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 package java.lang; 26 27 import java.io.ObjectStreamField; 28 import java.io.UnsupportedEncodingException; 29 import java.nio.charset.Charset; 30 import java.util.ArrayList; 31 import java.util.Arrays; 32 import java.util.Comparator; 33 import java.util.Formatter; 34 import java.util.Locale; 35 import java.util.regex.Matcher; 36 import java.util.regex.Pattern; 37 import java.util.regex.PatternSyntaxException; 38 39 /** 40 * The {@code String} class represents character strings. All 41 * string literals in Java programs, such as {@code "abc"}, are 42 * implemented as instances of this class. 43 * <p> 44 * Strings are constant; their values cannot be changed after they 45 * are created. String buffers support mutable strings. 46 * Because String objects are immutable they can be shared. For example: 47 * <p><blockquote><pre> 48 * String str = "abc"; 49 * </pre></blockquote><p> 50 * is equivalent to: 51 * <p><blockquote><pre> 52 * char data[] = {'a', 'b', 'c'}; 53 * String str = new String(data); 54 * </pre></blockquote><p> 55 * Here are some more examples of how strings can be used: 56 * <p><blockquote><pre> 57 * System.out.println("abc"); 58 * String cde = "cde"; 59 * System.out.println("abc" + cde); 60 * String c = "abc".substring(2,3); 61 * String d = cde.substring(1, 2); 62 * </pre></blockquote> 63 * <p> 64 * The class {@code String} includes methods for examining 65 * individual characters of the sequence, for comparing strings, for 66 * searching strings, for extracting substrings, and for creating a 67 * copy of a string with all characters translated to uppercase or to 68 * lowercase. Case mapping is based on the Unicode Standard version 69 * specified by the {@link java.lang.Character Character} class. 70 * <p> 71 * The Java language provides special support for the string 72 * concatenation operator ( + ), and for conversion of 73 * other objects to strings. String concatenation is implemented 74 * through the {@code StringBuilder}(or {@code StringBuffer}) 75 * class and its {@code append} method. 76 * String conversions are implemented through the method 77 * {@code toString}, defined by {@code Object} and 78 * inherited by all classes in Java. For additional information on 79 * string concatenation and conversion, see Gosling, Joy, and Steele, 80 * <i>The Java Language Specification</i>. 81 * 82 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor 83 * or method in this class will cause a {@link NullPointerException} to be 84 * thrown. 85 * 86 * <p>A {@code String} represents a string in the UTF-16 format 87 * in which <em>supplementary characters</em> are represented by <em>surrogate 88 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 89 * Character Representations</a> in the {@code Character} class for 90 * more information). 91 * Index values refer to {@code char} code units, so a supplementary 92 * character uses two positions in a {@code String}. 93 * <p>The {@code String} class provides methods for dealing with 94 * Unicode code points (i.e., characters), in addition to those for 95 * dealing with Unicode code units (i.e., {@code char} values). 96 * 97 * @author Lee Boynton 98 * @author Arthur van Hoff 99 * @author Martin Buchholz 100 * @author Ulf Zibis 101 * @see java.lang.Object#toString() 102 * @see java.lang.StringBuffer 103 * @see java.lang.StringBuilder 104 * @see java.nio.charset.Charset 105 * @since JDK1.0 106 */ 107 public final class String 108 implements java.io.Serializable, Comparable<String>, CharSequence { 109 110 /** The value is used for character storage. */ 111 private final char value[]; 112 113 /** Cache the hash code for the string */ 114 private int hash; // Default to 0 115 116 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 117 private static final long serialVersionUID = -6849794470754667710L; 118 119 /** 120 * Class String is special cased within the Serialization Stream Protocol. 121 * 122 * A String instance is written initially into an ObjectOutputStream in the 123 * following format: 124 * <pre> 125 * {@code TC_STRING} (utf String) 126 * </pre> 127 * The String is written by method {@code DataOutput.writeUTF}. 128 * A new handle is generated to refer to all future references to the 129 * string instance within the stream. 130 */ 131 private static final ObjectStreamField[] serialPersistentFields = 132 new ObjectStreamField[0]; 133 134 /** 135 * Initializes a newly created {@code String} object so that it represents 136 * an empty character sequence. Note that use of this constructor is 137 * unnecessary since Strings are immutable. 138 */ 139 public String() { 140 this.value = new char[0]; 141 } 142 143 /** 144 * Initializes a newly created {@code String} object so that it represents 145 * the same sequence of characters as the argument; in other words, the 146 * newly created string is a copy of the argument string. Unless an 147 * explicit copy of {@code original} is needed, use of this constructor is 148 * unnecessary since Strings are immutable. 149 * 150 * @param original 151 * A {@code String} 152 */ 153 public String(String original) { 154 this.value = original.value; 155 this.hash = original.hash; 156 } 157 158 /** 159 * Allocates a new {@code String} so that it represents the sequence of 160 * characters currently contained in the character array argument. The 161 * contents of the character array are copied; subsequent modification of 162 * the character array does not affect the newly created string. 163 * 164 * @param value 165 * The initial value of the string 166 */ 167 public String(char value[]) { 168 this.value = Arrays.copyOf(value, value.length); 169 } 170 171 /** 172 * Allocates a new {@code String} that contains characters from a subarray 173 * of the character array argument. The {@code offset} argument is the 174 * index of the first character of the subarray and the {@code count} 175 * argument specifies the length of the subarray. The contents of the 176 * subarray are copied; subsequent modification of the character array does 177 * not affect the newly created string. 178 * 179 * @param value 180 * Array that is the source of characters 181 * 182 * @param offset 183 * The initial offset 184 * 185 * @param count 186 * The length 187 * 188 * @throws IndexOutOfBoundsException 189 * If the {@code offset} and {@code count} arguments index 190 * characters outside the bounds of the {@code value} array 191 */ 192 public String(char value[], int offset, int count) { 193 if (offset < 0) { 194 throw new StringIndexOutOfBoundsException(offset); 195 } 196 if (count < 0) { 197 throw new StringIndexOutOfBoundsException(count); 198 } 199 // Note: offset or count might be near -1>>>1. 200 if (offset > value.length - count) { 201 throw new StringIndexOutOfBoundsException(offset + count); 202 } 203 this.value = Arrays.copyOfRange(value, offset, offset+count); 204 } 205 206 /** 207 * Allocates a new {@code String} that contains characters from a subarray 208 * of the <a href="Character.html#unicode">Unicode code point</a> array 209 * argument. The {@code offset} argument is the index of the first code 210 * point of the subarray and the {@code count} argument specifies the 211 * length of the subarray. The contents of the subarray are converted to 212 * {@code char}s; subsequent modification of the {@code int} array does not 213 * affect the newly created string. 214 * 215 * @param codePoints 216 * Array that is the source of Unicode code points 217 * 218 * @param offset 219 * The initial offset 220 * 221 * @param count 222 * The length 223 * 224 * @throws IllegalArgumentException 225 * If any invalid Unicode code point is found in {@code 226 * codePoints} 227 * 228 * @throws IndexOutOfBoundsException 229 * If the {@code offset} and {@code count} arguments index 230 * characters outside the bounds of the {@code codePoints} array 231 * 232 * @since 1.5 233 */ 234 public String(int[] codePoints, int offset, int count) { 235 if (offset < 0) { 236 throw new StringIndexOutOfBoundsException(offset); 237 } 238 if (count < 0) { 239 throw new StringIndexOutOfBoundsException(count); 240 } 241 // Note: offset or count might be near -1>>>1. 242 if (offset > codePoints.length - count) { 243 throw new StringIndexOutOfBoundsException(offset + count); 244 } 245 246 final int end = offset + count; 247 248 // Pass 1: Compute precise size of char[] 249 int n = count; 250 for (int i = offset; i < end; i++) { 251 int c = codePoints[i]; 252 if (Character.isBmpCodePoint(c)) 253 continue; 254 else if (Character.isValidCodePoint(c)) 255 n++; 256 else throw new IllegalArgumentException(Integer.toString(c)); 257 } 258 259 // Pass 2: Allocate and fill in char[] 260 final char[] v = new char[n]; 261 262 for (int i = offset, j = 0; i < end; i++, j++) { 263 int c = codePoints[i]; 264 if (Character.isBmpCodePoint(c)) 265 v[j] = (char)c; 266 else 267 Character.toSurrogates(c, v, j++); 268 } 269 270 this.value = v; 271 } 272 273 /** 274 * Allocates a new {@code String} constructed from a subarray of an array 275 * of 8-bit integer values. 276 * 277 * <p> The {@code offset} argument is the index of the first byte of the 278 * subarray, and the {@code count} argument specifies the length of the 279 * subarray. 280 * 281 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 282 * specified in the method above. 283 * 284 * @deprecated This method does not properly convert bytes into characters. 285 * As of JDK 1.1, the preferred way to do this is via the 286 * {@code String} constructors that take a {@link 287 * java.nio.charset.Charset}, charset name, or that use the platform's 288 * default charset. 289 * 290 * @param ascii 291 * The bytes to be converted to characters 292 * 293 * @param hibyte 294 * The top 8 bits of each 16-bit Unicode code unit 295 * 296 * @param offset 297 * The initial offset 298 * @param count 299 * The length 300 * 301 * @throws IndexOutOfBoundsException 302 * If the {@code offset} or {@code count} argument is invalid 303 * 304 * @see #String(byte[], int) 305 * @see #String(byte[], int, int, java.lang.String) 306 * @see #String(byte[], int, int, java.nio.charset.Charset) 307 * @see #String(byte[], int, int) 308 * @see #String(byte[], java.lang.String) 309 * @see #String(byte[], java.nio.charset.Charset) 310 * @see #String(byte[]) 311 */ 312 @Deprecated 313 public String(byte ascii[], int hibyte, int offset, int count) { 314 checkBounds(ascii, offset, count); 315 char value[] = new char[count]; 316 317 if (hibyte == 0) { 318 for (int i = count; i-- > 0;) { 319 value[i] = (char)(ascii[i + offset] & 0xff); 320 } 321 } else { 322 hibyte <<= 8; 323 for (int i = count; i-- > 0;) { 324 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff)); 325 } 326 } 327 this.value = value; 328 } 329 330 /** 331 * Allocates a new {@code String} containing characters constructed from 332 * an array of 8-bit integer values. Each character <i>c</i>in the 333 * resulting string is constructed from the corresponding component 334 * <i>b</i> in the byte array such that: 335 * 336 * <blockquote><pre> 337 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 338 * | (<b><i>b</i></b> & 0xff)) 339 * </pre></blockquote> 340 * 341 * @deprecated This method does not properly convert bytes into 342 * characters. As of JDK 1.1, the preferred way to do this is via the 343 * {@code String} constructors that take a {@link 344 * java.nio.charset.Charset}, charset name, or that use the platform's 345 * default charset. 346 * 347 * @param ascii 348 * The bytes to be converted to characters 349 * 350 * @param hibyte 351 * The top 8 bits of each 16-bit Unicode code unit 352 * 353 * @see #String(byte[], int, int, java.lang.String) 354 * @see #String(byte[], int, int, java.nio.charset.Charset) 355 * @see #String(byte[], int, int) 356 * @see #String(byte[], java.lang.String) 357 * @see #String(byte[], java.nio.charset.Charset) 358 * @see #String(byte[]) 359 */ 360 @Deprecated 361 public String(byte ascii[], int hibyte) { 362 this(ascii, hibyte, 0, ascii.length); 363 } 364 365 /* Common private utility method used to bounds check the byte array 366 * and requested offset & length values used by the String(byte[],..) 367 * constructors. 368 */ 369 private static void checkBounds(byte[] bytes, int offset, int length) { 370 if (length < 0) 371 throw new StringIndexOutOfBoundsException(length); 372 if (offset < 0) 373 throw new StringIndexOutOfBoundsException(offset); 374 if (offset > bytes.length - length) 375 throw new StringIndexOutOfBoundsException(offset + length); 376 } 377 378 /** 379 * Constructs a new {@code String} by decoding the specified subarray of 380 * bytes using the specified charset. The length of the new {@code String} 381 * is a function of the charset, and hence may not be equal to the length 382 * of the subarray. 383 * 384 * <p> The behavior of this constructor when the given bytes are not valid 385 * in the given charset is unspecified. The {@link 386 * java.nio.charset.CharsetDecoder} class should be used when more control 387 * over the decoding process is required. 388 * 389 * @param bytes 390 * The bytes to be decoded into characters 391 * 392 * @param offset 393 * The index of the first byte to decode 394 * 395 * @param length 396 * The number of bytes to decode 397 398 * @param charsetName 399 * The name of a supported {@linkplain java.nio.charset.Charset 400 * charset} 401 * 402 * @throws UnsupportedEncodingException 403 * If the named charset is not supported 404 * 405 * @throws IndexOutOfBoundsException 406 * If the {@code offset} and {@code length} arguments index 407 * characters outside the bounds of the {@code bytes} array 408 * 409 * @since JDK1.1 410 */ 411 public String(byte bytes[], int offset, int length, String charsetName) 412 throws UnsupportedEncodingException { 413 if (charsetName == null) 414 throw new NullPointerException("charsetName"); 415 checkBounds(bytes, offset, length); 416 this.value = StringCoding.decode(charsetName, bytes, offset, length); 417 } 418 419 /** 420 * Constructs a new {@code String} by decoding the specified subarray of 421 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 422 * The length of the new {@code String} is a function of the charset, and 423 * hence may not be equal to the length of the subarray. 424 * 425 * <p> This method always replaces malformed-input and unmappable-character 426 * sequences with this charset's default replacement string. The {@link 427 * java.nio.charset.CharsetDecoder} class should be used when more control 428 * over the decoding process is required. 429 * 430 * @param bytes 431 * The bytes to be decoded into characters 432 * 433 * @param offset 434 * The index of the first byte to decode 435 * 436 * @param length 437 * The number of bytes to decode 438 * 439 * @param charset 440 * The {@linkplain java.nio.charset.Charset charset} to be used to 441 * decode the {@code bytes} 442 * 443 * @throws IndexOutOfBoundsException 444 * If the {@code offset} and {@code length} arguments index 445 * characters outside the bounds of the {@code bytes} array 446 * 447 * @since 1.6 448 */ 449 public String(byte bytes[], int offset, int length, Charset charset) { 450 if (charset == null) 451 throw new NullPointerException("charset"); 452 checkBounds(bytes, offset, length); 453 this.value = StringCoding.decode(charset, bytes, offset, length); 454 } 455 456 /** 457 * Constructs a new {@code String} by decoding the specified array of bytes 458 * using the specified {@linkplain java.nio.charset.Charset charset}. The 459 * length of the new {@code String} is a function of the charset, and hence 460 * may not be equal to the length of the byte array. 461 * 462 * <p> The behavior of this constructor when the given bytes are not valid 463 * in the given charset is unspecified. The {@link 464 * java.nio.charset.CharsetDecoder} class should be used when more control 465 * over the decoding process is required. 466 * 467 * @param bytes 468 * The bytes to be decoded into characters 469 * 470 * @param charsetName 471 * The name of a supported {@linkplain java.nio.charset.Charset 472 * charset} 473 * 474 * @throws UnsupportedEncodingException 475 * If the named charset is not supported 476 * 477 * @since JDK1.1 478 */ 479 public String(byte bytes[], String charsetName) 480 throws UnsupportedEncodingException { 481 this(bytes, 0, bytes.length, charsetName); 482 } 483 484 /** 485 * Constructs a new {@code String} by decoding the specified array of 486 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 487 * The length of the new {@code String} is a function of the charset, and 488 * hence may not be equal to the length of the byte array. 489 * 490 * <p> This method always replaces malformed-input and unmappable-character 491 * sequences with this charset's default replacement string. The {@link 492 * java.nio.charset.CharsetDecoder} class should be used when more control 493 * over the decoding process is required. 494 * 495 * @param bytes 496 * The bytes to be decoded into characters 497 * 498 * @param charset 499 * The {@linkplain java.nio.charset.Charset charset} to be used to 500 * decode the {@code bytes} 501 * 502 * @since 1.6 503 */ 504 public String(byte bytes[], Charset charset) { 505 this(bytes, 0, bytes.length, charset); 506 } 507 508 /** 509 * Constructs a new {@code String} by decoding the specified subarray of 510 * bytes using the platform's default charset. The length of the new 511 * {@code String} is a function of the charset, and hence may not be equal 512 * to the length of the subarray. 513 * 514 * <p> The behavior of this constructor when the given bytes are not valid 515 * in the default charset is unspecified. The {@link 516 * java.nio.charset.CharsetDecoder} class should be used when more control 517 * over the decoding process is required. 518 * 519 * @param bytes 520 * The bytes to be decoded into characters 521 * 522 * @param offset 523 * The index of the first byte to decode 524 * 525 * @param length 526 * The number of bytes to decode 527 * 528 * @throws IndexOutOfBoundsException 529 * If the {@code offset} and the {@code length} arguments index 530 * characters outside the bounds of the {@code bytes} array 531 * 532 * @since JDK1.1 533 */ 534 public String(byte bytes[], int offset, int length) { 535 checkBounds(bytes, offset, length); 536 this.value = StringCoding.decode(bytes, offset, length); 537 } 538 539 /** 540 * Constructs a new {@code String} by decoding the specified array of bytes 541 * using the platform's default charset. The length of the new {@code 542 * String} is a function of the charset, and hence may not be equal to the 543 * length of the byte array. 544 * 545 * <p> The behavior of this constructor when the given bytes are not valid 546 * in the default charset is unspecified. The {@link 547 * java.nio.charset.CharsetDecoder} class should be used when more control 548 * over the decoding process is required. 549 * 550 * @param bytes 551 * The bytes to be decoded into characters 552 * 553 * @since JDK1.1 554 */ 555 public String(byte bytes[]) { 556 this(bytes, 0, bytes.length); 557 } 558 559 /** 560 * Allocates a new string that contains the sequence of characters 561 * currently contained in the string buffer argument. The contents of the 562 * string buffer are copied; subsequent modification of the string buffer 563 * does not affect the newly created string. 564 * 565 * @param buffer 566 * A {@code StringBuffer} 567 */ 568 public String(StringBuffer buffer) { 569 synchronized(buffer) { 570 this.value = Arrays.copyOf(buffer.getValue(), buffer.length()); 571 } 572 } 573 574 /** 575 * Allocates a new string that contains the sequence of characters 576 * currently contained in the string builder argument. The contents of the 577 * string builder are copied; subsequent modification of the string builder 578 * does not affect the newly created string. 579 * 580 * <p> This constructor is provided to ease migration to {@code 581 * StringBuilder}. Obtaining a string from a string builder via the {@code 582 * toString} method is likely to run faster and is generally preferred. 583 * 584 * @param builder 585 * A {@code StringBuilder} 586 * 587 * @since 1.5 588 */ 589 public String(StringBuilder builder) { 590 this.value = Arrays.copyOf(builder.getValue(), builder.length()); 591 } 592 593 /* 594 * Package private constructor which shares value array for speed. 595 * this constructor is always expected to be called with share==true. 596 * a separate constructor is needed because we already have a public 597 * String(char[]) constructor that makes a copy of the given char[]. 598 */ 599 String(char[] value, boolean share) { 600 // assert share : "unshared not supported"; 601 this.value = value; 602 } 603 604 /** 605 * Package private constructor 606 * 607 * @deprecated Use {@link #String(char[],int,int)} instead. 608 */ 609 @Deprecated 610 String(int offset, int count, char[] value) { 611 this(value, offset, count); 612 } 613 614 /** 615 * Returns the length of this string. 616 * The length is equal to the number of <a href="Character.html#unicode">Unicode 617 * code units</a> in the string. 618 * 619 * @return the length of the sequence of characters represented by this 620 * object. 621 */ 622 public int length() { 623 return value.length; 624 } 625 626 /** 627 * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>. 628 * 629 * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise 630 * <tt>false</tt> 631 * 632 * @since 1.6 633 */ 634 public boolean isEmpty() { 635 return value.length == 0; 636 } 637 638 /** 639 * Returns the {@code char} value at the 640 * specified index. An index ranges from {@code 0} to 641 * {@code length() - 1}. The first {@code char} value of the sequence 642 * is at index {@code 0}, the next at index {@code 1}, 643 * and so on, as for array indexing. 644 * 645 * <p>If the {@code char} value specified by the index is a 646 * <a href="Character.html#unicode">surrogate</a>, the surrogate 647 * value is returned. 648 * 649 * @param index the index of the {@code char} value. 650 * @return the {@code char} value at the specified index of this string. 651 * The first {@code char} value is at index {@code 0}. 652 * @exception IndexOutOfBoundsException if the {@code index} 653 * argument is negative or not less than the length of this 654 * string. 655 */ 656 public char charAt(int index) { 657 if ((index < 0) || (index >= value.length)) { 658 throw new StringIndexOutOfBoundsException(index); 659 } 660 return value[index]; 661 } 662 663 /** 664 * Returns the character (Unicode code point) at the specified 665 * index. The index refers to {@code char} values 666 * (Unicode code units) and ranges from {@code 0} to 667 * {@link #length()}{@code - 1}. 668 * 669 * <p> If the {@code char} value specified at the given index 670 * is in the high-surrogate range, the following index is less 671 * than the length of this {@code String}, and the 672 * {@code char} value at the following index is in the 673 * low-surrogate range, then the supplementary code point 674 * corresponding to this surrogate pair is returned. Otherwise, 675 * the {@code char} value at the given index is returned. 676 * 677 * @param index the index to the {@code char} values 678 * @return the code point value of the character at the 679 * {@code index} 680 * @exception IndexOutOfBoundsException if the {@code index} 681 * argument is negative or not less than the length of this 682 * string. 683 * @since 1.5 684 */ 685 public int codePointAt(int index) { 686 if ((index < 0) || (index >= value.length)) { 687 throw new StringIndexOutOfBoundsException(index); 688 } 689 return Character.codePointAtImpl(value, index, value.length); 690 } 691 692 /** 693 * Returns the character (Unicode code point) before the specified 694 * index. The index refers to {@code char} values 695 * (Unicode code units) and ranges from {@code 1} to {@link 696 * CharSequence#length() length}. 697 * 698 * <p> If the {@code char} value at {@code (index - 1)} 699 * is in the low-surrogate range, {@code (index - 2)} is not 700 * negative, and the {@code char} value at {@code (index - 701 * 2)} is in the high-surrogate range, then the 702 * supplementary code point value of the surrogate pair is 703 * returned. If the {@code char} value at {@code index - 704 * 1} is an unpaired low-surrogate or a high-surrogate, the 705 * surrogate value is returned. 706 * 707 * @param index the index following the code point that should be returned 708 * @return the Unicode code point value before the given index. 709 * @exception IndexOutOfBoundsException if the {@code index} 710 * argument is less than 1 or greater than the length 711 * of this string. 712 * @since 1.5 713 */ 714 public int codePointBefore(int index) { 715 int i = index - 1; 716 if ((i < 0) || (i >= value.length)) { 717 throw new StringIndexOutOfBoundsException(index); 718 } 719 return Character.codePointBeforeImpl(value, index, 0); 720 } 721 722 /** 723 * Returns the number of Unicode code points in the specified text 724 * range of this {@code String}. The text range begins at the 725 * specified {@code beginIndex} and extends to the 726 * {@code char} at index {@code endIndex - 1}. Thus the 727 * length (in {@code char}s) of the text range is 728 * {@code endIndex-beginIndex}. Unpaired surrogates within 729 * the text range count as one code point each. 730 * 731 * @param beginIndex the index to the first {@code char} of 732 * the text range. 733 * @param endIndex the index after the last {@code char} of 734 * the text range. 735 * @return the number of Unicode code points in the specified text 736 * range 737 * @exception IndexOutOfBoundsException if the 738 * {@code beginIndex} is negative, or {@code endIndex} 739 * is larger than the length of this {@code String}, or 740 * {@code beginIndex} is larger than {@code endIndex}. 741 * @since 1.5 742 */ 743 public int codePointCount(int beginIndex, int endIndex) { 744 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) { 745 throw new IndexOutOfBoundsException(); 746 } 747 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex); 748 } 749 750 /** 751 * Returns the index within this {@code String} that is 752 * offset from the given {@code index} by 753 * {@code codePointOffset} code points. Unpaired surrogates 754 * within the text range given by {@code index} and 755 * {@code codePointOffset} count as one code point each. 756 * 757 * @param index the index to be offset 758 * @param codePointOffset the offset in code points 759 * @return the index within this {@code String} 760 * @exception IndexOutOfBoundsException if {@code index} 761 * is negative or larger then the length of this 762 * {@code String}, or if {@code codePointOffset} is positive 763 * and the substring starting with {@code index} has fewer 764 * than {@code codePointOffset} code points, 765 * or if {@code codePointOffset} is negative and the substring 766 * before {@code index} has fewer than the absolute value 767 * of {@code codePointOffset} code points. 768 * @since 1.5 769 */ 770 public int offsetByCodePoints(int index, int codePointOffset) { 771 if (index < 0 || index > value.length) { 772 throw new IndexOutOfBoundsException(); 773 } 774 return Character.offsetByCodePointsImpl(value, 0, value.length, 775 index, codePointOffset); 776 } 777 778 /** 779 * Copy characters from this string into dst starting at dstBegin. 780 * This method doesn't perform any range checking. 781 */ 782 void getChars(char dst[], int dstBegin) { 783 System.arraycopy(value, 0, dst, dstBegin, value.length); 784 } 785 786 /** 787 * Copies characters from this string into the destination character 788 * array. 789 * <p> 790 * The first character to be copied is at index {@code srcBegin}; 791 * the last character to be copied is at index {@code srcEnd-1} 792 * (thus the total number of characters to be copied is 793 * {@code srcEnd-srcBegin}). The characters are copied into the 794 * subarray of {@code dst} starting at index {@code dstBegin} 795 * and ending at index: 796 * <p><blockquote><pre> 797 * dstbegin + (srcEnd-srcBegin) - 1 798 * </pre></blockquote> 799 * 800 * @param srcBegin index of the first character in the string 801 * to copy. 802 * @param srcEnd index after the last character in the string 803 * to copy. 804 * @param dst the destination array. 805 * @param dstBegin the start offset in the destination array. 806 * @exception IndexOutOfBoundsException If any of the following 807 * is true: 808 * <ul><li>{@code srcBegin} is negative. 809 * <li>{@code srcBegin} is greater than {@code srcEnd} 810 * <li>{@code srcEnd} is greater than the length of this 811 * string 812 * <li>{@code dstBegin} is negative 813 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 814 * {@code dst.length}</ul> 815 */ 816 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 817 if (srcBegin < 0) { 818 throw new StringIndexOutOfBoundsException(srcBegin); 819 } 820 if (srcEnd > value.length) { 821 throw new StringIndexOutOfBoundsException(srcEnd); 822 } 823 if (srcBegin > srcEnd) { 824 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 825 } 826 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin); 827 } 828 829 /** 830 * Copies characters from this string into the destination byte array. Each 831 * byte receives the 8 low-order bits of the corresponding character. The 832 * eight high-order bits of each character are not copied and do not 833 * participate in the transfer in any way. 834 * 835 * <p> The first character to be copied is at index {@code srcBegin}; the 836 * last character to be copied is at index {@code srcEnd-1}. The total 837 * number of characters to be copied is {@code srcEnd-srcBegin}. The 838 * characters, converted to bytes, are copied into the subarray of {@code 839 * dst} starting at index {@code dstBegin} and ending at index: 840 * 841 * <blockquote><pre> 842 * dstbegin + (srcEnd-srcBegin) - 1 843 * </pre></blockquote> 844 * 845 * @deprecated This method does not properly convert characters into 846 * bytes. As of JDK 1.1, the preferred way to do this is via the 847 * {@link #getBytes()} method, which uses the platform's default charset. 848 * 849 * @param srcBegin 850 * Index of the first character in the string to copy 851 * 852 * @param srcEnd 853 * Index after the last character in the string to copy 854 * 855 * @param dst 856 * The destination array 857 * 858 * @param dstBegin 859 * The start offset in the destination array 860 * 861 * @throws IndexOutOfBoundsException 862 * If any of the following is true: 863 * <ul> 864 * <li> {@code srcBegin} is negative 865 * <li> {@code srcBegin} is greater than {@code srcEnd} 866 * <li> {@code srcEnd} is greater than the length of this String 867 * <li> {@code dstBegin} is negative 868 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 869 * dst.length} 870 * </ul> 871 */ 872 @Deprecated 873 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 874 if (srcBegin < 0) { 875 throw new StringIndexOutOfBoundsException(srcBegin); 876 } 877 if (srcEnd > value.length) { 878 throw new StringIndexOutOfBoundsException(srcEnd); 879 } 880 if (srcBegin > srcEnd) { 881 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 882 } 883 int j = dstBegin; 884 int n = srcEnd; 885 int i = srcBegin; 886 char[] val = value; /* avoid getfield opcode */ 887 888 while (i < n) { 889 dst[j++] = (byte)val[i++]; 890 } 891 } 892 893 /** 894 * Encodes this {@code String} into a sequence of bytes using the named 895 * charset, storing the result into a new byte array. 896 * 897 * <p> The behavior of this method when this string cannot be encoded in 898 * the given charset is unspecified. The {@link 899 * java.nio.charset.CharsetEncoder} class should be used when more control 900 * over the encoding process is required. 901 * 902 * @param charsetName 903 * The name of a supported {@linkplain java.nio.charset.Charset 904 * charset} 905 * 906 * @return The resultant byte array 907 * 908 * @throws UnsupportedEncodingException 909 * If the named charset is not supported 910 * 911 * @since JDK1.1 912 */ 913 public byte[] getBytes(String charsetName) 914 throws UnsupportedEncodingException { 915 if (charsetName == null) throw new NullPointerException(); 916 return StringCoding.encode(charsetName, value, 0, value.length); 917 } 918 919 /** 920 * Encodes this {@code String} into a sequence of bytes using the given 921 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 922 * new byte array. 923 * 924 * <p> This method always replaces malformed-input and unmappable-character 925 * sequences with this charset's default replacement byte array. The 926 * {@link java.nio.charset.CharsetEncoder} class should be used when more 927 * control over the encoding process is required. 928 * 929 * @param charset 930 * The {@linkplain java.nio.charset.Charset} to be used to encode 931 * the {@code String} 932 * 933 * @return The resultant byte array 934 * 935 * @since 1.6 936 */ 937 public byte[] getBytes(Charset charset) { 938 if (charset == null) throw new NullPointerException(); 939 return StringCoding.encode(charset, value, 0, value.length); 940 } 941 942 /** 943 * Encodes this {@code String} into a sequence of bytes using the 944 * platform's default charset, storing the result into a new byte array. 945 * 946 * <p> The behavior of this method when this string cannot be encoded in 947 * the default charset is unspecified. The {@link 948 * java.nio.charset.CharsetEncoder} class should be used when more control 949 * over the encoding process is required. 950 * 951 * @return The resultant byte array 952 * 953 * @since JDK1.1 954 */ 955 public byte[] getBytes() { 956 return StringCoding.encode(value, 0, value.length); 957 } 958 959 /** 960 * Compares this string to the specified object. The result is {@code 961 * true} if and only if the argument is not {@code null} and is a {@code 962 * String} object that represents the same sequence of characters as this 963 * object. 964 * 965 * @param anObject 966 * The object to compare this {@code String} against 967 * 968 * @return {@code true} if the given object represents a {@code String} 969 * equivalent to this string, {@code false} otherwise 970 * 971 * @see #compareTo(String) 972 * @see #equalsIgnoreCase(String) 973 */ 974 public boolean equals(Object anObject) { 975 if (this == anObject) { 976 return true; 977 } 978 if (anObject instanceof String) { 979 String anotherString = (String) anObject; 980 int n = value.length; 981 if (n == anotherString.value.length) { 982 char v1[] = value; 983 char v2[] = anotherString.value; 984 int i = 0; 985 while (n-- != 0) { 986 if (v1[i] != v2[i]) 987 return false; 988 i++; 989 } 990 return true; 991 } 992 } 993 return false; 994 } 995 996 /** 997 * Compares this string to the specified {@code StringBuffer}. The result 998 * is {@code true} if and only if this {@code String} represents the same 999 * sequence of characters as the specified {@code StringBuffer}. 1000 * 1001 * @param sb 1002 * The {@code StringBuffer} to compare this {@code String} against 1003 * 1004 * @return {@code true} if this {@code String} represents the same 1005 * sequence of characters as the specified {@code StringBuffer}, 1006 * {@code false} otherwise 1007 * 1008 * @since 1.4 1009 */ 1010 public boolean contentEquals(StringBuffer sb) { 1011 synchronized (sb) { 1012 return contentEquals((CharSequence) sb); 1013 } 1014 } 1015 1016 /** 1017 * Compares this string to the specified {@code CharSequence}. The result 1018 * is {@code true} if and only if this {@code String} represents the same 1019 * sequence of char values as the specified sequence. 1020 * 1021 * @param cs 1022 * The sequence to compare this {@code String} against 1023 * 1024 * @return {@code true} if this {@code String} represents the same 1025 * sequence of char values as the specified sequence, {@code 1026 * false} otherwise 1027 * 1028 * @since 1.5 1029 */ 1030 public boolean contentEquals(CharSequence cs) { 1031 if (value.length != cs.length()) 1032 return false; 1033 // Argument is a StringBuffer, StringBuilder 1034 if (cs instanceof AbstractStringBuilder) { 1035 char v1[] = value; 1036 char v2[] = ((AbstractStringBuilder) cs).getValue(); 1037 int i = 0; 1038 int n = value.length; 1039 while (n-- != 0) { 1040 if (v1[i] != v2[i]) 1041 return false; 1042 i++; 1043 } 1044 return true; 1045 } 1046 // Argument is a String 1047 if (cs.equals(this)) 1048 return true; 1049 // Argument is a generic CharSequence 1050 char v1[] = value; 1051 int i = 0; 1052 int n = value.length; 1053 while (n-- != 0) { 1054 if (v1[i] != cs.charAt(i)) 1055 return false; 1056 i++; 1057 } 1058 return true; 1059 } 1060 1061 /** 1062 * Compares this {@code String} to another {@code String}, ignoring case 1063 * considerations. Two strings are considered equal ignoring case if they 1064 * are of the same length and corresponding characters in the two strings 1065 * are equal ignoring case. 1066 * 1067 * <p> Two characters {@code c1} and {@code c2} are considered the same 1068 * ignoring case if at least one of the following is true: 1069 * <ul> 1070 * <li> The two characters are the same (as compared by the 1071 * {@code ==} operator) 1072 * <li> Applying the method {@link 1073 * java.lang.Character#toUpperCase(char)} to each character 1074 * produces the same result 1075 * <li> Applying the method {@link 1076 * java.lang.Character#toLowerCase(char)} to each character 1077 * produces the same result 1078 * </ul> 1079 * 1080 * @param anotherString 1081 * The {@code String} to compare this {@code String} against 1082 * 1083 * @return {@code true} if the argument is not {@code null} and it 1084 * represents an equivalent {@code String} ignoring case; {@code 1085 * false} otherwise 1086 * 1087 * @see #equals(Object) 1088 */ 1089 public boolean equalsIgnoreCase(String anotherString) { 1090 return (this == anotherString) ? true 1091 : (anotherString != null) 1092 && (anotherString.value.length == value.length) 1093 && regionMatches(true, 0, anotherString, 0, value.length); 1094 } 1095 1096 /** 1097 * Compares two strings lexicographically. 1098 * The comparison is based on the Unicode value of each character in 1099 * the strings. The character sequence represented by this 1100 * {@code String} object is compared lexicographically to the 1101 * character sequence represented by the argument string. The result is 1102 * a negative integer if this {@code String} object 1103 * lexicographically precedes the argument string. The result is a 1104 * positive integer if this {@code String} object lexicographically 1105 * follows the argument string. The result is zero if the strings 1106 * are equal; {@code compareTo} returns {@code 0} exactly when 1107 * the {@link #equals(Object)} method would return {@code true}. 1108 * <p> 1109 * This is the definition of lexicographic ordering. If two strings are 1110 * different, then either they have different characters at some index 1111 * that is a valid index for both strings, or their lengths are different, 1112 * or both. If they have different characters at one or more index 1113 * positions, let <i>k</i> be the smallest such index; then the string 1114 * whose character at position <i>k</i> has the smaller value, as 1115 * determined by using the < operator, lexicographically precedes the 1116 * other string. In this case, {@code compareTo} returns the 1117 * difference of the two character values at position {@code k} in 1118 * the two string -- that is, the value: 1119 * <blockquote><pre> 1120 * this.charAt(k)-anotherString.charAt(k) 1121 * </pre></blockquote> 1122 * If there is no index position at which they differ, then the shorter 1123 * string lexicographically precedes the longer string. In this case, 1124 * {@code compareTo} returns the difference of the lengths of the 1125 * strings -- that is, the value: 1126 * <blockquote><pre> 1127 * this.length()-anotherString.length() 1128 * </pre></blockquote> 1129 * 1130 * @param anotherString the {@code String} to be compared. 1131 * @return the value {@code 0} if the argument string is equal to 1132 * this string; a value less than {@code 0} if this string 1133 * is lexicographically less than the string argument; and a 1134 * value greater than {@code 0} if this string is 1135 * lexicographically greater than the string argument. 1136 */ 1137 public int compareTo(String anotherString) { 1138 int len1 = value.length; 1139 int len2 = anotherString.value.length; 1140 int lim = Math.min(len1, len2); 1141 char v1[] = value; 1142 char v2[] = anotherString.value; 1143 1144 int k = 0; 1145 while (k < lim) { 1146 char c1 = v1[k]; 1147 char c2 = v2[k]; 1148 if (c1 != c2) { 1149 return c1 - c2; 1150 } 1151 k++; 1152 } 1153 return len1 - len2; 1154 } 1155 1156 /** 1157 * A Comparator that orders {@code String} objects as by 1158 * {@code compareToIgnoreCase}. This comparator is serializable. 1159 * <p> 1160 * Note that this Comparator does <em>not</em> take locale into account, 1161 * and will result in an unsatisfactory ordering for certain locales. 1162 * The java.text package provides <em>Collators</em> to allow 1163 * locale-sensitive ordering. 1164 * 1165 * @see java.text.Collator#compare(String, String) 1166 * @since 1.2 1167 */ 1168 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1169 = new CaseInsensitiveComparator(); 1170 private static class CaseInsensitiveComparator 1171 implements Comparator<String>, java.io.Serializable { 1172 // use serialVersionUID from JDK 1.2.2 for interoperability 1173 private static final long serialVersionUID = 8575799808933029326L; 1174 1175 public int compare(String s1, String s2) { 1176 int n1 = s1.length(); 1177 int n2 = s2.length(); 1178 int min = Math.min(n1, n2); 1179 for (int i = 0; i < min; i++) { 1180 char c1 = s1.charAt(i); 1181 char c2 = s2.charAt(i); 1182 if (c1 != c2) { 1183 c1 = Character.toUpperCase(c1); 1184 c2 = Character.toUpperCase(c2); 1185 if (c1 != c2) { 1186 c1 = Character.toLowerCase(c1); 1187 c2 = Character.toLowerCase(c2); 1188 if (c1 != c2) { 1189 // No overflow because of numeric promotion 1190 return c1 - c2; 1191 } 1192 } 1193 } 1194 } 1195 return n1 - n2; 1196 } 1197 1198 /** Replaces the de-serialized object. */ 1199 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1200 } 1201 1202 /** 1203 * Compares two strings lexicographically, ignoring case 1204 * differences. This method returns an integer whose sign is that of 1205 * calling {@code compareTo} with normalized versions of the strings 1206 * where case differences have been eliminated by calling 1207 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1208 * each character. 1209 * <p> 1210 * Note that this method 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 * @param str the {@code String} to be compared. 1216 * @return a negative integer, zero, or a positive integer as the 1217 * specified String is greater than, equal to, or less 1218 * than this String, ignoring case considerations. 1219 * @see java.text.Collator#compare(String, String) 1220 * @since 1.2 1221 */ 1222 public int compareToIgnoreCase(String str) { 1223 return CASE_INSENSITIVE_ORDER.compare(this, str); 1224 } 1225 1226 /** 1227 * Tests if two string regions are equal. 1228 * <p> 1229 * A substring of this <tt>String</tt> object is compared to a substring 1230 * of the argument other. The result is true if these substrings 1231 * represent identical character sequences. The substring of this 1232 * <tt>String</tt> object to be compared begins at index <tt>toffset</tt> 1233 * and has length <tt>len</tt>. The substring of other to be compared 1234 * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The 1235 * result is <tt>false</tt> if and only if at least one of the following 1236 * is true: 1237 * <ul><li><tt>toffset</tt> is negative. 1238 * <li><tt>ooffset</tt> is negative. 1239 * <li><tt>toffset+len</tt> is greater than the length of this 1240 * <tt>String</tt> object. 1241 * <li><tt>ooffset+len</tt> is greater than the length of the other 1242 * argument. 1243 * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt> 1244 * such that: 1245 * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt> 1246 * </ul> 1247 * 1248 * @param toffset the starting offset of the subregion in this string. 1249 * @param other the string argument. 1250 * @param ooffset the starting offset of the subregion in the string 1251 * argument. 1252 * @param len the number of characters to compare. 1253 * @return {@code true} if the specified subregion of this string 1254 * exactly matches the specified subregion of the string argument; 1255 * {@code false} otherwise. 1256 */ 1257 public boolean regionMatches(int toffset, String other, int ooffset, 1258 int len) { 1259 char ta[] = value; 1260 int to = toffset; 1261 char pa[] = other.value; 1262 int po = ooffset; 1263 // Note: toffset, ooffset, or len might be near -1>>>1. 1264 if ((ooffset < 0) || (toffset < 0) 1265 || (toffset > (long)value.length - len) 1266 || (ooffset > (long)other.value.length - len)) { 1267 return false; 1268 } 1269 while (len-- > 0) { 1270 if (ta[to++] != pa[po++]) { 1271 return false; 1272 } 1273 } 1274 return true; 1275 } 1276 1277 /** 1278 * Tests if two string regions are equal. 1279 * <p> 1280 * A substring of this <tt>String</tt> object is compared to a substring 1281 * of the argument <tt>other</tt>. The result is <tt>true</tt> if these 1282 * substrings represent character sequences that are the same, ignoring 1283 * case if and only if <tt>ignoreCase</tt> is true. The substring of 1284 * this <tt>String</tt> object to be compared begins at index 1285 * <tt>toffset</tt> and has length <tt>len</tt>. The substring of 1286 * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and 1287 * has length <tt>len</tt>. The result is <tt>false</tt> if and only if 1288 * at least one of the following is true: 1289 * <ul><li><tt>toffset</tt> is negative. 1290 * <li><tt>ooffset</tt> is negative. 1291 * <li><tt>toffset+len</tt> is greater than the length of this 1292 * <tt>String</tt> object. 1293 * <li><tt>ooffset+len</tt> is greater than the length of the other 1294 * argument. 1295 * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative 1296 * integer <i>k</i> less than <tt>len</tt> such that: 1297 * <blockquote><pre> 1298 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1299 * </pre></blockquote> 1300 * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative 1301 * integer <i>k</i> less than <tt>len</tt> such that: 1302 * <blockquote><pre> 1303 * Character.toLowerCase(this.charAt(toffset+k)) != 1304 Character.toLowerCase(other.charAt(ooffset+k)) 1305 * </pre></blockquote> 1306 * and: 1307 * <blockquote><pre> 1308 * Character.toUpperCase(this.charAt(toffset+k)) != 1309 * Character.toUpperCase(other.charAt(ooffset+k)) 1310 * </pre></blockquote> 1311 * </ul> 1312 * 1313 * @param ignoreCase if {@code true}, ignore case when comparing 1314 * characters. 1315 * @param toffset the starting offset of the subregion in this 1316 * string. 1317 * @param other the string argument. 1318 * @param ooffset the starting offset of the subregion in the string 1319 * argument. 1320 * @param len the number of characters to compare. 1321 * @return {@code true} if the specified subregion of this string 1322 * matches the specified subregion of the string argument; 1323 * {@code false} otherwise. Whether the matching is exact 1324 * or case insensitive depends on the {@code ignoreCase} 1325 * argument. 1326 */ 1327 public boolean regionMatches(boolean ignoreCase, int toffset, 1328 String other, int ooffset, int len) { 1329 char ta[] = value; 1330 int to = toffset; 1331 char pa[] = other.value; 1332 int po = ooffset; 1333 // Note: toffset, ooffset, or len might be near -1>>>1. 1334 if ((ooffset < 0) || (toffset < 0) 1335 || (toffset > (long)value.length - len) 1336 || (ooffset > (long)other.value.length - len)) { 1337 return false; 1338 } 1339 while (len-- > 0) { 1340 char c1 = ta[to++]; 1341 char c2 = pa[po++]; 1342 if (c1 == c2) { 1343 continue; 1344 } 1345 if (ignoreCase) { 1346 // If characters don't match but case may be ignored, 1347 // try converting both characters to uppercase. 1348 // If the results match, then the comparison scan should 1349 // continue. 1350 char u1 = Character.toUpperCase(c1); 1351 char u2 = Character.toUpperCase(c2); 1352 if (u1 == u2) { 1353 continue; 1354 } 1355 // Unfortunately, conversion to uppercase does not work properly 1356 // for the Georgian alphabet, which has strange rules about case 1357 // conversion. So we need to make one last check before 1358 // exiting. 1359 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) { 1360 continue; 1361 } 1362 } 1363 return false; 1364 } 1365 return true; 1366 } 1367 1368 /** 1369 * Tests if the substring of this string beginning at the 1370 * specified index starts with the specified prefix. 1371 * 1372 * @param prefix the prefix. 1373 * @param toffset where to begin looking in this string. 1374 * @return {@code true} if the character sequence represented by the 1375 * argument is a prefix of the substring of this object starting 1376 * at index {@code toffset}; {@code false} otherwise. 1377 * The result is {@code false} if {@code toffset} is 1378 * negative or greater than the length of this 1379 * {@code String} object; otherwise the result is the same 1380 * as the result of the expression 1381 * <pre> 1382 * this.substring(toffset).startsWith(prefix) 1383 * </pre> 1384 */ 1385 public boolean startsWith(String prefix, int toffset) { 1386 char ta[] = value; 1387 int to = toffset; 1388 char pa[] = prefix.value; 1389 int po = 0; 1390 int pc = prefix.value.length; 1391 // Note: toffset might be near -1>>>1. 1392 if ((toffset < 0) || (toffset > value.length - pc)) { 1393 return false; 1394 } 1395 while (--pc >= 0) { 1396 if (ta[to++] != pa[po++]) { 1397 return false; 1398 } 1399 } 1400 return true; 1401 } 1402 1403 /** 1404 * Tests if this string starts with the specified prefix. 1405 * 1406 * @param prefix the prefix. 1407 * @return {@code true} if the character sequence represented by the 1408 * argument is a prefix of the character sequence represented by 1409 * this string; {@code false} otherwise. 1410 * Note also that {@code true} will be returned if the 1411 * argument is an empty string or is equal to this 1412 * {@code String} object as determined by the 1413 * {@link #equals(Object)} method. 1414 * @since 1. 0 1415 */ 1416 public boolean startsWith(String prefix) { 1417 return startsWith(prefix, 0); 1418 } 1419 1420 /** 1421 * Tests if this string ends with the specified suffix. 1422 * 1423 * @param suffix the suffix. 1424 * @return {@code true} if the character sequence represented by the 1425 * argument is a suffix of the character sequence represented by 1426 * this object; {@code false} otherwise. Note that the 1427 * result will be {@code true} if the argument is the 1428 * empty string or is equal to this {@code String} object 1429 * as determined by the {@link #equals(Object)} method. 1430 */ 1431 public boolean endsWith(String suffix) { 1432 return startsWith(suffix, value.length - suffix.value.length); 1433 } 1434 1435 /** 1436 * Returns a hash code for this string. The hash code for a 1437 * {@code String} object is computed as 1438 * <blockquote><pre> 1439 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1440 * </pre></blockquote> 1441 * using {@code int} arithmetic, where {@code s[i]} is the 1442 * <i>i</i>th character of the string, {@code n} is the length of 1443 * the string, and {@code ^} indicates exponentiation. 1444 * (The hash value of the empty string is zero.) 1445 * 1446 * @return a hash code value for this object. 1447 */ 1448 public int hashCode() { 1449 int h = hash; 1450 if (h == 0 && value.length > 0) { 1451 char val[] = value; 1452 1453 for (int i = 0; i < value.length; i++) { 1454 h = 31 * h + val[i]; 1455 } 1456 hash = h; 1457 } 1458 return h; 1459 } 1460 1461 /** 1462 * Returns the index within this string of the first occurrence of 1463 * the specified character. If a character with value 1464 * {@code ch} occurs in the character sequence represented by 1465 * this {@code String} object, then the index (in Unicode 1466 * code units) of the first such occurrence is returned. For 1467 * values of {@code ch} in the range from 0 to 0xFFFF 1468 * (inclusive), this is the smallest value <i>k</i> such that: 1469 * <blockquote><pre> 1470 * this.charAt(<i>k</i>) == ch 1471 * </pre></blockquote> 1472 * is true. For other values of {@code ch}, it is the 1473 * smallest value <i>k</i> such that: 1474 * <blockquote><pre> 1475 * this.codePointAt(<i>k</i>) == ch 1476 * </pre></blockquote> 1477 * is true. In either case, if no such character occurs in this 1478 * string, then {@code -1} is returned. 1479 * 1480 * @param ch a character (Unicode code point). 1481 * @return the index of the first occurrence of the character in the 1482 * character sequence represented by this object, or 1483 * {@code -1} if the character does not occur. 1484 */ 1485 public int indexOf(int ch) { 1486 return indexOf(ch, 0); 1487 } 1488 1489 /** 1490 * Returns the index within this string of the first occurrence of the 1491 * specified character, starting the search at the specified index. 1492 * <p> 1493 * If a character with value {@code ch} occurs in the 1494 * character sequence represented by this {@code String} 1495 * object at an index no smaller than {@code fromIndex}, then 1496 * the index of the first such occurrence is returned. For values 1497 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1498 * this is the smallest value <i>k</i> such that: 1499 * <blockquote><pre> 1500 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex) 1501 * </pre></blockquote> 1502 * is true. For other values of {@code ch}, it is the 1503 * smallest value <i>k</i> such that: 1504 * <blockquote><pre> 1505 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex) 1506 * </pre></blockquote> 1507 * is true. In either case, if no such character occurs in this 1508 * string at or after position {@code fromIndex}, then 1509 * {@code -1} is returned. 1510 * 1511 * <p> 1512 * There is no restriction on the value of {@code fromIndex}. If it 1513 * is negative, it has the same effect as if it were zero: this entire 1514 * string may be searched. If it is greater than the length of this 1515 * string, it has the same effect as if it were equal to the length of 1516 * this string: {@code -1} is returned. 1517 * 1518 * <p>All indices are specified in {@code char} values 1519 * (Unicode code units). 1520 * 1521 * @param ch a character (Unicode code point). 1522 * @param fromIndex the index to start the search from. 1523 * @return the index of the first occurrence of the character in the 1524 * character sequence represented by this object that is greater 1525 * than or equal to {@code fromIndex}, or {@code -1} 1526 * if the character does not occur. 1527 */ 1528 public int indexOf(int ch, int fromIndex) { 1529 final int max = value.length; 1530 if (fromIndex < 0) { 1531 fromIndex = 0; 1532 } else if (fromIndex >= max) { 1533 // Note: fromIndex might be near -1>>>1. 1534 return -1; 1535 } 1536 1537 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1538 // handle most cases here (ch is a BMP code point or a 1539 // negative value (invalid code point)) 1540 final char[] value = this.value; 1541 for (int i = fromIndex; i < max; i++) { 1542 if (value[i] == ch) { 1543 return i; 1544 } 1545 } 1546 return -1; 1547 } else { 1548 return indexOfSupplementary(ch, fromIndex); 1549 } 1550 } 1551 1552 /** 1553 * Handles (rare) calls of indexOf with a supplementary character. 1554 */ 1555 private int indexOfSupplementary(int ch, int fromIndex) { 1556 if (Character.isValidCodePoint(ch)) { 1557 final char[] value = this.value; 1558 final char hi = Character.highSurrogate(ch); 1559 final char lo = Character.lowSurrogate(ch); 1560 final int max = value.length - 1; 1561 for (int i = fromIndex; i < max; i++) { 1562 if (value[i] == hi && value[i + 1] == lo) { 1563 return i; 1564 } 1565 } 1566 } 1567 return -1; 1568 } 1569 1570 /** 1571 * Returns the index within this string of the last occurrence of 1572 * the specified character. For values of {@code ch} in the 1573 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1574 * units) returned is the largest value <i>k</i> such that: 1575 * <blockquote><pre> 1576 * this.charAt(<i>k</i>) == ch 1577 * </pre></blockquote> 1578 * is true. For other values of {@code ch}, it is the 1579 * largest value <i>k</i> such that: 1580 * <blockquote><pre> 1581 * this.codePointAt(<i>k</i>) == ch 1582 * </pre></blockquote> 1583 * is true. In either case, if no such character occurs in this 1584 * string, then {@code -1} is returned. The 1585 * {@code String} is searched backwards starting at the last 1586 * character. 1587 * 1588 * @param ch a character (Unicode code point). 1589 * @return the index of the last occurrence of the character in the 1590 * character sequence represented by this object, or 1591 * {@code -1} if the character does not occur. 1592 */ 1593 public int lastIndexOf(int ch) { 1594 return lastIndexOf(ch, value.length - 1); 1595 } 1596 1597 /** 1598 * Returns the index within this string of the last occurrence of 1599 * the specified character, searching backward starting at the 1600 * specified index. For values of {@code ch} in the range 1601 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1602 * value <i>k</i> such that: 1603 * <blockquote><pre> 1604 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex) 1605 * </pre></blockquote> 1606 * is true. For other values of {@code ch}, it is the 1607 * largest value <i>k</i> such that: 1608 * <blockquote><pre> 1609 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex) 1610 * </pre></blockquote> 1611 * is true. In either case, if no such character occurs in this 1612 * string at or before position {@code fromIndex}, then 1613 * {@code -1} is returned. 1614 * 1615 * <p>All indices are specified in {@code char} values 1616 * (Unicode code units). 1617 * 1618 * @param ch a character (Unicode code point). 1619 * @param fromIndex the index to start the search from. There is no 1620 * restriction on the value of {@code fromIndex}. If it is 1621 * greater than or equal to the length of this string, it has 1622 * the same effect as if it were equal to one less than the 1623 * length of this string: this entire string may be searched. 1624 * If it is negative, it has the same effect as if it were -1: 1625 * -1 is returned. 1626 * @return the index of the last occurrence of the character in the 1627 * character sequence represented by this object that is less 1628 * than or equal to {@code fromIndex}, or {@code -1} 1629 * if the character does not occur before that point. 1630 */ 1631 public int lastIndexOf(int ch, int fromIndex) { 1632 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1633 // handle most cases here (ch is a BMP code point or a 1634 // negative value (invalid code point)) 1635 final char[] value = this.value; 1636 int i = Math.min(fromIndex, value.length - 1); 1637 for (; i >= 0; i--) { 1638 if (value[i] == ch) { 1639 return i; 1640 } 1641 } 1642 return -1; 1643 } else { 1644 return lastIndexOfSupplementary(ch, fromIndex); 1645 } 1646 } 1647 1648 /** 1649 * Handles (rare) calls of lastIndexOf with a supplementary character. 1650 */ 1651 private int lastIndexOfSupplementary(int ch, int fromIndex) { 1652 if (Character.isValidCodePoint(ch)) { 1653 final char[] value = this.value; 1654 char hi = Character.highSurrogate(ch); 1655 char lo = Character.lowSurrogate(ch); 1656 int i = Math.min(fromIndex, value.length - 2); 1657 for (; i >= 0; i--) { 1658 if (value[i] == hi && value[i + 1] == lo) { 1659 return i; 1660 } 1661 } 1662 } 1663 return -1; 1664 } 1665 1666 /** 1667 * Returns the index within this string of the first occurrence of the 1668 * specified substring. 1669 * 1670 * <p>The returned index is the smallest value <i>k</i> for which: 1671 * <blockquote><pre> 1672 * this.startsWith(str, <i>k</i>) 1673 * </pre></blockquote> 1674 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1675 * 1676 * @param str the substring to search for. 1677 * @return the index of the first occurrence of the specified substring, 1678 * or {@code -1} if there is no such occurrence. 1679 */ 1680 public int indexOf(String str) { 1681 return indexOf(str, 0); 1682 } 1683 1684 /** 1685 * Returns the index within this string of the first occurrence of the 1686 * specified substring, starting at the specified index. 1687 * 1688 * <p>The returned index is the smallest value <i>k</i> for which: 1689 * <blockquote><pre> 1690 * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>) 1691 * </pre></blockquote> 1692 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1693 * 1694 * @param str the substring to search for. 1695 * @param fromIndex the index from which to start the search. 1696 * @return the index of the first occurrence of the specified substring, 1697 * starting at the specified index, 1698 * or {@code -1} if there is no such occurrence. 1699 */ 1700 public int indexOf(String str, int fromIndex) { 1701 return indexOf(value, 0, value.length, 1702 str.value, 0, str.value.length, fromIndex); 1703 } 1704 1705 /** 1706 * Code shared by String and StringBuffer to do searches. The 1707 * source is the character array being searched, and the target 1708 * is the string being searched for. 1709 * 1710 * @param source the characters being searched. 1711 * @param sourceOffset offset of the source string. 1712 * @param sourceCount count of the source string. 1713 * @param target the characters being searched for. 1714 * @param targetOffset offset of the target string. 1715 * @param targetCount count of the target string. 1716 * @param fromIndex the index to begin searching from. 1717 */ 1718 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1719 char[] target, int targetOffset, int targetCount, 1720 int fromIndex) { 1721 if (fromIndex >= sourceCount) { 1722 return (targetCount == 0 ? sourceCount : -1); 1723 } 1724 if (fromIndex < 0) { 1725 fromIndex = 0; 1726 } 1727 if (targetCount == 0) { 1728 return fromIndex; 1729 } 1730 1731 char first = target[targetOffset]; 1732 int max = sourceOffset + (sourceCount - targetCount); 1733 1734 for (int i = sourceOffset + fromIndex; i <= max; i++) { 1735 /* Look for first character. */ 1736 if (source[i] != first) { 1737 while (++i <= max && source[i] != first); 1738 } 1739 1740 /* Found first character, now look at the rest of v2 */ 1741 if (i <= max) { 1742 int j = i + 1; 1743 int end = j + targetCount - 1; 1744 for (int k = targetOffset + 1; j < end && source[j] 1745 == target[k]; j++, k++); 1746 1747 if (j == end) { 1748 /* Found whole string. */ 1749 return i - sourceOffset; 1750 } 1751 } 1752 } 1753 return -1; 1754 } 1755 1756 /** 1757 * Returns the index within this string of the last occurrence of the 1758 * specified substring. The last occurrence of the empty string "" 1759 * is considered to occur at the index value {@code this.length()}. 1760 * 1761 * <p>The returned index is the largest value <i>k</i> for which: 1762 * <blockquote><pre> 1763 * this.startsWith(str, <i>k</i>) 1764 * </pre></blockquote> 1765 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1766 * 1767 * @param str the substring to search for. 1768 * @return the index of the last occurrence of the specified substring, 1769 * or {@code -1} if there is no such occurrence. 1770 */ 1771 public int lastIndexOf(String str) { 1772 return lastIndexOf(str, value.length); 1773 } 1774 1775 /** 1776 * Returns the index within this string of the last occurrence of the 1777 * specified substring, searching backward starting at the specified index. 1778 * 1779 * <p>The returned index is the largest value <i>k</i> for which: 1780 * <blockquote><pre> 1781 * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>) 1782 * </pre></blockquote> 1783 * If no such value of <i>k</i> exists, then {@code -1} is returned. 1784 * 1785 * @param str the substring to search for. 1786 * @param fromIndex the index to start the search from. 1787 * @return the index of the last occurrence of the specified substring, 1788 * searching backward from the specified index, 1789 * or {@code -1} if there is no such occurrence. 1790 */ 1791 public int lastIndexOf(String str, int fromIndex) { 1792 return lastIndexOf(value, 0, value.length, 1793 str.value, 0, str.value.length, fromIndex); 1794 } 1795 1796 /** 1797 * Code shared by String and StringBuffer to do searches. The 1798 * source is the character array being searched, and the target 1799 * is the string being searched for. 1800 * 1801 * @param source the characters being searched. 1802 * @param sourceOffset offset of the source string. 1803 * @param sourceCount count of the source string. 1804 * @param target the characters being searched for. 1805 * @param targetOffset offset of the target string. 1806 * @param targetCount count of the target string. 1807 * @param fromIndex the index to begin searching from. 1808 */ 1809 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1810 char[] target, int targetOffset, int targetCount, 1811 int fromIndex) { 1812 /* 1813 * Check arguments; return immediately where possible. For 1814 * consistency, don't check for null str. 1815 */ 1816 int rightIndex = sourceCount - targetCount; 1817 if (fromIndex < 0) { 1818 return -1; 1819 } 1820 if (fromIndex > rightIndex) { 1821 fromIndex = rightIndex; 1822 } 1823 /* Empty string always matches. */ 1824 if (targetCount == 0) { 1825 return fromIndex; 1826 } 1827 1828 int strLastIndex = targetOffset + targetCount - 1; 1829 char strLastChar = target[strLastIndex]; 1830 int min = sourceOffset + targetCount - 1; 1831 int i = min + fromIndex; 1832 1833 startSearchForLastChar: 1834 while (true) { 1835 while (i >= min && source[i] != strLastChar) { 1836 i--; 1837 } 1838 if (i < min) { 1839 return -1; 1840 } 1841 int j = i - 1; 1842 int start = j - (targetCount - 1); 1843 int k = strLastIndex - 1; 1844 1845 while (j > start) { 1846 if (source[j--] != target[k--]) { 1847 i--; 1848 continue startSearchForLastChar; 1849 } 1850 } 1851 return start - sourceOffset + 1; 1852 } 1853 } 1854 1855 /** 1856 * Returns a new string that is a substring of this string. The 1857 * substring begins with the character at the specified index and 1858 * extends to the end of this string. <p> 1859 * Examples: 1860 * <blockquote><pre> 1861 * "unhappy".substring(2) returns "happy" 1862 * "Harbison".substring(3) returns "bison" 1863 * "emptiness".substring(9) returns "" (an empty string) 1864 * </pre></blockquote> 1865 * 1866 * @param beginIndex the beginning index, inclusive. 1867 * @return the specified substring. 1868 * @exception IndexOutOfBoundsException if 1869 * {@code beginIndex} is negative or larger than the 1870 * length of this {@code String} object. 1871 */ 1872 public String substring(int beginIndex) { 1873 if (beginIndex < 0) { 1874 throw new StringIndexOutOfBoundsException(beginIndex); 1875 } 1876 int subLen = value.length - beginIndex; 1877 if (subLen < 0) { 1878 throw new StringIndexOutOfBoundsException(subLen); 1879 } 1880 return (beginIndex == 0) ? this : new String(value, beginIndex, subLen); 1881 } 1882 1883 /** 1884 * Returns a new string that is a substring of this string. The 1885 * substring begins at the specified {@code beginIndex} and 1886 * extends to the character at index {@code endIndex - 1}. 1887 * Thus the length of the substring is {@code endIndex-beginIndex}. 1888 * <p> 1889 * Examples: 1890 * <blockquote><pre> 1891 * "hamburger".substring(4, 8) returns "urge" 1892 * "smiles".substring(1, 5) returns "mile" 1893 * </pre></blockquote> 1894 * 1895 * @param beginIndex the beginning index, inclusive. 1896 * @param endIndex the ending index, exclusive. 1897 * @return the specified substring. 1898 * @exception IndexOutOfBoundsException if the 1899 * {@code beginIndex} is negative, or 1900 * {@code endIndex} is larger than the length of 1901 * this {@code String} object, or 1902 * {@code beginIndex} is larger than 1903 * {@code endIndex}. 1904 */ 1905 public String substring(int beginIndex, int endIndex) { 1906 if (beginIndex < 0) { 1907 throw new StringIndexOutOfBoundsException(beginIndex); 1908 } 1909 if (endIndex > value.length) { 1910 throw new StringIndexOutOfBoundsException(endIndex); 1911 } 1912 int subLen = endIndex - beginIndex; 1913 if (subLen < 0) { 1914 throw new StringIndexOutOfBoundsException(subLen); 1915 } 1916 return ((beginIndex == 0) && (endIndex == value.length)) ? this 1917 : new String(value, beginIndex, subLen); 1918 } 1919 1920 /** 1921 * Returns a new character sequence that is a subsequence of this sequence. 1922 * 1923 * <p> An invocation of this method of the form 1924 * 1925 * <blockquote><pre> 1926 * str.subSequence(begin, end)</pre></blockquote> 1927 * 1928 * behaves in exactly the same way as the invocation 1929 * 1930 * <blockquote><pre> 1931 * str.substring(begin, end)</pre></blockquote> 1932 * 1933 * This method is defined so that the <tt>String</tt> class can implement 1934 * the {@link CharSequence} interface. </p> 1935 * 1936 * @param beginIndex the begin index, inclusive. 1937 * @param endIndex the end index, exclusive. 1938 * @return the specified subsequence. 1939 * 1940 * @throws IndexOutOfBoundsException 1941 * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative, 1942 * if <tt>endIndex</tt> is greater than <tt>length()</tt>, 1943 * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt> 1944 * 1945 * @since 1.4 1946 * @spec JSR-51 1947 */ 1948 public CharSequence subSequence(int beginIndex, int endIndex) { 1949 return this.substring(beginIndex, endIndex); 1950 } 1951 1952 /** 1953 * Concatenates the specified string to the end of this string. 1954 * <p> 1955 * If the length of the argument string is {@code 0}, then this 1956 * {@code String} object is returned. Otherwise, a new 1957 * {@code String} object is created, representing a character 1958 * sequence that is the concatenation of the character sequence 1959 * represented by this {@code String} object and the character 1960 * sequence represented by the argument string.<p> 1961 * Examples: 1962 * <blockquote><pre> 1963 * "cares".concat("s") returns "caress" 1964 * "to".concat("get").concat("her") returns "together" 1965 * </pre></blockquote> 1966 * 1967 * @param str the {@code String} that is concatenated to the end 1968 * of this {@code String}. 1969 * @return a string that represents the concatenation of this object's 1970 * characters followed by the string argument's characters. 1971 */ 1972 public String concat(String str) { 1973 int otherLen = str.length(); 1974 if (otherLen == 0) { 1975 return this; 1976 } 1977 int len = value.length; 1978 char buf[] = Arrays.copyOf(value, len + otherLen); 1979 str.getChars(buf, len); 1980 return new String(buf, true); 1981 } 1982 1983 /** 1984 * Returns a new string resulting from replacing all occurrences of 1985 * {@code oldChar} in this string with {@code newChar}. 1986 * <p> 1987 * If the character {@code oldChar} does not occur in the 1988 * character sequence represented by this {@code String} object, 1989 * then a reference to this {@code String} object is returned. 1990 * Otherwise, a new {@code String} object is created that 1991 * represents a character sequence identical to the character sequence 1992 * represented by this {@code String} object, except that every 1993 * occurrence of {@code oldChar} is replaced by an occurrence 1994 * of {@code newChar}. 1995 * <p> 1996 * Examples: 1997 * <blockquote><pre> 1998 * "mesquite in your cellar".replace('e', 'o') 1999 * returns "mosquito in your collar" 2000 * "the war of baronets".replace('r', 'y') 2001 * returns "the way of bayonets" 2002 * "sparring with a purple porpoise".replace('p', 't') 2003 * returns "starring with a turtle tortoise" 2004 * "JonL".replace('q', 'x') returns "JonL" (no change) 2005 * </pre></blockquote> 2006 * 2007 * @param oldChar the old character. 2008 * @param newChar the new character. 2009 * @return a string derived from this string by replacing every 2010 * occurrence of {@code oldChar} with {@code newChar}. 2011 */ 2012 public String replace(char oldChar, char newChar) { 2013 if (oldChar != newChar) { 2014 int len = value.length; 2015 int i = -1; 2016 char[] val = value; /* avoid getfield opcode */ 2017 2018 while (++i < len) { 2019 if (val[i] == oldChar) { 2020 break; 2021 } 2022 } 2023 if (i < len) { 2024 char buf[] = new char[len]; 2025 for (int j = 0; j < i; j++) { 2026 buf[j] = val[j]; 2027 } 2028 while (i < len) { 2029 char c = val[i]; 2030 buf[i] = (c == oldChar) ? newChar : c; 2031 i++; 2032 } 2033 return new String(buf, true); 2034 } 2035 } 2036 return this; 2037 } 2038 2039 /** 2040 * Tells whether or not this string matches the given <a 2041 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2042 * 2043 * <p> An invocation of this method of the form 2044 * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the 2045 * same result as the expression 2046 * 2047 * <blockquote><tt> {@link java.util.regex.Pattern}.{@link 2048 * java.util.regex.Pattern#matches(String,CharSequence) 2049 * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote> 2050 * 2051 * @param regex 2052 * the regular expression to which this string is to be matched 2053 * 2054 * @return <tt>true</tt> if, and only if, this string matches the 2055 * given regular expression 2056 * 2057 * @throws PatternSyntaxException 2058 * if the regular expression's syntax is invalid 2059 * 2060 * @see java.util.regex.Pattern 2061 * 2062 * @since 1.4 2063 * @spec JSR-51 2064 */ 2065 public boolean matches(String regex) { 2066 return Pattern.matches(regex, this); 2067 } 2068 2069 /** 2070 * Returns true if and only if this string contains the specified 2071 * sequence of char values. 2072 * 2073 * @param s the sequence to search for 2074 * @return true if this string contains {@code s}, false otherwise 2075 * @throws NullPointerException if {@code s} is {@code null} 2076 * @since 1.5 2077 */ 2078 public boolean contains(CharSequence s) { 2079 return indexOf(s.toString()) > -1; 2080 } 2081 2082 /** 2083 * Replaces the first substring of this string that matches the given <a 2084 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2085 * given replacement. 2086 * 2087 * <p> An invocation of this method of the form 2088 * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt> 2089 * yields exactly the same result as the expression 2090 * 2091 * <blockquote><tt> 2092 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile 2093 * compile}(</tt><i>regex</i><tt>).{@link 2094 * java.util.regex.Pattern#matcher(java.lang.CharSequence) 2095 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst 2096 * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote> 2097 * 2098 *<p> 2099 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the 2100 * replacement string may cause the results to be different than if it were 2101 * being treated as a literal replacement string; see 2102 * {@link java.util.regex.Matcher#replaceFirst}. 2103 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2104 * meaning of these characters, if desired. 2105 * 2106 * @param regex 2107 * the regular expression to which this string is to be matched 2108 * @param replacement 2109 * the string to be substituted for the first match 2110 * 2111 * @return The resulting <tt>String</tt> 2112 * 2113 * @throws PatternSyntaxException 2114 * if the regular expression's syntax is invalid 2115 * 2116 * @see java.util.regex.Pattern 2117 * 2118 * @since 1.4 2119 * @spec JSR-51 2120 */ 2121 public String replaceFirst(String regex, String replacement) { 2122 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2123 } 2124 2125 /** 2126 * Replaces each substring of this string that matches the given <a 2127 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2128 * given replacement. 2129 * 2130 * <p> An invocation of this method of the form 2131 * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt> 2132 * yields exactly the same result as the expression 2133 * 2134 * <blockquote><tt> 2135 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile 2136 * compile}(</tt><i>regex</i><tt>).{@link 2137 * java.util.regex.Pattern#matcher(java.lang.CharSequence) 2138 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll 2139 * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote> 2140 * 2141 *<p> 2142 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the 2143 * replacement string may cause the results to be different than if it were 2144 * being treated as a literal replacement string; see 2145 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2146 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2147 * meaning of these characters, if desired. 2148 * 2149 * @param regex 2150 * the regular expression to which this string is to be matched 2151 * @param replacement 2152 * the string to be substituted for each match 2153 * 2154 * @return The resulting <tt>String</tt> 2155 * 2156 * @throws PatternSyntaxException 2157 * if the regular expression's syntax is invalid 2158 * 2159 * @see java.util.regex.Pattern 2160 * 2161 * @since 1.4 2162 * @spec JSR-51 2163 */ 2164 public String replaceAll(String regex, String replacement) { 2165 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2166 } 2167 2168 /** 2169 * Replaces each substring of this string that matches the literal target 2170 * sequence with the specified literal replacement sequence. The 2171 * replacement proceeds from the beginning of the string to the end, for 2172 * example, replacing "aa" with "b" in the string "aaa" will result in 2173 * "ba" rather than "ab". 2174 * 2175 * @param target The sequence of char values to be replaced 2176 * @param replacement The replacement sequence of char values 2177 * @return The resulting string 2178 * @throws NullPointerException if {@code target} or 2179 * {@code replacement} is {@code null}. 2180 * @since 1.5 2181 */ 2182 public String replace(CharSequence target, CharSequence replacement) { 2183 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher( 2184 this).replaceAll(Matcher.quoteReplacement(replacement.toString())); 2185 } 2186 2187 /** 2188 * Splits this string around matches of the given 2189 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2190 * 2191 * <p> The array returned by this method contains each substring of this 2192 * string that is terminated by another substring that matches the given 2193 * expression or is terminated by the end of the string. The substrings in 2194 * the array are in the order in which they occur in this string. If the 2195 * expression does not match any part of the input then the resulting array 2196 * has just one element, namely this string. 2197 * 2198 * <p> The <tt>limit</tt> parameter controls the number of times the 2199 * pattern is applied and therefore affects the length of the resulting 2200 * array. If the limit <i>n</i> is greater than zero then the pattern 2201 * will be applied at most <i>n</i> - 1 times, the array's 2202 * length will be no greater than <i>n</i>, and the array's last entry 2203 * will contain all input beyond the last matched delimiter. If <i>n</i> 2204 * is non-positive then the pattern will be applied as many times as 2205 * possible and the array can have any length. If <i>n</i> is zero then 2206 * the pattern will be applied as many times as possible, the array can 2207 * have any length, and trailing empty strings will be discarded. 2208 * 2209 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the 2210 * following results with these parameters: 2211 * 2212 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2213 * <tr> 2214 * <th>Regex</th> 2215 * <th>Limit</th> 2216 * <th>Result</th> 2217 * </tr> 2218 * <tr><td align=center>:</td> 2219 * <td align=center>2</td> 2220 * <td><tt>{ "boo", "and:foo" }</tt></td></tr> 2221 * <tr><td align=center>:</td> 2222 * <td align=center>5</td> 2223 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> 2224 * <tr><td align=center>:</td> 2225 * <td align=center>-2</td> 2226 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> 2227 * <tr><td align=center>o</td> 2228 * <td align=center>5</td> 2229 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr> 2230 * <tr><td align=center>o</td> 2231 * <td align=center>-2</td> 2232 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr> 2233 * <tr><td align=center>o</td> 2234 * <td align=center>0</td> 2235 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr> 2236 * </table></blockquote> 2237 * 2238 * <p> An invocation of this method of the form 2239 * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt> 2240 * yields the same result as the expression 2241 * 2242 * <blockquote> 2243 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile 2244 * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link 2245 * java.util.regex.Pattern#split(java.lang.CharSequence,int) 2246 * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt> 2247 * </blockquote> 2248 * 2249 * 2250 * @param regex 2251 * the delimiting regular expression 2252 * 2253 * @param limit 2254 * the result threshold, as described above 2255 * 2256 * @return the array of strings computed by splitting this string 2257 * around matches of the given regular expression 2258 * 2259 * @throws PatternSyntaxException 2260 * if the regular expression's syntax is invalid 2261 * 2262 * @see java.util.regex.Pattern 2263 * 2264 * @since 1.4 2265 * @spec JSR-51 2266 */ 2267 public String[] split(String regex, int limit) { 2268 /* fastpath if the regex is a 2269 (1)one-char String and this character is not one of the 2270 RegEx's meta characters ".$|()[{^?*+\\", or 2271 (2)two-char String and the first char is the backslash and 2272 the second is not the ascii digit or ascii letter. 2273 */ 2274 char ch = 0; 2275 if (((regex.value.length == 1 && 2276 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2277 (regex.length() == 2 && 2278 regex.charAt(0) == '\\' && 2279 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2280 ((ch-'a')|('z'-ch)) < 0 && 2281 ((ch-'A')|('Z'-ch)) < 0)) && 2282 (ch < Character.MIN_HIGH_SURROGATE || 2283 ch > Character.MAX_LOW_SURROGATE)) 2284 { 2285 int off = 0; 2286 int next = 0; 2287 boolean limited = limit > 0; 2288 ArrayList<String> list = new ArrayList<>(); 2289 while ((next = indexOf(ch, off)) != -1) { 2290 if (!limited || list.size() < limit - 1) { 2291 list.add(substring(off, next)); 2292 off = next + 1; 2293 } else { // last one 2294 //assert (list.size() == limit - 1); 2295 list.add(substring(off, value.length)); 2296 off = value.length; 2297 break; 2298 } 2299 } 2300 // If no match was found, return this 2301 if (off == 0) 2302 return new String[]{this}; 2303 2304 // Add remaining segment 2305 if (!limited || list.size() < limit) 2306 list.add(substring(off, value.length)); 2307 2308 // Construct result 2309 int resultSize = list.size(); 2310 if (limit == 0) 2311 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) 2312 resultSize--; 2313 String[] result = new String[resultSize]; 2314 return list.subList(0, resultSize).toArray(result); 2315 } 2316 return Pattern.compile(regex).split(this, limit); 2317 } 2318 2319 /** 2320 * Splits this string around matches of the given <a 2321 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2322 * 2323 * <p> This method works as if by invoking the two-argument {@link 2324 * #split(String, int) split} method with the given expression and a limit 2325 * argument of zero. Trailing empty strings are therefore not included in 2326 * the resulting array. 2327 * 2328 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the following 2329 * results with these expressions: 2330 * 2331 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2332 * <tr> 2333 * <th>Regex</th> 2334 * <th>Result</th> 2335 * </tr> 2336 * <tr><td align=center>:</td> 2337 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> 2338 * <tr><td align=center>o</td> 2339 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr> 2340 * </table></blockquote> 2341 * 2342 * 2343 * @param regex 2344 * the delimiting regular expression 2345 * 2346 * @return the array of strings computed by splitting this string 2347 * around matches of the given regular expression 2348 * 2349 * @throws PatternSyntaxException 2350 * if the regular expression's syntax is invalid 2351 * 2352 * @see java.util.regex.Pattern 2353 * 2354 * @since 1.4 2355 * @spec JSR-51 2356 */ 2357 public String[] split(String regex) { 2358 return split(regex, 0); 2359 } 2360 2361 /** 2362 * Converts all of the characters in this {@code String} to lower 2363 * case using the rules of the given {@code Locale}. Case mapping is based 2364 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2365 * class. Since case mappings are not always 1:1 char mappings, the resulting 2366 * {@code String} may be a different length than the original {@code String}. 2367 * <p> 2368 * Examples of lowercase mappings are in the following table: 2369 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2370 * <tr> 2371 * <th>Language Code of Locale</th> 2372 * <th>Upper Case</th> 2373 * <th>Lower Case</th> 2374 * <th>Description</th> 2375 * </tr> 2376 * <tr> 2377 * <td>tr (Turkish)</td> 2378 * <td>\u0130</td> 2379 * <td>\u0069</td> 2380 * <td>capital letter I with dot above -> small letter i</td> 2381 * </tr> 2382 * <tr> 2383 * <td>tr (Turkish)</td> 2384 * <td>\u0049</td> 2385 * <td>\u0131</td> 2386 * <td>capital letter I -> small letter dotless i </td> 2387 * </tr> 2388 * <tr> 2389 * <td>(all)</td> 2390 * <td>French Fries</td> 2391 * <td>french fries</td> 2392 * <td>lowercased all chars in String</td> 2393 * </tr> 2394 * <tr> 2395 * <td>(all)</td> 2396 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2397 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2398 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2399 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2400 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2401 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2402 * <td>lowercased all chars in String</td> 2403 * </tr> 2404 * </table> 2405 * 2406 * @param locale use the case transformation rules for this locale 2407 * @return the {@code String}, converted to lowercase. 2408 * @see java.lang.String#toLowerCase() 2409 * @see java.lang.String#toUpperCase() 2410 * @see java.lang.String#toUpperCase(Locale) 2411 * @since 1.1 2412 */ 2413 public String toLowerCase(Locale locale) { 2414 if (locale == null) { 2415 throw new NullPointerException(); 2416 } 2417 2418 int firstUpper; 2419 final int len = value.length; 2420 2421 /* Now check if there are any characters that need to be changed. */ 2422 scan: { 2423 for (firstUpper = 0 ; firstUpper < len; ) { 2424 char c = value[firstUpper]; 2425 if ((c >= Character.MIN_HIGH_SURROGATE) 2426 && (c <= Character.MAX_HIGH_SURROGATE)) { 2427 int supplChar = codePointAt(firstUpper); 2428 if (supplChar != Character.toLowerCase(supplChar)) { 2429 break scan; 2430 } 2431 firstUpper += Character.charCount(supplChar); 2432 } else { 2433 if (c != Character.toLowerCase(c)) { 2434 break scan; 2435 } 2436 firstUpper++; 2437 } 2438 } 2439 return this; 2440 } 2441 2442 char[] result = new char[len]; 2443 int resultOffset = 0; /* result may grow, so i+resultOffset 2444 * is the write location in result */ 2445 2446 /* Just copy the first few lowerCase characters. */ 2447 System.arraycopy(value, 0, result, 0, firstUpper); 2448 2449 String lang = locale.getLanguage(); 2450 boolean localeDependent = 2451 (lang == "tr" || lang == "az" || lang == "lt"); 2452 char[] lowerCharArray; 2453 int lowerChar; 2454 int srcChar; 2455 int srcCount; 2456 for (int i = firstUpper; i < len; i += srcCount) { 2457 srcChar = (int)value[i]; 2458 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE 2459 && (char)srcChar <= Character.MAX_HIGH_SURROGATE) { 2460 srcChar = codePointAt(i); 2461 srcCount = Character.charCount(srcChar); 2462 } else { 2463 srcCount = 1; 2464 } 2465 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA 2466 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale); 2467 } else if (srcChar == '\u0130') { // LATIN CAPITAL LETTER I DOT 2468 lowerChar = Character.ERROR; 2469 } else { 2470 lowerChar = Character.toLowerCase(srcChar); 2471 } 2472 if ((lowerChar == Character.ERROR) 2473 || (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) { 2474 if (lowerChar == Character.ERROR) { 2475 if (!localeDependent && srcChar == '\u0130') { 2476 lowerCharArray = 2477 ConditionalSpecialCasing.toLowerCaseCharArray(this, i, Locale.ENGLISH); 2478 } else { 2479 lowerCharArray = 2480 ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale); 2481 } 2482 } else if (srcCount == 2) { 2483 resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount; 2484 continue; 2485 } else { 2486 lowerCharArray = Character.toChars(lowerChar); 2487 } 2488 2489 /* Grow result if needed */ 2490 int mapLen = lowerCharArray.length; 2491 if (mapLen > srcCount) { 2492 char[] result2 = new char[result.length + mapLen - srcCount]; 2493 System.arraycopy(result, 0, result2, 0, i + resultOffset); 2494 result = result2; 2495 } 2496 for (int x = 0; x < mapLen; ++x) { 2497 result[i + resultOffset + x] = lowerCharArray[x]; 2498 } 2499 resultOffset += (mapLen - srcCount); 2500 } else { 2501 result[i + resultOffset] = (char)lowerChar; 2502 } 2503 } 2504 return new String(result, 0, len + resultOffset); 2505 } 2506 2507 /** 2508 * Converts all of the characters in this {@code String} to lower 2509 * case using the rules of the default locale. This is equivalent to calling 2510 * {@code toLowerCase(Locale.getDefault())}. 2511 * <p> 2512 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2513 * results if used for strings that are intended to be interpreted locale 2514 * independently. 2515 * Examples are programming language identifiers, protocol keys, and HTML 2516 * tags. 2517 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2518 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2519 * LATIN SMALL LETTER DOTLESS I character. 2520 * To obtain correct results for locale insensitive strings, use 2521 * {@code toLowerCase(Locale.ENGLISH)}. 2522 * <p> 2523 * @return the {@code String}, converted to lowercase. 2524 * @see java.lang.String#toLowerCase(Locale) 2525 */ 2526 public String toLowerCase() { 2527 return toLowerCase(Locale.getDefault()); 2528 } 2529 2530 /** 2531 * Converts all of the characters in this {@code String} to upper 2532 * case using the rules of the given {@code Locale}. Case mapping is based 2533 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2534 * class. Since case mappings are not always 1:1 char mappings, the resulting 2535 * {@code String} may be a different length than the original {@code String}. 2536 * <p> 2537 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2538 * <p> 2539 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2540 * <tr> 2541 * <th>Language Code of Locale</th> 2542 * <th>Lower Case</th> 2543 * <th>Upper Case</th> 2544 * <th>Description</th> 2545 * </tr> 2546 * <tr> 2547 * <td>tr (Turkish)</td> 2548 * <td>\u0069</td> 2549 * <td>\u0130</td> 2550 * <td>small letter i -> capital letter I with dot above</td> 2551 * </tr> 2552 * <tr> 2553 * <td>tr (Turkish)</td> 2554 * <td>\u0131</td> 2555 * <td>\u0049</td> 2556 * <td>small letter dotless i -> capital letter I</td> 2557 * </tr> 2558 * <tr> 2559 * <td>(all)</td> 2560 * <td>\u00df</td> 2561 * <td>\u0053 \u0053</td> 2562 * <td>small letter sharp s -> two letters: SS</td> 2563 * </tr> 2564 * <tr> 2565 * <td>(all)</td> 2566 * <td>Fahrvergnügen</td> 2567 * <td>FAHRVERGNÜGEN</td> 2568 * <td></td> 2569 * </tr> 2570 * </table> 2571 * @param locale use the case transformation rules for this locale 2572 * @return the {@code String}, converted to uppercase. 2573 * @see java.lang.String#toUpperCase() 2574 * @see java.lang.String#toLowerCase() 2575 * @see java.lang.String#toLowerCase(Locale) 2576 * @since 1.1 2577 */ 2578 public String toUpperCase(Locale locale) { 2579 if (locale == null) { 2580 throw new NullPointerException(); 2581 } 2582 2583 int firstLower; 2584 final int len = value.length; 2585 2586 /* Now check if there are any characters that need to be changed. */ 2587 scan: { 2588 for (firstLower = 0 ; firstLower < len; ) { 2589 int c = (int)value[firstLower]; 2590 int srcCount; 2591 if ((c >= Character.MIN_HIGH_SURROGATE) 2592 && (c <= Character.MAX_HIGH_SURROGATE)) { 2593 c = codePointAt(firstLower); 2594 srcCount = Character.charCount(c); 2595 } else { 2596 srcCount = 1; 2597 } 2598 int upperCaseChar = Character.toUpperCaseEx(c); 2599 if ((upperCaseChar == Character.ERROR) 2600 || (c != upperCaseChar)) { 2601 break scan; 2602 } 2603 firstLower += srcCount; 2604 } 2605 return this; 2606 } 2607 2608 char[] result = new char[len]; /* may grow */ 2609 int resultOffset = 0; /* result may grow, so i+resultOffset 2610 * is the write location in result */ 2611 2612 /* Just copy the first few upperCase characters. */ 2613 System.arraycopy(value, 0, result, 0, firstLower); 2614 2615 String lang = locale.getLanguage(); 2616 boolean localeDependent = 2617 (lang == "tr" || lang == "az" || lang == "lt"); 2618 char[] upperCharArray; 2619 int upperChar; 2620 int srcChar; 2621 int srcCount; 2622 for (int i = firstLower; i < len; i += srcCount) { 2623 srcChar = (int)value[i]; 2624 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE && 2625 (char)srcChar <= Character.MAX_HIGH_SURROGATE) { 2626 srcChar = codePointAt(i); 2627 srcCount = Character.charCount(srcChar); 2628 } else { 2629 srcCount = 1; 2630 } 2631 if (localeDependent) { 2632 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale); 2633 } else { 2634 upperChar = Character.toUpperCaseEx(srcChar); 2635 } 2636 if ((upperChar == Character.ERROR) 2637 || (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) { 2638 if (upperChar == Character.ERROR) { 2639 if (localeDependent) { 2640 upperCharArray = 2641 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale); 2642 } else { 2643 upperCharArray = Character.toUpperCaseCharArray(srcChar); 2644 } 2645 } else if (srcCount == 2) { 2646 resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount; 2647 continue; 2648 } else { 2649 upperCharArray = Character.toChars(upperChar); 2650 } 2651 2652 /* Grow result if needed */ 2653 int mapLen = upperCharArray.length; 2654 if (mapLen > srcCount) { 2655 char[] result2 = new char[result.length + mapLen - srcCount]; 2656 System.arraycopy(result, 0, result2, 0, i + resultOffset); 2657 result = result2; 2658 } 2659 for (int x = 0; x < mapLen; ++x) { 2660 result[i + resultOffset + x] = upperCharArray[x]; 2661 } 2662 resultOffset += (mapLen - srcCount); 2663 } else { 2664 result[i + resultOffset] = (char)upperChar; 2665 } 2666 } 2667 return new String(result, 0, len + resultOffset); 2668 } 2669 2670 /** 2671 * Converts all of the characters in this {@code String} to upper 2672 * case using the rules of the default locale. This method is equivalent to 2673 * {@code toUpperCase(Locale.getDefault())}. 2674 * <p> 2675 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2676 * results if used for strings that are intended to be interpreted locale 2677 * independently. 2678 * Examples are programming language identifiers, protocol keys, and HTML 2679 * tags. 2680 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2681 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2682 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2683 * To obtain correct results for locale insensitive strings, use 2684 * {@code toUpperCase(Locale.ENGLISH)}. 2685 * <p> 2686 * @return the {@code String}, converted to uppercase. 2687 * @see java.lang.String#toUpperCase(Locale) 2688 */ 2689 public String toUpperCase() { 2690 return toUpperCase(Locale.getDefault()); 2691 } 2692 2693 /** 2694 * Returns a copy of the string, with leading and trailing whitespace 2695 * omitted. 2696 * <p> 2697 * If this {@code String} object represents an empty character 2698 * sequence, or the first and last characters of character sequence 2699 * represented by this {@code String} object both have codes 2700 * greater than {@code '\u005Cu0020'} (the space character), then a 2701 * reference to this {@code String} object is returned. 2702 * <p> 2703 * Otherwise, if there is no character with a code greater than 2704 * {@code '\u005Cu0020'} in the string, then a new 2705 * {@code String} object representing an empty string is created 2706 * and returned. 2707 * <p> 2708 * Otherwise, let <i>k</i> be the index of the first character in the 2709 * string whose code is greater than {@code '\u005Cu0020'}, and let 2710 * <i>m</i> be the index of the last character in the string whose code 2711 * is greater than {@code '\u005Cu0020'}. A new {@code String} 2712 * object is created, representing the substring of this string that 2713 * begins with the character at index <i>k</i> and ends with the 2714 * character at index <i>m</i>-that is, the result of 2715 * <code>this.substring(<i>k</i>, <i>m</i>+1)</code>. 2716 * <p> 2717 * This method may be used to trim whitespace (as defined above) from 2718 * the beginning and end of a string. 2719 * 2720 * @return A copy of this string with leading and trailing white 2721 * space removed, or this string if it has no leading or 2722 * trailing white space. 2723 */ 2724 public String trim() { 2725 int len = value.length; 2726 int st = 0; 2727 char[] val = value; /* avoid getfield opcode */ 2728 2729 while ((st < len) && (val[st] <= ' ')) { 2730 st++; 2731 } 2732 while ((st < len) && (val[len - 1] <= ' ')) { 2733 len--; 2734 } 2735 return ((st > 0) || (len < value.length)) ? substring(st, len) : this; 2736 } 2737 2738 /** 2739 * This object (which is already a string!) is itself returned. 2740 * 2741 * @return the string itself. 2742 */ 2743 public String toString() { 2744 return this; 2745 } 2746 2747 /** 2748 * Converts this string to a new character array. 2749 * 2750 * @return a newly allocated character array whose length is the length 2751 * of this string and whose contents are initialized to contain 2752 * the character sequence represented by this string. 2753 */ 2754 public char[] toCharArray() { 2755 return Arrays.copyOf(value, value.length); 2756 } 2757 2758 /** 2759 * Returns a formatted string using the specified format string and 2760 * arguments. 2761 * 2762 * <p> The locale always used is the one returned by {@link 2763 * java.util.Locale#getDefault() Locale.getDefault()}. 2764 * 2765 * @param format 2766 * A <a href="../util/Formatter.html#syntax">format string</a> 2767 * 2768 * @param args 2769 * Arguments referenced by the format specifiers in the format 2770 * string. If there are more arguments than format specifiers, the 2771 * extra arguments are ignored. The number of arguments is 2772 * variable and may be zero. The maximum number of arguments is 2773 * limited by the maximum dimension of a Java array as defined by 2774 * <cite>The Java™ Virtual Machine Specification</cite>. 2775 * The behaviour on a 2776 * <tt>null</tt> argument depends on the <a 2777 * href="../util/Formatter.html#syntax">conversion</a>. 2778 * 2779 * @throws IllegalFormatException 2780 * If a format string contains an illegal syntax, a format 2781 * specifier that is incompatible with the given arguments, 2782 * insufficient arguments given the format string, or other 2783 * illegal conditions. For specification of all possible 2784 * formatting errors, see the <a 2785 * href="../util/Formatter.html#detail">Details</a> section of the 2786 * formatter class specification. 2787 * 2788 * @throws NullPointerException 2789 * If the <tt>format</tt> is <tt>null</tt> 2790 * 2791 * @return A formatted string 2792 * 2793 * @see java.util.Formatter 2794 * @since 1.5 2795 */ 2796 public static String format(String format, Object... args) { 2797 return new Formatter().format(format, args).toString(); 2798 } 2799 2800 /** 2801 * Returns a formatted string using the specified locale, format string, 2802 * and arguments. 2803 * 2804 * @param l 2805 * The {@linkplain java.util.Locale locale} to apply during 2806 * formatting. If <tt>l</tt> is <tt>null</tt> then no localization 2807 * is applied. 2808 * 2809 * @param format 2810 * A <a href="../util/Formatter.html#syntax">format string</a> 2811 * 2812 * @param args 2813 * Arguments referenced by the format specifiers in the format 2814 * string. If there are more arguments than format specifiers, the 2815 * extra arguments are ignored. The number of arguments is 2816 * variable and may be zero. The maximum number of arguments is 2817 * limited by the maximum dimension of a Java array as defined by 2818 * <cite>The Java™ Virtual Machine Specification</cite>. 2819 * The behaviour on a 2820 * <tt>null</tt> argument depends on the <a 2821 * href="../util/Formatter.html#syntax">conversion</a>. 2822 * 2823 * @throws IllegalFormatException 2824 * If a format string contains an illegal syntax, a format 2825 * specifier that is incompatible with the given arguments, 2826 * insufficient arguments given the format string, or other 2827 * illegal conditions. For specification of all possible 2828 * formatting errors, see the <a 2829 * href="../util/Formatter.html#detail">Details</a> section of the 2830 * formatter class specification 2831 * 2832 * @throws NullPointerException 2833 * If the <tt>format</tt> is <tt>null</tt> 2834 * 2835 * @return A formatted string 2836 * 2837 * @see java.util.Formatter 2838 * @since 1.5 2839 */ 2840 public static String format(Locale l, String format, Object... args) { 2841 return new Formatter(l).format(format, args).toString(); 2842 } 2843 2844 /** 2845 * Returns the string representation of the {@code Object} argument. 2846 * 2847 * @param obj an {@code Object}. 2848 * @return if the argument is {@code null}, then a string equal to 2849 * {@code "null"}; otherwise, the value of 2850 * {@code obj.toString()} is returned. 2851 * @see java.lang.Object#toString() 2852 */ 2853 public static String valueOf(Object obj) { 2854 return (obj == null) ? "null" : obj.toString(); 2855 } 2856 2857 /** 2858 * Returns the string representation of the {@code char} array 2859 * argument. The contents of the character array are copied; subsequent 2860 * modification of the character array does not affect the newly 2861 * created string. 2862 * 2863 * @param data a {@code char} array. 2864 * @return a newly allocated string representing the same sequence of 2865 * characters contained in the character array argument. 2866 */ 2867 public static String valueOf(char data[]) { 2868 return new String(data); 2869 } 2870 2871 /** 2872 * Returns the string representation of a specific subarray of the 2873 * {@code char} array argument. 2874 * <p> 2875 * The {@code offset} argument is the index of the first 2876 * character of the subarray. The {@code count} argument 2877 * specifies the length of the subarray. The contents of the subarray 2878 * are copied; subsequent modification of the character array does not 2879 * affect the newly created string. 2880 * 2881 * @param data the character array. 2882 * @param offset the initial offset into the value of the 2883 * {@code String}. 2884 * @param count the length of the value of the {@code String}. 2885 * @return a string representing the sequence of characters contained 2886 * in the subarray of the character array argument. 2887 * @exception IndexOutOfBoundsException if {@code offset} is 2888 * negative, or {@code count} is negative, or 2889 * {@code offset+count} is larger than 2890 * {@code data.length}. 2891 */ 2892 public static String valueOf(char data[], int offset, int count) { 2893 return new String(data, offset, count); 2894 } 2895 2896 /** 2897 * Returns a String that represents the character sequence in the 2898 * array specified. 2899 * 2900 * @param data the character array. 2901 * @param offset initial offset of the subarray. 2902 * @param count length of the subarray. 2903 * @return a {@code String} that contains the characters of the 2904 * specified subarray of the character array. 2905 */ 2906 public static String copyValueOf(char data[], int offset, int count) { 2907 // All public String constructors now copy the data. 2908 return new String(data, offset, count); 2909 } 2910 2911 /** 2912 * Returns a String that represents the character sequence in the 2913 * array specified. 2914 * 2915 * @param data the character array. 2916 * @return a {@code String} that contains the characters of the 2917 * character array. 2918 */ 2919 public static String copyValueOf(char data[]) { 2920 return copyValueOf(data, 0, data.length); 2921 } 2922 2923 /** 2924 * Returns the string representation of the {@code boolean} argument. 2925 * 2926 * @param b a {@code boolean}. 2927 * @return if the argument is {@code true}, a string equal to 2928 * {@code "true"} is returned; otherwise, a string equal to 2929 * {@code "false"} is returned. 2930 */ 2931 public static String valueOf(boolean b) { 2932 return b ? "true" : "false"; 2933 } 2934 2935 /** 2936 * Returns the string representation of the {@code char} 2937 * argument. 2938 * 2939 * @param c a {@code char}. 2940 * @return a string of length {@code 1} containing 2941 * as its single character the argument {@code c}. 2942 */ 2943 public static String valueOf(char c) { 2944 char data[] = {c}; 2945 return new String(data, true); 2946 } 2947 2948 /** 2949 * Returns the string representation of the {@code int} argument. 2950 * <p> 2951 * The representation is exactly the one returned by the 2952 * {@code Integer.toString} method of one argument. 2953 * 2954 * @param i an {@code int}. 2955 * @return a string representation of the {@code int} argument. 2956 * @see java.lang.Integer#toString(int, int) 2957 */ 2958 public static String valueOf(int i) { 2959 return Integer.toString(i); 2960 } 2961 2962 /** 2963 * Returns the string representation of the {@code long} argument. 2964 * <p> 2965 * The representation is exactly the one returned by the 2966 * {@code Long.toString} method of one argument. 2967 * 2968 * @param l a {@code long}. 2969 * @return a string representation of the {@code long} argument. 2970 * @see java.lang.Long#toString(long) 2971 */ 2972 public static String valueOf(long l) { 2973 return Long.toString(l); 2974 } 2975 2976 /** 2977 * Returns the string representation of the {@code float} argument. 2978 * <p> 2979 * The representation is exactly the one returned by the 2980 * {@code Float.toString} method of one argument. 2981 * 2982 * @param f a {@code float}. 2983 * @return a string representation of the {@code float} argument. 2984 * @see java.lang.Float#toString(float) 2985 */ 2986 public static String valueOf(float f) { 2987 return Float.toString(f); 2988 } 2989 2990 /** 2991 * Returns the string representation of the {@code double} argument. 2992 * <p> 2993 * The representation is exactly the one returned by the 2994 * {@code Double.toString} method of one argument. 2995 * 2996 * @param d a {@code double}. 2997 * @return a string representation of the {@code double} argument. 2998 * @see java.lang.Double#toString(double) 2999 */ 3000 public static String valueOf(double d) { 3001 return Double.toString(d); 3002 } 3003 3004 /** 3005 * Returns a canonical representation for the string object. 3006 * <p> 3007 * A pool of strings, initially empty, is maintained privately by the 3008 * class {@code String}. 3009 * <p> 3010 * When the intern method is invoked, if the pool already contains a 3011 * string equal to this {@code String} object as determined by 3012 * the {@link #equals(Object)} method, then the string from the pool is 3013 * returned. Otherwise, this {@code String} object is added to the 3014 * pool and a reference to this {@code String} object is returned. 3015 * <p> 3016 * It follows that for any two strings {@code s} and {@code t}, 3017 * {@code s.intern() == t.intern()} is {@code true} 3018 * if and only if {@code s.equals(t)} is {@code true}. 3019 * <p> 3020 * All literal strings and string-valued constant expressions are 3021 * interned. String literals are defined in section 3.10.5 of the 3022 * <cite>The Java™ Language Specification</cite>. 3023 * 3024 * @return a string that has the same contents as this string, but is 3025 * guaranteed to be from a pool of unique strings. 3026 */ 3027 public native String intern(); 3028 }