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</code> class represents character strings. All 42 * string literals in Java programs, such as <code>"abc"</code>, 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</code> 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</code>(or <code>StringBuffer</code>) 76 * class and its <code>append</code> method. 77 * String conversions are implemented through the method 78 * <code>toString</code>, defined by <code>Object</code> 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</code> 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</code> class for 91 * more information). 92 * Index values refer to <code>char</code> code units, so a supplementary 93 * character uses two positions in a <code>String</code>. 94 * <p>The <code>String</code> 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</code> 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 { 112 /** The value is used for character storage. */ 113 private final char value[]; 114 115 /** The offset is the first index of the storage that is used. */ 116 private final int offset; 117 118 /** The count is the number of characters in the String. */ 119 private final int count; 120 121 /** Cache the hash code for the string */ 122 private int hash; // Default to 0 123 124 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 125 private static final long serialVersionUID = -6849794470754667710L; 126 127 /** 128 * Class String is special cased within the Serialization Stream Protocol. 129 * 130 * A String instance is written initially into an ObjectOutputStream in the 131 * following format: 132 * <pre> 133 * <code>TC_STRING</code> (utf String) 134 * </pre> 135 * The String is written by method <code>DataOutput.writeUTF</code>. 136 * A new handle is generated to refer to all future references to the 137 * string instance within the stream. 138 */ 139 private static final ObjectStreamField[] serialPersistentFields = 140 new ObjectStreamField[0]; 141 142 /** 143 * Initializes a newly created {@code String} object so that it represents 144 * an empty character sequence. Note that use of this constructor is 145 * unnecessary since Strings are immutable. 146 */ 147 public String() { 148 this.offset = 0; 149 this.count = 0; 150 this.value = new char[0]; 151 } 152 153 /** 154 * Initializes a newly created {@code String} object so that it represents 155 * the same sequence of characters as the argument; in other words, the 156 * newly created string is a copy of the argument string. Unless an 157 * explicit copy of {@code original} is needed, use of this constructor is 158 * unnecessary since Strings are immutable. 159 * 160 * @param original 161 * A {@code String} 162 */ 163 public String(String original) { 164 int size = original.count; 165 char[] originalValue = original.value; 166 char[] v; 167 if (originalValue.length > size) { 168 // The array representing the String is bigger than the new 169 // String itself. Perhaps this constructor is being called 170 // in order to trim the baggage, so make a copy of the array. 171 int off = original.offset; 172 v = Arrays.copyOfRange(originalValue, off, off+size); 173 } else { 174 // The array representing the String is the same 175 // size as the String, so no point in making a copy. 176 v = originalValue; 177 } 178 this.offset = 0; 179 this.count = size; 180 this.value = v; 181 } 182 183 /** 184 * Allocates a new {@code String} so that it represents the sequence of 185 * characters currently contained in the character array argument. The 186 * contents of the character array are copied; subsequent modification of 187 * the character array does not affect the newly created string. 188 * 189 * @param value 190 * The initial value of the string 191 */ 192 public String(char value[]) { 193 int size = value.length; 194 this.offset = 0; 195 this.count = size; 196 this.value = Arrays.copyOf(value, size); 197 } 198 199 /** 200 * Allocates a new {@code String} that contains characters from a subarray 201 * of the character array argument. The {@code offset} argument is the 202 * index of the first character of the subarray and the {@code count} 203 * argument specifies the length of the subarray. The contents of the 204 * subarray are copied; subsequent modification of the character array does 205 * not affect the newly created string. 206 * 207 * @param value 208 * Array that is the source of characters 209 * 210 * @param offset 211 * The initial offset 212 * 213 * @param count 214 * The length 215 * 216 * @throws IndexOutOfBoundsException 217 * If the {@code offset} and {@code count} arguments index 218 * characters outside the bounds of the {@code value} array 219 */ 220 public String(char value[], int offset, int count) { 221 if (offset < 0) { 222 throw new StringIndexOutOfBoundsException(offset); 223 } 224 if (count < 0) { 225 throw new StringIndexOutOfBoundsException(count); 226 } 227 // Note: offset or count might be near -1>>>1. 228 if (offset > value.length - count) { 229 throw new StringIndexOutOfBoundsException(offset + count); 230 } 231 this.offset = 0; 232 this.count = count; 233 this.value = Arrays.copyOfRange(value, offset, offset+count); 234 } 235 236 /** 237 * Allocates a new {@code String} that contains characters from a subarray 238 * of the <a href="Character.html#unicode">Unicode code point</a> array 239 * argument. The {@code offset} argument is the index of the first code 240 * point of the subarray and the {@code count} argument specifies the 241 * length of the subarray. The contents of the subarray are converted to 242 * {@code char}s; subsequent modification of the {@code int} array does not 243 * affect the newly created string. 244 * 245 * @param codePoints 246 * Array that is the source of Unicode code points 247 * 248 * @param offset 249 * The initial offset 250 * 251 * @param count 252 * The length 253 * 254 * @throws IllegalArgumentException 255 * If any invalid Unicode code point is found in {@code 256 * codePoints} 257 * 258 * @throws IndexOutOfBoundsException 259 * If the {@code offset} and {@code count} arguments index 260 * characters outside the bounds of the {@code codePoints} array 261 * 262 * @since 1.5 263 */ 264 public String(int[] codePoints, int offset, int count) { 265 if (offset < 0) { 266 throw new StringIndexOutOfBoundsException(offset); 267 } 268 if (count < 0) { 269 throw new StringIndexOutOfBoundsException(count); 270 } 271 // Note: offset or count might be near -1>>>1. 272 if (offset > codePoints.length - count) { 273 throw new StringIndexOutOfBoundsException(offset + count); 274 } 275 276 final int end = offset + count; 277 278 // Pass 1: Compute precise size of char[] 279 int n = count; 280 for (int i = offset; i < end; i++) { 281 int c = codePoints[i]; 282 if (Character.isBmpCodePoint(c)) 283 continue; 284 else if (Character.isValidCodePoint(c)) 285 n++; 286 else throw new IllegalArgumentException(Integer.toString(c)); 287 } 288 289 // Pass 2: Allocate and fill in char[] 290 final char[] v = new char[n]; 291 292 for (int i = offset, j = 0; i < end; i++, j++) { 293 int c = codePoints[i]; 294 if (Character.isBmpCodePoint(c)) 295 v[j] = (char) c; 296 else 297 Character.toSurrogates(c, v, j++); 298 } 299 300 this.value = v; 301 this.count = n; 302 this.offset = 0; 303 } 304 305 /** 306 * Allocates a new {@code String} constructed from a subarray of an array 307 * of 8-bit integer values. 308 * 309 * <p> The {@code offset} argument is the index of the first byte of the 310 * subarray, and the {@code count} argument specifies the length of the 311 * subarray. 312 * 313 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 314 * specified in the method above. 315 * 316 * @deprecated This method does not properly convert bytes into characters. 317 * As of JDK 1.1, the preferred way to do this is via the 318 * {@code String} constructors that take a {@link 319 * java.nio.charset.Charset}, charset name, or that use the platform's 320 * default charset. 321 * 322 * @param ascii 323 * The bytes to be converted to characters 324 * 325 * @param hibyte 326 * The top 8 bits of each 16-bit Unicode code unit 327 * 328 * @param offset 329 * The initial offset 330 * @param count 331 * The length 332 * 333 * @throws IndexOutOfBoundsException 334 * If the {@code offset} or {@code count} argument is invalid 335 * 336 * @see #String(byte[], int) 337 * @see #String(byte[], int, int, java.lang.String) 338 * @see #String(byte[], int, int, java.nio.charset.Charset) 339 * @see #String(byte[], int, int) 340 * @see #String(byte[], java.lang.String) 341 * @see #String(byte[], java.nio.charset.Charset) 342 * @see #String(byte[]) 343 */ 344 @Deprecated 345 public String(byte ascii[], int hibyte, int offset, int count) { 346 checkBounds(ascii, offset, count); 347 char value[] = new char[count]; 348 349 if (hibyte == 0) { 350 for (int i = count ; i-- > 0 ;) { 351 value[i] = (char) (ascii[i + offset] & 0xff); 352 } 353 } else { 354 hibyte <<= 8; 355 for (int i = count ; i-- > 0 ;) { 356 value[i] = (char) (hibyte | (ascii[i + offset] & 0xff)); 357 } 358 } 359 this.offset = 0; 360 this.count = count; 361 this.value = value; 362 } 363 364 /** 365 * Allocates a new {@code String} containing characters constructed from 366 * an array of 8-bit integer values. Each character <i>c</i>in the 367 * resulting string is constructed from the corresponding component 368 * <i>b</i> in the byte array such that: 369 * 370 * <blockquote><pre> 371 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 372 * | (<b><i>b</i></b> & 0xff)) 373 * </pre></blockquote> 374 * 375 * @deprecated This method does not properly convert bytes into 376 * characters. As of JDK 1.1, the preferred way to do this is via the 377 * {@code String} constructors that take a {@link 378 * java.nio.charset.Charset}, charset name, or that use the platform's 379 * default charset. 380 * 381 * @param ascii 382 * The bytes to be converted to characters 383 * 384 * @param hibyte 385 * The top 8 bits of each 16-bit Unicode code unit 386 * 387 * @see #String(byte[], int, int, java.lang.String) 388 * @see #String(byte[], int, int, java.nio.charset.Charset) 389 * @see #String(byte[], int, int) 390 * @see #String(byte[], java.lang.String) 391 * @see #String(byte[], java.nio.charset.Charset) 392 * @see #String(byte[]) 393 */ 394 @Deprecated 395 public String(byte ascii[], int hibyte) { 396 this(ascii, hibyte, 0, ascii.length); 397 } 398 399 /* Common private utility method used to bounds check the byte array 400 * and requested offset & length values used by the String(byte[],..) 401 * constructors. 402 */ 403 private static void checkBounds(byte[] bytes, int offset, int length) { 404 if (length < 0) 405 throw new StringIndexOutOfBoundsException(length); 406 if (offset < 0) 407 throw new StringIndexOutOfBoundsException(offset); 408 if (offset > bytes.length - length) 409 throw new StringIndexOutOfBoundsException(offset + length); 410 } 411 412 /** 413 * Constructs a new {@code String} by decoding the specified subarray of 414 * bytes using the specified charset. The length of the new {@code String} 415 * is a function of the charset, and hence may not be equal to the length 416 * of the subarray. 417 * 418 * <p> The behavior of this constructor when the given bytes are not valid 419 * in the given charset is unspecified. The {@link 420 * java.nio.charset.CharsetDecoder} class should be used when more control 421 * over the decoding process is required. 422 * 423 * @param bytes 424 * The bytes to be decoded into characters 425 * 426 * @param offset 427 * The index of the first byte to decode 428 * 429 * @param length 430 * The number of bytes to decode 431 432 * @param charsetName 433 * The name of a supported {@linkplain java.nio.charset.Charset 434 * charset} 435 * 436 * @throws UnsupportedEncodingException 437 * If the named charset is not supported 438 * 439 * @throws IndexOutOfBoundsException 440 * If the {@code offset} and {@code length} arguments index 441 * characters outside the bounds of the {@code bytes} array 442 * 443 * @since JDK1.1 444 */ 445 public String(byte bytes[], int offset, int length, String charsetName) 446 throws UnsupportedEncodingException 447 { 448 if (charsetName == null) 449 throw new NullPointerException("charsetName"); 450 checkBounds(bytes, offset, length); 451 char[] v = StringCoding.decode(charsetName, bytes, offset, length); 452 this.offset = 0; 453 this.count = v.length; 454 this.value = v; 455 } 456 457 /** 458 * Constructs a new {@code String} by decoding the specified subarray of 459 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 460 * The length of the new {@code String} is a function of the charset, and 461 * hence may not be equal to the length of the subarray. 462 * 463 * <p> This method always replaces malformed-input and unmappable-character 464 * sequences with this charset's default replacement string. The {@link 465 * java.nio.charset.CharsetDecoder} class should be used when more control 466 * over the decoding process is required. 467 * 468 * @param bytes 469 * The bytes to be decoded into characters 470 * 471 * @param offset 472 * The index of the first byte to decode 473 * 474 * @param length 475 * The number of bytes to decode 476 * 477 * @param charset 478 * The {@linkplain java.nio.charset.Charset charset} to be used to 479 * decode the {@code bytes} 480 * 481 * @throws IndexOutOfBoundsException 482 * If the {@code offset} and {@code length} arguments index 483 * characters outside the bounds of the {@code bytes} array 484 * 485 * @since 1.6 486 */ 487 public String(byte bytes[], int offset, int length, Charset charset) { 488 if (charset == null) 489 throw new NullPointerException("charset"); 490 checkBounds(bytes, offset, length); 491 char[] v = StringCoding.decode(charset, bytes, offset, length); 492 this.offset = 0; 493 this.count = v.length; 494 this.value = v; 495 } 496 497 /** 498 * Constructs a new {@code String} by decoding the specified array of bytes 499 * using the specified {@linkplain java.nio.charset.Charset charset}. The 500 * length of the new {@code String} is a function of the charset, and hence 501 * may not be equal to the length of the byte array. 502 * 503 * <p> The behavior of this constructor when the given bytes are not valid 504 * in the given charset is unspecified. The {@link 505 * java.nio.charset.CharsetDecoder} class should be used when more control 506 * over the decoding process is required. 507 * 508 * @param bytes 509 * The bytes to be decoded into characters 510 * 511 * @param charsetName 512 * The name of a supported {@linkplain java.nio.charset.Charset 513 * charset} 514 * 515 * @throws UnsupportedEncodingException 516 * If the named charset is not supported 517 * 518 * @since JDK1.1 519 */ 520 public String(byte bytes[], String charsetName) 521 throws UnsupportedEncodingException 522 { 523 this(bytes, 0, bytes.length, charsetName); 524 } 525 526 /** 527 * Constructs a new {@code String} by decoding the specified array of 528 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 529 * The length of the new {@code String} is a function of the charset, and 530 * hence may not be equal to the length of the byte array. 531 * 532 * <p> This method always replaces malformed-input and unmappable-character 533 * sequences with this charset's default replacement string. The {@link 534 * java.nio.charset.CharsetDecoder} class should be used when more control 535 * over the decoding process is required. 536 * 537 * @param bytes 538 * The bytes to be decoded into characters 539 * 540 * @param charset 541 * The {@linkplain java.nio.charset.Charset charset} to be used to 542 * decode the {@code bytes} 543 * 544 * @since 1.6 545 */ 546 public String(byte bytes[], Charset charset) { 547 this(bytes, 0, bytes.length, charset); 548 } 549 550 /** 551 * Constructs a new {@code String} by decoding the specified subarray of 552 * bytes using the platform's default charset. The length of the new 553 * {@code String} is a function of the charset, and hence may not be equal 554 * to the length of the subarray. 555 * 556 * <p> The behavior of this constructor when the given bytes are not valid 557 * in the default charset is unspecified. The {@link 558 * java.nio.charset.CharsetDecoder} class should be used when more control 559 * over the decoding process is required. 560 * 561 * @param bytes 562 * The bytes to be decoded into characters 563 * 564 * @param offset 565 * The index of the first byte to decode 566 * 567 * @param length 568 * The number of bytes to decode 569 * 570 * @throws IndexOutOfBoundsException 571 * If the {@code offset} and the {@code length} arguments index 572 * characters outside the bounds of the {@code bytes} array 573 * 574 * @since JDK1.1 575 */ 576 public String(byte bytes[], int offset, int length) { 577 checkBounds(bytes, offset, length); 578 char[] v = StringCoding.decode(bytes, offset, length); 579 this.offset = 0; 580 this.count = v.length; 581 this.value = v; 582 } 583 584 /** 585 * Constructs a new {@code String} by decoding the specified array of bytes 586 * using the platform's default charset. The length of the new {@code 587 * String} is a function of the charset, and hence may not be equal to the 588 * length of the byte array. 589 * 590 * <p> The behavior of this constructor when the given bytes are not valid 591 * in the default charset is unspecified. The {@link 592 * java.nio.charset.CharsetDecoder} class should be used when more control 593 * over the decoding process is required. 594 * 595 * @param bytes 596 * The bytes to be decoded into characters 597 * 598 * @since JDK1.1 599 */ 600 public String(byte bytes[]) { 601 this(bytes, 0, bytes.length); 602 } 603 604 /** 605 * Allocates a new string that contains the sequence of characters 606 * currently contained in the string buffer argument. The contents of the 607 * string buffer are copied; subsequent modification of the string buffer 608 * does not affect the newly created string. 609 * 610 * @param buffer 611 * A {@code StringBuffer} 612 */ 613 public String(StringBuffer buffer) { 614 String result = buffer.toString(); 615 this.value = result.value; 616 this.count = result.count; 617 this.offset = result.offset; 618 } 619 620 /** 621 * Allocates a new string that contains the sequence of characters 622 * currently contained in the string builder argument. The contents of the 623 * string builder are copied; subsequent modification of the string builder 624 * does not affect the newly created string. 625 * 626 * <p> This constructor is provided to ease migration to {@code 627 * StringBuilder}. Obtaining a string from a string builder via the {@code 628 * toString} method is likely to run faster and is generally preferred. 629 * 630 * @param builder 631 * A {@code StringBuilder} 632 * 633 * @since 1.5 634 */ 635 public String(StringBuilder builder) { 636 String result = builder.toString(); 637 this.value = result.value; 638 this.count = result.count; 639 this.offset = result.offset; 640 } 641 642 643 // Package private constructor which shares value array for speed. 644 String(int offset, int count, char value[]) { 645 this.value = value; 646 this.offset = offset; 647 this.count = count; 648 } 649 650 /** 651 * Returns the length of this string. 652 * The length is equal to the number of <a href="Character.html#unicode">Unicode 653 * code units</a> in the string. 654 * 655 * @return the length of the sequence of characters represented by this 656 * object. 657 */ 658 public int length() { 659 return count; 660 } 661 662 /** 663 * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>. 664 * 665 * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise 666 * <tt>false</tt> 667 * 668 * @since 1.6 669 */ 670 public boolean isEmpty() { 671 return count == 0; 672 } 673 674 /** 675 * Returns the <code>char</code> value at the 676 * specified index. An index ranges from <code>0</code> to 677 * <code>length() - 1</code>. The first <code>char</code> value of the sequence 678 * is at index <code>0</code>, the next at index <code>1</code>, 679 * and so on, as for array indexing. 680 * 681 * <p>If the <code>char</code> value specified by the index is a 682 * <a href="Character.html#unicode">surrogate</a>, the surrogate 683 * value is returned. 684 * 685 * @param index the index of the <code>char</code> value. 686 * @return the <code>char</code> value at the specified index of this string. 687 * The first <code>char</code> value is at index <code>0</code>. 688 * @exception IndexOutOfBoundsException if the <code>index</code> 689 * argument is negative or not less than the length of this 690 * string. 691 */ 692 public char charAt(int index) { 693 if ((index < 0) || (index >= count)) { 694 throw new StringIndexOutOfBoundsException(index); 695 } 696 return value[index + offset]; 697 } 698 699 /** 700 * Returns the character (Unicode code point) at the specified 701 * index. The index refers to <code>char</code> values 702 * (Unicode code units) and ranges from <code>0</code> to 703 * {@link #length()}<code> - 1</code>. 704 * 705 * <p> If the <code>char</code> value specified at the given index 706 * is in the high-surrogate range, the following index is less 707 * than the length of this <code>String</code>, and the 708 * <code>char</code> value at the following index is in the 709 * low-surrogate range, then the supplementary code point 710 * corresponding to this surrogate pair is returned. Otherwise, 711 * the <code>char</code> value at the given index is returned. 712 * 713 * @param index the index to the <code>char</code> values 714 * @return the code point value of the character at the 715 * <code>index</code> 716 * @exception IndexOutOfBoundsException if the <code>index</code> 717 * argument is negative or not less than the length of this 718 * string. 719 * @since 1.5 720 */ 721 public int codePointAt(int index) { 722 if ((index < 0) || (index >= count)) { 723 throw new StringIndexOutOfBoundsException(index); 724 } 725 return Character.codePointAtImpl(value, offset + index, offset + count); 726 } 727 728 /** 729 * Returns the character (Unicode code point) before the specified 730 * index. The index refers to <code>char</code> values 731 * (Unicode code units) and ranges from <code>1</code> to {@link 732 * CharSequence#length() length}. 733 * 734 * <p> If the <code>char</code> value at <code>(index - 1)</code> 735 * is in the low-surrogate range, <code>(index - 2)</code> is not 736 * negative, and the <code>char</code> value at <code>(index - 737 * 2)</code> is in the high-surrogate range, then the 738 * supplementary code point value of the surrogate pair is 739 * returned. If the <code>char</code> value at <code>index - 740 * 1</code> is an unpaired low-surrogate or a high-surrogate, the 741 * surrogate value is returned. 742 * 743 * @param index the index following the code point that should be returned 744 * @return the Unicode code point value before the given index. 745 * @exception IndexOutOfBoundsException if the <code>index</code> 746 * argument is less than 1 or greater than the length 747 * of this string. 748 * @since 1.5 749 */ 750 public int codePointBefore(int index) { 751 int i = index - 1; 752 if ((i < 0) || (i >= count)) { 753 throw new StringIndexOutOfBoundsException(index); 754 } 755 return Character.codePointBeforeImpl(value, offset + index, offset); 756 } 757 758 /** 759 * Returns the number of Unicode code points in the specified text 760 * range of this <code>String</code>. The text range begins at the 761 * specified <code>beginIndex</code> and extends to the 762 * <code>char</code> at index <code>endIndex - 1</code>. Thus the 763 * length (in <code>char</code>s) of the text range is 764 * <code>endIndex-beginIndex</code>. Unpaired surrogates within 765 * the text range count as one code point each. 766 * 767 * @param beginIndex the index to the first <code>char</code> of 768 * the text range. 769 * @param endIndex the index after the last <code>char</code> of 770 * the text range. 771 * @return the number of Unicode code points in the specified text 772 * range 773 * @exception IndexOutOfBoundsException if the 774 * <code>beginIndex</code> is negative, or <code>endIndex</code> 775 * is larger than the length of this <code>String</code>, or 776 * <code>beginIndex</code> is larger than <code>endIndex</code>. 777 * @since 1.5 778 */ 779 public int codePointCount(int beginIndex, int endIndex) { 780 if (beginIndex < 0 || endIndex > count || beginIndex > endIndex) { 781 throw new IndexOutOfBoundsException(); 782 } 783 return Character.codePointCountImpl(value, offset+beginIndex, endIndex-beginIndex); 784 } 785 786 /** 787 * Returns the index within this <code>String</code> that is 788 * offset from the given <code>index</code> by 789 * <code>codePointOffset</code> code points. Unpaired surrogates 790 * within the text range given by <code>index</code> and 791 * <code>codePointOffset</code> count as one code point each. 792 * 793 * @param index the index to be offset 794 * @param codePointOffset the offset in code points 795 * @return the index within this <code>String</code> 796 * @exception IndexOutOfBoundsException if <code>index</code> 797 * is negative or larger then the length of this 798 * <code>String</code>, or if <code>codePointOffset</code> is positive 799 * and the substring starting with <code>index</code> has fewer 800 * than <code>codePointOffset</code> code points, 801 * or if <code>codePointOffset</code> is negative and the substring 802 * before <code>index</code> has fewer than the absolute value 803 * of <code>codePointOffset</code> code points. 804 * @since 1.5 805 */ 806 public int offsetByCodePoints(int index, int codePointOffset) { 807 if (index < 0 || index > count) { 808 throw new IndexOutOfBoundsException(); 809 } 810 return Character.offsetByCodePointsImpl(value, offset, count, 811 offset+index, codePointOffset) - offset; 812 } 813 814 /** 815 * Copy characters from this string into dst starting at dstBegin. 816 * This method doesn't perform any range checking. 817 */ 818 void getChars(char dst[], int dstBegin) { 819 System.arraycopy(value, offset, dst, dstBegin, count); 820 } 821 822 /** 823 * Copies characters from this string into the destination character 824 * array. 825 * <p> 826 * The first character to be copied is at index <code>srcBegin</code>; 827 * the last character to be copied is at index <code>srcEnd-1</code> 828 * (thus the total number of characters to be copied is 829 * <code>srcEnd-srcBegin</code>). The characters are copied into the 830 * subarray of <code>dst</code> starting at index <code>dstBegin</code> 831 * and ending at index: 832 * <p><blockquote><pre> 833 * dstbegin + (srcEnd-srcBegin) - 1 834 * </pre></blockquote> 835 * 836 * @param srcBegin index of the first character in the string 837 * to copy. 838 * @param srcEnd index after the last character in the string 839 * to copy. 840 * @param dst the destination array. 841 * @param dstBegin the start offset in the destination array. 842 * @exception IndexOutOfBoundsException If any of the following 843 * is true: 844 * <ul><li><code>srcBegin</code> is negative. 845 * <li><code>srcBegin</code> is greater than <code>srcEnd</code> 846 * <li><code>srcEnd</code> is greater than the length of this 847 * string 848 * <li><code>dstBegin</code> is negative 849 * <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than 850 * <code>dst.length</code></ul> 851 */ 852 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 853 if (srcBegin < 0) { 854 throw new StringIndexOutOfBoundsException(srcBegin); 855 } 856 if (srcEnd > count) { 857 throw new StringIndexOutOfBoundsException(srcEnd); 858 } 859 if (srcBegin > srcEnd) { 860 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 861 } 862 System.arraycopy(value, offset + srcBegin, dst, dstBegin, 863 srcEnd - srcBegin); 864 } 865 866 /** 867 * Copies characters from this string into the destination byte array. Each 868 * byte receives the 8 low-order bits of the corresponding character. The 869 * eight high-order bits of each character are not copied and do not 870 * participate in the transfer in any way. 871 * 872 * <p> The first character to be copied is at index {@code srcBegin}; the 873 * last character to be copied is at index {@code srcEnd-1}. The total 874 * number of characters to be copied is {@code srcEnd-srcBegin}. The 875 * characters, converted to bytes, are copied into the subarray of {@code 876 * dst} starting at index {@code dstBegin} and ending at index: 877 * 878 * <blockquote><pre> 879 * dstbegin + (srcEnd-srcBegin) - 1 880 * </pre></blockquote> 881 * 882 * @deprecated This method does not properly convert characters into 883 * bytes. As of JDK 1.1, the preferred way to do this is via the 884 * {@link #getBytes()} method, which uses the platform's default charset. 885 * 886 * @param srcBegin 887 * Index of the first character in the string to copy 888 * 889 * @param srcEnd 890 * Index after the last character in the string to copy 891 * 892 * @param dst 893 * The destination array 894 * 895 * @param dstBegin 896 * The start offset in the destination array 897 * 898 * @throws IndexOutOfBoundsException 899 * If any of the following is true: 900 * <ul> 901 * <li> {@code srcBegin} is negative 902 * <li> {@code srcBegin} is greater than {@code srcEnd} 903 * <li> {@code srcEnd} is greater than the length of this String 904 * <li> {@code dstBegin} is negative 905 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 906 * dst.length} 907 * </ul> 908 */ 909 @Deprecated 910 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 911 if (srcBegin < 0) { 912 throw new StringIndexOutOfBoundsException(srcBegin); 913 } 914 if (srcEnd > count) { 915 throw new StringIndexOutOfBoundsException(srcEnd); 916 } 917 if (srcBegin > srcEnd) { 918 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 919 } 920 int j = dstBegin; 921 int n = offset + srcEnd; 922 int i = offset + srcBegin; 923 char[] val = value; /* avoid getfield opcode */ 924 925 while (i < n) { 926 dst[j++] = (byte)val[i++]; 927 } 928 } 929 930 /** 931 * Encodes this {@code String} into a sequence of bytes using the named 932 * charset, storing the result into a new byte array. 933 * 934 * <p> The behavior of this method when this string cannot be encoded in 935 * the given charset is unspecified. The {@link 936 * java.nio.charset.CharsetEncoder} class should be used when more control 937 * over the encoding process is required. 938 * 939 * @param charsetName 940 * The name of a supported {@linkplain java.nio.charset.Charset 941 * charset} 942 * 943 * @return The resultant byte array 944 * 945 * @throws UnsupportedEncodingException 946 * If the named charset is not supported 947 * 948 * @since JDK1.1 949 */ 950 public byte[] getBytes(String charsetName) 951 throws UnsupportedEncodingException 952 { 953 if (charsetName == null) throw new NullPointerException(); 954 return StringCoding.encode(charsetName, value, offset, count); 955 } 956 957 /** 958 * Encodes this {@code String} into a sequence of bytes using the given 959 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 960 * new byte array. 961 * 962 * <p> This method always replaces malformed-input and unmappable-character 963 * sequences with this charset's default replacement byte array. The 964 * {@link java.nio.charset.CharsetEncoder} class should be used when more 965 * control over the encoding process is required. 966 * 967 * @param charset 968 * The {@linkplain java.nio.charset.Charset} to be used to encode 969 * the {@code String} 970 * 971 * @return The resultant byte array 972 * 973 * @since 1.6 974 */ 975 public byte[] getBytes(Charset charset) { 976 if (charset == null) throw new NullPointerException(); 977 return StringCoding.encode(charset, value, offset, count); 978 } 979 980 /** 981 * Encodes this {@code String} into a sequence of bytes using the 982 * platform's default charset, storing the result into a new byte array. 983 * 984 * <p> The behavior of this method when this string cannot be encoded in 985 * the default charset is unspecified. The {@link 986 * java.nio.charset.CharsetEncoder} class should be used when more control 987 * over the encoding process is required. 988 * 989 * @return The resultant byte array 990 * 991 * @since JDK1.1 992 */ 993 public byte[] getBytes() { 994 return StringCoding.encode(value, offset, count); 995 } 996 997 /** 998 * Compares this string to the specified object. The result is {@code 999 * true} if and only if the argument is not {@code null} and is a {@code 1000 * String} object that represents the same sequence of characters as this 1001 * object. 1002 * 1003 * @param anObject 1004 * The object to compare this {@code String} against 1005 * 1006 * @return {@code true} if the given object represents a {@code String} 1007 * equivalent to this string, {@code false} otherwise 1008 * 1009 * @see #compareTo(String) 1010 * @see #equalsIgnoreCase(String) 1011 */ 1012 public boolean equals(Object anObject) { 1013 if (this == anObject) { 1014 return true; 1015 } 1016 if (anObject instanceof String) { 1017 String anotherString = (String)anObject; 1018 int n = count; 1019 if (n == anotherString.count) { 1020 char v1[] = value; 1021 char v2[] = anotherString.value; 1022 int i = offset; 1023 int j = anotherString.offset; 1024 while (n-- != 0) { 1025 if (v1[i++] != v2[j++]) 1026 return false; 1027 } 1028 return true; 1029 } 1030 } 1031 return false; 1032 } 1033 1034 /** 1035 * Compares this string to the specified {@code StringBuffer}. The result 1036 * is {@code true} if and only if this {@code String} represents the same 1037 * sequence of characters as the specified {@code StringBuffer}. 1038 * 1039 * @param sb 1040 * The {@code StringBuffer} to compare this {@code String} against 1041 * 1042 * @return {@code true} if this {@code String} represents the same 1043 * sequence of characters as the specified {@code StringBuffer}, 1044 * {@code false} otherwise 1045 * 1046 * @since 1.4 1047 */ 1048 public boolean contentEquals(StringBuffer sb) { 1049 synchronized(sb) { 1050 return contentEquals((CharSequence)sb); 1051 } 1052 } 1053 1054 /** 1055 * Compares this string to the specified {@code CharSequence}. The result 1056 * is {@code true} if and only if this {@code String} represents the same 1057 * sequence of char values as the specified sequence. 1058 * 1059 * @param cs 1060 * The sequence to compare this {@code String} against 1061 * 1062 * @return {@code true} if this {@code String} represents the same 1063 * sequence of char values as the specified sequence, {@code 1064 * false} otherwise 1065 * 1066 * @since 1.5 1067 */ 1068 public boolean contentEquals(CharSequence cs) { 1069 if (count != cs.length()) 1070 return false; 1071 // Argument is a StringBuffer, StringBuilder 1072 if (cs instanceof AbstractStringBuilder) { 1073 char v1[] = value; 1074 char v2[] = ((AbstractStringBuilder)cs).getValue(); 1075 int i = offset; 1076 int j = 0; 1077 int n = count; 1078 while (n-- != 0) { 1079 if (v1[i++] != v2[j++]) 1080 return false; 1081 } 1082 return true; 1083 } 1084 // Argument is a String 1085 if (cs.equals(this)) 1086 return true; 1087 // Argument is a generic CharSequence 1088 char v1[] = value; 1089 int i = offset; 1090 int j = 0; 1091 int n = count; 1092 while (n-- != 0) { 1093 if (v1[i++] != cs.charAt(j++)) 1094 return false; 1095 } 1096 return true; 1097 } 1098 1099 /** 1100 * Compares this {@code String} to another {@code String}, ignoring case 1101 * considerations. Two strings are considered equal ignoring case if they 1102 * are of the same length and corresponding characters in the two strings 1103 * are equal ignoring case. 1104 * 1105 * <p> Two characters {@code c1} and {@code c2} are considered the same 1106 * ignoring case if at least one of the following is true: 1107 * <ul> 1108 * <li> The two characters are the same (as compared by the 1109 * {@code ==} operator) 1110 * <li> Applying the method {@link 1111 * java.lang.Character#toUpperCase(char)} to each character 1112 * produces the same result 1113 * <li> Applying the method {@link 1114 * java.lang.Character#toLowerCase(char)} to each character 1115 * produces the same result 1116 * </ul> 1117 * 1118 * @param anotherString 1119 * The {@code String} to compare this {@code String} against 1120 * 1121 * @return {@code true} if the argument is not {@code null} and it 1122 * represents an equivalent {@code String} ignoring case; {@code 1123 * false} otherwise 1124 * 1125 * @see #equals(Object) 1126 */ 1127 public boolean equalsIgnoreCase(String anotherString) { 1128 return (this == anotherString) ? true : 1129 (anotherString != null) && (anotherString.count == count) && 1130 regionMatches(true, 0, anotherString, 0, count); 1131 } 1132 1133 /** 1134 * Compares two strings lexicographically. 1135 * The comparison is based on the Unicode value of each character in 1136 * the strings. The character sequence represented by this 1137 * <code>String</code> object is compared lexicographically to the 1138 * character sequence represented by the argument string. The result is 1139 * a negative integer if this <code>String</code> object 1140 * lexicographically precedes the argument string. The result is a 1141 * positive integer if this <code>String</code> object lexicographically 1142 * follows the argument string. The result is zero if the strings 1143 * are equal; <code>compareTo</code> returns <code>0</code> exactly when 1144 * the {@link #equals(Object)} method would return <code>true</code>. 1145 * <p> 1146 * This is the definition of lexicographic ordering. If two strings are 1147 * different, then either they have different characters at some index 1148 * that is a valid index for both strings, or their lengths are different, 1149 * or both. If they have different characters at one or more index 1150 * positions, let <i>k</i> be the smallest such index; then the string 1151 * whose character at position <i>k</i> has the smaller value, as 1152 * determined by using the < operator, lexicographically precedes the 1153 * other string. In this case, <code>compareTo</code> returns the 1154 * difference of the two character values at position <code>k</code> in 1155 * the two string -- that is, the value: 1156 * <blockquote><pre> 1157 * this.charAt(k)-anotherString.charAt(k) 1158 * </pre></blockquote> 1159 * If there is no index position at which they differ, then the shorter 1160 * string lexicographically precedes the longer string. In this case, 1161 * <code>compareTo</code> returns the difference of the lengths of the 1162 * strings -- that is, the value: 1163 * <blockquote><pre> 1164 * this.length()-anotherString.length() 1165 * </pre></blockquote> 1166 * 1167 * @param anotherString the <code>String</code> to be compared. 1168 * @return the value <code>0</code> if the argument string is equal to 1169 * this string; a value less than <code>0</code> if this string 1170 * is lexicographically less than the string argument; and a 1171 * value greater than <code>0</code> if this string is 1172 * lexicographically greater than the string argument. 1173 */ 1174 public int compareTo(String anotherString) { 1175 int len1 = count; 1176 int len2 = anotherString.count; 1177 int n = Math.min(len1, len2); 1178 char v1[] = value; 1179 char v2[] = anotherString.value; 1180 int i = offset; 1181 int j = anotherString.offset; 1182 1183 if (i == j) { 1184 int k = i; 1185 int lim = n + i; 1186 while (k < lim) { 1187 char c1 = v1[k]; 1188 char c2 = v2[k]; 1189 if (c1 != c2) { 1190 return c1 - c2; 1191 } 1192 k++; 1193 } 1194 } else { 1195 while (n-- != 0) { 1196 char c1 = v1[i++]; 1197 char c2 = v2[j++]; 1198 if (c1 != c2) { 1199 return c1 - c2; 1200 } 1201 } 1202 } 1203 return len1 - len2; 1204 } 1205 1206 /** 1207 * A Comparator that orders <code>String</code> objects as by 1208 * <code>compareToIgnoreCase</code>. This comparator is serializable. 1209 * <p> 1210 * Note that this Comparator does <em>not</em> take locale into account, 1211 * and will result in an unsatisfactory ordering for certain locales. 1212 * The java.text package provides <em>Collators</em> to allow 1213 * locale-sensitive ordering. 1214 * 1215 * @see java.text.Collator#compare(String, String) 1216 * @since 1.2 1217 */ 1218 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1219 = new CaseInsensitiveComparator(); 1220 private static class CaseInsensitiveComparator 1221 implements Comparator<String>, java.io.Serializable { 1222 // use serialVersionUID from JDK 1.2.2 for interoperability 1223 private static final long serialVersionUID = 8575799808933029326L; 1224 1225 public int compare(String s1, String s2) { 1226 int n1 = s1.length(); 1227 int n2 = s2.length(); 1228 int min = Math.min(n1, n2); 1229 for (int i = 0; i < min; i++) { 1230 char c1 = s1.charAt(i); 1231 char c2 = s2.charAt(i); 1232 if (c1 != c2) { 1233 c1 = Character.toUpperCase(c1); 1234 c2 = Character.toUpperCase(c2); 1235 if (c1 != c2) { 1236 c1 = Character.toLowerCase(c1); 1237 c2 = Character.toLowerCase(c2); 1238 if (c1 != c2) { 1239 // No overflow because of numeric promotion 1240 return c1 - c2; 1241 } 1242 } 1243 } 1244 } 1245 return n1 - n2; 1246 } 1247 } 1248 1249 /** 1250 * Compares two strings lexicographically, ignoring case 1251 * differences. This method returns an integer whose sign is that of 1252 * calling <code>compareTo</code> with normalized versions of the strings 1253 * where case differences have been eliminated by calling 1254 * <code>Character.toLowerCase(Character.toUpperCase(character))</code> on 1255 * each character. 1256 * <p> 1257 * Note that this method does <em>not</em> take locale into account, 1258 * and will result in an unsatisfactory ordering for certain locales. 1259 * The java.text package provides <em>collators</em> to allow 1260 * locale-sensitive ordering. 1261 * 1262 * @param str the <code>String</code> to be compared. 1263 * @return a negative integer, zero, or a positive integer as the 1264 * specified String is greater than, equal to, or less 1265 * than this String, ignoring case considerations. 1266 * @see java.text.Collator#compare(String, String) 1267 * @since 1.2 1268 */ 1269 public int compareToIgnoreCase(String str) { 1270 return CASE_INSENSITIVE_ORDER.compare(this, str); 1271 } 1272 1273 /** 1274 * Tests if two string regions are equal. 1275 * <p> 1276 * A substring of this <tt>String</tt> object is compared to a substring 1277 * of the argument other. The result is true if these substrings 1278 * represent identical character sequences. The substring of this 1279 * <tt>String</tt> object to be compared begins at index <tt>toffset</tt> 1280 * and has length <tt>len</tt>. The substring of other to be compared 1281 * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The 1282 * result is <tt>false</tt> if and only if at least one of the following 1283 * is true: 1284 * <ul><li><tt>toffset</tt> is negative. 1285 * <li><tt>ooffset</tt> is negative. 1286 * <li><tt>toffset+len</tt> is greater than the length of this 1287 * <tt>String</tt> object. 1288 * <li><tt>ooffset+len</tt> is greater than the length of the other 1289 * argument. 1290 * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt> 1291 * such that: 1292 * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt> 1293 * </ul> 1294 * 1295 * @param toffset the starting offset of the subregion in this string. 1296 * @param other the string argument. 1297 * @param ooffset the starting offset of the subregion in the string 1298 * argument. 1299 * @param len the number of characters to compare. 1300 * @return <code>true</code> if the specified subregion of this string 1301 * exactly matches the specified subregion of the string argument; 1302 * <code>false</code> otherwise. 1303 */ 1304 public boolean regionMatches(int toffset, String other, int ooffset, 1305 int len) { 1306 char ta[] = value; 1307 int to = offset + toffset; 1308 char pa[] = other.value; 1309 int po = other.offset + ooffset; 1310 // Note: toffset, ooffset, or len might be near -1>>>1. 1311 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) 1312 || (ooffset > (long)other.count - len)) { 1313 return false; 1314 } 1315 while (len-- > 0) { 1316 if (ta[to++] != pa[po++]) { 1317 return false; 1318 } 1319 } 1320 return true; 1321 } 1322 1323 /** 1324 * Tests if two string regions are equal. 1325 * <p> 1326 * A substring of this <tt>String</tt> object is compared to a substring 1327 * of the argument <tt>other</tt>. The result is <tt>true</tt> if these 1328 * substrings represent character sequences that are the same, ignoring 1329 * case if and only if <tt>ignoreCase</tt> is true. The substring of 1330 * this <tt>String</tt> object to be compared begins at index 1331 * <tt>toffset</tt> and has length <tt>len</tt>. The substring of 1332 * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and 1333 * has length <tt>len</tt>. The result is <tt>false</tt> if and only if 1334 * at least one of the following is true: 1335 * <ul><li><tt>toffset</tt> is negative. 1336 * <li><tt>ooffset</tt> is negative. 1337 * <li><tt>toffset+len</tt> is greater than the length of this 1338 * <tt>String</tt> object. 1339 * <li><tt>ooffset+len</tt> is greater than the length of the other 1340 * argument. 1341 * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative 1342 * integer <i>k</i> less than <tt>len</tt> such that: 1343 * <blockquote><pre> 1344 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1345 * </pre></blockquote> 1346 * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative 1347 * integer <i>k</i> less than <tt>len</tt> such that: 1348 * <blockquote><pre> 1349 * Character.toLowerCase(this.charAt(toffset+k)) != 1350 Character.toLowerCase(other.charAt(ooffset+k)) 1351 * </pre></blockquote> 1352 * and: 1353 * <blockquote><pre> 1354 * Character.toUpperCase(this.charAt(toffset+k)) != 1355 * Character.toUpperCase(other.charAt(ooffset+k)) 1356 * </pre></blockquote> 1357 * </ul> 1358 * 1359 * @param ignoreCase if <code>true</code>, ignore case when comparing 1360 * characters. 1361 * @param toffset the starting offset of the subregion in this 1362 * string. 1363 * @param other the string argument. 1364 * @param ooffset the starting offset of the subregion in the string 1365 * argument. 1366 * @param len the number of characters to compare. 1367 * @return <code>true</code> if the specified subregion of this string 1368 * matches the specified subregion of the string argument; 1369 * <code>false</code> otherwise. Whether the matching is exact 1370 * or case insensitive depends on the <code>ignoreCase</code> 1371 * argument. 1372 */ 1373 public boolean regionMatches(boolean ignoreCase, int toffset, 1374 String other, int ooffset, int len) { 1375 char ta[] = value; 1376 int to = offset + toffset; 1377 char pa[] = other.value; 1378 int po = other.offset + ooffset; 1379 // Note: toffset, ooffset, or len might be near -1>>>1. 1380 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) || 1381 (ooffset > (long)other.count - len)) { 1382 return false; 1383 } 1384 while (len-- > 0) { 1385 char c1 = ta[to++]; 1386 char c2 = pa[po++]; 1387 if (c1 == c2) { 1388 continue; 1389 } 1390 if (ignoreCase) { 1391 // If characters don't match but case may be ignored, 1392 // try converting both characters to uppercase. 1393 // If the results match, then the comparison scan should 1394 // continue. 1395 char u1 = Character.toUpperCase(c1); 1396 char u2 = Character.toUpperCase(c2); 1397 if (u1 == u2) { 1398 continue; 1399 } 1400 // Unfortunately, conversion to uppercase does not work properly 1401 // for the Georgian alphabet, which has strange rules about case 1402 // conversion. So we need to make one last check before 1403 // exiting. 1404 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) { 1405 continue; 1406 } 1407 } 1408 return false; 1409 } 1410 return true; 1411 } 1412 1413 /** 1414 * Tests if the substring of this string beginning at the 1415 * specified index starts with the specified prefix. 1416 * 1417 * @param prefix the prefix. 1418 * @param toffset where to begin looking in this string. 1419 * @return <code>true</code> if the character sequence represented by the 1420 * argument is a prefix of the substring of this object starting 1421 * at index <code>toffset</code>; <code>false</code> otherwise. 1422 * The result is <code>false</code> if <code>toffset</code> is 1423 * negative or greater than the length of this 1424 * <code>String</code> object; otherwise the result is the same 1425 * as the result of the expression 1426 * <pre> 1427 * this.substring(toffset).startsWith(prefix) 1428 * </pre> 1429 */ 1430 public boolean startsWith(String prefix, int toffset) { 1431 char ta[] = value; 1432 int to = offset + toffset; 1433 char pa[] = prefix.value; 1434 int po = prefix.offset; 1435 int pc = prefix.count; 1436 // Note: toffset might be near -1>>>1. 1437 if ((toffset < 0) || (toffset > count - pc)) { 1438 return false; 1439 } 1440 while (--pc >= 0) { 1441 if (ta[to++] != pa[po++]) { 1442 return false; 1443 } 1444 } 1445 return true; 1446 } 1447 1448 /** 1449 * Tests if this string starts with the specified prefix. 1450 * 1451 * @param prefix the prefix. 1452 * @return <code>true</code> if the character sequence represented by the 1453 * argument is a prefix of the character sequence represented by 1454 * this string; <code>false</code> otherwise. 1455 * Note also that <code>true</code> will be returned if the 1456 * argument is an empty string or is equal to this 1457 * <code>String</code> object as determined by the 1458 * {@link #equals(Object)} method. 1459 * @since 1. 0 1460 */ 1461 public boolean startsWith(String prefix) { 1462 return startsWith(prefix, 0); 1463 } 1464 1465 /** 1466 * Tests if this string ends with the specified suffix. 1467 * 1468 * @param suffix the suffix. 1469 * @return <code>true</code> if the character sequence represented by the 1470 * argument is a suffix of the character sequence represented by 1471 * this object; <code>false</code> otherwise. Note that the 1472 * result will be <code>true</code> if the argument is the 1473 * empty string or is equal to this <code>String</code> object 1474 * as determined by the {@link #equals(Object)} method. 1475 */ 1476 public boolean endsWith(String suffix) { 1477 return startsWith(suffix, count - suffix.count); 1478 } 1479 1480 /** 1481 * Returns a hash code for this string. The hash code for a 1482 * <code>String</code> object is computed as 1483 * <blockquote><pre> 1484 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1485 * </pre></blockquote> 1486 * using <code>int</code> arithmetic, where <code>s[i]</code> is the 1487 * <i>i</i>th character of the string, <code>n</code> is the length of 1488 * the string, and <code>^</code> indicates exponentiation. 1489 * (The hash value of the empty string is zero.) 1490 * 1491 * @return a hash code value for this object. 1492 */ 1493 public int hashCode() { 1494 int h = hash; 1495 if (h == 0 && count > 0) { 1496 int off = offset; 1497 char val[] = value; 1498 int len = count; 1499 1500 for (int i = 0; i < len; i++) { 1501 h = 31*h + val[off++]; 1502 } 1503 hash = h; 1504 } 1505 return h; 1506 } 1507 1508 /** 1509 * Returns the index within this string of the first occurrence of 1510 * the specified character. If a character with value 1511 * <code>ch</code> occurs in the character sequence represented by 1512 * this <code>String</code> object, then the index (in Unicode 1513 * code units) of the first such occurrence is returned. For 1514 * values of <code>ch</code> in the range from 0 to 0xFFFF 1515 * (inclusive), this is the smallest value <i>k</i> such that: 1516 * <blockquote><pre> 1517 * this.charAt(<i>k</i>) == ch 1518 * </pre></blockquote> 1519 * is true. For other values of <code>ch</code>, it is the 1520 * smallest value <i>k</i> such that: 1521 * <blockquote><pre> 1522 * this.codePointAt(<i>k</i>) == ch 1523 * </pre></blockquote> 1524 * is true. In either case, if no such character occurs in this 1525 * string, then <code>-1</code> is returned. 1526 * 1527 * @param ch a character (Unicode code point). 1528 * @return the index of the first occurrence of the character in the 1529 * character sequence represented by this object, or 1530 * <code>-1</code> if the character does not occur. 1531 */ 1532 public int indexOf(int ch) { 1533 return indexOf(ch, 0); 1534 } 1535 1536 /** 1537 * Returns the index within this string of the first occurrence of the 1538 * specified character, starting the search at the specified index. 1539 * <p> 1540 * If a character with value <code>ch</code> occurs in the 1541 * character sequence represented by this <code>String</code> 1542 * object at an index no smaller than <code>fromIndex</code>, then 1543 * the index of the first such occurrence is returned. For values 1544 * of <code>ch</code> in the range from 0 to 0xFFFF (inclusive), 1545 * this is the smallest value <i>k</i> such that: 1546 * <blockquote><pre> 1547 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex) 1548 * </pre></blockquote> 1549 * is true. For other values of <code>ch</code>, it is the 1550 * smallest value <i>k</i> such that: 1551 * <blockquote><pre> 1552 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex) 1553 * </pre></blockquote> 1554 * is true. In either case, if no such character occurs in this 1555 * string at or after position <code>fromIndex</code>, then 1556 * <code>-1</code> is returned. 1557 * 1558 * <p> 1559 * There is no restriction on the value of <code>fromIndex</code>. If it 1560 * is negative, it has the same effect as if it were zero: this entire 1561 * string may be searched. If it is greater than the length of this 1562 * string, it has the same effect as if it were equal to the length of 1563 * this string: <code>-1</code> is returned. 1564 * 1565 * <p>All indices are specified in <code>char</code> values 1566 * (Unicode code units). 1567 * 1568 * @param ch a character (Unicode code point). 1569 * @param fromIndex the index to start the search from. 1570 * @return the index of the first occurrence of the character in the 1571 * character sequence represented by this object that is greater 1572 * than or equal to <code>fromIndex</code>, or <code>-1</code> 1573 * if the character does not occur. 1574 */ 1575 public int indexOf(int ch, int fromIndex) { 1576 if (fromIndex < 0) { 1577 fromIndex = 0; 1578 } else if (fromIndex >= count) { 1579 // Note: fromIndex might be near -1>>>1. 1580 return -1; 1581 } 1582 1583 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1584 // handle most cases here (ch is a BMP code point or a 1585 // negative value (invalid code point)) 1586 final char[] value = this.value; 1587 final int offset = this.offset; 1588 final int max = offset + count; 1589 for (int i = offset + fromIndex; i < max ; i++) { 1590 if (value[i] == ch) { 1591 return i - offset; 1592 } 1593 } 1594 return -1; 1595 } else { 1596 return indexOfSupplementary(ch, fromIndex); 1597 } 1598 } 1599 1600 /** 1601 * Handles (rare) calls of indexOf with a supplementary character. 1602 */ 1603 private int indexOfSupplementary(int ch, int fromIndex) { 1604 if (Character.isValidCodePoint(ch)) { 1605 final char[] value = this.value; 1606 final int offset = this.offset; 1607 final char hi = Character.highSurrogate(ch); 1608 final char lo = Character.lowSurrogate(ch); 1609 final int max = offset + count - 1; 1610 for (int i = offset + fromIndex; i < max; i++) { 1611 if (value[i] == hi && value[i+1] == lo) { 1612 return i - offset; 1613 } 1614 } 1615 } 1616 return -1; 1617 } 1618 1619 /** 1620 * Returns the index within this string of the last occurrence of 1621 * the specified character. For values of <code>ch</code> in the 1622 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1623 * units) returned is the largest value <i>k</i> such that: 1624 * <blockquote><pre> 1625 * this.charAt(<i>k</i>) == ch 1626 * </pre></blockquote> 1627 * is true. For other values of <code>ch</code>, it is the 1628 * largest value <i>k</i> such that: 1629 * <blockquote><pre> 1630 * this.codePointAt(<i>k</i>) == ch 1631 * </pre></blockquote> 1632 * is true. In either case, if no such character occurs in this 1633 * string, then <code>-1</code> is returned. The 1634 * <code>String</code> is searched backwards starting at the last 1635 * character. 1636 * 1637 * @param ch a character (Unicode code point). 1638 * @return the index of the last occurrence of the character in the 1639 * character sequence represented by this object, or 1640 * <code>-1</code> if the character does not occur. 1641 */ 1642 public int lastIndexOf(int ch) { 1643 return lastIndexOf(ch, count - 1); 1644 } 1645 1646 /** 1647 * Returns the index within this string of the last occurrence of 1648 * the specified character, searching backward starting at the 1649 * specified index. For values of <code>ch</code> in the range 1650 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1651 * value <i>k</i> such that: 1652 * <blockquote><pre> 1653 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex) 1654 * </pre></blockquote> 1655 * is true. For other values of <code>ch</code>, it is the 1656 * largest value <i>k</i> such that: 1657 * <blockquote><pre> 1658 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex) 1659 * </pre></blockquote> 1660 * is true. In either case, if no such character occurs in this 1661 * string at or before position <code>fromIndex</code>, then 1662 * <code>-1</code> is returned. 1663 * 1664 * <p>All indices are specified in <code>char</code> values 1665 * (Unicode code units). 1666 * 1667 * @param ch a character (Unicode code point). 1668 * @param fromIndex the index to start the search from. There is no 1669 * restriction on the value of <code>fromIndex</code>. If it is 1670 * greater than or equal to the length of this string, it has 1671 * the same effect as if it were equal to one less than the 1672 * length of this string: this entire string may be searched. 1673 * If it is negative, it has the same effect as if it were -1: 1674 * -1 is returned. 1675 * @return the index of the last occurrence of the character in the 1676 * character sequence represented by this object that is less 1677 * than or equal to <code>fromIndex</code>, or <code>-1</code> 1678 * if the character does not occur before that point. 1679 */ 1680 public int lastIndexOf(int ch, int fromIndex) { 1681 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1682 // handle most cases here (ch is a BMP code point or a 1683 // negative value (invalid code point)) 1684 final char[] value = this.value; 1685 final int offset = this.offset; 1686 int i = offset + Math.min(fromIndex, count - 1); 1687 for (; i >= offset ; i--) { 1688 if (value[i] == ch) { 1689 return i - offset; 1690 } 1691 } 1692 return -1; 1693 } else { 1694 return lastIndexOfSupplementary(ch, fromIndex); 1695 } 1696 } 1697 1698 /** 1699 * Handles (rare) calls of lastIndexOf with a supplementary character. 1700 */ 1701 private int lastIndexOfSupplementary(int ch, int fromIndex) { 1702 if (Character.isValidCodePoint(ch)) { 1703 final char[] value = this.value; 1704 final int offset = this.offset; 1705 char hi = Character.highSurrogate(ch); 1706 char lo = Character.lowSurrogate(ch); 1707 int i = offset + Math.min(fromIndex, count - 2); 1708 for (; i >= offset; i--) { 1709 if (value[i] == hi && value[i+1] == lo) { 1710 return i - offset; 1711 } 1712 } 1713 } 1714 return -1; 1715 } 1716 1717 /** 1718 * Returns the index within this string of the first occurrence of the 1719 * specified substring. 1720 * 1721 * <p>The returned index is the smallest value <i>k</i> for which: 1722 * <blockquote><pre> 1723 * this.startsWith(str, <i>k</i>) 1724 * </pre></blockquote> 1725 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1726 * 1727 * @param str the substring to search for. 1728 * @return the index of the first occurrence of the specified substring, 1729 * or {@code -1} if there is no such occurrence. 1730 */ 1731 public int indexOf(String str) { 1732 return indexOf(str, 0); 1733 } 1734 1735 /** 1736 * Returns the index within this string of the first occurrence of the 1737 * specified substring, starting at the specified index. 1738 * 1739 * <p>The returned index is the smallest value <i>k</i> for which: 1740 * <blockquote><pre> 1741 * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>) 1742 * </pre></blockquote> 1743 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1744 * 1745 * @param str the substring to search for. 1746 * @param fromIndex the index from which to start the search. 1747 * @return the index of the first occurrence of the specified substring, 1748 * starting at the specified index, 1749 * or {@code -1} if there is no such occurrence. 1750 */ 1751 public int indexOf(String str, int fromIndex) { 1752 return indexOf(value, offset, count, 1753 str.value, str.offset, str.count, fromIndex); 1754 } 1755 1756 /** 1757 * Code shared by String and StringBuffer to do searches. The 1758 * source is the character array being searched, and the target 1759 * is the string being searched for. 1760 * 1761 * @param source the characters being searched. 1762 * @param sourceOffset offset of the source string. 1763 * @param sourceCount count of the source string. 1764 * @param target the characters being searched for. 1765 * @param targetOffset offset of the target string. 1766 * @param targetCount count of the target string. 1767 * @param fromIndex the index to begin searching from. 1768 */ 1769 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1770 char[] target, int targetOffset, int targetCount, 1771 int fromIndex) { 1772 if (fromIndex >= sourceCount) { 1773 return (targetCount == 0 ? sourceCount : -1); 1774 } 1775 if (fromIndex < 0) { 1776 fromIndex = 0; 1777 } 1778 if (targetCount == 0) { 1779 return fromIndex; 1780 } 1781 1782 char first = target[targetOffset]; 1783 int max = sourceOffset + (sourceCount - targetCount); 1784 1785 for (int i = sourceOffset + fromIndex; i <= max; i++) { 1786 /* Look for first character. */ 1787 if (source[i] != first) { 1788 while (++i <= max && source[i] != first); 1789 } 1790 1791 /* Found first character, now look at the rest of v2 */ 1792 if (i <= max) { 1793 int j = i + 1; 1794 int end = j + targetCount - 1; 1795 for (int k = targetOffset + 1; j < end && source[j] == 1796 target[k]; j++, k++); 1797 1798 if (j == end) { 1799 /* Found whole string. */ 1800 return i - sourceOffset; 1801 } 1802 } 1803 } 1804 return -1; 1805 } 1806 1807 /** 1808 * Returns the index within this string of the last occurrence of the 1809 * specified substring. The last occurrence of the empty string "" 1810 * is considered to occur at the index value {@code this.length()}. 1811 * 1812 * <p>The returned index is the largest value <i>k</i> for which: 1813 * <blockquote><pre> 1814 * this.startsWith(str, <i>k</i>) 1815 * </pre></blockquote> 1816 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1817 * 1818 * @param str the substring to search for. 1819 * @return the index of the last occurrence of the specified substring, 1820 * or {@code -1} if there is no such occurrence. 1821 */ 1822 public int lastIndexOf(String str) { 1823 return lastIndexOf(str, count); 1824 } 1825 1826 /** 1827 * Returns the index within this string of the last occurrence of the 1828 * specified substring, searching backward starting at the specified index. 1829 * 1830 * <p>The returned index is the largest value <i>k</i> for which: 1831 * <blockquote><pre> 1832 * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>) 1833 * </pre></blockquote> 1834 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1835 * 1836 * @param str the substring to search for. 1837 * @param fromIndex the index to start the search from. 1838 * @return the index of the last occurrence of the specified substring, 1839 * searching backward from the specified index, 1840 * or {@code -1} if there is no such occurrence. 1841 */ 1842 public int lastIndexOf(String str, int fromIndex) { 1843 return lastIndexOf(value, offset, count, 1844 str.value, str.offset, str.count, fromIndex); 1845 } 1846 1847 /** 1848 * Code shared by String and StringBuffer to do searches. The 1849 * source is the character array being searched, and the target 1850 * is the string being searched for. 1851 * 1852 * @param source the characters being searched. 1853 * @param sourceOffset offset of the source string. 1854 * @param sourceCount count of the source string. 1855 * @param target the characters being searched for. 1856 * @param targetOffset offset of the target string. 1857 * @param targetCount count of the target string. 1858 * @param fromIndex the index to begin searching from. 1859 */ 1860 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1861 char[] target, int targetOffset, int targetCount, 1862 int fromIndex) { 1863 /* 1864 * Check arguments; return immediately where possible. For 1865 * consistency, don't check for null str. 1866 */ 1867 int rightIndex = sourceCount - targetCount; 1868 if (fromIndex < 0) { 1869 return -1; 1870 } 1871 if (fromIndex > rightIndex) { 1872 fromIndex = rightIndex; 1873 } 1874 /* Empty string always matches. */ 1875 if (targetCount == 0) { 1876 return fromIndex; 1877 } 1878 1879 int strLastIndex = targetOffset + targetCount - 1; 1880 char strLastChar = target[strLastIndex]; 1881 int min = sourceOffset + targetCount - 1; 1882 int i = min + fromIndex; 1883 1884 startSearchForLastChar: 1885 while (true) { 1886 while (i >= min && source[i] != strLastChar) { 1887 i--; 1888 } 1889 if (i < min) { 1890 return -1; 1891 } 1892 int j = i - 1; 1893 int start = j - (targetCount - 1); 1894 int k = strLastIndex - 1; 1895 1896 while (j > start) { 1897 if (source[j--] != target[k--]) { 1898 i--; 1899 continue startSearchForLastChar; 1900 } 1901 } 1902 return start - sourceOffset + 1; 1903 } 1904 } 1905 1906 /** 1907 * Returns a new string that is a substring of this string. The 1908 * substring begins with the character at the specified index and 1909 * extends to the end of this string. <p> 1910 * Examples: 1911 * <blockquote><pre> 1912 * "unhappy".substring(2) returns "happy" 1913 * "Harbison".substring(3) returns "bison" 1914 * "emptiness".substring(9) returns "" (an empty string) 1915 * </pre></blockquote> 1916 * 1917 * @param beginIndex the beginning index, inclusive. 1918 * @return the specified substring. 1919 * @exception IndexOutOfBoundsException if 1920 * <code>beginIndex</code> is negative or larger than the 1921 * length of this <code>String</code> object. 1922 */ 1923 public String substring(int beginIndex) { 1924 return substring(beginIndex, count); 1925 } 1926 1927 /** 1928 * Returns a new string that is a substring of this string. The 1929 * substring begins at the specified <code>beginIndex</code> and 1930 * extends to the character at index <code>endIndex - 1</code>. 1931 * Thus the length of the substring is <code>endIndex-beginIndex</code>. 1932 * <p> 1933 * Examples: 1934 * <blockquote><pre> 1935 * "hamburger".substring(4, 8) returns "urge" 1936 * "smiles".substring(1, 5) returns "mile" 1937 * </pre></blockquote> 1938 * 1939 * @param beginIndex the beginning index, inclusive. 1940 * @param endIndex the ending index, exclusive. 1941 * @return the specified substring. 1942 * @exception IndexOutOfBoundsException if the 1943 * <code>beginIndex</code> is negative, or 1944 * <code>endIndex</code> is larger than the length of 1945 * this <code>String</code> object, or 1946 * <code>beginIndex</code> is larger than 1947 * <code>endIndex</code>. 1948 */ 1949 public String substring(int beginIndex, int endIndex) { 1950 if (beginIndex < 0) { 1951 throw new StringIndexOutOfBoundsException(beginIndex); 1952 } 1953 if (endIndex > count) { 1954 throw new StringIndexOutOfBoundsException(endIndex); 1955 } 1956 if (beginIndex > endIndex) { 1957 throw new StringIndexOutOfBoundsException(endIndex - beginIndex); 1958 } 1959 return ((beginIndex == 0) && (endIndex == count)) ? this : 1960 new String(offset + beginIndex, endIndex - beginIndex, value); 1961 } 1962 1963 /** 1964 * Returns a new character sequence that is a subsequence of this sequence. 1965 * 1966 * <p> An invocation of this method of the form 1967 * 1968 * <blockquote><pre> 1969 * str.subSequence(begin, end)</pre></blockquote> 1970 * 1971 * behaves in exactly the same way as the invocation 1972 * 1973 * <blockquote><pre> 1974 * str.substring(begin, end)</pre></blockquote> 1975 * 1976 * This method is defined so that the <tt>String</tt> class can implement 1977 * the {@link CharSequence} interface. </p> 1978 * 1979 * @param beginIndex the begin index, inclusive. 1980 * @param endIndex the end index, exclusive. 1981 * @return the specified subsequence. 1982 * 1983 * @throws IndexOutOfBoundsException 1984 * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative, 1985 * if <tt>endIndex</tt> is greater than <tt>length()</tt>, 1986 * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt> 1987 * 1988 * @since 1.4 1989 * @spec JSR-51 1990 */ 1991 public CharSequence subSequence(int beginIndex, int endIndex) { 1992 return this.substring(beginIndex, endIndex); 1993 } 1994 1995 /** 1996 * Concatenates the specified string to the end of this string. 1997 * <p> 1998 * If the length of the argument string is <code>0</code>, then this 1999 * <code>String</code> object is returned. Otherwise, a new 2000 * <code>String</code> object is created, representing a character 2001 * sequence that is the concatenation of the character sequence 2002 * represented by this <code>String</code> object and the character 2003 * sequence represented by the argument string.<p> 2004 * Examples: 2005 * <blockquote><pre> 2006 * "cares".concat("s") returns "caress" 2007 * "to".concat("get").concat("her") returns "together" 2008 * </pre></blockquote> 2009 * 2010 * @param str the <code>String</code> that is concatenated to the end 2011 * of this <code>String</code>. 2012 * @return a string that represents the concatenation of this object's 2013 * characters followed by the string argument's characters. 2014 */ 2015 public String concat(String str) { 2016 int otherLen = str.length(); 2017 if (otherLen == 0) { 2018 return this; 2019 } 2020 char buf[] = new char[count + otherLen]; 2021 getChars(0, count, buf, 0); 2022 str.getChars(0, otherLen, buf, count); 2023 return new String(0, count + otherLen, buf); 2024 } 2025 2026 /** 2027 * Returns a new string resulting from replacing all occurrences of 2028 * <code>oldChar</code> in this string with <code>newChar</code>. 2029 * <p> 2030 * If the character <code>oldChar</code> does not occur in the 2031 * character sequence represented by this <code>String</code> object, 2032 * then a reference to this <code>String</code> object is returned. 2033 * Otherwise, a new <code>String</code> object is created that 2034 * represents a character sequence identical to the character sequence 2035 * represented by this <code>String</code> object, except that every 2036 * occurrence of <code>oldChar</code> is replaced by an occurrence 2037 * of <code>newChar</code>. 2038 * <p> 2039 * Examples: 2040 * <blockquote><pre> 2041 * "mesquite in your cellar".replace('e', 'o') 2042 * returns "mosquito in your collar" 2043 * "the war of baronets".replace('r', 'y') 2044 * returns "the way of bayonets" 2045 * "sparring with a purple porpoise".replace('p', 't') 2046 * returns "starring with a turtle tortoise" 2047 * "JonL".replace('q', 'x') returns "JonL" (no change) 2048 * </pre></blockquote> 2049 * 2050 * @param oldChar the old character. 2051 * @param newChar the new character. 2052 * @return a string derived from this string by replacing every 2053 * occurrence of <code>oldChar</code> with <code>newChar</code>. 2054 */ 2055 public String replace(char oldChar, char newChar) { 2056 if (oldChar != newChar) { 2057 int len = count; 2058 int i = -1; 2059 char[] val = value; /* avoid getfield opcode */ 2060 int off = offset; /* avoid getfield opcode */ 2061 2062 while (++i < len) { 2063 if (val[off + i] == oldChar) { 2064 break; 2065 } 2066 } 2067 if (i < len) { 2068 char buf[] = new char[len]; 2069 for (int j = 0 ; j < i ; j++) { 2070 buf[j] = val[off+j]; 2071 } 2072 while (i < len) { 2073 char c = val[off + i]; 2074 buf[i] = (c == oldChar) ? newChar : c; 2075 i++; 2076 } 2077 return new String(0, len, buf); 2078 } 2079 } 2080 return this; 2081 } 2082 2083 /** 2084 * Tells whether or not this string matches the given <a 2085 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2086 * 2087 * <p> An invocation of this method of the form 2088 * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the 2089 * same result as the expression 2090 * 2091 * <blockquote><tt> {@link java.util.regex.Pattern}.{@link 2092 * java.util.regex.Pattern#matches(String,CharSequence) 2093 * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote> 2094 * 2095 * @param regex 2096 * the regular expression to which this string is to be matched 2097 * 2098 * @return <tt>true</tt> if, and only if, this string matches the 2099 * given regular expression 2100 * 2101 * @throws PatternSyntaxException 2102 * if the regular expression's syntax is invalid 2103 * 2104 * @see java.util.regex.Pattern 2105 * 2106 * @since 1.4 2107 * @spec JSR-51 2108 */ 2109 public boolean matches(String regex) { 2110 return Pattern.matches(regex, this); 2111 } 2112 2113 /** 2114 * Returns true if and only if this string contains the specified 2115 * sequence of char values. 2116 * 2117 * @param s the sequence to search for 2118 * @return true if this string contains <code>s</code>, false otherwise 2119 * @throws NullPointerException if <code>s</code> is <code>null</code> 2120 * @since 1.5 2121 */ 2122 public boolean contains(CharSequence s) { 2123 return indexOf(s.toString()) > -1; 2124 } 2125 2126 /** 2127 * Replaces the first substring of this string that matches the given <a 2128 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2129 * given replacement. 2130 * 2131 * <p> An invocation of this method of the form 2132 * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt> 2133 * yields exactly the same result as the expression 2134 * 2135 * <blockquote><tt> 2136 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile 2137 * compile}(</tt><i>regex</i><tt>).{@link 2138 * java.util.regex.Pattern#matcher(java.lang.CharSequence) 2139 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst 2140 * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote> 2141 * 2142 *<p> 2143 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the 2144 * replacement string may cause the results to be different than if it were 2145 * being treated as a literal replacement string; see 2146 * {@link java.util.regex.Matcher#replaceFirst}. 2147 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2148 * meaning of these characters, if desired. 2149 * 2150 * @param regex 2151 * the regular expression to which this string is to be matched 2152 * @param replacement 2153 * the string to be substituted for the first match 2154 * 2155 * @return The resulting <tt>String</tt> 2156 * 2157 * @throws PatternSyntaxException 2158 * if the regular expression's syntax is invalid 2159 * 2160 * @see java.util.regex.Pattern 2161 * 2162 * @since 1.4 2163 * @spec JSR-51 2164 */ 2165 public String replaceFirst(String regex, String replacement) { 2166 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2167 } 2168 2169 /** 2170 * Replaces each substring of this string that matches the given <a 2171 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2172 * given replacement. 2173 * 2174 * <p> An invocation of this method of the form 2175 * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt> 2176 * yields exactly the same result as the expression 2177 * 2178 * <blockquote><tt> 2179 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile 2180 * compile}(</tt><i>regex</i><tt>).{@link 2181 * java.util.regex.Pattern#matcher(java.lang.CharSequence) 2182 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll 2183 * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote> 2184 * 2185 *<p> 2186 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the 2187 * replacement string may cause the results to be different than if it were 2188 * being treated as a literal replacement string; see 2189 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2190 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2191 * meaning of these characters, if desired. 2192 * 2193 * @param regex 2194 * the regular expression to which this string is to be matched 2195 * @param replacement 2196 * the string to be substituted for each match 2197 * 2198 * @return The resulting <tt>String</tt> 2199 * 2200 * @throws PatternSyntaxException 2201 * if the regular expression's syntax is invalid 2202 * 2203 * @see java.util.regex.Pattern 2204 * 2205 * @since 1.4 2206 * @spec JSR-51 2207 */ 2208 public String replaceAll(String regex, String replacement) { 2209 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2210 } 2211 2212 /** 2213 * Replaces each substring of this string that matches the literal target 2214 * sequence with the specified literal replacement sequence. The 2215 * replacement proceeds from the beginning of the string to the end, for 2216 * example, replacing "aa" with "b" in the string "aaa" will result in 2217 * "ba" rather than "ab". 2218 * 2219 * @param target The sequence of char values to be replaced 2220 * @param replacement The replacement sequence of char values 2221 * @return The resulting string 2222 * @throws NullPointerException if <code>target</code> or 2223 * <code>replacement</code> is <code>null</code>. 2224 * @since 1.5 2225 */ 2226 public String replace(CharSequence target, CharSequence replacement) { 2227 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher( 2228 this).replaceAll(Matcher.quoteReplacement(replacement.toString())); 2229 } 2230 2231 /** 2232 * Splits this string around matches of the given 2233 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2234 * 2235 * <p> The array returned by this method contains each substring of this 2236 * string that is terminated by another substring that matches the given 2237 * expression or is terminated by the end of the string. The substrings in 2238 * the array are in the order in which they occur in this string. If the 2239 * expression does not match any part of the input then the resulting array 2240 * has just one element, namely this string. 2241 * 2242 * <p> The <tt>limit</tt> parameter controls the number of times the 2243 * pattern is applied and therefore affects the length of the resulting 2244 * array. If the limit <i>n</i> is greater than zero then the pattern 2245 * will be applied at most <i>n</i> - 1 times, the array's 2246 * length will be no greater than <i>n</i>, and the array's last entry 2247 * will contain all input beyond the last matched delimiter. If <i>n</i> 2248 * is non-positive then the pattern will be applied as many times as 2249 * possible and the array can have any length. If <i>n</i> is zero then 2250 * the pattern will be applied as many times as possible, the array can 2251 * have any length, and trailing empty strings will be discarded. 2252 * 2253 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the 2254 * following results with these parameters: 2255 * 2256 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2257 * <tr> 2258 * <th>Regex</th> 2259 * <th>Limit</th> 2260 * <th>Result</th> 2261 * </tr> 2262 * <tr><td align=center>:</td> 2263 * <td align=center>2</td> 2264 * <td><tt>{ "boo", "and:foo" }</tt></td></tr> 2265 * <tr><td align=center>:</td> 2266 * <td align=center>5</td> 2267 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> 2268 * <tr><td align=center>:</td> 2269 * <td align=center>-2</td> 2270 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> 2271 * <tr><td align=center>o</td> 2272 * <td align=center>5</td> 2273 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr> 2274 * <tr><td align=center>o</td> 2275 * <td align=center>-2</td> 2276 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr> 2277 * <tr><td align=center>o</td> 2278 * <td align=center>0</td> 2279 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr> 2280 * </table></blockquote> 2281 * 2282 * <p> An invocation of this method of the form 2283 * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt> 2284 * yields the same result as the expression 2285 * 2286 * <blockquote> 2287 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile 2288 * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link 2289 * java.util.regex.Pattern#split(java.lang.CharSequence,int) 2290 * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt> 2291 * </blockquote> 2292 * 2293 * 2294 * @param regex 2295 * the delimiting regular expression 2296 * 2297 * @param limit 2298 * the result threshold, as described above 2299 * 2300 * @return the array of strings computed by splitting this string 2301 * around matches of the given regular expression 2302 * 2303 * @throws PatternSyntaxException 2304 * if the regular expression's syntax is invalid 2305 * 2306 * @see java.util.regex.Pattern 2307 * 2308 * @since 1.4 2309 * @spec JSR-51 2310 */ 2311 public String[] split(String regex, int limit) { 2312 /* fastpath if the regex is a 2313 (1)one-char String and this character is not one of the 2314 RegEx's meta characters ".$|()[{^?*+\\", or 2315 (2)two-char String and the first char is the backslash and 2316 the second is not the ascii digit or ascii letter. 2317 */ 2318 char ch = 0; 2319 if (((regex.count == 1 && 2320 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2321 (regex.length() == 2 && 2322 regex.charAt(0) == '\\' && 2323 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2324 ((ch-'a')|('z'-ch)) < 0 && 2325 ((ch-'A')|('Z'-ch)) < 0)) && 2326 (ch < Character.MIN_HIGH_SURROGATE || 2327 ch > Character.MAX_LOW_SURROGATE)) 2328 { 2329 int off = 0; 2330 int next = 0; 2331 boolean limited = limit > 0; 2332 ArrayList<String> list = new ArrayList<>(); 2333 while ((next = indexOf(ch, off)) != -1) { 2334 if (!limited || list.size() < limit - 1) { 2335 list.add(substring(off, next)); 2336 off = next + 1; 2337 } else { // last one 2338 //assert (list.size() == limit - 1); 2339 list.add(substring(off, count)); 2340 off = count; 2341 break; 2342 } 2343 } 2344 // If no match was found, return this 2345 if (off == 0) 2346 return new String[] { this }; 2347 2348 // Add remaining segment 2349 if (!limited || list.size() < limit) 2350 list.add(substring(off, count)); 2351 2352 // Construct result 2353 int resultSize = list.size(); 2354 if (limit == 0) 2355 while (resultSize > 0 && list.get(resultSize-1).length() == 0) 2356 resultSize--; 2357 String[] result = new String[resultSize]; 2358 return list.subList(0, resultSize).toArray(result); 2359 } 2360 return Pattern.compile(regex).split(this, limit); 2361 } 2362 2363 /** 2364 * Splits this string around matches of the given <a 2365 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2366 * 2367 * <p> This method works as if by invoking the two-argument {@link 2368 * #split(String, int) split} method with the given expression and a limit 2369 * argument of zero. Trailing empty strings are therefore not included in 2370 * the resulting array. 2371 * 2372 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the following 2373 * results with these expressions: 2374 * 2375 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2376 * <tr> 2377 * <th>Regex</th> 2378 * <th>Result</th> 2379 * </tr> 2380 * <tr><td align=center>:</td> 2381 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> 2382 * <tr><td align=center>o</td> 2383 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr> 2384 * </table></blockquote> 2385 * 2386 * 2387 * @param regex 2388 * the delimiting regular expression 2389 * 2390 * @return the array of strings computed by splitting this string 2391 * around matches of the given regular expression 2392 * 2393 * @throws PatternSyntaxException 2394 * if the regular expression's syntax is invalid 2395 * 2396 * @see java.util.regex.Pattern 2397 * 2398 * @since 1.4 2399 * @spec JSR-51 2400 */ 2401 public String[] split(String regex) { 2402 return split(regex, 0); 2403 } 2404 2405 /** 2406 * Converts all of the characters in this <code>String</code> to lower 2407 * case using the rules of the given <code>Locale</code>. Case mapping is based 2408 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2409 * class. Since case mappings are not always 1:1 char mappings, the resulting 2410 * <code>String</code> may be a different length than the original <code>String</code>. 2411 * <p> 2412 * Examples of lowercase mappings are in the following table: 2413 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2414 * <tr> 2415 * <th>Language Code of Locale</th> 2416 * <th>Upper Case</th> 2417 * <th>Lower Case</th> 2418 * <th>Description</th> 2419 * </tr> 2420 * <tr> 2421 * <td>tr (Turkish)</td> 2422 * <td>\u0130</td> 2423 * <td>\u0069</td> 2424 * <td>capital letter I with dot above -> small letter i</td> 2425 * </tr> 2426 * <tr> 2427 * <td>tr (Turkish)</td> 2428 * <td>\u0049</td> 2429 * <td>\u0131</td> 2430 * <td>capital letter I -> small letter dotless i </td> 2431 * </tr> 2432 * <tr> 2433 * <td>(all)</td> 2434 * <td>French Fries</td> 2435 * <td>french fries</td> 2436 * <td>lowercased all chars in String</td> 2437 * </tr> 2438 * <tr> 2439 * <td>(all)</td> 2440 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2441 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2442 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2443 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2444 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2445 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2446 * <td>lowercased all chars in String</td> 2447 * </tr> 2448 * </table> 2449 * 2450 * @param locale use the case transformation rules for this locale 2451 * @return the <code>String</code>, converted to lowercase. 2452 * @see java.lang.String#toLowerCase() 2453 * @see java.lang.String#toUpperCase() 2454 * @see java.lang.String#toUpperCase(Locale) 2455 * @since 1.1 2456 */ 2457 public String toLowerCase(Locale locale) { 2458 if (locale == null) { 2459 throw new NullPointerException(); 2460 } 2461 2462 int firstUpper; 2463 2464 /* Now check if there are any characters that need to be changed. */ 2465 scan: { 2466 for (firstUpper = 0 ; firstUpper < count; ) { 2467 char c = value[offset+firstUpper]; 2468 if ((c >= Character.MIN_HIGH_SURROGATE) && 2469 (c <= Character.MAX_HIGH_SURROGATE)) { 2470 int supplChar = codePointAt(firstUpper); 2471 if (supplChar != Character.toLowerCase(supplChar)) { 2472 break scan; 2473 } 2474 firstUpper += Character.charCount(supplChar); 2475 } else { 2476 if (c != Character.toLowerCase(c)) { 2477 break scan; 2478 } 2479 firstUpper++; 2480 } 2481 } 2482 return this; 2483 } 2484 2485 char[] result = new char[count]; 2486 int resultOffset = 0; /* result may grow, so i+resultOffset 2487 * is the write location in result */ 2488 2489 /* Just copy the first few lowerCase characters. */ 2490 System.arraycopy(value, offset, result, 0, firstUpper); 2491 2492 String lang = locale.getLanguage(); 2493 boolean localeDependent = 2494 (lang == "tr" || lang == "az" || lang == "lt"); 2495 char[] lowerCharArray; 2496 int lowerChar; 2497 int srcChar; 2498 int srcCount; 2499 for (int i = firstUpper; i < count; i += srcCount) { 2500 srcChar = (int)value[offset+i]; 2501 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE && 2502 (char)srcChar <= Character.MAX_HIGH_SURROGATE) { 2503 srcChar = codePointAt(i); 2504 srcCount = Character.charCount(srcChar); 2505 } else { 2506 srcCount = 1; 2507 } 2508 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA 2509 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale); 2510 } else if (srcChar == '\u0130') { // LATIN CAPITAL LETTER I DOT 2511 lowerChar = Character.ERROR; 2512 } else { 2513 lowerChar = Character.toLowerCase(srcChar); 2514 } 2515 if ((lowerChar == Character.ERROR) || 2516 (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) { 2517 if (lowerChar == Character.ERROR) { 2518 if (!localeDependent && srcChar == '\u0130') { 2519 lowerCharArray = 2520 ConditionalSpecialCasing.toLowerCaseCharArray(this, i, Locale.ENGLISH); 2521 } else { 2522 lowerCharArray = 2523 ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale); 2524 } 2525 } else if (srcCount == 2) { 2526 resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount; 2527 continue; 2528 } else { 2529 lowerCharArray = Character.toChars(lowerChar); 2530 } 2531 2532 /* Grow result if needed */ 2533 int mapLen = lowerCharArray.length; 2534 if (mapLen > srcCount) { 2535 char[] result2 = new char[result.length + mapLen - srcCount]; 2536 System.arraycopy(result, 0, result2, 0, 2537 i + resultOffset); 2538 result = result2; 2539 } 2540 for (int x=0; x<mapLen; ++x) { 2541 result[i+resultOffset+x] = lowerCharArray[x]; 2542 } 2543 resultOffset += (mapLen - srcCount); 2544 } else { 2545 result[i+resultOffset] = (char)lowerChar; 2546 } 2547 } 2548 return new String(0, count+resultOffset, result); 2549 } 2550 2551 /** 2552 * Converts all of the characters in this <code>String</code> to lower 2553 * case using the rules of the default locale. This is equivalent to calling 2554 * <code>toLowerCase(Locale.getDefault())</code>. 2555 * <p> 2556 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2557 * results if used for strings that are intended to be interpreted locale 2558 * independently. 2559 * Examples are programming language identifiers, protocol keys, and HTML 2560 * tags. 2561 * For instance, <code>"TITLE".toLowerCase()</code> in a Turkish locale 2562 * returns <code>"t\u005Cu0131tle"</code>, where '\u005Cu0131' is the 2563 * LATIN SMALL LETTER DOTLESS I character. 2564 * To obtain correct results for locale insensitive strings, use 2565 * <code>toLowerCase(Locale.ENGLISH)</code>. 2566 * <p> 2567 * @return the <code>String</code>, converted to lowercase. 2568 * @see java.lang.String#toLowerCase(Locale) 2569 */ 2570 public String toLowerCase() { 2571 return toLowerCase(Locale.getDefault()); 2572 } 2573 2574 /** 2575 * Converts all of the characters in this <code>String</code> to upper 2576 * case using the rules of the given <code>Locale</code>. Case mapping is based 2577 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2578 * class. Since case mappings are not always 1:1 char mappings, the resulting 2579 * <code>String</code> may be a different length than the original <code>String</code>. 2580 * <p> 2581 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2582 * <p> 2583 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2584 * <tr> 2585 * <th>Language Code of Locale</th> 2586 * <th>Lower Case</th> 2587 * <th>Upper Case</th> 2588 * <th>Description</th> 2589 * </tr> 2590 * <tr> 2591 * <td>tr (Turkish)</td> 2592 * <td>\u0069</td> 2593 * <td>\u0130</td> 2594 * <td>small letter i -> capital letter I with dot above</td> 2595 * </tr> 2596 * <tr> 2597 * <td>tr (Turkish)</td> 2598 * <td>\u0131</td> 2599 * <td>\u0049</td> 2600 * <td>small letter dotless i -> capital letter I</td> 2601 * </tr> 2602 * <tr> 2603 * <td>(all)</td> 2604 * <td>\u00df</td> 2605 * <td>\u0053 \u0053</td> 2606 * <td>small letter sharp s -> two letters: SS</td> 2607 * </tr> 2608 * <tr> 2609 * <td>(all)</td> 2610 * <td>Fahrvergnügen</td> 2611 * <td>FAHRVERGNÜGEN</td> 2612 * <td></td> 2613 * </tr> 2614 * </table> 2615 * @param locale use the case transformation rules for this locale 2616 * @return the <code>String</code>, converted to uppercase. 2617 * @see java.lang.String#toUpperCase() 2618 * @see java.lang.String#toLowerCase() 2619 * @see java.lang.String#toLowerCase(Locale) 2620 * @since 1.1 2621 */ 2622 public String toUpperCase(Locale locale) { 2623 if (locale == null) { 2624 throw new NullPointerException(); 2625 } 2626 2627 int firstLower; 2628 2629 /* Now check if there are any characters that need to be changed. */ 2630 scan: { 2631 for (firstLower = 0 ; firstLower < count; ) { 2632 int c = (int)value[offset+firstLower]; 2633 int srcCount; 2634 if ((c >= Character.MIN_HIGH_SURROGATE) && 2635 (c <= Character.MAX_HIGH_SURROGATE)) { 2636 c = codePointAt(firstLower); 2637 srcCount = Character.charCount(c); 2638 } else { 2639 srcCount = 1; 2640 } 2641 int upperCaseChar = Character.toUpperCaseEx(c); 2642 if ((upperCaseChar == Character.ERROR) || 2643 (c != upperCaseChar)) { 2644 break scan; 2645 } 2646 firstLower += srcCount; 2647 } 2648 return this; 2649 } 2650 2651 char[] result = new char[count]; /* may grow */ 2652 int resultOffset = 0; /* result may grow, so i+resultOffset 2653 * is the write location in result */ 2654 2655 /* Just copy the first few upperCase characters. */ 2656 System.arraycopy(value, offset, result, 0, firstLower); 2657 2658 String lang = locale.getLanguage(); 2659 boolean localeDependent = 2660 (lang == "tr" || lang == "az" || lang == "lt"); 2661 char[] upperCharArray; 2662 int upperChar; 2663 int srcChar; 2664 int srcCount; 2665 for (int i = firstLower; i < count; i += srcCount) { 2666 srcChar = (int)value[offset+i]; 2667 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE && 2668 (char)srcChar <= Character.MAX_HIGH_SURROGATE) { 2669 srcChar = codePointAt(i); 2670 srcCount = Character.charCount(srcChar); 2671 } else { 2672 srcCount = 1; 2673 } 2674 if (localeDependent) { 2675 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale); 2676 } else { 2677 upperChar = Character.toUpperCaseEx(srcChar); 2678 } 2679 if ((upperChar == Character.ERROR) || 2680 (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) { 2681 if (upperChar == Character.ERROR) { 2682 if (localeDependent) { 2683 upperCharArray = 2684 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale); 2685 } else { 2686 upperCharArray = Character.toUpperCaseCharArray(srcChar); 2687 } 2688 } else if (srcCount == 2) { 2689 resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount; 2690 continue; 2691 } else { 2692 upperCharArray = Character.toChars(upperChar); 2693 } 2694 2695 /* Grow result if needed */ 2696 int mapLen = upperCharArray.length; 2697 if (mapLen > srcCount) { 2698 char[] result2 = new char[result.length + mapLen - srcCount]; 2699 System.arraycopy(result, 0, result2, 0, 2700 i + resultOffset); 2701 result = result2; 2702 } 2703 for (int x=0; x<mapLen; ++x) { 2704 result[i+resultOffset+x] = upperCharArray[x]; 2705 } 2706 resultOffset += (mapLen - srcCount); 2707 } else { 2708 result[i+resultOffset] = (char)upperChar; 2709 } 2710 } 2711 return new String(0, count+resultOffset, result); 2712 } 2713 2714 /** 2715 * Converts all of the characters in this <code>String</code> to upper 2716 * case using the rules of the default locale. This method is equivalent to 2717 * <code>toUpperCase(Locale.getDefault())</code>. 2718 * <p> 2719 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2720 * results if used for strings that are intended to be interpreted locale 2721 * independently. 2722 * Examples are programming language identifiers, protocol keys, and HTML 2723 * tags. 2724 * For instance, <code>"title".toUpperCase()</code> in a Turkish locale 2725 * returns <code>"T\u005Cu0130TLE"</code>, where '\u005Cu0130' is the 2726 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2727 * To obtain correct results for locale insensitive strings, use 2728 * <code>toUpperCase(Locale.ENGLISH)</code>. 2729 * <p> 2730 * @return the <code>String</code>, converted to uppercase. 2731 * @see java.lang.String#toUpperCase(Locale) 2732 */ 2733 public String toUpperCase() { 2734 return toUpperCase(Locale.getDefault()); 2735 } 2736 2737 /** 2738 * Returns a copy of the string, with leading and trailing whitespace 2739 * omitted. 2740 * <p> 2741 * If this <code>String</code> object represents an empty character 2742 * sequence, or the first and last characters of character sequence 2743 * represented by this <code>String</code> object both have codes 2744 * greater than <code>'\u0020'</code> (the space character), then a 2745 * reference to this <code>String</code> object is returned. 2746 * <p> 2747 * Otherwise, if there is no character with a code greater than 2748 * <code>'\u0020'</code> in the string, then a new 2749 * <code>String</code> object representing an empty string is created 2750 * and returned. 2751 * <p> 2752 * Otherwise, let <i>k</i> be the index of the first character in the 2753 * string whose code is greater than <code>'\u0020'</code>, and let 2754 * <i>m</i> be the index of the last character in the string whose code 2755 * is greater than <code>'\u0020'</code>. A new <code>String</code> 2756 * object is created, representing the substring of this string that 2757 * begins with the character at index <i>k</i> and ends with the 2758 * character at index <i>m</i>-that is, the result of 2759 * <code>this.substring(<i>k</i>, <i>m</i>+1)</code>. 2760 * <p> 2761 * This method may be used to trim whitespace (as defined above) from 2762 * the beginning and end of a string. 2763 * 2764 * @return A copy of this string with leading and trailing white 2765 * space removed, or this string if it has no leading or 2766 * trailing white space. 2767 */ 2768 public String trim() { 2769 int len = count; 2770 int st = 0; 2771 int off = offset; /* avoid getfield opcode */ 2772 char[] val = value; /* avoid getfield opcode */ 2773 2774 while ((st < len) && (val[off + st] <= ' ')) { 2775 st++; 2776 } 2777 while ((st < len) && (val[off + len - 1] <= ' ')) { 2778 len--; 2779 } 2780 return ((st > 0) || (len < count)) ? substring(st, len) : this; 2781 } 2782 2783 /** 2784 * This object (which is already a string!) is itself returned. 2785 * 2786 * @return the string itself. 2787 */ 2788 public String toString() { 2789 return this; 2790 } 2791 2792 /** 2793 * Converts this string to a new character array. 2794 * 2795 * @return a newly allocated character array whose length is the length 2796 * of this string and whose contents are initialized to contain 2797 * the character sequence represented by this string. 2798 */ 2799 public char[] toCharArray() { 2800 char result[] = new char[count]; 2801 getChars(0, count, result, 0); 2802 return result; 2803 } 2804 2805 /** 2806 * Returns a formatted string using the specified format string and 2807 * arguments. 2808 * 2809 * <p> The locale always used is the one returned by {@link 2810 * java.util.Locale#getDefault() Locale.getDefault()}. 2811 * 2812 * @param format 2813 * A <a href="../util/Formatter.html#syntax">format string</a> 2814 * 2815 * @param args 2816 * Arguments referenced by the format specifiers in the format 2817 * string. If there are more arguments than format specifiers, the 2818 * extra arguments are ignored. The number of arguments is 2819 * variable and may be zero. The maximum number of arguments is 2820 * limited by the maximum dimension of a Java array as defined by 2821 * <cite>The Java™ Virtual Machine Specification</cite>. 2822 * The behaviour on a 2823 * <tt>null</tt> argument depends on the <a 2824 * href="../util/Formatter.html#syntax">conversion</a>. 2825 * 2826 * @throws IllegalFormatException 2827 * If a format string contains an illegal syntax, a format 2828 * specifier that is incompatible with the given arguments, 2829 * insufficient arguments given the format string, or other 2830 * illegal conditions. For specification of all possible 2831 * formatting errors, see the <a 2832 * href="../util/Formatter.html#detail">Details</a> section of the 2833 * formatter class specification. 2834 * 2835 * @throws NullPointerException 2836 * If the <tt>format</tt> is <tt>null</tt> 2837 * 2838 * @return A formatted string 2839 * 2840 * @see java.util.Formatter 2841 * @since 1.5 2842 */ 2843 public static String format(String format, Object ... args) { 2844 return new Formatter().format(format, args).toString(); 2845 } 2846 2847 /** 2848 * Returns a formatted string using the specified locale, format string, 2849 * and arguments. 2850 * 2851 * @param l 2852 * The {@linkplain java.util.Locale locale} to apply during 2853 * formatting. If <tt>l</tt> is <tt>null</tt> then no localization 2854 * is applied. 2855 * 2856 * @param format 2857 * A <a href="../util/Formatter.html#syntax">format string</a> 2858 * 2859 * @param args 2860 * Arguments referenced by the format specifiers in the format 2861 * string. If there are more arguments than format specifiers, the 2862 * extra arguments are ignored. The number of arguments is 2863 * variable and may be zero. The maximum number of arguments is 2864 * limited by the maximum dimension of a Java array as defined by 2865 * <cite>The Java™ Virtual Machine Specification</cite>. 2866 * The behaviour on a 2867 * <tt>null</tt> argument depends on the <a 2868 * href="../util/Formatter.html#syntax">conversion</a>. 2869 * 2870 * @throws IllegalFormatException 2871 * If a format string contains an illegal syntax, a format 2872 * specifier that is incompatible with the given arguments, 2873 * insufficient arguments given the format string, or other 2874 * illegal conditions. For specification of all possible 2875 * formatting errors, see the <a 2876 * href="../util/Formatter.html#detail">Details</a> section of the 2877 * formatter class specification 2878 * 2879 * @throws NullPointerException 2880 * If the <tt>format</tt> is <tt>null</tt> 2881 * 2882 * @return A formatted string 2883 * 2884 * @see java.util.Formatter 2885 * @since 1.5 2886 */ 2887 public static String format(Locale l, String format, Object ... args) { 2888 return new Formatter(l).format(format, args).toString(); 2889 } 2890 2891 /** 2892 * Returns the string representation of the <code>Object</code> argument. 2893 * 2894 * @param obj an <code>Object</code>. 2895 * @return if the argument is <code>null</code>, then a string equal to 2896 * <code>"null"</code>; otherwise, the value of 2897 * <code>obj.toString()</code> is returned. 2898 * @see java.lang.Object#toString() 2899 */ 2900 public static String valueOf(Object obj) { 2901 return (obj == null) ? "null" : obj.toString(); 2902 } 2903 2904 /** 2905 * Returns the string representation of the <code>char</code> array 2906 * argument. The contents of the character array are copied; subsequent 2907 * modification of the character array does not affect the newly 2908 * created string. 2909 * 2910 * @param data a <code>char</code> array. 2911 * @return a newly allocated string representing the same sequence of 2912 * characters contained in the character array argument. 2913 */ 2914 public static String valueOf(char data[]) { 2915 return new String(data); 2916 } 2917 2918 /** 2919 * Returns the string representation of a specific subarray of the 2920 * <code>char</code> array argument. 2921 * <p> 2922 * The <code>offset</code> argument is the index of the first 2923 * character of the subarray. The <code>count</code> argument 2924 * specifies the length of the subarray. The contents of the subarray 2925 * are copied; subsequent modification of the character array does not 2926 * affect the newly created string. 2927 * 2928 * @param data the character array. 2929 * @param offset the initial offset into the value of the 2930 * <code>String</code>. 2931 * @param count the length of the value of the <code>String</code>. 2932 * @return a string representing the sequence of characters contained 2933 * in the subarray of the character array argument. 2934 * @exception IndexOutOfBoundsException if <code>offset</code> is 2935 * negative, or <code>count</code> is negative, or 2936 * <code>offset+count</code> is larger than 2937 * <code>data.length</code>. 2938 */ 2939 public static String valueOf(char data[], int offset, int count) { 2940 return new String(data, offset, count); 2941 } 2942 2943 /** 2944 * Returns a String that represents the character sequence in the 2945 * array specified. 2946 * 2947 * @param data the character array. 2948 * @param offset initial offset of the subarray. 2949 * @param count length of the subarray. 2950 * @return a <code>String</code> that contains the characters of the 2951 * specified subarray of the character array. 2952 */ 2953 public static String copyValueOf(char data[], int offset, int count) { 2954 // All public String constructors now copy the data. 2955 return new String(data, offset, count); 2956 } 2957 2958 /** 2959 * Returns a String that represents the character sequence in the 2960 * array specified. 2961 * 2962 * @param data the character array. 2963 * @return a <code>String</code> that contains the characters of the 2964 * character array. 2965 */ 2966 public static String copyValueOf(char data[]) { 2967 return copyValueOf(data, 0, data.length); 2968 } 2969 2970 /** 2971 * Returns the string representation of the <code>boolean</code> argument. 2972 * 2973 * @param b a <code>boolean</code>. 2974 * @return if the argument is <code>true</code>, a string equal to 2975 * <code>"true"</code> is returned; otherwise, a string equal to 2976 * <code>"false"</code> is returned. 2977 */ 2978 public static String valueOf(boolean b) { 2979 return b ? "true" : "false"; 2980 } 2981 2982 /** 2983 * Returns the string representation of the <code>char</code> 2984 * argument. 2985 * 2986 * @param c a <code>char</code>. 2987 * @return a string of length <code>1</code> containing 2988 * as its single character the argument <code>c</code>. 2989 */ 2990 public static String valueOf(char c) { 2991 char data[] = {c}; 2992 return new String(0, 1, data); 2993 } 2994 2995 /** 2996 * Returns the string representation of the <code>int</code> argument. 2997 * <p> 2998 * The representation is exactly the one returned by the 2999 * <code>Integer.toString</code> method of one argument. 3000 * 3001 * @param i an <code>int</code>. 3002 * @return a string representation of the <code>int</code> argument. 3003 * @see java.lang.Integer#toString(int, int) 3004 */ 3005 public static String valueOf(int i) { 3006 return Integer.toString(i); 3007 } 3008 3009 /** 3010 * Returns the string representation of the <code>long</code> argument. 3011 * <p> 3012 * The representation is exactly the one returned by the 3013 * <code>Long.toString</code> method of one argument. 3014 * 3015 * @param l a <code>long</code>. 3016 * @return a string representation of the <code>long</code> argument. 3017 * @see java.lang.Long#toString(long) 3018 */ 3019 public static String valueOf(long l) { 3020 return Long.toString(l); 3021 } 3022 3023 /** 3024 * Returns the string representation of the <code>float</code> argument. 3025 * <p> 3026 * The representation is exactly the one returned by the 3027 * <code>Float.toString</code> method of one argument. 3028 * 3029 * @param f a <code>float</code>. 3030 * @return a string representation of the <code>float</code> argument. 3031 * @see java.lang.Float#toString(float) 3032 */ 3033 public static String valueOf(float f) { 3034 return Float.toString(f); 3035 } 3036 3037 /** 3038 * Returns the string representation of the <code>double</code> argument. 3039 * <p> 3040 * The representation is exactly the one returned by the 3041 * <code>Double.toString</code> method of one argument. 3042 * 3043 * @param d a <code>double</code>. 3044 * @return a string representation of the <code>double</code> argument. 3045 * @see java.lang.Double#toString(double) 3046 */ 3047 public static String valueOf(double d) { 3048 return Double.toString(d); 3049 } 3050 3051 /** 3052 * Returns a canonical representation for the string object. 3053 * <p> 3054 * A pool of strings, initially empty, is maintained privately by the 3055 * class <code>String</code>. 3056 * <p> 3057 * When the intern method is invoked, if the pool already contains a 3058 * string equal to this <code>String</code> object as determined by 3059 * the {@link #equals(Object)} method, then the string from the pool is 3060 * returned. Otherwise, this <code>String</code> object is added to the 3061 * pool and a reference to this <code>String</code> object is returned. 3062 * <p> 3063 * It follows that for any two strings <code>s</code> and <code>t</code>, 3064 * <code>s.intern() == t.intern()</code> is <code>true</code> 3065 * if and only if <code>s.equals(t)</code> is <code>true</code>. 3066 * <p> 3067 * All literal strings and string-valued constant expressions are 3068 * interned. String literals are defined in section 3.10.5 of the 3069 * <cite>The Java™ Language Specification</cite>. 3070 * 3071 * @return a string that has the same contents as this string, but is 3072 * guaranteed to be from a pool of unique strings. 3073 */ 3074 public native String intern(); 3075 3076 /** 3077 * Seed value used for each alternative hash calculated. 3078 */ 3079 private static final int HASHING_SEED; 3080 3081 static { 3082 long nanos = System.nanoTime(); 3083 long now = System.currentTimeMillis(); 3084 int SEED_MATERIAL[] = { 3085 System.identityHashCode(String.class), 3086 System.identityHashCode(System.class), 3087 System.identityHashCode(Thread.currentThread()), 3088 (int) (nanos >>> 32), 3089 (int) nanos, 3090 (int) (now >>> 32), 3091 (int) now, 3092 (int) (System.nanoTime() >> 2) 3093 }; 3094 3095 int h = 0; 3096 for(int each : SEED_MATERIAL) { 3097 h ^= each; 3098 } 3099 3100 // Spread bits to regularize both segment and index locations, 3101 // using variant of single-word Wang/Jenkins hash. 3102 h += (h << 15) ^ 0xffffcd7d; 3103 h ^= (h >>> 10); 3104 h += (h << 3); 3105 h ^= (h >>> 6); 3106 h += (h << 2) + (h << 14); 3107 3108 HASHING_SEED = h ^ (h >>> 16); 3109 } 3110 3111 /** 3112 * Cached value of the alternative hashing algorithm result 3113 */ 3114 private transient int hash32 = 0; 3115 3116 /** 3117 * Calculates a 32-bit hash value for this string. 3118 * 3119 * @return a 32-bit hash value for this string. 3120 */ 3121 int hash32() { 3122 int h = hash32; 3123 if (0 == h) { 3124 // harmless data race on hash32 here. 3125 h = sun.misc.Hashing.murmur3_32(HASHING_SEED, value, offset, count); 3126 3127 // ensure result is not zero to avoid recalcing 3128 h = (0 != h) ? h : 1; 3129 3130 hash32 = h; 3131 } 3132 3133 return h; 3134 } 3135 3136 }