pattern will be applied as many times as 2251 * possible and the array can have any length. If <i>n</i> is zero then 2252 * the pattern will be applied as many times as possible, the array can 2253 * have any length, and trailing empty strings will be discarded. 2254 * 2255 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the 2256 * following results with these parameters: 2257 * 2258 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2259 * <tr> 2260 * <th>Regex</th> 2261 * <th>Limit</th> 2262 * <th>Result</th> 2263 * </tr> 2264 * <tr><td align=center>:</td> 2265 * <td align=center>2</td> 2266 * <td><tt>{ "boo", "and:foo" }</tt></td></tr> 2267 * <tr><td align=center>:</td> 2268 * <td align=center>5</td> 2269 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> 2270 * <tr><td align=center>:</td> 2271 * <td align=center>-2</td> 2272 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> 2273 * <tr><td align=center>o</td> 2274 * <td align=center>5</td> 2275 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr> 2276 * <tr><td align=center>o</td> 2277 * <td align=center>-2</td> 2278 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr> 2279 * <tr><td align=center>o</td> 2280 * <td align=center>0</td> 2281 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr> 2282 * </table></blockquote> 2283 * 2284 * <p> An invocation of this method of the form 2285 * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt> 2286 * yields the same result as the expression 2287 * 2288 * <blockquote> 2289 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile 2290 * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link 2291 * java.util.regex.Pattern#split(java.lang.CharSequence,int) 2292 * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt> 2293 * </blockquote> 2294 * 2295 * 2296 * @param regex 2297 * the delimiting regular expression 2298 * 2299 * @param limit 2300 * the result threshold, as described above 2301 * 2302 * @return the array of strings computed by splitting this string 2303 * around matches of the given regular expression 2304 * 2305 * @throws PatternSyntaxException 2306 * if the regular expression's syntax is invalid 2307 * 2308 * @see java.util.regex.Pattern 2309 * 2310 * @since 1.4 2311 * @spec JSR-51 2312 */ 2313 public String[] split(String regex, int limit) { 2314 /* fastpath if the regex is a 2315 (1)one-char String and this character is not one of the 2316 RegEx's meta characters ".$|()[{^?*+\\", or 2317 (2)two-char String and the first char is the backslash and 2318 the second is not the ascii digit or ascii letter. 2319 */ 2320 char ch = 0; 2321 if (((regex.count == 1 && 2322 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2323 (regex.length() == 2 && 2324 regex.charAt(0) == '\\' && 2325 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2326 ((ch-'a')|('z'-ch)) < 0 && 2327 ((ch-'A')|('Z'-ch)) < 0)) && 2328 (ch < Character.MIN_HIGH_SURROGATE || 2329 ch > Character.MAX_LOW_SURROGATE)) 2330 { 2331 int off = 0; 2332 int next = 0; 2333 boolean limited = limit > 0; 2334 ArrayList<String> list = new ArrayList<>(); 2335 while ((next = indexOf(ch, off)) != -1) { 2336 if (!limited || list.size() < limit - 1) { 2337 list.add(substring(off, next)); 2338 off = next + 1; 2339 } else { // last one 2340 //assert (list.size() == limit - 1); 2341 list.add(substring(off, count)); 2342 off = count; 2343 break; 2344 } 2345 } 2346 // If no match was found, return this 2347 if (off == 0) 2348 return new String[] { this }; 2349 2350 // Add remaining segment 2351 if (!limited || list.size() < limit) 2352 list.add(substring(off, count)); 2353 2354 // Construct result 2355 int resultSize = list.size(); 2356 if (limit == 0) 2357 while (resultSize > 0 && list.get(resultSize-1).length() == 0) 2358 resultSize--; 2359 String[] result = new String[resultSize]; 2360 return list.subList(0, resultSize).toArray(result); 2361 } 2362 return Pattern.compile(regex).split(this, limit); 2363 } 2364 2365 /** 2366 * Splits this string around matches of the given <a 2367 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2368 * 2369 * <p> This method works as if by invoking the two-argument {@link 2370 * #split(String, int) split} method with the given expression and a limit 2371 * argument of zero. Trailing empty strings are therefore not included in 2372 * the resulting array. 2373 * 2374 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the following 2375 * results with these expressions: 2376 * 2377 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2378 * <tr> 2379 * <th>Regex</th> 2380 * <th>Result</th> 2381 * </tr> 2382 * <tr><td align=center>:</td> 2383 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> 2384 * <tr><td align=center>o</td> 2385 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr> 2386 * </table></blockquote> 2387 * 2388 * 2389 * @param regex 2390 * the delimiting regular expression 2391 * 2392 * @return the array of strings computed by splitting this string 2393 * around matches of the given regular expression 2394 * 2395 * @throws PatternSyntaxException 2396 * if the regular expression's syntax is invalid 2397 * 2398 * @see java.util.regex.Pattern 2399 * 2400 * @since 1.4 2401 * @spec JSR-51 2402 */ 2403 public String[] split(String regex) { 2404 return split(regex, 0); 2405 } 2406 2407 /** 2408 * Converts all of the characters in this {@code String} to lower 2409 * case using the rules of the given {@code Locale}. Case mapping is based 2410 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2411 * class. Since case mappings are not always 1:1 char mappings, the resulting 2412 * {@code String} may be a different length than the original {@code String}. 2413 * <p> 2414 * Examples of lowercase mappings are in the following table: 2415 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2416 * <tr> 2417 * <th>Language Code of Locale</th> 2418 * <th>Upper Case</th> 2419 * <th>Lower Case</th> 2420 * <th>Description</th> 2421 * </tr> 2422 * <tr> 2423 * <td>tr (Turkish)</td> 2424 * <td>\u0130</td> 2425 * <td>\u0069</td> 2426 * <td>capital letter I with dot above -> small letter i</td> 2427 * </tr> 2428 * <tr> 2429 * <td>tr (Turkish)</td> 2430 * <td>\u0049</td> 2431 * <td>\u0131</td> 2432 * <td>capital letter I -> small letter dotless i </td> 2433 * </tr> 2434 * <tr> 2435 * <td>(all)</td> 2436 * <td>French Fries</td> 2437 * <td>french fries</td> 2438 * <td>lowercased all chars in String</td> 2439 * </tr> 2440 * <tr> 2441 * <td>(all)</td> 2442 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2443 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2444 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2445 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2446 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2447 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2448 * <td>lowercased all chars in String</td> 2449 * </tr> 2450 * </table> 2451 * 2452 * @param locale use the case transformation rules for this locale 2453 * @return the {@code String}, converted to lowercase. 2454 * @see java.lang.String#toLowerCase() 2455 * @see java.lang.String#toUpperCase() 2456 * @see java.lang.String#toUpperCase(Locale) 2457 * @since 1.1 2458 */ 2459 public String toLowerCase(Locale locale) { 2460 if (locale == null) { 2461 throw new NullPointerException(); 2462 } 2463 2464 int firstUpper; 2465 2466 /* Now check if there are any characters that need to be changed. */ 2467 scan: { 2468 for (firstUpper = 0 ; firstUpper < count; ) { 2469 char c = value[offset+firstUpper]; 2470 if ((c >= Character.MIN_HIGH_SURROGATE) && 2471 (c <= Character.MAX_HIGH_SURROGATE)) { 2472 int supplChar = codePointAt(firstUpper); 2473 if (supplChar != Character.toLowerCase(supplChar)) { 2474 break scan; 2475 } 2476 firstUpper += Character.charCount(supplChar); 2477 } else { 2478 if (c != Character.toLowerCase(c)) { 2479 break scan; 2480 } 2481 firstUpper++; 2482 } 2483 } 2484 return this; 2485 } 2486 2487 char[] result = new char[count]; 2488 int resultOffset = 0; /* result may grow, so i+resultOffset 2489 * is the write location in result */ 2490 2491 /* Just copy the first few lowerCase characters. */ 2492 System.arraycopy(value, offset, result, 0, firstUpper); 2493 2494 String lang = locale.getLanguage(); 2495 boolean localeDependent = 2496 (lang == "tr" || lang == "az" || lang == "lt"); 2497 char[] lowerCharArray; 2498 int lowerChar; 2499 int srcChar; 2500 int srcCount; 2501 for (int i = firstUpper; i < count; i += srcCount) { 2502 srcChar = (int)value[offset+i]; 2503 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE && 2504 (char)srcChar <= Character.MAX_HIGH_SURROGATE) { 2505 srcChar = codePointAt(i); 2506 srcCount = Character.charCount(srcChar); 2507 } else { 2508 srcCount = 1; 2509 } 2510 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA 2511 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale); 2512 } else if (srcChar == '\u0130') { // LATIN CAPITAL LETTER I DOT 2513 lowerChar = Character.ERROR; 2514 } else { 2515 lowerChar = Character.toLowerCase(srcChar); 2516 } 2517 if ((lowerChar == Character.ERROR) || 2518 (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) { 2519 if (lowerChar == Character.ERROR) { 2520 if (!localeDependent && srcChar == '\u0130') { 2521 lowerCharArray = 2522 ConditionalSpecialCasing.toLowerCaseCharArray(this, i, Locale.ENGLISH); 2523 } else { 2524 lowerCharArray = 2525 ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale); 2526 } 2527 } else if (srcCount == 2) { 2528 resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount; 2529 continue; 2530 } else { 2531 lowerCharArray = Character.toChars(lowerChar); 2532 } 2533 2534 /* Grow result if needed */ 2535 int mapLen = lowerCharArray.length; 2536 if (mapLen > srcCount) { 2537 char[] result2 = new char[result.length + mapLen - srcCount]; 2538 System.arraycopy(result, 0, result2, 0, 2539 i + resultOffset); 2540 result = result2; 2541 } 2542 for (int x=0; x<mapLen; ++x) { 2543 result[i+resultOffset+x] = lowerCharArray[x]; 2544 } 2545 resultOffset += (mapLen - srcCount); 2546 } else { 2547 result[i+resultOffset] = (char)lowerChar; 2548 } 2549 } 2550 return new String(0, count+resultOffset, result); 2551 } 2552 2553 /** 2554 * Converts all of the characters in this {@code String} to lower 2555 * case using the rules of the default locale. This is equivalent to calling 2556 * {@code toLowerCase(Locale.getDefault())}. 2557 * <p> 2558 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2559 * results if used for strings that are intended to be interpreted locale 2560 * independently. 2561 * Examples are programming language identifiers, protocol keys, and HTML 2562 * tags. 2563 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2564 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2565 * LATIN SMALL LETTER DOTLESS I character. 2566 * To obtain correct results for locale insensitive strings, use 2567 * {@code toLowerCase(Locale.ENGLISH)}. 2568 * <p> 2569 * @return the {@code String}, converted to lowercase. 2570 * @see java.lang.String#toLowerCase(Locale) 2571 */ 2572 public String toLowerCase() { 2573 return toLowerCase(Locale.getDefault()); 2574 } 2575 2576 /** 2577 * Converts all of the characters in this {@code String} to upper 2578 * case using the rules of the given {@code Locale}. Case mapping is based 2579 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2580 * class. Since case mappings are not always 1:1 char mappings, the resulting 2581 * {@code String} may be a different length than the original {@code String}. 2582 * <p> 2583 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2584 * <p> 2585 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2586 * <tr> 2587 * <th>Language Code of Locale</th> 2588 * <th>Lower Case</th> 2589 * <th>Upper Case</th> 2590 * <th>Description</th> 2591 * </tr> 2592 * <tr> 2593 * <td>tr (Turkish)</td> 2594 * <td>\u0069</td> 2595 * <td>\u0130</td> 2596 * <td>small letter i -> capital letter I with dot above</td> 2597 * </tr> 2598 * <tr> 2599 * <td>tr (Turkish)</td> 2600 * <td>\u0131</td> 2601 * <td>\u0049</td> 2602 * <td>small letter dotless i -> capital letter I</td> 2603 * </tr> 2604 * <tr> 2605 * <td>(all)</td> 2606 * <td>\u00df</td> 2607 * <td>\u0053 \u0053</td> 2608 * <td>small letter sharp s -> two letters: SS</td> 2609 * </tr> 2610 * <tr> 2611 * <td>(all)</td> 2612 * <td>Fahrvergnügen</td> 2613 * <td>FAHRVERGNÜGEN</td> 2614 * <td></td> 2615 * </tr> 2616 * </table> 2617 * @param locale use the case transformation rules for this locale 2618 * @return the {@code String}, converted to uppercase. 2619 * @see java.lang.String#toUpperCase() 2620 * @see java.lang.String#toLowerCase() 2621 * @see java.lang.String#toLowerCase(Locale) 2622 * @since 1.1 2623 */ 2624 public String toUpperCase(Locale locale) { 2625 if (locale == null) { 2626 throw new NullPointerException(); 2627 } 2628 2629 int firstLower; 2630 2631 /* Now check if there are any characters that need to be changed. */ 2632 scan: { 2633 for (firstLower = 0 ; firstLower < count; ) { 2634 int c = (int)value[offset+firstLower]; 2635 int srcCount; 2636 if ((c >= Character.MIN_HIGH_SURROGATE) && 2637 (c <= Character.MAX_HIGH_SURROGATE)) { 2638 c = codePointAt(firstLower); 2639 srcCount = Character.charCount(c); 2640 } else { 2641 srcCount = 1; 2642 } 2643 int upperCaseChar = Character.toUpperCaseEx(c); 2644 if ((upperCaseChar == Character.ERROR) || 2645 (c != upperCaseChar)) { 2646 break scan; 2647 } 2648 firstLower += srcCount; 2649 } 2650 return this; 2651 } 2652 2653 char[] result = new char[count]; /* may grow */ 2654 int resultOffset = 0; /* result may grow, so i+resultOffset 2655 * is the write location in result */ 2656 2657 /* Just copy the first few upperCase characters. */ 2658 System.arraycopy(value, offset, result, 0, firstLower); 2659 2660 String lang = locale.getLanguage(); 2661 boolean localeDependent = 2662 (lang == "tr" || lang == "az" || lang == "lt"); 2663 char[] upperCharArray; 2664 int upperChar; 2665 int srcChar; 2666 int srcCount; 2667 for (int i = firstLower; i < count; i += srcCount) { 2668 srcChar = (int)value[offset+i]; 2669 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE && 2670 (char)srcChar <= Character.MAX_HIGH_SURROGATE) { 2671 srcChar = codePointAt(i); 2672 srcCount = Character.charCount(srcChar); 2673 } else { 2674 srcCount = 1; 2675 } 2676 if (localeDependent) { 2677 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale); 2678 } else { 2679 upperChar = Character.toUpperCaseEx(srcChar); 2680 } 2681 if ((upperChar == Character.ERROR) || 2682 (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) { 2683 if (upperChar == Character.ERROR) { 2684 if (localeDependent) { 2685 upperCharArray = 2686 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale); 2687 } else { 2688 upperCharArray = Character.toUpperCaseCharArray(srcChar); 2689 } 2690 } else if (srcCount == 2) { 2691 resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount; 2692 continue; 2693 } else { 2694 upperCharArray = Character.toChars(upperChar); 2695 } 2696 2697 /* Grow result if needed */ 2698 int mapLen = upperCharArray.length; 2699 if (mapLen > srcCount) { 2700 char[] result2 = new char[result.length + mapLen - srcCount]; 2701 System.arraycopy(result, 0, result2, 0, 2702 i + resultOffset); 2703 result = result2; 2704 } 2705 for (int x=0; x<mapLen; ++x) { 2706 result[i+resultOffset+x] = upperCharArray[x]; 2707 } 2708 resultOffset += (mapLen - srcCount); 2709 } else { 2710 result[i+resultOffset] = (char)upperChar; 2711 } 2712 } 2713 return new String(0, count+resultOffset, result); 2714 } 2715 2716 /** 2717 * Converts all of the characters in this {@code String} to upper 2718 * case using the rules of the default locale. This method is equivalent to 2719 * {@code toUpperCase(Locale.getDefault())}. 2720 * <p> 2721 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2722 * results if used for strings that are intended to be interpreted locale 2723 * independently. 2724 * Examples are programming language identifiers, protocol keys, and HTML 2725 * tags. 2726 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2727 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2728 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2729 * To obtain correct results for locale insensitive strings, use 2730 * {@code toUpperCase(Locale.ENGLISH)}. 2731 * <p> 2732 * @return the {@code String}, converted to uppercase. 2733 * @see java.lang.String#toUpperCase(Locale) 2734 */ 2735 public String toUpperCase() { 2736 return toUpperCase(Locale.getDefault()); 2737 } 2738 2739 /** 2740 * Returns a copy of the string, with leading and trailing whitespace 2741 * omitted. 2742 * <p> 2743 * If this {@code String} object represents an empty character 2744 * sequence, or the first and last characters of character sequence 2745 * represented by this {@code String} object both have codes 2746 * greater than {@code '\u005Cu0020'} (the space character), then a 2747 * reference to this {@code String} object is returned. 2748 * <p> 2749 * Otherwise, if there is no character with a code greater than 2750 * {@code '\u005Cu0020'} in the string, then a new 2751 * {@code String} object representing an empty string is created 2752 * and returned. 2753 * <p> 2754 * Otherwise, let <i>k</i> be the index of the first character in the 2755 * string whose code is greater than {@code '\u005Cu0020'}, and let 2756 * <i>m</i> be the index of the last character in the string whose code 2757 * is greater than {@code '\u005Cu0020'}. A new {@code String} 2758 * object is created, representing the substring of this string that 2759 * begins with the character at index <i>k</i> and ends with the 2760 * character at index <i>m</i>-that is, the result of 2761 * <code>this.substring(<i>k</i>, <i>m</i>+1)</code>. 2762 * <p> 2763 * This method may be used to trim whitespace (as defined above) from 2764 * the beginning and end of a string. 2765 * 2766 * @return A copy of this string with leading and trailing white 2767 * space removed, or this string if it has no leading or 2768 * trailing white space. 2769 */ 2770 public String trim() { 2771 int len = count; 2772 int st = 0; 2773 int off = offset; /* avoid getfield opcode */ 2774 char[] val = value; /* avoid getfield opcode */ 2775 2776 while ((st < len) && (val[off + st] <= ' ')) { 2777 st++; 2778 } 2779 while ((st < len) && (val[off + len - 1] <= ' ')) { 2780 len--; 2781 } 2782 return ((st > 0) || (len < count)) ? substring(st, len) : this; 2783 } 2784 2785 /** 2786 * This object (which is already a string!) is itself returned. 2787 * 2788 * @return the string itself. 2789 */ 2790 public String toString() { 2791 return this; 2792 } 2793 2794 /** 2795 * Converts this string to a new character array. 2796 * 2797 * @return a newly allocated character array whose length is the length 2798 * of this string and whose contents are initialized to contain 2799 * the character sequence represented by this string. 2800 */ 2801 public char[] toCharArray() { 2802 char result[] = new char[count]; 2803 getChars(0, count, result, 0); 2804 return result; 2805 } 2806 2807 /** 2808 * Returns a formatted string using the specified format string and 2809 * arguments. 2810 * 2811 * <p> The locale always used is the one returned by {@link 2812 * java.util.Locale#getDefault() Locale.getDefault()}. 2813 * 2814 * @param format 2815 * A <a href="../util/Formatter.html#syntax">format string</a> 2816 * 2817 * @param args 2818 * Arguments referenced by the format specifiers in the format 2819 * string. If there are more arguments than format specifiers, the 2820 * extra arguments are ignored. The number of arguments is 2821 * variable and may be zero. The maximum number of arguments is 2822 * limited by the maximum dimension of a Java array as defined by 2823 * <cite>The Java™ Virtual Machine Specification</cite>. 2824 * The behaviour on a 2825 * <tt>null</tt> argument depends on the <a 2826 * href="../util/Formatter.html#syntax">conversion</a>. 2827 * 2828 * @throws IllegalFormatException 2829 * If a format string contains an illegal syntax, a format 2830 * specifier that is incompatible with the given arguments, 2831 * insufficient arguments given the format string, or other 2832 * illegal conditions. For specification of all possible 2833 * formatting errors, see the <a 2834 * href="../util/Formatter.html#detail">Details</a> section of the 2835 * formatter class specification. 2836 * 2837 * @throws NullPointerException 2838 * If the <tt>format</tt> is <tt>null</tt> 2839 * 2840 * @return A formatted string 2841 * 2842 * @see java.util.Formatter 2843 * @since 1.5 2844 */ 2845 public static String format(String format, Object ... args) { 2846 return new Formatter().format(format, args).toString(); 2847 } 2848 2849 /** 2850 * Returns a formatted string using the specified locale, format string, 2851 * and arguments. 2852 * 2853 * @param l 2854 * The {@linkplain java.util.Locale locale} to apply during 2855 * formatting. If <tt>l</tt> is <tt>null</tt> then no localization 2856 * is applied. 2857 * 2858 * @param format 2859 * A <a href="../util/Formatter.html#syntax">format string</a> 2860 * 2861 * @param args 2862 * Arguments referenced by the format specifiers in the format 2863 * string. If there are more arguments than format specifiers, the 2864 * extra arguments are ignored. The number of arguments is 2865 * variable and may be zero. The maximum number of arguments is 2866 * limited by the maximum dimension of a Java array as defined by 2867 * <cite>The Java™ Virtual Machine Specification</cite>. 2868 * The behaviour on a 2869 * <tt>null</tt> argument depends on the <a 2870 * href="../util/Formatter.html#syntax">conversion</a>. 2871 * 2872 * @throws IllegalFormatException 2873 * If a format string contains an illegal syntax, a format 2874 * specifier that is incompatible with the given arguments, 2875 * insufficient arguments given the format string, or other 2876 * illegal conditions. For specification of all possible 2877 * formatting errors, see the <a 2878 * href="../util/Formatter.html#detail">Details</a> section of the 2879 * formatter class specification 2880 * 2881 * @throws NullPointerException 2882 * If the <tt>format</tt> is <tt>null</tt> 2883 * 2884 * @return A formatted string 2885 * 2886 * @see java.util.Formatter 2887 * @since 1.5 2888 */ 2889 public static String format(Locale l, String format, Object ... args) { 2890 return new Formatter(l).format(format, args).toString(); 2891 } 2892 2893 /** 2894 * Returns the string representation of the {@code Object} argument. 2895 * 2896 * @param obj an {@code Object}. 2897 * @return if the argument is {@code null}, then a string equal to 2898 * {@code "null"}; otherwise, the value of 2899 * {@code obj.toString()} is returned. 2900 * @see java.lang.Object#toString() 2901 */ 2902 public static String valueOf(Object obj) { 2903 return (obj == null) ? "null" : obj.toString(); 2904 } 2905 2906 /** 2907 * Returns the string representation of the {@code char} array 2908 * argument. The contents of the character array are copied; subsequent 2909 * modification of the character array does not affect the newly 2910 * created string. 2911 * 2912 * @param data a {@code char} array. 2913 * @return a newly allocated string representing the same sequence of 2914 * characters contained in the character array argument. 2915 */ 2916 public static String valueOf(char data[]) { 2917 return new String(data); 2918 } 2919 2920 /** 2921 * Returns the string representation of a specific subarray of the 2922 * {@code char} array argument. 2923 * <p> 2924 * The {@code offset} argument is the index of the first 2925 * character of the subarray. The {@code count} argument 2926 * specifies the length of the subarray. The contents of the subarray 2927 * are copied; subsequent modification of the character array does not 2928 * affect the newly created string. 2929 * 2930 * @param data the character array. 2931 * @param offset the initial offset into the value of the 2932 * {@code String}. 2933 * @param count the length of the value of the {@code String}. 2934 * @return a string representing the sequence of characters contained 2935 * in the subarray of the character array argument. 2936 * @exception IndexOutOfBoundsException if {@code offset} is 2937 * negative, or {@code count} is negative, or 2938 * {@code offset+count} is larger than 2939 * {@code data.length}. 2940 */ 2941 public static String valueOf(char data[], int offset, int count) { 2942 return new String(data, offset, count); 2943 } 2944 2945 /** 2946 * Returns a String that represents the character sequence in the 2947 * array specified. 2948 * 2949 * @param data the character array. 2950 * @param offset initial offset of the subarray. 2951 * @param count length of the subarray. 2952 * @return a {@code String} that contains the characters of the 2953 * specified subarray of the character array. 2954 */ 2955 public static String copyValueOf(char data[], int offset, int count) { 2956 // All public String constructors now copy the data. 2957 return new String(data, offset, count); 2958 } 2959 2960 /** 2961 * Returns a String that represents the character sequence in the 2962 * array specified. 2963 * 2964 * @param data the character array. 2965 * @return a {@code String} that contains the characters of the 2966 * character array. 2967 */ 2968 public static String copyValueOf(char data[]) { 2969 return copyValueOf(data, 0, data.length); 2970 } 2971 2972 /** 2973 * Returns the string representation of the {@code boolean} argument. 2974 * 2975 * @param b a {@code boolean}. 2976 * @return if the argument is {@code true}, a string equal to 2977 * {@code "true"} is returned; otherwise, a string equal to 2978 * {@code "false"} is returned. 2979 */ 2980 public static String valueOf(boolean b) { 2981 return b ? "true" : "false"; 2982 } 2983 2984 /** 2985 * Returns the string representation of the {@code char} 2986 * argument. 2987 * 2988 * @param c a {@code char}. 2989 * @return a string of length {@code 1} containing 2990 * as its single character the argument {@code c}. 2991 */ 2992 public static String valueOf(char c) { 2993 char data[] = {c}; 2994 return new String(0, 1, data); 2995 } 2996 2997 /** 2998 * Returns the string representation of the {@code int} argument. 2999 * <p> 3000 * The representation is exactly the one returned by the 3001 * {@code Integer.toString} method of one argument. 3002 * 3003 * @param i an {@code int}. 3004 * @return a string representation of the {@code int} argument. 3005 * @see java.lang.Integer#toString(int, int) 3006 */ 3007 public static String valueOf(int i) { 3008 return Integer.toString(i); 3009 } 3010 3011 /** 3012 * Returns the string representation of the {@code long} argument. 3013 * <p> 3014 * The representation is exactly the one returned by the 3015 * {@code Long.toString} method of one argument. 3016 * 3017 * @param l a {@code long}. 3018 * @return a string representation of the {@code long} argument. 3019 * @see java.lang.Long#toString(long) 3020 */ 3021 public static String valueOf(long l) { 3022 return Long.toString(l); 3023 } 3024 3025 /** 3026 * Returns the string representation of the {@code float} argument. 3027 * <p> 3028 * The representation is exactly the one returned by the 3029 * {@code Float.toString} method of one argument. 3030 * 3031 * @param f a {@code float}. 3032 * @return a string representation of the {@code float} argument. 3033 * @see java.lang.Float#toString(float) 3034 */ 3035 public static String valueOf(float f) { 3036 return Float.toString(f); 3037 } 3038 3039 /** 3040 * Returns the string representation of the {@code double} argument. 3041 * <p> 3042 * The representation is exactly the one returned by the 3043 * {@code Double.toString} method of one argument. 3044 * 3045 * @param d a {@code double}. 3046 * @return a string representation of the {@code double} argument. 3047 * @see java.lang.Double#toString(double) 3048 */ 3049 public static String valueOf(double d) { 3050 return Double.toString(d); 3051 } 3052 3053 /** 3054 * Returns a canonical representation for the string object. 3055 * <p> 3056 * A pool of strings, initially empty, is maintained privately by the 3057 * class {@code String}. 3058 * <p> 3059 * When the intern method is invoked, if the pool already contains a 3060 * string equal to this {@code String} object as determined by 3061 * the {@link #equals(Object)} method, then the string from the pool is 3062 * returned. Otherwise, this {@code String} object is added to the 3063 * pool and a reference to this {@code String} object is returned. 3064 * <p> 3065 * It follows that for any two strings {@code s} and {@code t}, 3066 * {@code s.intern() == t.intern()} is {@code true} 3067 * if and only if {@code s.equals(t)} is {@code true}. 3068 * <p> 3069 * All literal strings and string-valued constant expressions are 3070 * interned. String literals are defined in section 3.10.5 of the 3071 * <cite>The Java™ Language Specification</cite>. 3072 * 3073 * @return a string that has the same contents as this string, but is 3074 * guaranteed to be from a pool of unique strings. 3075 */ 3076 public native String intern(); 3077 3078 /** 3079 * Seed value used for each alternative hash calculated. 3080 */ 3081 private static final int HASHING_SEED; 3082 3083 static { 3084 long nanos = System.nanoTime(); 3085 long now = System.currentTimeMillis(); 3086 int SEED_MATERIAL[] = { 3087 System.identityHashCode(String.class), 3088 System.identityHashCode(System.class), 3089 System.identityHashCode(Thread.currentThread()), 3090 (int) (nanos >>> 32), 3091 (int) nanos, 3092 (int) (now >>> 32), 3093 (int) now, 3094 (int) (System.nanoTime() >> 2) 3095 }; 3096 3097 HASHING_SEED = sun.misc.Hashing.murmur3_32(SEED_MATERIAL); 3098 } 3099 3100 /** 3101 * Cached value of the hashing algorithm result 3102 */ 3103 private transient int hash32 = 0; 3104 3105 /** 3106 * {@inheritDoc} 3107 * 3108 * <p/> 3109 * The hash value will never be zero. 3110 */ 3111 public int hash32() { 3112 int h = hash32; 3113 if (0 == h) { 3114 // harmless data race on hash32 here. 3115 h = sun.misc.Hashing.murmur3_32(HASHING_SEED, value, offset, count); 3116 3117 // ensure result is not zero to avoid recalcing 3118 h = (0 != h) ? h : 1; 3119 3120 hash32 = h; 3121 } 3122 3123 return h; 3124 } 3125 3126 }