1 /* 2 * Copyright (c) 1994, 2014, Oracle and/or its affiliates. All rights reserved. 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4 * 5 * This code is free software; you can redistribute it and/or modify it 6 * under the terms of the GNU General Public License version 2 only, as 7 * published by the Free Software Foundation. Oracle designates this 8 * particular file as subject to the "Classpath" exception as provided 9 * by Oracle in the LICENSE file that accompanied this code. 10 * 11 * This code is distributed in the hope that it will be useful, but WITHOUT 12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 14 * version 2 for more details (a copy is included in the LICENSE file that 15 * accompanied this code). 16 * 17 * You should have received a copy of the GNU General Public License version 18 * 2 along with this work; if not, write to the Free Software Foundation, 19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 20 * 21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 22 * or visit www.oracle.com if you need additional information or have any 23 * questions. 24 */ 25 26 package java.lang; 27 28 import java.io.ObjectStreamField; 29 import java.io.UnsupportedEncodingException; 30 import java.nio.charset.Charset; 31 import java.util.ArrayList; 32 import java.util.Arrays; 33 import java.util.Comparator; 34 import java.util.Formatter; 35 import java.util.Locale; 36 import java.util.Objects; 37 import java.util.StringJoiner; 38 import java.util.regex.Matcher; 39 import java.util.regex.Pattern; 40 import java.util.regex.PatternSyntaxException; 41 42 /** 43 * The {@code String} class represents character strings. All 44 * string literals in Java programs, such as {@code "abc"}, are 45 * implemented as instances of this class. 46 * <p> 47 * Strings are constant; their values cannot be changed after they 48 * are created. String buffers support mutable strings. 49 * Because String objects are immutable they can be shared. For example: 50 * <blockquote><pre> 51 * String str = "abc"; 52 * </pre></blockquote><p> 53 * is equivalent to: 54 * <blockquote><pre> 55 * char data[] = {'a', 'b', 'c'}; 56 * String str = new String(data); 57 * </pre></blockquote><p> 58 * Here are some more examples of how strings can be used: 59 * <blockquote><pre> 60 * System.out.println("abc"); 61 * String cde = "cde"; 62 * System.out.println("abc" + cde); 63 * String c = "abc".substring(2,3); 64 * String d = cde.substring(1, 2); 65 * </pre></blockquote> 66 * <p> 67 * The class {@code String} includes methods for examining 68 * individual characters of the sequence, for comparing strings, for 69 * searching strings, for extracting substrings, and for creating a 70 * copy of a string with all characters translated to uppercase or to 71 * lowercase. Case mapping is based on the Unicode Standard version 72 * specified by the {@link java.lang.Character Character} class. 73 * <p> 74 * The Java language provides special support for the string 75 * concatenation operator ( + ), and for conversion of 76 * other objects to strings. String concatenation is implemented 77 * through the {@code StringBuilder}(or {@code StringBuffer}) 78 * class and its {@code append} method. 79 * String conversions are implemented through the method 80 * {@code toString}, defined by {@code Object} and 81 * inherited by all classes in Java. For additional information on 82 * string concatenation and conversion, see Gosling, Joy, and Steele, 83 * <i>The Java Language Specification</i>. 84 * 85 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor 86 * or method in this class will cause a {@link NullPointerException} to be 87 * thrown. 88 * 89 * <p>A {@code String} represents a string in the UTF-16 format 90 * in which <em>supplementary characters</em> are represented by <em>surrogate 91 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 92 * Character Representations</a> in the {@code Character} class for 93 * more information). 94 * Index values refer to {@code char} code units, so a supplementary 95 * character uses two positions in a {@code String}. 96 * <p>The {@code String} class provides methods for dealing with 97 * Unicode code points (i.e., characters), in addition to those for 98 * dealing with Unicode code units (i.e., {@code char} values). 99 * 100 * @author Lee Boynton 101 * @author Arthur van Hoff 102 * @author Martin Buchholz 103 * @author Ulf Zibis 104 * @see java.lang.Object#toString() 105 * @see java.lang.StringBuffer 106 * @see java.lang.StringBuilder 107 * @see java.nio.charset.Charset 108 * @since 1.0 109 */ 110 111 public final class String 112 implements java.io.Serializable, Comparable<String>, CharSequence { 113 /** The value is used for character storage. */ 114 private final char value[]; 115 116 /** Cache the hash code for the string */ 117 private int hash; // Default to 0 118 119 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 120 private static final long serialVersionUID = -6849794470754667710L; 121 122 /** 123 * Class String is special cased within the Serialization Stream Protocol. 124 * 125 * A String instance is written into an ObjectOutputStream according to 126 * <a href="{@docRoot}/../platform/serialization/spec/output.html"> 127 * Object Serialization Specification, Section 6.2, "Stream Elements"</a> 128 */ 129 private static final ObjectStreamField[] serialPersistentFields = 130 new ObjectStreamField[0]; 131 132 /** 133 * a shared instance of the string value for empty strings. 134 */ 135 private static final char[] EMPTY_STRING_VALUE = new char[0]; 136 137 /** 138 * Initializes a newly created {@code String} object so that it represents 139 * an empty character sequence. Note that use of this constructor is 140 * unnecessary since Strings are immutable. 141 */ 142 public String() { 143 this.value = EMPTY_STRING_VALUE; 144 } 145 146 /** 147 * Initializes a newly created {@code String} object so that it represents 148 * the same sequence of characters as the argument; in other words, the 149 * newly created string is a copy of the argument string. Unless an 150 * explicit copy of {@code original} is needed, use of this constructor is 151 * unnecessary since Strings are immutable. 152 * 153 * @param original 154 * A {@code String} 155 */ 156 public String(String original) { 157 this.value = original.value; 158 this.hash = original.hash; 159 } 160 161 /** 162 * Allocates a new {@code String} so that it represents the sequence of 163 * characters currently contained in the character array argument. The 164 * contents of the character array are copied; subsequent modification of 165 * the character array does not affect the newly created string. 166 * 167 * @param value 168 * The initial value of the string 169 */ 170 public String(char value[]) { 171 this.value = Arrays.copyOf(value, value.length); 172 } 173 174 /** 175 * Allocates a new {@code String} that contains characters from a subarray 176 * of the character array argument. The {@code offset} argument is the 177 * index of the first character of the subarray and the {@code count} 178 * argument specifies the length of the subarray. The contents of the 179 * subarray are copied; subsequent modification of the character array does 180 * not affect the newly created string. 181 * 182 * @param value 183 * Array that is the source of characters 184 * 185 * @param offset 186 * The initial offset 187 * 188 * @param count 189 * The length 190 * 191 * @throws IndexOutOfBoundsException 192 * If {@code offset} is negative, {@code count} is negative, or 193 * {@code offset} is greater than {@code value.length - count} 194 */ 195 public String(char value[], int offset, int count) { 196 if (offset < 0) { 197 throw new StringIndexOutOfBoundsException(offset); 198 } 199 if (count < 0) { 200 throw new StringIndexOutOfBoundsException(count); 201 } 202 // Note: offset or count might be near -1>>>1. 203 if (offset > value.length - count) { 204 throw new StringIndexOutOfBoundsException(offset + count); 205 } 206 this.value = Arrays.copyOfRange(value, offset, offset+count); 207 } 208 209 /** 210 * Allocates a new {@code String} that contains characters from a subarray 211 * of the <a href="Character.html#unicode">Unicode code point</a> array 212 * argument. The {@code offset} argument is the index of the first code 213 * point of the subarray and the {@code count} argument specifies the 214 * length of the subarray. The contents of the subarray are converted to 215 * {@code char}s; subsequent modification of the {@code int} array does not 216 * affect the newly created string. 217 * 218 * @param codePoints 219 * Array that is the source of Unicode code points 220 * 221 * @param offset 222 * The initial offset 223 * 224 * @param count 225 * The length 226 * 227 * @throws IllegalArgumentException 228 * If any invalid Unicode code point is found in {@code 229 * codePoints} 230 * 231 * @throws IndexOutOfBoundsException 232 * If {@code offset} is negative, {@code count} is negative, or 233 * {@code offset} is greater than {@code codePoints.length - count} 234 * 235 * @since 1.5 236 */ 237 public String(int[] codePoints, int offset, int count) { 238 if (offset < 0) { 239 throw new StringIndexOutOfBoundsException(offset); 240 } 241 if (count < 0) { 242 throw new StringIndexOutOfBoundsException(count); 243 } 244 // Note: offset or count might be near -1>>>1. 245 if (offset > codePoints.length - count) { 246 throw new StringIndexOutOfBoundsException(offset + count); 247 } 248 249 final int end = offset + count; 250 251 // Pass 1: Compute precise size of char[] 252 int n = count; 253 for (int i = offset; i < end; i++) { 254 int c = codePoints[i]; 255 if (Character.isBmpCodePoint(c)) 256 continue; 257 else if (Character.isValidCodePoint(c)) 258 n++; 259 else throw new IllegalArgumentException(Integer.toString(c)); 260 } 261 262 // Pass 2: Allocate and fill in char[] 263 final char[] v = new char[n]; 264 265 for (int i = offset, j = 0; i < end; i++, j++) { 266 int c = codePoints[i]; 267 if (Character.isBmpCodePoint(c)) 268 v[j] = (char)c; 269 else 270 Character.toSurrogates(c, v, j++); 271 } 272 273 this.value = v; 274 } 275 276 /** 277 * Allocates a new {@code String} constructed from a subarray of an array 278 * of 8-bit integer values. 279 * 280 * <p> The {@code offset} argument is the index of the first byte of the 281 * subarray, and the {@code count} argument specifies the length of the 282 * subarray. 283 * 284 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 285 * specified in the method above. 286 * 287 * @deprecated This method does not properly convert bytes into characters. 288 * As of JDK 1.1, the preferred way to do this is via the 289 * {@code String} constructors that take a {@link 290 * java.nio.charset.Charset}, charset name, or that use the platform's 291 * default charset. 292 * 293 * @param ascii 294 * The bytes to be converted to characters 295 * 296 * @param hibyte 297 * The top 8 bits of each 16-bit Unicode code unit 298 * 299 * @param offset 300 * The initial offset 301 * @param count 302 * The length 303 * 304 * @throws IndexOutOfBoundsException 305 * If {@code offset} is negative, {@code count} is negative, or 306 * {@code offset} is greater than {@code ascii.length - count} 307 * 308 * @see #String(byte[], int) 309 * @see #String(byte[], int, int, java.lang.String) 310 * @see #String(byte[], int, int, java.nio.charset.Charset) 311 * @see #String(byte[], int, int) 312 * @see #String(byte[], java.lang.String) 313 * @see #String(byte[], java.nio.charset.Charset) 314 * @see #String(byte[]) 315 */ 316 @Deprecated 317 public String(byte ascii[], int hibyte, int offset, int count) { 318 checkBounds(ascii, offset, count); 319 char value[] = new char[count]; 320 321 if (hibyte == 0) { 322 for (int i = count; i-- > 0;) { 323 value[i] = (char)(ascii[i + offset] & 0xff); 324 } 325 } else { 326 hibyte <<= 8; 327 for (int i = count; i-- > 0;) { 328 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff)); 329 } 330 } 331 this.value = value; 332 } 333 334 /** 335 * Allocates a new {@code String} containing characters constructed from 336 * an array of 8-bit integer values. Each character <i>c</i>in the 337 * resulting string is constructed from the corresponding component 338 * <i>b</i> in the byte array such that: 339 * 340 * <blockquote><pre> 341 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 342 * | (<b><i>b</i></b> & 0xff)) 343 * </pre></blockquote> 344 * 345 * @deprecated This method does not properly convert bytes into 346 * characters. As of JDK 1.1, the preferred way to do this is via the 347 * {@code String} constructors that take a {@link 348 * java.nio.charset.Charset}, charset name, or that use the platform's 349 * default charset. 350 * 351 * @param ascii 352 * The bytes to be converted to characters 353 * 354 * @param hibyte 355 * The top 8 bits of each 16-bit Unicode code unit 356 * 357 * @see #String(byte[], int, int, java.lang.String) 358 * @see #String(byte[], int, int, java.nio.charset.Charset) 359 * @see #String(byte[], int, int) 360 * @see #String(byte[], java.lang.String) 361 * @see #String(byte[], java.nio.charset.Charset) 362 * @see #String(byte[]) 363 */ 364 @Deprecated 365 public String(byte ascii[], int hibyte) { 366 this(ascii, hibyte, 0, ascii.length); 367 } 368 369 /* Common private utility method used to bounds check the byte array 370 * and requested offset & length values used by the String(byte[],..) 371 * constructors. 372 */ 373 private static void checkBounds(byte[] bytes, int offset, int length) { 374 if (length < 0) 375 throw new StringIndexOutOfBoundsException(length); 376 if (offset < 0) 377 throw new StringIndexOutOfBoundsException(offset); 378 if (offset > bytes.length - length) 379 throw new StringIndexOutOfBoundsException(offset + length); 380 } 381 382 /** 383 * Constructs a new {@code String} by decoding the specified subarray of 384 * bytes using the specified charset. The length of the new {@code String} 385 * is a function of the charset, and hence may not be equal to the length 386 * of the subarray. 387 * 388 * <p> The behavior of this constructor when the given bytes are not valid 389 * in the given charset is unspecified. The {@link 390 * java.nio.charset.CharsetDecoder} class should be used when more control 391 * over the decoding process is required. 392 * 393 * @param bytes 394 * The bytes to be decoded into characters 395 * 396 * @param offset 397 * The index of the first byte to decode 398 * 399 * @param length 400 * The number of bytes to decode 401 402 * @param charsetName 403 * The name of a supported {@linkplain java.nio.charset.Charset 404 * charset} 405 * 406 * @throws UnsupportedEncodingException 407 * If the named charset is not supported 408 * 409 * @throws IndexOutOfBoundsException 410 * If {@code offset} is negative, {@code length} is negative, or 411 * {@code offset} is greater than {@code bytes.length - length} 412 * 413 * @since 1.1 414 */ 415 public String(byte bytes[], int offset, int length, String charsetName) 416 throws UnsupportedEncodingException { 417 if (charsetName == null) 418 throw new NullPointerException("charsetName"); 419 checkBounds(bytes, offset, length); 420 this.value = StringCoding.decode(charsetName, bytes, offset, length); 421 } 422 423 /** 424 * Constructs a new {@code String} by decoding the specified subarray of 425 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 426 * The length of the new {@code String} is a function of the charset, and 427 * hence may not be equal to the length of the subarray. 428 * 429 * <p> This method always replaces malformed-input and unmappable-character 430 * sequences with this charset's default replacement string. The {@link 431 * java.nio.charset.CharsetDecoder} class should be used when more control 432 * over the decoding process is required. 433 * 434 * @param bytes 435 * The bytes to be decoded into characters 436 * 437 * @param offset 438 * The index of the first byte to decode 439 * 440 * @param length 441 * The number of bytes to decode 442 * 443 * @param charset 444 * The {@linkplain java.nio.charset.Charset charset} to be used to 445 * decode the {@code bytes} 446 * 447 * @throws IndexOutOfBoundsException 448 * If {@code offset} is negative, {@code length} is negative, or 449 * {@code offset} is greater than {@code bytes.length - length} 450 * 451 * @since 1.6 452 */ 453 public String(byte bytes[], int offset, int length, Charset charset) { 454 if (charset == null) 455 throw new NullPointerException("charset"); 456 checkBounds(bytes, offset, length); 457 this.value = StringCoding.decode(charset, bytes, offset, length); 458 } 459 460 /** 461 * Constructs a new {@code String} by decoding the specified array of bytes 462 * using the specified {@linkplain java.nio.charset.Charset charset}. The 463 * length of the new {@code String} is a function of the charset, and hence 464 * may not be equal to the length of the byte array. 465 * 466 * <p> The behavior of this constructor when the given bytes are not valid 467 * in the given charset is unspecified. The {@link 468 * java.nio.charset.CharsetDecoder} class should be used when more control 469 * over the decoding process is required. 470 * 471 * @param bytes 472 * The bytes to be decoded into characters 473 * 474 * @param charsetName 475 * The name of a supported {@linkplain java.nio.charset.Charset 476 * charset} 477 * 478 * @throws UnsupportedEncodingException 479 * If the named charset is not supported 480 * 481 * @since 1.1 482 */ 483 public String(byte bytes[], String charsetName) 484 throws UnsupportedEncodingException { 485 this(bytes, 0, bytes.length, charsetName); 486 } 487 488 /** 489 * Constructs a new {@code String} by decoding the specified array of 490 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 491 * The length of the new {@code String} is a function of the charset, and 492 * hence may not be equal to the length of the byte array. 493 * 494 * <p> This method always replaces malformed-input and unmappable-character 495 * sequences with this charset's default replacement string. The {@link 496 * java.nio.charset.CharsetDecoder} class should be used when more control 497 * over the decoding process is required. 498 * 499 * @param bytes 500 * The bytes to be decoded into characters 501 * 502 * @param charset 503 * The {@linkplain java.nio.charset.Charset charset} to be used to 504 * decode the {@code bytes} 505 * 506 * @since 1.6 507 */ 508 public String(byte bytes[], Charset charset) { 509 this(bytes, 0, bytes.length, charset); 510 } 511 512 /** 513 * Constructs a new {@code String} by decoding the specified subarray of 514 * bytes using the platform's default charset. The length of the new 515 * {@code String} is a function of the charset, and hence may not be equal 516 * to the length of the subarray. 517 * 518 * <p> The behavior of this constructor when the given bytes are not valid 519 * in the default charset is unspecified. The {@link 520 * java.nio.charset.CharsetDecoder} class should be used when more control 521 * over the decoding process is required. 522 * 523 * @param bytes 524 * The bytes to be decoded into characters 525 * 526 * @param offset 527 * The index of the first byte to decode 528 * 529 * @param length 530 * The number of bytes to decode 531 * 532 * @throws IndexOutOfBoundsException 533 * If {@code offset} is negative, {@code length} is negative, or 534 * {@code offset} is greater than {@code bytes.length - length} 535 * 536 * @since 1.1 537 */ 538 public String(byte bytes[], int offset, int length) { 539 checkBounds(bytes, offset, length); 540 this.value = StringCoding.decode(bytes, offset, length); 541 } 542 543 /** 544 * Constructs a new {@code String} by decoding the specified array of bytes 545 * using the platform's default charset. The length of the new {@code 546 * String} is a function of the charset, and hence may not be equal to the 547 * length of the byte array. 548 * 549 * <p> The behavior of this constructor when the given bytes are not valid 550 * in the default charset is unspecified. The {@link 551 * java.nio.charset.CharsetDecoder} class should be used when more control 552 * over the decoding process is required. 553 * 554 * @param bytes 555 * The bytes to be decoded into characters 556 * 557 * @since 1.1 558 */ 559 public String(byte bytes[]) { 560 this(bytes, 0, bytes.length); 561 } 562 563 /** 564 * Allocates a new string that contains the sequence of characters 565 * currently contained in the string buffer argument. The contents of the 566 * string buffer are copied; subsequent modification of the string buffer 567 * does not affect the newly created string. 568 * 569 * @param buffer 570 * A {@code StringBuffer} 571 */ 572 public String(StringBuffer buffer) { 573 synchronized(buffer) { 574 this.value = Arrays.copyOf(buffer.getValue(), buffer.length()); 575 } 576 } 577 578 /** 579 * Allocates a new string that contains the sequence of characters 580 * currently contained in the string builder argument. The contents of the 581 * string builder are copied; subsequent modification of the string builder 582 * does not affect the newly created string. 583 * 584 * <p> This constructor is provided to ease migration to {@code 585 * StringBuilder}. Obtaining a string from a string builder via the {@code 586 * toString} method is likely to run faster and is generally preferred. 587 * 588 * @param builder 589 * A {@code StringBuilder} 590 * 591 * @since 1.5 592 */ 593 public String(StringBuilder builder) { 594 this.value = Arrays.copyOf(builder.getValue(), builder.length()); 595 } 596 597 /* 598 * Package private constructor which shares value array for speed. 599 * this constructor is always expected to be called with share==true. 600 * a separate constructor is needed because we already have a public 601 * String(char[]) constructor that makes a copy of the given char[]. 602 */ 603 String(char[] value, boolean share) { 604 // assert share : "unshared not supported"; 605 this.value = value; 606 } 607 608 /** 609 * Returns the length of this string. 610 * The length is equal to the number of <a href="Character.html#unicode">Unicode 611 * code units</a> in the string. 612 * 613 * @return the length of the sequence of characters represented by this 614 * object. 615 */ 616 public int length() { 617 return value.length; 618 } 619 620 /** 621 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 622 * 623 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 624 * {@code false} 625 * 626 * @since 1.6 627 */ 628 public boolean isEmpty() { 629 return value.length == 0; 630 } 631 632 /** 633 * Returns the {@code char} value at the 634 * specified index. An index ranges from {@code 0} to 635 * {@code length() - 1}. The first {@code char} value of the sequence 636 * is at index {@code 0}, the next at index {@code 1}, 637 * and so on, as for array indexing. 638 * 639 * <p>If the {@code char} value specified by the index is a 640 * <a href="Character.html#unicode">surrogate</a>, the surrogate 641 * value is returned. 642 * 643 * @param index the index of the {@code char} value. 644 * @return the {@code char} value at the specified index of this string. 645 * The first {@code char} value is at index {@code 0}. 646 * @exception IndexOutOfBoundsException if the {@code index} 647 * argument is negative or not less than the length of this 648 * string. 649 */ 650 public char charAt(int index) { 651 if ((index < 0) || (index >= value.length)) { 652 throw new StringIndexOutOfBoundsException(index); 653 } 654 return value[index]; 655 } 656 657 /** 658 * Returns the character (Unicode code point) at the specified 659 * index. The index refers to {@code char} values 660 * (Unicode code units) and ranges from {@code 0} to 661 * {@link #length()}{@code - 1}. 662 * 663 * <p> If the {@code char} value specified at the given index 664 * is in the high-surrogate range, the following index is less 665 * than the length of this {@code String}, and the 666 * {@code char} value at the following index is in the 667 * low-surrogate range, then the supplementary code point 668 * corresponding to this surrogate pair is returned. Otherwise, 669 * the {@code char} value at the given index is returned. 670 * 671 * @param index the index to the {@code char} values 672 * @return the code point value of the character at the 673 * {@code index} 674 * @exception IndexOutOfBoundsException if the {@code index} 675 * argument is negative or not less than the length of this 676 * string. 677 * @since 1.5 678 */ 679 public int codePointAt(int index) { 680 if ((index < 0) || (index >= value.length)) { 681 throw new StringIndexOutOfBoundsException(index); 682 } 683 return Character.codePointAtImpl(value, index, value.length); 684 } 685 686 /** 687 * Returns the character (Unicode code point) before the specified 688 * index. The index refers to {@code char} values 689 * (Unicode code units) and ranges from {@code 1} to {@link 690 * CharSequence#length() length}. 691 * 692 * <p> If the {@code char} value at {@code (index - 1)} 693 * is in the low-surrogate range, {@code (index - 2)} is not 694 * negative, and the {@code char} value at {@code (index - 695 * 2)} is in the high-surrogate range, then the 696 * supplementary code point value of the surrogate pair is 697 * returned. If the {@code char} value at {@code index - 698 * 1} is an unpaired low-surrogate or a high-surrogate, the 699 * surrogate value is returned. 700 * 701 * @param index the index following the code point that should be returned 702 * @return the Unicode code point value before the given index. 703 * @exception IndexOutOfBoundsException if the {@code index} 704 * argument is less than 1 or greater than the length 705 * of this string. 706 * @since 1.5 707 */ 708 public int codePointBefore(int index) { 709 int i = index - 1; 710 if ((i < 0) || (i >= value.length)) { 711 throw new StringIndexOutOfBoundsException(index); 712 } 713 return Character.codePointBeforeImpl(value, index, 0); 714 } 715 716 /** 717 * Returns the number of Unicode code points in the specified text 718 * range of this {@code String}. The text range begins at the 719 * specified {@code beginIndex} and extends to the 720 * {@code char} at index {@code endIndex - 1}. Thus the 721 * length (in {@code char}s) of the text range is 722 * {@code endIndex-beginIndex}. Unpaired surrogates within 723 * the text range count as one code point each. 724 * 725 * @param beginIndex the index to the first {@code char} of 726 * the text range. 727 * @param endIndex the index after the last {@code char} of 728 * the text range. 729 * @return the number of Unicode code points in the specified text 730 * range 731 * @exception IndexOutOfBoundsException if the 732 * {@code beginIndex} is negative, or {@code endIndex} 733 * is larger than the length of this {@code String}, or 734 * {@code beginIndex} is larger than {@code endIndex}. 735 * @since 1.5 736 */ 737 public int codePointCount(int beginIndex, int endIndex) { 738 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) { 739 throw new IndexOutOfBoundsException(); 740 } 741 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex); 742 } 743 744 /** 745 * Returns the index within this {@code String} that is 746 * offset from the given {@code index} by 747 * {@code codePointOffset} code points. Unpaired surrogates 748 * within the text range given by {@code index} and 749 * {@code codePointOffset} count as one code point each. 750 * 751 * @param index the index to be offset 752 * @param codePointOffset the offset in code points 753 * @return the index within this {@code String} 754 * @exception IndexOutOfBoundsException if {@code index} 755 * is negative or larger then the length of this 756 * {@code String}, or if {@code codePointOffset} is positive 757 * and the substring starting with {@code index} has fewer 758 * than {@code codePointOffset} code points, 759 * or if {@code codePointOffset} is negative and the substring 760 * before {@code index} has fewer than the absolute value 761 * of {@code codePointOffset} code points. 762 * @since 1.5 763 */ 764 public int offsetByCodePoints(int index, int codePointOffset) { 765 if (index < 0 || index > value.length) { 766 throw new IndexOutOfBoundsException(); 767 } 768 return Character.offsetByCodePointsImpl(value, 0, value.length, 769 index, codePointOffset); 770 } 771 772 /** 773 * Copy characters from this string into dst starting at dstBegin. 774 * This method doesn't perform any range checking. 775 */ 776 void getChars(char dst[], int dstBegin) { 777 System.arraycopy(value, 0, dst, dstBegin, value.length); 778 } 779 780 /** 781 * Copies characters from this string into the destination character 782 * array. 783 * <p> 784 * The first character to be copied is at index {@code srcBegin}; 785 * the last character to be copied is at index {@code srcEnd-1} 786 * (thus the total number of characters to be copied is 787 * {@code srcEnd-srcBegin}). The characters are copied into the 788 * subarray of {@code dst} starting at index {@code dstBegin} 789 * and ending at index: 790 * <blockquote><pre> 791 * dstbegin + (srcEnd-srcBegin) - 1 792 * </pre></blockquote> 793 * 794 * @param srcBegin index of the first character in the string 795 * to copy. 796 * @param srcEnd index after the last character in the string 797 * to copy. 798 * @param dst the destination array. 799 * @param dstBegin the start offset in the destination array. 800 * @exception IndexOutOfBoundsException If any of the following 801 * is true: 802 * <ul><li>{@code srcBegin} is negative. 803 * <li>{@code srcBegin} is greater than {@code srcEnd} 804 * <li>{@code srcEnd} is greater than the length of this 805 * string 806 * <li>{@code dstBegin} is negative 807 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 808 * {@code dst.length}</ul> 809 */ 810 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 811 if (srcBegin < 0) { 812 throw new StringIndexOutOfBoundsException(srcBegin); 813 } 814 if (srcEnd > value.length) { 815 throw new StringIndexOutOfBoundsException(srcEnd); 816 } 817 if (srcBegin > srcEnd) { 818 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 819 } 820 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin); 821 } 822 823 /** 824 * Copies characters from this string into the destination byte array. Each 825 * byte receives the 8 low-order bits of the corresponding character. The 826 * eight high-order bits of each character are not copied and do not 827 * participate in the transfer in any way. 828 * 829 * <p> The first character to be copied is at index {@code srcBegin}; the 830 * last character to be copied is at index {@code srcEnd-1}. The total 831 * number of characters to be copied is {@code srcEnd-srcBegin}. The 832 * characters, converted to bytes, are copied into the subarray of {@code 833 * dst} starting at index {@code dstBegin} and ending at index: 834 * 835 * <blockquote><pre> 836 * dstbegin + (srcEnd-srcBegin) - 1 837 * </pre></blockquote> 838 * 839 * @deprecated This method does not properly convert characters into 840 * bytes. As of JDK 1.1, the preferred way to do this is via the 841 * {@link #getBytes()} method, which uses the platform's default charset. 842 * 843 * @param srcBegin 844 * Index of the first character in the string to copy 845 * 846 * @param srcEnd 847 * Index after the last character in the string to copy 848 * 849 * @param dst 850 * The destination array 851 * 852 * @param dstBegin 853 * The start offset in the destination array 854 * 855 * @throws IndexOutOfBoundsException 856 * If any of the following is true: 857 * <ul> 858 * <li> {@code srcBegin} is negative 859 * <li> {@code srcBegin} is greater than {@code srcEnd} 860 * <li> {@code srcEnd} is greater than the length of this String 861 * <li> {@code dstBegin} is negative 862 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 863 * dst.length} 864 * </ul> 865 */ 866 @Deprecated 867 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 868 if (srcBegin < 0) { 869 throw new StringIndexOutOfBoundsException(srcBegin); 870 } 871 if (srcEnd > value.length) { 872 throw new StringIndexOutOfBoundsException(srcEnd); 873 } 874 if (srcBegin > srcEnd) { 875 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 876 } 877 Objects.requireNonNull(dst); 878 879 int j = dstBegin; 880 int n = srcEnd; 881 int i = srcBegin; 882 char[] val = value; /* avoid getfield opcode */ 883 884 while (i < n) { 885 dst[j++] = (byte)val[i++]; 886 } 887 } 888 889 /** 890 * Encodes this {@code String} into a sequence of bytes using the named 891 * charset, storing the result into a new byte array. 892 * 893 * <p> The behavior of this method when this string cannot be encoded in 894 * the given charset is unspecified. The {@link 895 * java.nio.charset.CharsetEncoder} class should be used when more control 896 * over the encoding process is required. 897 * 898 * @param charsetName 899 * The name of a supported {@linkplain java.nio.charset.Charset 900 * charset} 901 * 902 * @return The resultant byte array 903 * 904 * @throws UnsupportedEncodingException 905 * If the named charset is not supported 906 * 907 * @since 1.1 908 */ 909 public byte[] getBytes(String charsetName) 910 throws UnsupportedEncodingException { 911 if (charsetName == null) throw new NullPointerException(); 912 return StringCoding.encode(charsetName, value, 0, value.length); 913 } 914 915 /** 916 * Encodes this {@code String} into a sequence of bytes using the given 917 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 918 * new byte array. 919 * 920 * <p> This method always replaces malformed-input and unmappable-character 921 * sequences with this charset's default replacement byte array. The 922 * {@link java.nio.charset.CharsetEncoder} class should be used when more 923 * control over the encoding process is required. 924 * 925 * @param charset 926 * The {@linkplain java.nio.charset.Charset} to be used to encode 927 * the {@code String} 928 * 929 * @return The resultant byte array 930 * 931 * @since 1.6 932 */ 933 public byte[] getBytes(Charset charset) { 934 if (charset == null) throw new NullPointerException(); 935 return StringCoding.encode(charset, value, 0, value.length); 936 } 937 938 /** 939 * Encodes this {@code String} into a sequence of bytes using the 940 * platform's default charset, storing the result into a new byte array. 941 * 942 * <p> The behavior of this method when this string cannot be encoded in 943 * the default charset is unspecified. The {@link 944 * java.nio.charset.CharsetEncoder} class should be used when more control 945 * over the encoding process is required. 946 * 947 * @return The resultant byte array 948 * 949 * @since 1.1 950 */ 951 public byte[] getBytes() { 952 return StringCoding.encode(value, 0, value.length); 953 } 954 955 /** 956 * Compares this string to the specified object. The result is {@code 957 * true} if and only if the argument is not {@code null} and is a {@code 958 * String} object that represents the same sequence of characters as this 959 * object. 960 * 961 * @param anObject 962 * The object to compare this {@code String} against 963 * 964 * @return {@code true} if the given object represents a {@code String} 965 * equivalent to this string, {@code false} otherwise 966 * 967 * @see #compareTo(String) 968 * @see #equalsIgnoreCase(String) 969 */ 970 public boolean equals(Object anObject) { 971 if (this == anObject) { 972 return true; 973 } 974 if (anObject instanceof String) { 975 String anotherString = (String)anObject; 976 int n = value.length; 977 if (n == anotherString.value.length) { 978 char v1[] = value; 979 char v2[] = anotherString.value; 980 int i = 0; 981 while (n-- != 0) { 982 if (v1[i] != v2[i]) 983 return false; 984 i++; 985 } 986 return true; 987 } 988 } 989 return false; 990 } 991 992 /** 993 * Compares this string to the specified {@code StringBuffer}. The result 994 * is {@code true} if and only if this {@code String} represents the same 995 * sequence of characters as the specified {@code StringBuffer}. This method 996 * synchronizes on the {@code StringBuffer}. 997 * 998 * @param sb 999 * The {@code StringBuffer} to compare this {@code String} against 1000 * 1001 * @return {@code true} if this {@code String} represents the same 1002 * sequence of characters as the specified {@code StringBuffer}, 1003 * {@code false} otherwise 1004 * 1005 * @since 1.4 1006 */ 1007 public boolean contentEquals(StringBuffer sb) { 1008 return contentEquals((CharSequence)sb); 1009 } 1010 1011 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1012 char v1[] = value; 1013 char v2[] = sb.getValue(); 1014 int n = v1.length; 1015 if (n != sb.length()) { 1016 return false; 1017 } 1018 for (int i = 0; i < n; i++) { 1019 if (v1[i] != v2[i]) { 1020 return false; 1021 } 1022 } 1023 return true; 1024 } 1025 1026 /** 1027 * Compares this string to the specified {@code CharSequence}. The 1028 * result is {@code true} if and only if this {@code String} represents the 1029 * same sequence of char values as the specified sequence. Note that if the 1030 * {@code CharSequence} is a {@code StringBuffer} then the method 1031 * synchronizes on it. 1032 * 1033 * @param cs 1034 * The sequence to compare this {@code String} against 1035 * 1036 * @return {@code true} if this {@code String} represents the same 1037 * sequence of char values as the specified sequence, {@code 1038 * false} otherwise 1039 * 1040 * @since 1.5 1041 */ 1042 public boolean contentEquals(CharSequence cs) { 1043 // Argument is a StringBuffer, StringBuilder 1044 if (cs instanceof AbstractStringBuilder) { 1045 if (cs instanceof StringBuffer) { 1046 synchronized(cs) { 1047 return nonSyncContentEquals((AbstractStringBuilder)cs); 1048 } 1049 } else { 1050 return nonSyncContentEquals((AbstractStringBuilder)cs); 1051 } 1052 } 1053 // Argument is a String 1054 if (cs instanceof String) { 1055 return equals(cs); 1056 } 1057 // Argument is a generic CharSequence 1058 char v1[] = value; 1059 int n = v1.length; 1060 if (n != cs.length()) { 1061 return false; 1062 } 1063 for (int i = 0; i < n; i++) { 1064 if (v1[i] != cs.charAt(i)) { 1065 return false; 1066 } 1067 } 1068 return true; 1069 } 1070 1071 /** 1072 * Compares this {@code String} to another {@code String}, ignoring case 1073 * considerations. Two strings are considered equal ignoring case if they 1074 * are of the same length and corresponding characters in the two strings 1075 * are equal ignoring case. 1076 * 1077 * <p> Two characters {@code c1} and {@code c2} are considered the same 1078 * ignoring case if at least one of the following is true: 1079 * <ul> 1080 * <li> The two characters are the same (as compared by the 1081 * {@code ==} operator) 1082 * <li> Applying the method {@link 1083 * java.lang.Character#toUpperCase(char)} to each character 1084 * produces the same result 1085 * <li> Applying the method {@link 1086 * java.lang.Character#toLowerCase(char)} to each character 1087 * produces the same result 1088 * </ul> 1089 * 1090 * @param anotherString 1091 * The {@code String} to compare this {@code String} against 1092 * 1093 * @return {@code true} if the argument is not {@code null} and it 1094 * represents an equivalent {@code String} ignoring case; {@code 1095 * false} otherwise 1096 * 1097 * @see #equals(Object) 1098 */ 1099 public boolean equalsIgnoreCase(String anotherString) { 1100 return (this == anotherString) ? true 1101 : (anotherString != null) 1102 && (anotherString.value.length == value.length) 1103 && regionMatches(true, 0, anotherString, 0, value.length); 1104 } 1105 1106 /** 1107 * Compares two strings lexicographically. 1108 * The comparison is based on the Unicode value of each character in 1109 * the strings. The character sequence represented by this 1110 * {@code String} object is compared lexicographically to the 1111 * character sequence represented by the argument string. The result is 1112 * a negative integer if this {@code String} object 1113 * lexicographically precedes the argument string. The result is a 1114 * positive integer if this {@code String} object lexicographically 1115 * follows the argument string. The result is zero if the strings 1116 * are equal; {@code compareTo} returns {@code 0} exactly when 1117 * the {@link #equals(Object)} method would return {@code true}. 1118 * <p> 1119 * This is the definition of lexicographic ordering. If two strings are 1120 * different, then either they have different characters at some index 1121 * that is a valid index for both strings, or their lengths are different, 1122 * or both. If they have different characters at one or more index 1123 * positions, let <i>k</i> be the smallest such index; then the string 1124 * whose character at position <i>k</i> has the smaller value, as 1125 * determined by using the < operator, lexicographically precedes the 1126 * other string. In this case, {@code compareTo} returns the 1127 * difference of the two character values at position {@code k} in 1128 * the two string -- that is, the value: 1129 * <blockquote><pre> 1130 * this.charAt(k)-anotherString.charAt(k) 1131 * </pre></blockquote> 1132 * If there is no index position at which they differ, then the shorter 1133 * string lexicographically precedes the longer string. In this case, 1134 * {@code compareTo} returns the difference of the lengths of the 1135 * strings -- that is, the value: 1136 * <blockquote><pre> 1137 * this.length()-anotherString.length() 1138 * </pre></blockquote> 1139 * 1140 * @param anotherString the {@code String} to be compared. 1141 * @return the value {@code 0} if the argument string is equal to 1142 * this string; a value less than {@code 0} if this string 1143 * is lexicographically less than the string argument; and a 1144 * value greater than {@code 0} if this string is 1145 * lexicographically greater than the string argument. 1146 */ 1147 public int compareTo(String anotherString) { 1148 int len1 = value.length; 1149 int len2 = anotherString.value.length; 1150 int lim = Math.min(len1, len2); 1151 char v1[] = value; 1152 char v2[] = anotherString.value; 1153 1154 int k = 0; 1155 while (k < lim) { 1156 char c1 = v1[k]; 1157 char c2 = v2[k]; 1158 if (c1 != c2) { 1159 return c1 - c2; 1160 } 1161 k++; 1162 } 1163 return len1 - len2; 1164 } 1165 1166 /** 1167 * A Comparator that orders {@code String} objects as by 1168 * {@code compareToIgnoreCase}. This comparator is serializable. 1169 * <p> 1170 * Note that this Comparator does <em>not</em> take locale into account, 1171 * and will result in an unsatisfactory ordering for certain locales. 1172 * The java.text package provides <em>Collators</em> to allow 1173 * locale-sensitive ordering. 1174 * 1175 * @see java.text.Collator#compare(String, String) 1176 * @since 1.2 1177 */ 1178 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1179 = new CaseInsensitiveComparator(); 1180 private static class CaseInsensitiveComparator 1181 implements Comparator<String>, java.io.Serializable { 1182 // use serialVersionUID from JDK 1.2.2 for interoperability 1183 private static final long serialVersionUID = 8575799808933029326L; 1184 1185 public int compare(String s1, String s2) { 1186 int n1 = s1.length(); 1187 int n2 = s2.length(); 1188 int min = Math.min(n1, n2); 1189 for (int i = 0; i < min; i++) { 1190 char c1 = s1.charAt(i); 1191 char c2 = s2.charAt(i); 1192 if (c1 != c2) { 1193 c1 = Character.toUpperCase(c1); 1194 c2 = Character.toUpperCase(c2); 1195 if (c1 != c2) { 1196 c1 = Character.toLowerCase(c1); 1197 c2 = Character.toLowerCase(c2); 1198 if (c1 != c2) { 1199 // No overflow because of numeric promotion 1200 return c1 - c2; 1201 } 1202 } 1203 } 1204 } 1205 return n1 - n2; 1206 } 1207 1208 /** Replaces the de-serialized object. */ 1209 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1210 } 1211 1212 /** 1213 * Compares two strings lexicographically, ignoring case 1214 * differences. This method returns an integer whose sign is that of 1215 * calling {@code compareTo} with normalized versions of the strings 1216 * where case differences have been eliminated by calling 1217 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1218 * each character. 1219 * <p> 1220 * Note that this method does <em>not</em> take locale into account, 1221 * and will result in an unsatisfactory ordering for certain locales. 1222 * The java.text package provides <em>collators</em> to allow 1223 * locale-sensitive ordering. 1224 * 1225 * @param str the {@code String} to be compared. 1226 * @return a negative integer, zero, or a positive integer as the 1227 * specified String is greater than, equal to, or less 1228 * than this String, ignoring case considerations. 1229 * @see java.text.Collator#compare(String, String) 1230 * @since 1.2 1231 */ 1232 public int compareToIgnoreCase(String str) { 1233 return CASE_INSENSITIVE_ORDER.compare(this, str); 1234 } 1235 1236 /** 1237 * Tests if two string regions are equal. 1238 * <p> 1239 * A substring of this {@code String} object is compared to a substring 1240 * of the argument other. The result is true if these substrings 1241 * represent identical character sequences. The substring of this 1242 * {@code String} object to be compared begins at index {@code toffset} 1243 * and has length {@code len}. The substring of other to be compared 1244 * begins at index {@code ooffset} and has length {@code len}. The 1245 * result is {@code false} if and only if at least one of the following 1246 * is true: 1247 * <ul><li>{@code toffset} is negative. 1248 * <li>{@code ooffset} is negative. 1249 * <li>{@code toffset+len} is greater than the length of this 1250 * {@code String} object. 1251 * <li>{@code ooffset+len} is greater than the length of the other 1252 * argument. 1253 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1254 * such that: 1255 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1256 * <i>k</i>{@code )} 1257 * </ul> 1258 * 1259 * @param toffset the starting offset of the subregion in this string. 1260 * @param other the string argument. 1261 * @param ooffset the starting offset of the subregion in the string 1262 * argument. 1263 * @param len the number of characters to compare. 1264 * @return {@code true} if the specified subregion of this string 1265 * exactly matches the specified subregion of the string argument; 1266 * {@code false} otherwise. 1267 */ 1268 public boolean regionMatches(int toffset, String other, int ooffset, 1269 int len) { 1270 char ta[] = value; 1271 int to = toffset; 1272 char pa[] = other.value; 1273 int po = ooffset; 1274 // Note: toffset, ooffset, or len might be near -1>>>1. 1275 if ((ooffset < 0) || (toffset < 0) 1276 || (toffset > (long)value.length - len) 1277 || (ooffset > (long)other.value.length - len)) { 1278 return false; 1279 } 1280 while (len-- > 0) { 1281 if (ta[to++] != pa[po++]) { 1282 return false; 1283 } 1284 } 1285 return true; 1286 } 1287 1288 /** 1289 * Tests if two string regions are equal. 1290 * <p> 1291 * A substring of this {@code String} object is compared to a substring 1292 * of the argument {@code other}. The result is {@code true} if these 1293 * substrings represent character sequences that are the same, ignoring 1294 * case if and only if {@code ignoreCase} is true. The substring of 1295 * this {@code String} object to be compared begins at index 1296 * {@code toffset} and has length {@code len}. The substring of 1297 * {@code other} to be compared begins at index {@code ooffset} and 1298 * has length {@code len}. The result is {@code false} if and only if 1299 * at least one of the following is true: 1300 * <ul><li>{@code toffset} is negative. 1301 * <li>{@code ooffset} is negative. 1302 * <li>{@code toffset+len} is greater than the length of this 1303 * {@code String} object. 1304 * <li>{@code ooffset+len} is greater than the length of the other 1305 * argument. 1306 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1307 * integer <i>k</i> less than {@code len} such that: 1308 * <blockquote><pre> 1309 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1310 * </pre></blockquote> 1311 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1312 * integer <i>k</i> less than {@code len} such that: 1313 * <blockquote><pre> 1314 * Character.toLowerCase(this.charAt(toffset+k)) != 1315 Character.toLowerCase(other.charAt(ooffset+k)) 1316 * </pre></blockquote> 1317 * and: 1318 * <blockquote><pre> 1319 * Character.toUpperCase(this.charAt(toffset+k)) != 1320 * Character.toUpperCase(other.charAt(ooffset+k)) 1321 * </pre></blockquote> 1322 * </ul> 1323 * 1324 * @param ignoreCase if {@code true}, ignore case when comparing 1325 * characters. 1326 * @param toffset the starting offset of the subregion in this 1327 * string. 1328 * @param other the string argument. 1329 * @param ooffset the starting offset of the subregion in the string 1330 * argument. 1331 * @param len the number of characters to compare. 1332 * @return {@code true} if the specified subregion of this string 1333 * matches the specified subregion of the string argument; 1334 * {@code false} otherwise. Whether the matching is exact 1335 * or case insensitive depends on the {@code ignoreCase} 1336 * argument. 1337 */ 1338 public boolean regionMatches(boolean ignoreCase, int toffset, 1339 String other, int ooffset, int len) { 1340 char ta[] = value; 1341 int to = toffset; 1342 char pa[] = other.value; 1343 int po = ooffset; 1344 // Note: toffset, ooffset, or len might be near -1>>>1. 1345 if ((ooffset < 0) || (toffset < 0) 1346 || (toffset > (long)value.length - len) 1347 || (ooffset > (long)other.value.length - len)) { 1348 return false; 1349 } 1350 while (len-- > 0) { 1351 char c1 = ta[to++]; 1352 char c2 = pa[po++]; 1353 if (c1 == c2) { 1354 continue; 1355 } 1356 if (ignoreCase) { 1357 // If characters don't match but case may be ignored, 1358 // try converting both characters to uppercase. 1359 // If the results match, then the comparison scan should 1360 // continue. 1361 char u1 = Character.toUpperCase(c1); 1362 char u2 = Character.toUpperCase(c2); 1363 if (u1 == u2) { 1364 continue; 1365 } 1366 // Unfortunately, conversion to uppercase does not work properly 1367 // for the Georgian alphabet, which has strange rules about case 1368 // conversion. So we need to make one last check before 1369 // exiting. 1370 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) { 1371 continue; 1372 } 1373 } 1374 return false; 1375 } 1376 return true; 1377 } 1378 1379 /** 1380 * Tests if the substring of this string beginning at the 1381 * specified index starts with the specified prefix. 1382 * 1383 * @param prefix the prefix. 1384 * @param toffset where to begin looking in this string. 1385 * @return {@code true} if the character sequence represented by the 1386 * argument is a prefix of the substring of this object starting 1387 * at index {@code toffset}; {@code false} otherwise. 1388 * The result is {@code false} if {@code toffset} is 1389 * negative or greater than the length of this 1390 * {@code String} object; otherwise the result is the same 1391 * as the result of the expression 1392 * <pre> 1393 * this.substring(toffset).startsWith(prefix) 1394 * </pre> 1395 */ 1396 public boolean startsWith(String prefix, int toffset) { 1397 char ta[] = value; 1398 int to = toffset; 1399 char pa[] = prefix.value; 1400 int po = 0; 1401 int pc = prefix.value.length; 1402 // Note: toffset might be near -1>>>1. 1403 if ((toffset < 0) || (toffset > value.length - pc)) { 1404 return false; 1405 } 1406 while (--pc >= 0) { 1407 if (ta[to++] != pa[po++]) { 1408 return false; 1409 } 1410 } 1411 return true; 1412 } 1413 1414 /** 1415 * Tests if this string starts with the specified prefix. 1416 * 1417 * @param prefix the prefix. 1418 * @return {@code true} if the character sequence represented by the 1419 * argument is a prefix of the character sequence represented by 1420 * this string; {@code false} otherwise. 1421 * Note also that {@code true} will be returned if the 1422 * argument is an empty string or is equal to this 1423 * {@code String} object as determined by the 1424 * {@link #equals(Object)} method. 1425 * @since 1.0 1426 */ 1427 public boolean startsWith(String prefix) { 1428 return startsWith(prefix, 0); 1429 } 1430 1431 /** 1432 * Tests if this string ends with the specified suffix. 1433 * 1434 * @param suffix the suffix. 1435 * @return {@code true} if the character sequence represented by the 1436 * argument is a suffix of the character sequence represented by 1437 * this object; {@code false} otherwise. Note that the 1438 * result will be {@code true} if the argument is the 1439 * empty string or is equal to this {@code String} object 1440 * as determined by the {@link #equals(Object)} method. 1441 */ 1442 public boolean endsWith(String suffix) { 1443 return startsWith(suffix, value.length - suffix.value.length); 1444 } 1445 1446 /** 1447 * Returns a hash code for this string. The hash code for a 1448 * {@code String} object is computed as 1449 * <blockquote><pre> 1450 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1451 * </pre></blockquote> 1452 * using {@code int} arithmetic, where {@code s[i]} is the 1453 * <i>i</i>th character of the string, {@code n} is the length of 1454 * the string, and {@code ^} indicates exponentiation. 1455 * (The hash value of the empty string is zero.) 1456 * 1457 * @return a hash code value for this object. 1458 */ 1459 public int hashCode() { 1460 int h = hash; 1461 if (h == 0) { 1462 for (char v : value) { 1463 h = 31 * h + v; 1464 } 1465 hash = h; 1466 } 1467 return h; 1468 } 1469 1470 /** 1471 * Returns the index within this string of the first occurrence of 1472 * the specified character. If a character with value 1473 * {@code ch} occurs in the character sequence represented by 1474 * this {@code String} object, then the index (in Unicode 1475 * code units) of the first such occurrence is returned. For 1476 * values of {@code ch} in the range from 0 to 0xFFFF 1477 * (inclusive), this is the smallest value <i>k</i> such that: 1478 * <blockquote><pre> 1479 * this.charAt(<i>k</i>) == ch 1480 * </pre></blockquote> 1481 * is true. For other values of {@code ch}, it is the 1482 * smallest value <i>k</i> such that: 1483 * <blockquote><pre> 1484 * this.codePointAt(<i>k</i>) == ch 1485 * </pre></blockquote> 1486 * is true. In either case, if no such character occurs in this 1487 * string, then {@code -1} is returned. 1488 * 1489 * @param ch a character (Unicode code point). 1490 * @return the index of the first occurrence of the character in the 1491 * character sequence represented by this object, or 1492 * {@code -1} if the character does not occur. 1493 */ 1494 public int indexOf(int ch) { 1495 return indexOf(ch, 0); 1496 } 1497 1498 /** 1499 * Returns the index within this string of the first occurrence of the 1500 * specified character, starting the search at the specified index. 1501 * <p> 1502 * If a character with value {@code ch} occurs in the 1503 * character sequence represented by this {@code String} 1504 * object at an index no smaller than {@code fromIndex}, then 1505 * the index of the first such occurrence is returned. For values 1506 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1507 * this is the smallest value <i>k</i> such that: 1508 * <blockquote><pre> 1509 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1510 * </pre></blockquote> 1511 * is true. For other values of {@code ch}, it is the 1512 * smallest value <i>k</i> such that: 1513 * <blockquote><pre> 1514 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1515 * </pre></blockquote> 1516 * is true. In either case, if no such character occurs in this 1517 * string at or after position {@code fromIndex}, then 1518 * {@code -1} is returned. 1519 * 1520 * <p> 1521 * There is no restriction on the value of {@code fromIndex}. If it 1522 * is negative, it has the same effect as if it were zero: this entire 1523 * string may be searched. If it is greater than the length of this 1524 * string, it has the same effect as if it were equal to the length of 1525 * this string: {@code -1} is returned. 1526 * 1527 * <p>All indices are specified in {@code char} values 1528 * (Unicode code units). 1529 * 1530 * @param ch a character (Unicode code point). 1531 * @param fromIndex the index to start the search from. 1532 * @return the index of the first occurrence of the character in the 1533 * character sequence represented by this object that is greater 1534 * than or equal to {@code fromIndex}, or {@code -1} 1535 * if the character does not occur. 1536 */ 1537 public int indexOf(int ch, int fromIndex) { 1538 final int max = value.length; 1539 if (fromIndex < 0) { 1540 fromIndex = 0; 1541 } else if (fromIndex >= max) { 1542 // Note: fromIndex might be near -1>>>1. 1543 return -1; 1544 } 1545 1546 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1547 // handle most cases here (ch is a BMP code point or a 1548 // negative value (invalid code point)) 1549 final char[] value = this.value; 1550 for (int i = fromIndex; i < max; i++) { 1551 if (value[i] == ch) { 1552 return i; 1553 } 1554 } 1555 return -1; 1556 } else { 1557 return indexOfSupplementary(ch, fromIndex); 1558 } 1559 } 1560 1561 /** 1562 * Handles (rare) calls of indexOf with a supplementary character. 1563 */ 1564 private int indexOfSupplementary(int ch, int fromIndex) { 1565 if (Character.isValidCodePoint(ch)) { 1566 final char[] value = this.value; 1567 final char hi = Character.highSurrogate(ch); 1568 final char lo = Character.lowSurrogate(ch); 1569 final int max = value.length - 1; 1570 for (int i = fromIndex; i < max; i++) { 1571 if (value[i] == hi && value[i + 1] == lo) { 1572 return i; 1573 } 1574 } 1575 } 1576 return -1; 1577 } 1578 1579 /** 1580 * Returns the index within this string of the last occurrence of 1581 * the specified character. For values of {@code ch} in the 1582 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1583 * units) returned is the largest value <i>k</i> such that: 1584 * <blockquote><pre> 1585 * this.charAt(<i>k</i>) == ch 1586 * </pre></blockquote> 1587 * is true. For other values of {@code ch}, it is the 1588 * largest value <i>k</i> such that: 1589 * <blockquote><pre> 1590 * this.codePointAt(<i>k</i>) == ch 1591 * </pre></blockquote> 1592 * is true. In either case, if no such character occurs in this 1593 * string, then {@code -1} is returned. The 1594 * {@code String} is searched backwards starting at the last 1595 * character. 1596 * 1597 * @param ch a character (Unicode code point). 1598 * @return the index of the last occurrence of the character in the 1599 * character sequence represented by this object, or 1600 * {@code -1} if the character does not occur. 1601 */ 1602 public int lastIndexOf(int ch) { 1603 return lastIndexOf(ch, value.length - 1); 1604 } 1605 1606 /** 1607 * Returns the index within this string of the last occurrence of 1608 * the specified character, searching backward starting at the 1609 * specified index. For values of {@code ch} in the range 1610 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1611 * value <i>k</i> such that: 1612 * <blockquote><pre> 1613 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1614 * </pre></blockquote> 1615 * is true. For other values of {@code ch}, it is the 1616 * largest value <i>k</i> such that: 1617 * <blockquote><pre> 1618 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1619 * </pre></blockquote> 1620 * is true. In either case, if no such character occurs in this 1621 * string at or before position {@code fromIndex}, then 1622 * {@code -1} is returned. 1623 * 1624 * <p>All indices are specified in {@code char} values 1625 * (Unicode code units). 1626 * 1627 * @param ch a character (Unicode code point). 1628 * @param fromIndex the index to start the search from. There is no 1629 * restriction on the value of {@code fromIndex}. If it is 1630 * greater than or equal to the length of this string, it has 1631 * the same effect as if it were equal to one less than the 1632 * length of this string: this entire string may be searched. 1633 * If it is negative, it has the same effect as if it were -1: 1634 * -1 is returned. 1635 * @return the index of the last occurrence of the character in the 1636 * character sequence represented by this object that is less 1637 * than or equal to {@code fromIndex}, or {@code -1} 1638 * if the character does not occur before that point. 1639 */ 1640 public int lastIndexOf(int ch, int fromIndex) { 1641 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1642 // handle most cases here (ch is a BMP code point or a 1643 // negative value (invalid code point)) 1644 final char[] value = this.value; 1645 int i = Math.min(fromIndex, value.length - 1); 1646 for (; i >= 0; i--) { 1647 if (value[i] == ch) { 1648 return i; 1649 } 1650 } 1651 return -1; 1652 } else { 1653 return lastIndexOfSupplementary(ch, fromIndex); 1654 } 1655 } 1656 1657 /** 1658 * Handles (rare) calls of lastIndexOf with a supplementary character. 1659 */ 1660 private int lastIndexOfSupplementary(int ch, int fromIndex) { 1661 if (Character.isValidCodePoint(ch)) { 1662 final char[] value = this.value; 1663 char hi = Character.highSurrogate(ch); 1664 char lo = Character.lowSurrogate(ch); 1665 int i = Math.min(fromIndex, value.length - 2); 1666 for (; i >= 0; i--) { 1667 if (value[i] == hi && value[i + 1] == lo) { 1668 return i; 1669 } 1670 } 1671 } 1672 return -1; 1673 } 1674 1675 /** 1676 * Returns the index within this string of the first occurrence of the 1677 * specified substring. 1678 * 1679 * <p>The returned index is the smallest value {@code k} for which: 1680 * <pre>{@code 1681 * this.startsWith(str, k) 1682 * }</pre> 1683 * If no such value of {@code k} exists, then {@code -1} is returned. 1684 * 1685 * @param str the substring to search for. 1686 * @return the index of the first occurrence of the specified substring, 1687 * or {@code -1} if there is no such occurrence. 1688 */ 1689 public int indexOf(String str) { 1690 return indexOf(str, 0); 1691 } 1692 1693 /** 1694 * Returns the index within this string of the first occurrence of the 1695 * specified substring, starting at the specified index. 1696 * 1697 * <p>The returned index is the smallest value {@code k} for which: 1698 * <pre>{@code 1699 * k >= Math.min(fromIndex, this.length()) && 1700 * this.startsWith(str, k) 1701 * }</pre> 1702 * If no such value of {@code k} exists, then {@code -1} is returned. 1703 * 1704 * @param str the substring to search for. 1705 * @param fromIndex the index from which to start the search. 1706 * @return the index of the first occurrence of the specified substring, 1707 * starting at the specified index, 1708 * or {@code -1} if there is no such occurrence. 1709 */ 1710 public int indexOf(String str, int fromIndex) { 1711 return indexOf(value, 0, value.length, 1712 str.value, 0, str.value.length, fromIndex); 1713 } 1714 1715 /** 1716 * Code shared by String and AbstractStringBuilder to do searches. The 1717 * source is the character array being searched, and the target 1718 * is the string being searched for. 1719 * 1720 * @param source the characters being searched. 1721 * @param sourceOffset offset of the source string. 1722 * @param sourceCount count of the source string. 1723 * @param target the characters being searched for. 1724 * @param fromIndex the index to begin searching from. 1725 */ 1726 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1727 String target, int fromIndex) { 1728 return indexOf(source, sourceOffset, sourceCount, 1729 target.value, 0, target.value.length, 1730 fromIndex); 1731 } 1732 1733 /** 1734 * Code shared by String and StringBuffer to do searches. The 1735 * source is the character array being searched, and the target 1736 * is the string being searched for. 1737 * 1738 * @param source the characters being searched. 1739 * @param sourceOffset offset of the source string. 1740 * @param sourceCount count of the source string. 1741 * @param target the characters being searched for. 1742 * @param targetOffset offset of the target string. 1743 * @param targetCount count of the target string. 1744 * @param fromIndex the index to begin searching from. 1745 */ 1746 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1747 char[] target, int targetOffset, int targetCount, 1748 int fromIndex) { 1749 if (fromIndex >= sourceCount) { 1750 return (targetCount == 0 ? sourceCount : -1); 1751 } 1752 if (fromIndex < 0) { 1753 fromIndex = 0; 1754 } 1755 if (targetCount == 0) { 1756 return fromIndex; 1757 } 1758 1759 char first = target[targetOffset]; 1760 int max = sourceOffset + (sourceCount - targetCount); 1761 1762 for (int i = sourceOffset + fromIndex; i <= max; i++) { 1763 /* Look for first character. */ 1764 if (source[i] != first) { 1765 while (++i <= max && source[i] != first); 1766 } 1767 1768 /* Found first character, now look at the rest of v2 */ 1769 if (i <= max) { 1770 int j = i + 1; 1771 int end = j + targetCount - 1; 1772 for (int k = targetOffset + 1; j < end && source[j] 1773 == target[k]; j++, k++); 1774 1775 if (j == end) { 1776 /* Found whole string. */ 1777 return i - sourceOffset; 1778 } 1779 } 1780 } 1781 return -1; 1782 } 1783 1784 /** 1785 * Returns the index within this string of the last occurrence of the 1786 * specified substring. The last occurrence of the empty string "" 1787 * is considered to occur at the index value {@code this.length()}. 1788 * 1789 * <p>The returned index is the largest value {@code k} for which: 1790 * <pre>{@code 1791 * this.startsWith(str, k) 1792 * }</pre> 1793 * If no such value of {@code k} exists, then {@code -1} is returned. 1794 * 1795 * @param str the substring to search for. 1796 * @return the index of the last occurrence of the specified substring, 1797 * or {@code -1} if there is no such occurrence. 1798 */ 1799 public int lastIndexOf(String str) { 1800 return lastIndexOf(str, value.length); 1801 } 1802 1803 /** 1804 * Returns the index within this string of the last occurrence of the 1805 * specified substring, searching backward starting at the specified index. 1806 * 1807 * <p>The returned index is the largest value {@code k} for which: 1808 * <pre>{@code 1809 * k <= Math.min(fromIndex, this.length()) && 1810 * this.startsWith(str, k) 1811 * }</pre> 1812 * If no such value of {@code k} exists, then {@code -1} is returned. 1813 * 1814 * @param str the substring to search for. 1815 * @param fromIndex the index to start the search from. 1816 * @return the index of the last occurrence of the specified substring, 1817 * searching backward from the specified index, 1818 * or {@code -1} if there is no such occurrence. 1819 */ 1820 public int lastIndexOf(String str, int fromIndex) { 1821 return lastIndexOf(value, 0, value.length, 1822 str.value, 0, str.value.length, fromIndex); 1823 } 1824 1825 /** 1826 * Code shared by String and AbstractStringBuilder to do searches. The 1827 * source is the character array being searched, and the target 1828 * is the string being searched for. 1829 * 1830 * @param source the characters being searched. 1831 * @param sourceOffset offset of the source string. 1832 * @param sourceCount count of the source string. 1833 * @param target the characters being searched for. 1834 * @param fromIndex the index to begin searching from. 1835 */ 1836 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1837 String target, int fromIndex) { 1838 return lastIndexOf(source, sourceOffset, sourceCount, 1839 target.value, 0, target.value.length, 1840 fromIndex); 1841 } 1842 1843 /** 1844 * Code shared by String and StringBuffer to do searches. The 1845 * source is the character array being searched, and the target 1846 * is the string being searched for. 1847 * 1848 * @param source the characters being searched. 1849 * @param sourceOffset offset of the source string. 1850 * @param sourceCount count of the source string. 1851 * @param target the characters being searched for. 1852 * @param targetOffset offset of the target string. 1853 * @param targetCount count of the target string. 1854 * @param fromIndex the index to begin searching from. 1855 */ 1856 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1857 char[] target, int targetOffset, int targetCount, 1858 int fromIndex) { 1859 /* 1860 * Check arguments; return immediately where possible. For 1861 * consistency, don't check for null str. 1862 */ 1863 int rightIndex = sourceCount - targetCount; 1864 if (fromIndex < 0) { 1865 return -1; 1866 } 1867 if (fromIndex > rightIndex) { 1868 fromIndex = rightIndex; 1869 } 1870 /* Empty string always matches. */ 1871 if (targetCount == 0) { 1872 return fromIndex; 1873 } 1874 1875 int strLastIndex = targetOffset + targetCount - 1; 1876 char strLastChar = target[strLastIndex]; 1877 int min = sourceOffset + targetCount - 1; 1878 int i = min + fromIndex; 1879 1880 startSearchForLastChar: 1881 while (true) { 1882 while (i >= min && source[i] != strLastChar) { 1883 i--; 1884 } 1885 if (i < min) { 1886 return -1; 1887 } 1888 int j = i - 1; 1889 int start = j - (targetCount - 1); 1890 int k = strLastIndex - 1; 1891 1892 while (j > start) { 1893 if (source[j--] != target[k--]) { 1894 i--; 1895 continue startSearchForLastChar; 1896 } 1897 } 1898 return start - sourceOffset + 1; 1899 } 1900 } 1901 1902 /** 1903 * Returns a string that is a substring of this string. The 1904 * substring begins with the character at the specified index and 1905 * extends to the end of this string. <p> 1906 * Examples: 1907 * <blockquote><pre> 1908 * "unhappy".substring(2) returns "happy" 1909 * "Harbison".substring(3) returns "bison" 1910 * "emptiness".substring(9) returns "" (an empty string) 1911 * </pre></blockquote> 1912 * 1913 * @param beginIndex the beginning index, inclusive. 1914 * @return the specified substring. 1915 * @exception IndexOutOfBoundsException if 1916 * {@code beginIndex} is negative or larger than the 1917 * length of this {@code String} object. 1918 */ 1919 public String substring(int beginIndex) { 1920 if (beginIndex < 0) { 1921 throw new StringIndexOutOfBoundsException(beginIndex); 1922 } 1923 int subLen = value.length - beginIndex; 1924 if (subLen < 0) { 1925 throw new StringIndexOutOfBoundsException(subLen); 1926 } 1927 return (beginIndex == 0) ? this : new String(value, beginIndex, subLen); 1928 } 1929 1930 /** 1931 * Returns a string that is a substring of this string. The 1932 * substring begins at the specified {@code beginIndex} and 1933 * extends to the character at index {@code endIndex - 1}. 1934 * Thus the length of the substring is {@code endIndex-beginIndex}. 1935 * <p> 1936 * Examples: 1937 * <blockquote><pre> 1938 * "hamburger".substring(4, 8) returns "urge" 1939 * "smiles".substring(1, 5) returns "mile" 1940 * </pre></blockquote> 1941 * 1942 * @param beginIndex the beginning index, inclusive. 1943 * @param endIndex the ending index, exclusive. 1944 * @return the specified substring. 1945 * @exception IndexOutOfBoundsException if the 1946 * {@code beginIndex} is negative, or 1947 * {@code endIndex} is larger than the length of 1948 * this {@code String} object, or 1949 * {@code beginIndex} is larger than 1950 * {@code endIndex}. 1951 */ 1952 public String substring(int beginIndex, int endIndex) { 1953 if (beginIndex < 0) { 1954 throw new StringIndexOutOfBoundsException(beginIndex); 1955 } 1956 if (endIndex > value.length) { 1957 throw new StringIndexOutOfBoundsException(endIndex); 1958 } 1959 int subLen = endIndex - beginIndex; 1960 if (subLen < 0) { 1961 throw new StringIndexOutOfBoundsException(subLen); 1962 } 1963 return ((beginIndex == 0) && (endIndex == value.length)) ? this 1964 : new String(value, beginIndex, subLen); 1965 } 1966 1967 /** 1968 * Returns a character sequence that is a subsequence of this sequence. 1969 * 1970 * <p> An invocation of this method of the form 1971 * 1972 * <blockquote><pre> 1973 * str.subSequence(begin, end)</pre></blockquote> 1974 * 1975 * behaves in exactly the same way as the invocation 1976 * 1977 * <blockquote><pre> 1978 * str.substring(begin, end)</pre></blockquote> 1979 * 1980 * @apiNote 1981 * This method is defined so that the {@code String} class can implement 1982 * the {@link CharSequence} interface. 1983 * 1984 * @param beginIndex the begin index, inclusive. 1985 * @param endIndex the end index, exclusive. 1986 * @return the specified subsequence. 1987 * 1988 * @throws IndexOutOfBoundsException 1989 * if {@code beginIndex} or {@code endIndex} is negative, 1990 * if {@code endIndex} is greater than {@code length()}, 1991 * or if {@code beginIndex} is greater than {@code endIndex} 1992 * 1993 * @since 1.4 1994 * @spec JSR-51 1995 */ 1996 public CharSequence subSequence(int beginIndex, int endIndex) { 1997 return this.substring(beginIndex, endIndex); 1998 } 1999 2000 /** 2001 * Concatenates the specified string to the end of this string. 2002 * <p> 2003 * If the length of the argument string is {@code 0}, then this 2004 * {@code String} object is returned. Otherwise, a 2005 * {@code String} object is returned that represents a character 2006 * sequence that is the concatenation of the character sequence 2007 * represented by this {@code String} object and the character 2008 * sequence represented by the argument string.<p> 2009 * Examples: 2010 * <blockquote><pre> 2011 * "cares".concat("s") returns "caress" 2012 * "to".concat("get").concat("her") returns "together" 2013 * </pre></blockquote> 2014 * 2015 * @param str the {@code String} that is concatenated to the end 2016 * of this {@code String}. 2017 * @return a string that represents the concatenation of this object's 2018 * characters followed by the string argument's characters. 2019 */ 2020 public String concat(String str) { 2021 int otherLen = str.length(); 2022 if (otherLen == 0) { 2023 return this; 2024 } 2025 int len = value.length; 2026 char buf[] = Arrays.copyOf(value, len + otherLen); 2027 str.getChars(buf, len); 2028 return new String(buf, true); 2029 } 2030 2031 /** 2032 * Returns a string resulting from replacing all occurrences of 2033 * {@code oldChar} in this string with {@code newChar}. 2034 * <p> 2035 * If the character {@code oldChar} does not occur in the 2036 * character sequence represented by this {@code String} object, 2037 * then a reference to this {@code String} object is returned. 2038 * Otherwise, a {@code String} object is returned that 2039 * represents a character sequence identical to the character sequence 2040 * represented by this {@code String} object, except that every 2041 * occurrence of {@code oldChar} is replaced by an occurrence 2042 * of {@code newChar}. 2043 * <p> 2044 * Examples: 2045 * <blockquote><pre> 2046 * "mesquite in your cellar".replace('e', 'o') 2047 * returns "mosquito in your collar" 2048 * "the war of baronets".replace('r', 'y') 2049 * returns "the way of bayonets" 2050 * "sparring with a purple porpoise".replace('p', 't') 2051 * returns "starring with a turtle tortoise" 2052 * "JonL".replace('q', 'x') returns "JonL" (no change) 2053 * </pre></blockquote> 2054 * 2055 * @param oldChar the old character. 2056 * @param newChar the new character. 2057 * @return a string derived from this string by replacing every 2058 * occurrence of {@code oldChar} with {@code newChar}. 2059 */ 2060 public String replace(char oldChar, char newChar) { 2061 if (oldChar != newChar) { 2062 int len = value.length; 2063 int i = -1; 2064 char[] val = value; /* avoid getfield opcode */ 2065 2066 while (++i < len) { 2067 if (val[i] == oldChar) { 2068 break; 2069 } 2070 } 2071 if (i < len) { 2072 char buf[] = new char[len]; 2073 for (int j = 0; j < i; j++) { 2074 buf[j] = val[j]; 2075 } 2076 while (i < len) { 2077 char c = val[i]; 2078 buf[i] = (c == oldChar) ? newChar : c; 2079 i++; 2080 } 2081 return new String(buf, true); 2082 } 2083 } 2084 return this; 2085 } 2086 2087 /** 2088 * Tells whether or not this string matches the given <a 2089 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2090 * 2091 * <p> An invocation of this method of the form 2092 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2093 * same result as the expression 2094 * 2095 * <blockquote> 2096 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2097 * matches(<i>regex</i>, <i>str</i>)} 2098 * </blockquote> 2099 * 2100 * @param regex 2101 * the regular expression to which this string is to be matched 2102 * 2103 * @return {@code true} if, and only if, this string matches the 2104 * given regular expression 2105 * 2106 * @throws PatternSyntaxException 2107 * if the regular expression's syntax is invalid 2108 * 2109 * @see java.util.regex.Pattern 2110 * 2111 * @since 1.4 2112 * @spec JSR-51 2113 */ 2114 public boolean matches(String regex) { 2115 return Pattern.matches(regex, this); 2116 } 2117 2118 /** 2119 * Returns true if and only if this string contains the specified 2120 * sequence of char values. 2121 * 2122 * @param s the sequence to search for 2123 * @return true if this string contains {@code s}, false otherwise 2124 * @since 1.5 2125 */ 2126 public boolean contains(CharSequence s) { 2127 return indexOf(s.toString()) >= 0; 2128 } 2129 2130 /** 2131 * Replaces the first substring of this string that matches the given <a 2132 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2133 * given replacement. 2134 * 2135 * <p> An invocation of this method of the form 2136 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2137 * yields exactly the same result as the expression 2138 * 2139 * <blockquote> 2140 * <code> 2141 * {@link java.util.regex.Pattern}.{@link 2142 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2143 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2144 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>) 2145 * </code> 2146 * </blockquote> 2147 * 2148 *<p> 2149 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2150 * replacement string may cause the results to be different than if it were 2151 * being treated as a literal replacement string; see 2152 * {@link java.util.regex.Matcher#replaceFirst}. 2153 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2154 * meaning of these characters, if desired. 2155 * 2156 * @param regex 2157 * the regular expression to which this string is to be matched 2158 * @param replacement 2159 * the string to be substituted for the first match 2160 * 2161 * @return The resulting {@code String} 2162 * 2163 * @throws PatternSyntaxException 2164 * if the regular expression's syntax is invalid 2165 * 2166 * @see java.util.regex.Pattern 2167 * 2168 * @since 1.4 2169 * @spec JSR-51 2170 */ 2171 public String replaceFirst(String regex, String replacement) { 2172 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2173 } 2174 2175 /** 2176 * Replaces each substring of this string that matches the given <a 2177 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2178 * given replacement. 2179 * 2180 * <p> An invocation of this method of the form 2181 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2182 * yields exactly the same result as the expression 2183 * 2184 * <blockquote> 2185 * <code> 2186 * {@link java.util.regex.Pattern}.{@link 2187 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2188 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2189 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2190 * </code> 2191 * </blockquote> 2192 * 2193 *<p> 2194 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2195 * replacement string may cause the results to be different than if it were 2196 * being treated as a literal replacement string; see 2197 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2198 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2199 * meaning of these characters, if desired. 2200 * 2201 * @param regex 2202 * the regular expression to which this string is to be matched 2203 * @param replacement 2204 * the string to be substituted for each match 2205 * 2206 * @return The resulting {@code String} 2207 * 2208 * @throws PatternSyntaxException 2209 * if the regular expression's syntax is invalid 2210 * 2211 * @see java.util.regex.Pattern 2212 * 2213 * @since 1.4 2214 * @spec JSR-51 2215 */ 2216 public String replaceAll(String regex, String replacement) { 2217 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2218 } 2219 2220 /** 2221 * Replaces each substring of this string that matches the literal target 2222 * sequence with the specified literal replacement sequence. The 2223 * replacement proceeds from the beginning of the string to the end, for 2224 * example, replacing "aa" with "b" in the string "aaa" will result in 2225 * "ba" rather than "ab". 2226 * 2227 * @param target The sequence of char values to be replaced 2228 * @param replacement The replacement sequence of char values 2229 * @return The resulting string 2230 * @since 1.5 2231 */ 2232 public String replace(CharSequence target, CharSequence replacement) { 2233 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher( 2234 this).replaceAll(Matcher.quoteReplacement(replacement.toString())); 2235 } 2236 2237 /** 2238 * Splits this string around matches of the given 2239 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2240 * 2241 * <p> The array returned by this method contains each substring of this 2242 * string that is terminated by another substring that matches the given 2243 * expression or is terminated by the end of the string. The substrings in 2244 * the array are in the order in which they occur in this string. If the 2245 * expression does not match any part of the input then the resulting array 2246 * has just one element, namely this string. 2247 * 2248 * <p> When there is a positive-width match at the beginning of this 2249 * string then an empty leading substring is included at the beginning 2250 * of the resulting array. A zero-width match at the beginning however 2251 * never produces such empty leading substring. 2252 * 2253 * <p> The {@code limit} parameter controls the number of times the 2254 * pattern is applied and therefore affects the length of the resulting 2255 * array. If the limit <i>n</i> is greater than zero then the pattern 2256 * will be applied at most <i>n</i> - 1 times, the array's 2257 * length will be no greater than <i>n</i>, and the array's last entry 2258 * will contain all input beyond the last matched delimiter. If <i>n</i> 2259 * is non-positive then the pattern will be applied as many times as 2260 * possible and the array can have any length. If <i>n</i> is zero then 2261 * the pattern will be applied as many times as possible, the array can 2262 * have any length, and trailing empty strings will be discarded. 2263 * 2264 * <p> The string {@code "boo:and:foo"}, for example, yields the 2265 * following results with these parameters: 2266 * 2267 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2268 * <tr> 2269 * <th>Regex</th> 2270 * <th>Limit</th> 2271 * <th>Result</th> 2272 * </tr> 2273 * <tr><td align=center>:</td> 2274 * <td align=center>2</td> 2275 * <td>{@code { "boo", "and:foo" }}</td></tr> 2276 * <tr><td align=center>:</td> 2277 * <td align=center>5</td> 2278 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2279 * <tr><td align=center>:</td> 2280 * <td align=center>-2</td> 2281 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2282 * <tr><td align=center>o</td> 2283 * <td align=center>5</td> 2284 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2285 * <tr><td align=center>o</td> 2286 * <td align=center>-2</td> 2287 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2288 * <tr><td align=center>o</td> 2289 * <td align=center>0</td> 2290 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2291 * </table></blockquote> 2292 * 2293 * <p> An invocation of this method of the form 2294 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2295 * yields the same result as the expression 2296 * 2297 * <blockquote> 2298 * <code> 2299 * {@link java.util.regex.Pattern}.{@link 2300 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2301 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2302 * </code> 2303 * </blockquote> 2304 * 2305 * 2306 * @param regex 2307 * the delimiting regular expression 2308 * 2309 * @param limit 2310 * the result threshold, as described above 2311 * 2312 * @return the array of strings computed by splitting this string 2313 * around matches of the given regular expression 2314 * 2315 * @throws PatternSyntaxException 2316 * if the regular expression's syntax is invalid 2317 * 2318 * @see java.util.regex.Pattern 2319 * 2320 * @since 1.4 2321 * @spec JSR-51 2322 */ 2323 public String[] split(String regex, int limit) { 2324 /* fastpath if the regex is a 2325 (1)one-char String and this character is not one of the 2326 RegEx's meta characters ".$|()[{^?*+\\", or 2327 (2)two-char String and the first char is the backslash and 2328 the second is not the ascii digit or ascii letter. 2329 */ 2330 char ch = 0; 2331 if (((regex.value.length == 1 && 2332 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2333 (regex.length() == 2 && 2334 regex.charAt(0) == '\\' && 2335 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2336 ((ch-'a')|('z'-ch)) < 0 && 2337 ((ch-'A')|('Z'-ch)) < 0)) && 2338 (ch < Character.MIN_HIGH_SURROGATE || 2339 ch > Character.MAX_LOW_SURROGATE)) 2340 { 2341 int off = 0; 2342 int next = 0; 2343 boolean limited = limit > 0; 2344 ArrayList<String> list = new ArrayList<>(); 2345 while ((next = indexOf(ch, off)) != -1) { 2346 if (!limited || list.size() < limit - 1) { 2347 list.add(substring(off, next)); 2348 off = next + 1; 2349 } else { // last one 2350 //assert (list.size() == limit - 1); 2351 list.add(substring(off, value.length)); 2352 off = value.length; 2353 break; 2354 } 2355 } 2356 // If no match was found, return this 2357 if (off == 0) 2358 return new String[]{this}; 2359 2360 // Add remaining segment 2361 if (!limited || list.size() < limit) 2362 list.add(substring(off, value.length)); 2363 2364 // Construct result 2365 int resultSize = list.size(); 2366 if (limit == 0) { 2367 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) { 2368 resultSize--; 2369 } 2370 } 2371 String[] result = new String[resultSize]; 2372 return list.subList(0, resultSize).toArray(result); 2373 } 2374 return Pattern.compile(regex).split(this, limit); 2375 } 2376 2377 /** 2378 * Splits this string around matches of the given <a 2379 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2380 * 2381 * <p> This method works as if by invoking the two-argument {@link 2382 * #split(String, int) split} method with the given expression and a limit 2383 * argument of zero. Trailing empty strings are therefore not included in 2384 * the resulting array. 2385 * 2386 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2387 * results with these expressions: 2388 * 2389 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2390 * <tr> 2391 * <th>Regex</th> 2392 * <th>Result</th> 2393 * </tr> 2394 * <tr><td align=center>:</td> 2395 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2396 * <tr><td align=center>o</td> 2397 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2398 * </table></blockquote> 2399 * 2400 * 2401 * @param regex 2402 * the delimiting regular expression 2403 * 2404 * @return the array of strings computed by splitting this string 2405 * around matches of the given regular expression 2406 * 2407 * @throws PatternSyntaxException 2408 * if the regular expression's syntax is invalid 2409 * 2410 * @see java.util.regex.Pattern 2411 * 2412 * @since 1.4 2413 * @spec JSR-51 2414 */ 2415 public String[] split(String regex) { 2416 return split(regex, 0); 2417 } 2418 2419 /** 2420 * Returns a new String composed of copies of the 2421 * {@code CharSequence elements} joined together with a copy of 2422 * the specified {@code delimiter}. 2423 * 2424 * <blockquote>For example, 2425 * <pre>{@code 2426 * String message = String.join("-", "Java", "is", "cool"); 2427 * // message returned is: "Java-is-cool" 2428 * }</pre></blockquote> 2429 * 2430 * Note that if an element is null, then {@code "null"} is added. 2431 * 2432 * @param delimiter the delimiter that separates each element 2433 * @param elements the elements to join together. 2434 * 2435 * @return a new {@code String} that is composed of the {@code elements} 2436 * separated by the {@code delimiter} 2437 * 2438 * @throws NullPointerException If {@code delimiter} or {@code elements} 2439 * is {@code null} 2440 * 2441 * @see java.util.StringJoiner 2442 * @since 1.8 2443 */ 2444 public static String join(CharSequence delimiter, CharSequence... elements) { 2445 Objects.requireNonNull(delimiter); 2446 Objects.requireNonNull(elements); 2447 // Number of elements not likely worth Arrays.stream overhead. 2448 StringJoiner joiner = new StringJoiner(delimiter); 2449 for (CharSequence cs: elements) { 2450 joiner.add(cs); 2451 } 2452 return joiner.toString(); 2453 } 2454 2455 /** 2456 * Returns a new {@code String} composed of copies of the 2457 * {@code CharSequence elements} joined together with a copy of the 2458 * specified {@code delimiter}. 2459 * 2460 * <blockquote>For example, 2461 * <pre>{@code 2462 * List<String> strings = new LinkedList<>(); 2463 * strings.add("Java");strings.add("is"); 2464 * strings.add("cool"); 2465 * String message = String.join(" ", strings); 2466 * //message returned is: "Java is cool" 2467 * 2468 * Set<String> strings = new LinkedHashSet<>(); 2469 * strings.add("Java"); strings.add("is"); 2470 * strings.add("very"); strings.add("cool"); 2471 * String message = String.join("-", strings); 2472 * //message returned is: "Java-is-very-cool" 2473 * }</pre></blockquote> 2474 * 2475 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2476 * 2477 * @param delimiter a sequence of characters that is used to separate each 2478 * of the {@code elements} in the resulting {@code String} 2479 * @param elements an {@code Iterable} that will have its {@code elements} 2480 * joined together. 2481 * 2482 * @return a new {@code String} that is composed from the {@code elements} 2483 * argument 2484 * 2485 * @throws NullPointerException If {@code delimiter} or {@code elements} 2486 * is {@code null} 2487 * 2488 * @see #join(CharSequence,CharSequence...) 2489 * @see java.util.StringJoiner 2490 * @since 1.8 2491 */ 2492 public static String join(CharSequence delimiter, 2493 Iterable<? extends CharSequence> elements) { 2494 Objects.requireNonNull(delimiter); 2495 Objects.requireNonNull(elements); 2496 StringJoiner joiner = new StringJoiner(delimiter); 2497 for (CharSequence cs: elements) { 2498 joiner.add(cs); 2499 } 2500 return joiner.toString(); 2501 } 2502 2503 /** 2504 * Converts all of the characters in this {@code String} to lower 2505 * case using the rules of the given {@code Locale}. Case mapping is based 2506 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2507 * class. Since case mappings are not always 1:1 char mappings, the resulting 2508 * {@code String} may be a different length than the original {@code String}. 2509 * <p> 2510 * Examples of lowercase mappings are in the following table: 2511 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2512 * <tr> 2513 * <th>Language Code of Locale</th> 2514 * <th>Upper Case</th> 2515 * <th>Lower Case</th> 2516 * <th>Description</th> 2517 * </tr> 2518 * <tr> 2519 * <td>tr (Turkish)</td> 2520 * <td>\u0130</td> 2521 * <td>\u0069</td> 2522 * <td>capital letter I with dot above -> small letter i</td> 2523 * </tr> 2524 * <tr> 2525 * <td>tr (Turkish)</td> 2526 * <td>\u0049</td> 2527 * <td>\u0131</td> 2528 * <td>capital letter I -> small letter dotless i </td> 2529 * </tr> 2530 * <tr> 2531 * <td>(all)</td> 2532 * <td>French Fries</td> 2533 * <td>french fries</td> 2534 * <td>lowercased all chars in String</td> 2535 * </tr> 2536 * <tr> 2537 * <td>(all)</td> 2538 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2539 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2540 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2541 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2542 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2543 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2544 * <td>lowercased all chars in String</td> 2545 * </tr> 2546 * </table> 2547 * 2548 * @param locale use the case transformation rules for this locale 2549 * @return the {@code String}, converted to lowercase. 2550 * @see java.lang.String#toLowerCase() 2551 * @see java.lang.String#toUpperCase() 2552 * @see java.lang.String#toUpperCase(Locale) 2553 * @since 1.1 2554 */ 2555 public String toLowerCase(Locale locale) { 2556 if (locale == null) { 2557 throw new NullPointerException(); 2558 } 2559 int first; 2560 boolean hasSurr = false; 2561 final int len = value.length; 2562 2563 // Now check if there are any characters that need to be changed, or are surrogate 2564 for (first = 0 ; first < len; first++) { 2565 int cp = (int)value[first]; 2566 if (Character.isSurrogate((char)cp)) { 2567 hasSurr = true; 2568 break; 2569 } 2570 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR 2571 break; 2572 } 2573 } 2574 if (first == len) 2575 return this; 2576 char[] result = new char[len]; 2577 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2578 // lowerCase characters. 2579 String lang = locale.getLanguage(); 2580 if (lang == "tr" || lang == "az" || lang == "lt") { 2581 return toLowerCaseEx(result, first, locale, true); 2582 } 2583 if (hasSurr) { 2584 return toLowerCaseEx(result, first, locale, false); 2585 } 2586 for (int i = first; i < len; i++) { 2587 int cp = (int)value[i]; 2588 if (cp == '\u03A3' || // GREEK CAPITAL LETTER SIGMA 2589 Character.isSurrogate((char)cp)) { 2590 return toLowerCaseEx(result, i, locale, false); 2591 } 2592 if (cp == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE 2593 return toLowerCaseEx(result, i, locale, true); 2594 } 2595 cp = Character.toLowerCase(cp); 2596 if (!Character.isBmpCodePoint(cp)) { 2597 return toLowerCaseEx(result, i, locale, false); 2598 } 2599 result[i] = (char)cp; 2600 } 2601 return new String(result, true); 2602 } 2603 2604 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) { 2605 int resultOffset = first; 2606 int srcCount; 2607 for (int i = first; i < value.length; i += srcCount) { 2608 int srcChar = (int)value[i]; 2609 int lowerChar; 2610 char[] lowerCharArray; 2611 srcCount = 1; 2612 if (Character.isSurrogate((char)srcChar)) { 2613 srcChar = codePointAt(i); 2614 srcCount = Character.charCount(srcChar); 2615 } 2616 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA 2617 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale); 2618 } else { 2619 lowerChar = Character.toLowerCase(srcChar); 2620 } 2621 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp 2622 result[resultOffset++] = (char)lowerChar; 2623 } else { 2624 if (lowerChar == Character.ERROR) { 2625 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale); 2626 } else if (srcCount == 2) { 2627 resultOffset += Character.toChars(lowerChar, result, resultOffset); 2628 continue; 2629 } else { 2630 lowerCharArray = Character.toChars(lowerChar); 2631 } 2632 /* Grow result if needed */ 2633 int mapLen = lowerCharArray.length; 2634 if (mapLen > srcCount) { 2635 char[] result2 = new char[result.length + mapLen - srcCount]; 2636 System.arraycopy(result, 0, result2, 0, resultOffset); 2637 result = result2; 2638 } 2639 for (int x = 0; x < mapLen; ++x) { 2640 result[resultOffset++] = lowerCharArray[x]; 2641 } 2642 } 2643 } 2644 return new String(result, 0, resultOffset); 2645 } 2646 2647 /** 2648 * Converts all of the characters in this {@code String} to lower 2649 * case using the rules of the default locale. This is equivalent to calling 2650 * {@code toLowerCase(Locale.getDefault())}. 2651 * <p> 2652 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2653 * results if used for strings that are intended to be interpreted locale 2654 * independently. 2655 * Examples are programming language identifiers, protocol keys, and HTML 2656 * tags. 2657 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2658 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2659 * LATIN SMALL LETTER DOTLESS I character. 2660 * To obtain correct results for locale insensitive strings, use 2661 * {@code toLowerCase(Locale.ROOT)}. 2662 * 2663 * @return the {@code String}, converted to lowercase. 2664 * @see java.lang.String#toLowerCase(Locale) 2665 */ 2666 public String toLowerCase() { 2667 return toLowerCase(Locale.getDefault()); 2668 } 2669 2670 /** 2671 * Converts all of the characters in this {@code String} to upper 2672 * case using the rules of the given {@code Locale}. Case mapping is based 2673 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2674 * class. Since case mappings are not always 1:1 char mappings, the resulting 2675 * {@code String} may be a different length than the original {@code String}. 2676 * <p> 2677 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2678 * 2679 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2680 * <tr> 2681 * <th>Language Code of Locale</th> 2682 * <th>Lower Case</th> 2683 * <th>Upper Case</th> 2684 * <th>Description</th> 2685 * </tr> 2686 * <tr> 2687 * <td>tr (Turkish)</td> 2688 * <td>\u0069</td> 2689 * <td>\u0130</td> 2690 * <td>small letter i -> capital letter I with dot above</td> 2691 * </tr> 2692 * <tr> 2693 * <td>tr (Turkish)</td> 2694 * <td>\u0131</td> 2695 * <td>\u0049</td> 2696 * <td>small letter dotless i -> capital letter I</td> 2697 * </tr> 2698 * <tr> 2699 * <td>(all)</td> 2700 * <td>\u00df</td> 2701 * <td>\u0053 \u0053</td> 2702 * <td>small letter sharp s -> two letters: SS</td> 2703 * </tr> 2704 * <tr> 2705 * <td>(all)</td> 2706 * <td>Fahrvergnügen</td> 2707 * <td>FAHRVERGNÜGEN</td> 2708 * <td></td> 2709 * </tr> 2710 * </table> 2711 * @param locale use the case transformation rules for this locale 2712 * @return the {@code String}, converted to uppercase. 2713 * @see java.lang.String#toUpperCase() 2714 * @see java.lang.String#toLowerCase() 2715 * @see java.lang.String#toLowerCase(Locale) 2716 * @since 1.1 2717 */ 2718 public String toUpperCase(Locale locale) { 2719 if (locale == null) { 2720 throw new NullPointerException(); 2721 } 2722 int first; 2723 boolean hasSurr = false; 2724 final int len = value.length; 2725 2726 // Now check if there are any characters that need to be changed, or are surrogate 2727 for (first = 0 ; first < len; first++ ) { 2728 int cp = (int)value[first]; 2729 if (Character.isSurrogate((char)cp)) { 2730 hasSurr = true; 2731 break; 2732 } 2733 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR 2734 break; 2735 } 2736 } 2737 if (first == len) { 2738 return this; 2739 } 2740 char[] result = new char[len]; 2741 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2742 // upperCase characters. 2743 String lang = locale.getLanguage(); 2744 if (lang == "tr" || lang == "az" || lang == "lt") { 2745 return toUpperCaseEx(result, first, locale, true); 2746 } 2747 if (hasSurr) { 2748 return toUpperCaseEx(result, first, locale, false); 2749 } 2750 for (int i = first; i < len; i++) { 2751 int cp = (int)value[i]; 2752 if (Character.isSurrogate((char)cp)) { 2753 return toUpperCaseEx(result, i, locale, false); 2754 } 2755 cp = Character.toUpperCaseEx(cp); 2756 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp 2757 return toUpperCaseEx(result, i, locale, false); 2758 } 2759 result[i] = (char)cp; 2760 } 2761 return new String(result, true); 2762 } 2763 2764 private String toUpperCaseEx(char[] result, int first, Locale locale, 2765 boolean localeDependent) { 2766 int resultOffset = first; 2767 int srcCount; 2768 for (int i = first; i < value.length; i += srcCount) { 2769 int srcChar = (int)value[i]; 2770 int upperChar; 2771 char[] upperCharArray; 2772 srcCount = 1; 2773 if (Character.isSurrogate((char)srcChar)) { 2774 srcChar = codePointAt(i); 2775 srcCount = Character.charCount(srcChar); 2776 } 2777 if (localeDependent) { 2778 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale); 2779 } else { 2780 upperChar = Character.toUpperCaseEx(srcChar); 2781 } 2782 if (Character.isBmpCodePoint(upperChar)) { 2783 result[resultOffset++] = (char)upperChar; 2784 } else { 2785 if (upperChar == Character.ERROR) { 2786 if (localeDependent) { 2787 upperCharArray = 2788 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale); 2789 } else { 2790 upperCharArray = Character.toUpperCaseCharArray(srcChar); 2791 } 2792 } else if (srcCount == 2) { 2793 resultOffset += Character.toChars(upperChar, result, resultOffset); 2794 continue; 2795 } else { 2796 upperCharArray = Character.toChars(upperChar); 2797 } 2798 /* Grow result if needed */ 2799 int mapLen = upperCharArray.length; 2800 if (mapLen > srcCount) { 2801 char[] result2 = new char[result.length + mapLen - srcCount]; 2802 System.arraycopy(result, 0, result2, 0, resultOffset); 2803 result = result2; 2804 } 2805 for (int x = 0; x < mapLen; ++x) { 2806 result[resultOffset++] = upperCharArray[x]; 2807 } 2808 } 2809 } 2810 return new String(result, 0, resultOffset); 2811 } 2812 2813 /** 2814 * Converts all of the characters in this {@code String} to upper 2815 * case using the rules of the default locale. This method is equivalent to 2816 * {@code toUpperCase(Locale.getDefault())}. 2817 * <p> 2818 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2819 * results if used for strings that are intended to be interpreted locale 2820 * independently. 2821 * Examples are programming language identifiers, protocol keys, and HTML 2822 * tags. 2823 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2824 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2825 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2826 * To obtain correct results for locale insensitive strings, use 2827 * {@code toUpperCase(Locale.ROOT)}. 2828 * 2829 * @return the {@code String}, converted to uppercase. 2830 * @see java.lang.String#toUpperCase(Locale) 2831 */ 2832 public String toUpperCase() { 2833 return toUpperCase(Locale.getDefault()); 2834 } 2835 2836 /** 2837 * Returns a string whose value is this string, with any leading and trailing 2838 * whitespace removed. 2839 * <p> 2840 * If this {@code String} object represents an empty character 2841 * sequence, or the first and last characters of character sequence 2842 * represented by this {@code String} object both have codes 2843 * greater than {@code '\u005Cu0020'} (the space character), then a 2844 * reference to this {@code String} object is returned. 2845 * <p> 2846 * Otherwise, if there is no character with a code greater than 2847 * {@code '\u005Cu0020'} in the string, then a 2848 * {@code String} object representing an empty string is 2849 * returned. 2850 * <p> 2851 * Otherwise, let <i>k</i> be the index of the first character in the 2852 * string whose code is greater than {@code '\u005Cu0020'}, and let 2853 * <i>m</i> be the index of the last character in the string whose code 2854 * is greater than {@code '\u005Cu0020'}. A {@code String} 2855 * object is returned, representing the substring of this string that 2856 * begins with the character at index <i>k</i> and ends with the 2857 * character at index <i>m</i>-that is, the result of 2858 * {@code this.substring(k, m + 1)}. 2859 * <p> 2860 * This method may be used to trim whitespace (as defined above) from 2861 * the beginning and end of a string. 2862 * 2863 * @return A string whose value is this string, with any leading and trailing white 2864 * space removed, or this string if it has no leading or 2865 * trailing white space. 2866 */ 2867 public String trim() { 2868 int len = value.length; 2869 int st = 0; 2870 char[] val = value; /* avoid getfield opcode */ 2871 2872 while ((st < len) && (val[st] <= ' ')) { 2873 st++; 2874 } 2875 while ((st < len) && (val[len - 1] <= ' ')) { 2876 len--; 2877 } 2878 return ((st > 0) || (len < value.length)) ? substring(st, len) : this; 2879 } 2880 2881 /** 2882 * This object (which is already a string!) is itself returned. 2883 * 2884 * @return the string itself. 2885 */ 2886 public String toString() { 2887 return this; 2888 } 2889 2890 /** 2891 * Converts this string to a new character array. 2892 * 2893 * @return a newly allocated character array whose length is the length 2894 * of this string and whose contents are initialized to contain 2895 * the character sequence represented by this string. 2896 */ 2897 public char[] toCharArray() { 2898 // Cannot use Arrays.copyOf because of class initialization order issues 2899 char result[] = new char[value.length]; 2900 System.arraycopy(value, 0, result, 0, value.length); 2901 return result; 2902 } 2903 2904 /** 2905 * Returns a formatted string using the specified format string and 2906 * arguments. 2907 * 2908 * <p> The locale always used is the one returned by {@link 2909 * java.util.Locale#getDefault() Locale.getDefault()}. 2910 * 2911 * @param format 2912 * A <a href="../util/Formatter.html#syntax">format string</a> 2913 * 2914 * @param args 2915 * Arguments referenced by the format specifiers in the format 2916 * string. If there are more arguments than format specifiers, the 2917 * extra arguments are ignored. The number of arguments is 2918 * variable and may be zero. The maximum number of arguments is 2919 * limited by the maximum dimension of a Java array as defined by 2920 * <cite>The Java™ Virtual Machine Specification</cite>. 2921 * The behaviour on a 2922 * {@code null} argument depends on the <a 2923 * href="../util/Formatter.html#syntax">conversion</a>. 2924 * 2925 * @throws java.util.IllegalFormatException 2926 * If a format string contains an illegal syntax, a format 2927 * specifier that is incompatible with the given arguments, 2928 * insufficient arguments given the format string, or other 2929 * illegal conditions. For specification of all possible 2930 * formatting errors, see the <a 2931 * href="../util/Formatter.html#detail">Details</a> section of the 2932 * formatter class specification. 2933 * 2934 * @return A formatted string 2935 * 2936 * @see java.util.Formatter 2937 * @since 1.5 2938 */ 2939 public static String format(String format, Object... args) { 2940 return new Formatter().format(format, args).toString(); 2941 } 2942 2943 /** 2944 * Returns a formatted string using the specified locale, format string, 2945 * and arguments. 2946 * 2947 * @param l 2948 * The {@linkplain java.util.Locale locale} to apply during 2949 * formatting. If {@code l} is {@code null} then no localization 2950 * is applied. 2951 * 2952 * @param format 2953 * A <a href="../util/Formatter.html#syntax">format string</a> 2954 * 2955 * @param args 2956 * Arguments referenced by the format specifiers in the format 2957 * string. If there are more arguments than format specifiers, the 2958 * extra arguments are ignored. The number of arguments is 2959 * variable and may be zero. The maximum number of arguments is 2960 * limited by the maximum dimension of a Java array as defined by 2961 * <cite>The Java™ Virtual Machine Specification</cite>. 2962 * The behaviour on a 2963 * {@code null} argument depends on the 2964 * <a href="../util/Formatter.html#syntax">conversion</a>. 2965 * 2966 * @throws java.util.IllegalFormatException 2967 * If a format string contains an illegal syntax, a format 2968 * specifier that is incompatible with the given arguments, 2969 * insufficient arguments given the format string, or other 2970 * illegal conditions. For specification of all possible 2971 * formatting errors, see the <a 2972 * href="../util/Formatter.html#detail">Details</a> section of the 2973 * formatter class specification 2974 * 2975 * @return A formatted string 2976 * 2977 * @see java.util.Formatter 2978 * @since 1.5 2979 */ 2980 public static String format(Locale l, String format, Object... args) { 2981 return new Formatter(l).format(format, args).toString(); 2982 } 2983 2984 /** 2985 * Returns the string representation of the {@code Object} argument. 2986 * 2987 * @param obj an {@code Object}. 2988 * @return if the argument is {@code null}, then a string equal to 2989 * {@code "null"}; otherwise, the value of 2990 * {@code obj.toString()} is returned. 2991 * @see java.lang.Object#toString() 2992 */ 2993 public static String valueOf(Object obj) { 2994 return (obj == null) ? "null" : obj.toString(); 2995 } 2996 2997 /** 2998 * Returns the string representation of the {@code char} array 2999 * argument. The contents of the character array are copied; subsequent 3000 * modification of the character array does not affect the returned 3001 * string. 3002 * 3003 * @param data the character array. 3004 * @return a {@code String} that contains the characters of the 3005 * character array. 3006 */ 3007 public static String valueOf(char data[]) { 3008 return new String(data); 3009 } 3010 3011 /** 3012 * Returns the string representation of a specific subarray of the 3013 * {@code char} array argument. 3014 * <p> 3015 * The {@code offset} argument is the index of the first 3016 * character of the subarray. The {@code count} argument 3017 * specifies the length of the subarray. The contents of the subarray 3018 * are copied; subsequent modification of the character array does not 3019 * affect the returned string. 3020 * 3021 * @param data the character array. 3022 * @param offset initial offset of the subarray. 3023 * @param count length of the subarray. 3024 * @return a {@code String} that contains the characters of the 3025 * specified subarray of the character array. 3026 * @exception IndexOutOfBoundsException if {@code offset} is 3027 * negative, or {@code count} is negative, or 3028 * {@code offset+count} is larger than 3029 * {@code data.length}. 3030 */ 3031 public static String valueOf(char data[], int offset, int count) { 3032 return new String(data, offset, count); 3033 } 3034 3035 /** 3036 * Equivalent to {@link #valueOf(char[], int, int)}. 3037 * 3038 * @param data the character array. 3039 * @param offset initial offset of the subarray. 3040 * @param count length of the subarray. 3041 * @return a {@code String} that contains the characters of the 3042 * specified subarray of the character array. 3043 * @exception IndexOutOfBoundsException if {@code offset} is 3044 * negative, or {@code count} is negative, or 3045 * {@code offset+count} is larger than 3046 * {@code data.length}. 3047 */ 3048 public static String copyValueOf(char data[], int offset, int count) { 3049 return new String(data, offset, count); 3050 } 3051 3052 /** 3053 * Equivalent to {@link #valueOf(char[])}. 3054 * 3055 * @param data the character array. 3056 * @return a {@code String} that contains the characters of the 3057 * character array. 3058 */ 3059 public static String copyValueOf(char data[]) { 3060 return new String(data); 3061 } 3062 3063 /** 3064 * Returns the string representation of the {@code boolean} argument. 3065 * 3066 * @param b a {@code boolean}. 3067 * @return if the argument is {@code true}, a string equal to 3068 * {@code "true"} is returned; otherwise, a string equal to 3069 * {@code "false"} is returned. 3070 */ 3071 public static String valueOf(boolean b) { 3072 return b ? "true" : "false"; 3073 } 3074 3075 /** 3076 * Returns the string representation of the {@code char} 3077 * argument. 3078 * 3079 * @param c a {@code char}. 3080 * @return a string of length {@code 1} containing 3081 * as its single character the argument {@code c}. 3082 */ 3083 public static String valueOf(char c) { 3084 char data[] = {c}; 3085 return new String(data, true); 3086 } 3087 3088 /** 3089 * Returns the string representation of the {@code int} argument. 3090 * <p> 3091 * The representation is exactly the one returned by the 3092 * {@code Integer.toString} method of one argument. 3093 * 3094 * @param i an {@code int}. 3095 * @return a string representation of the {@code int} argument. 3096 * @see java.lang.Integer#toString(int, int) 3097 */ 3098 public static String valueOf(int i) { 3099 return Integer.toString(i); 3100 } 3101 3102 /** 3103 * Returns the string representation of the {@code long} argument. 3104 * <p> 3105 * The representation is exactly the one returned by the 3106 * {@code Long.toString} method of one argument. 3107 * 3108 * @param l a {@code long}. 3109 * @return a string representation of the {@code long} argument. 3110 * @see java.lang.Long#toString(long) 3111 */ 3112 public static String valueOf(long l) { 3113 return Long.toString(l); 3114 } 3115 3116 /** 3117 * Returns the string representation of the {@code float} argument. 3118 * <p> 3119 * The representation is exactly the one returned by the 3120 * {@code Float.toString} method of one argument. 3121 * 3122 * @param f a {@code float}. 3123 * @return a string representation of the {@code float} argument. 3124 * @see java.lang.Float#toString(float) 3125 */ 3126 public static String valueOf(float f) { 3127 return Float.toString(f); 3128 } 3129 3130 /** 3131 * Returns the string representation of the {@code double} argument. 3132 * <p> 3133 * The representation is exactly the one returned by the 3134 * {@code Double.toString} method of one argument. 3135 * 3136 * @param d a {@code double}. 3137 * @return a string representation of the {@code double} argument. 3138 * @see java.lang.Double#toString(double) 3139 */ 3140 public static String valueOf(double d) { 3141 return Double.toString(d); 3142 } 3143 3144 /** 3145 * Returns a canonical representation for the string object. 3146 * <p> 3147 * A pool of strings, initially empty, is maintained privately by the 3148 * class {@code String}. 3149 * <p> 3150 * When the intern method is invoked, if the pool already contains a 3151 * string equal to this {@code String} object as determined by 3152 * the {@link #equals(Object)} method, then the string from the pool is 3153 * returned. Otherwise, this {@code String} object is added to the 3154 * pool and a reference to this {@code String} object is returned. 3155 * <p> 3156 * It follows that for any two strings {@code s} and {@code t}, 3157 * {@code s.intern() == t.intern()} is {@code true} 3158 * if and only if {@code s.equals(t)} is {@code true}. 3159 * <p> 3160 * All literal strings and string-valued constant expressions are 3161 * interned. String literals are defined in section 3.10.5 of the 3162 * <cite>The Java™ Language Specification</cite>. 3163 * 3164 * @return a string that has the same contents as this string, but is 3165 * guaranteed to be from a pool of unique strings. 3166 */ 3167 public native String intern(); 3168 }