1 /* 2 * Copyright (c) 1994, 2013, 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 JDK1.0 109 */ 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 * Initializes a newly created {@code String} object so that it represents 134 * an empty character sequence. Note that use of this constructor is 135 * unnecessary since Strings are immutable. 136 */ 137 public String() { 138 this.value = new char[0]; 139 } 140 141 /** 142 * Initializes a newly created {@code String} object so that it represents 143 * the same sequence of characters as the argument; in other words, the 144 * newly created string is a copy of the argument string. Unless an 145 * explicit copy of {@code original} is needed, use of this constructor is 146 * unnecessary since Strings are immutable. 147 * 148 * @param original 149 * A {@code String} 150 */ 151 public String(String original) { 152 this.value = original.value; 153 this.hash = original.hash; 154 } 155 156 /** 157 * Allocates a new {@code String} so that it represents the sequence of 158 * characters currently contained in the character array argument. The 159 * contents of the character array are copied; subsequent modification of 160 * the character array does not affect the newly created string. 161 * 162 * @param value 163 * The initial value of the string 164 */ 165 public String(char value[]) { 166 this.value = Arrays.copyOf(value, value.length); 167 } 168 169 /** 170 * Allocates a new {@code String} that contains characters from a subarray 171 * of the character array argument. The {@code offset} argument is the 172 * index of the first character of the subarray and the {@code count} 173 * argument specifies the length of the subarray. The contents of the 174 * subarray are copied; subsequent modification of the character array does 175 * not affect the newly created string. 176 * 177 * @param value 178 * Array that is the source of characters 179 * 180 * @param offset 181 * The initial offset 182 * 183 * @param count 184 * The length 185 * 186 * @throws IndexOutOfBoundsException 187 * If the {@code offset} and {@code count} arguments index 188 * characters outside the bounds of the {@code value} array 189 */ 190 public String(char value[], int offset, int count) { 191 if (offset < 0) { 192 throw new StringIndexOutOfBoundsException(offset); 193 } 194 if (count < 0) { 195 throw new StringIndexOutOfBoundsException(count); 196 } 197 // Note: offset or count might be near -1>>>1. 198 if (offset > value.length - count) { 199 throw new StringIndexOutOfBoundsException(offset + count); 200 } 201 this.value = Arrays.copyOfRange(value, offset, offset+count); 202 } 203 204 /** 205 * Allocates a new {@code String} that contains characters from a subarray 206 * of the <a href="Character.html#unicode">Unicode code point</a> array 207 * argument. The {@code offset} argument is the index of the first code 208 * point of the subarray and the {@code count} argument specifies the 209 * length of the subarray. The contents of the subarray are converted to 210 * {@code char}s; subsequent modification of the {@code int} array does not 211 * affect the newly created string. 212 * 213 * @param codePoints 214 * Array that is the source of Unicode code points 215 * 216 * @param offset 217 * The initial offset 218 * 219 * @param count 220 * The length 221 * 222 * @throws IllegalArgumentException 223 * If any invalid Unicode code point is found in {@code 224 * codePoints} 225 * 226 * @throws IndexOutOfBoundsException 227 * If the {@code offset} and {@code count} arguments index 228 * characters outside the bounds of the {@code codePoints} array 229 * 230 * @since 1.5 231 */ 232 public String(int[] codePoints, int offset, int count) { 233 if (offset < 0) { 234 throw new StringIndexOutOfBoundsException(offset); 235 } 236 if (count < 0) { 237 throw new StringIndexOutOfBoundsException(count); 238 } 239 // Note: offset or count might be near -1>>>1. 240 if (offset > codePoints.length - count) { 241 throw new StringIndexOutOfBoundsException(offset + count); 242 } 243 244 final int end = offset + count; 245 246 // Pass 1: Compute precise size of char[] 247 int n = count; 248 for (int i = offset; i < end; i++) { 249 int c = codePoints[i]; 250 if (Character.isBmpCodePoint(c)) 251 continue; 252 else if (Character.isValidCodePoint(c)) 253 n++; 254 else throw new IllegalArgumentException(Integer.toString(c)); 255 } 256 257 // Pass 2: Allocate and fill in char[] 258 final char[] v = new char[n]; 259 260 for (int i = offset, j = 0; i < end; i++, j++) { 261 int c = codePoints[i]; 262 if (Character.isBmpCodePoint(c)) 263 v[j] = (char)c; 264 else 265 Character.toSurrogates(c, v, j++); 266 } 267 268 this.value = v; 269 } 270 271 /** 272 * Allocates a new {@code String} constructed from a subarray of an array 273 * of 8-bit integer values. 274 * 275 * <p> The {@code offset} argument is the index of the first byte of the 276 * subarray, and the {@code count} argument specifies the length of the 277 * subarray. 278 * 279 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 280 * specified in the method above. 281 * 282 * @deprecated This method does not properly convert bytes into characters. 283 * As of JDK 1.1, the preferred way to do this is via the 284 * {@code String} constructors that take a {@link 285 * java.nio.charset.Charset}, charset name, or that use the platform's 286 * default charset. 287 * 288 * @param ascii 289 * The bytes to be converted to characters 290 * 291 * @param hibyte 292 * The top 8 bits of each 16-bit Unicode code unit 293 * 294 * @param offset 295 * The initial offset 296 * @param count 297 * The length 298 * 299 * @throws IndexOutOfBoundsException 300 * If the {@code offset} or {@code count} argument is invalid 301 * 302 * @see #String(byte[], int) 303 * @see #String(byte[], int, int, java.lang.String) 304 * @see #String(byte[], int, int, java.nio.charset.Charset) 305 * @see #String(byte[], int, int) 306 * @see #String(byte[], java.lang.String) 307 * @see #String(byte[], java.nio.charset.Charset) 308 * @see #String(byte[]) 309 */ 310 @Deprecated 311 public String(byte ascii[], int hibyte, int offset, int count) { 312 checkBounds(ascii, offset, count); 313 char value[] = new char[count]; 314 315 if (hibyte == 0) { 316 for (int i = count; i-- > 0;) { 317 value[i] = (char)(ascii[i + offset] & 0xff); 318 } 319 } else { 320 hibyte <<= 8; 321 for (int i = count; i-- > 0;) { 322 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff)); 323 } 324 } 325 this.value = value; 326 } 327 328 /** 329 * Allocates a new {@code String} containing characters constructed from 330 * an array of 8-bit integer values. Each character <i>c</i>in the 331 * resulting string is constructed from the corresponding component 332 * <i>b</i> in the byte array such that: 333 * 334 * <blockquote><pre> 335 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 336 * | (<b><i>b</i></b> & 0xff)) 337 * </pre></blockquote> 338 * 339 * @deprecated This method does not properly convert bytes into 340 * characters. As of JDK 1.1, the preferred way to do this is via the 341 * {@code String} constructors that take a {@link 342 * java.nio.charset.Charset}, charset name, or that use the platform's 343 * default charset. 344 * 345 * @param ascii 346 * The bytes to be converted to characters 347 * 348 * @param hibyte 349 * The top 8 bits of each 16-bit Unicode code unit 350 * 351 * @see #String(byte[], int, int, java.lang.String) 352 * @see #String(byte[], int, int, java.nio.charset.Charset) 353 * @see #String(byte[], int, int) 354 * @see #String(byte[], java.lang.String) 355 * @see #String(byte[], java.nio.charset.Charset) 356 * @see #String(byte[]) 357 */ 358 @Deprecated 359 public String(byte ascii[], int hibyte) { 360 this(ascii, hibyte, 0, ascii.length); 361 } 362 363 /* Common private utility method used to bounds check the byte array 364 * and requested offset & length values used by the String(byte[],..) 365 * constructors. 366 */ 367 private static void checkBounds(byte[] bytes, int offset, int length) { 368 if (length < 0) 369 throw new StringIndexOutOfBoundsException(length); 370 if (offset < 0) 371 throw new StringIndexOutOfBoundsException(offset); 372 if (offset > bytes.length - length) 373 throw new StringIndexOutOfBoundsException(offset + length); 374 } 375 376 /** 377 * Constructs a new {@code String} by decoding the specified subarray of 378 * bytes using the specified charset. The length of the new {@code String} 379 * is a function of the charset, and hence may not be equal to the length 380 * of the subarray. 381 * 382 * <p> The behavior of this constructor when the given bytes are not valid 383 * in the given charset is unspecified. The {@link 384 * java.nio.charset.CharsetDecoder} class should be used when more control 385 * over the decoding process is required. 386 * 387 * @param bytes 388 * The bytes to be decoded into characters 389 * 390 * @param offset 391 * The index of the first byte to decode 392 * 393 * @param length 394 * The number of bytes to decode 395 396 * @param charsetName 397 * The name of a supported {@linkplain java.nio.charset.Charset 398 * charset} 399 * 400 * @throws UnsupportedEncodingException 401 * If the named charset is not supported 402 * 403 * @throws IndexOutOfBoundsException 404 * If the {@code offset} and {@code length} arguments index 405 * characters outside the bounds of the {@code bytes} array 406 * 407 * @since JDK1.1 408 */ 409 public String(byte bytes[], int offset, int length, String charsetName) 410 throws UnsupportedEncodingException { 411 if (charsetName == null) 412 throw new NullPointerException("charsetName"); 413 checkBounds(bytes, offset, length); 414 this.value = StringCoding.decode(charsetName, bytes, offset, length); 415 } 416 417 /** 418 * Constructs a new {@code String} by decoding the specified subarray of 419 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 420 * The length of the new {@code String} is a function of the charset, and 421 * hence may not be equal to the length of the subarray. 422 * 423 * <p> This method always replaces malformed-input and unmappable-character 424 * sequences with this charset's default replacement string. The {@link 425 * java.nio.charset.CharsetDecoder} class should be used when more control 426 * over the decoding process is required. 427 * 428 * @param bytes 429 * The bytes to be decoded into characters 430 * 431 * @param offset 432 * The index of the first byte to decode 433 * 434 * @param length 435 * The number of bytes to decode 436 * 437 * @param charset 438 * The {@linkplain java.nio.charset.Charset charset} to be used to 439 * decode the {@code bytes} 440 * 441 * @throws IndexOutOfBoundsException 442 * If the {@code offset} and {@code length} arguments index 443 * characters outside the bounds of the {@code bytes} array 444 * 445 * @since 1.6 446 */ 447 public String(byte bytes[], int offset, int length, Charset charset) { 448 if (charset == null) 449 throw new NullPointerException("charset"); 450 checkBounds(bytes, offset, length); 451 this.value = StringCoding.decode(charset, bytes, offset, length); 452 } 453 454 /** 455 * Constructs a new {@code String} by decoding the specified array of bytes 456 * using the specified {@linkplain java.nio.charset.Charset charset}. The 457 * length of the new {@code String} is a function of the charset, and hence 458 * may not be equal to the length of the byte array. 459 * 460 * <p> The behavior of this constructor when the given bytes are not valid 461 * in the given charset is unspecified. The {@link 462 * java.nio.charset.CharsetDecoder} class should be used when more control 463 * over the decoding process is required. 464 * 465 * @param bytes 466 * The bytes to be decoded into characters 467 * 468 * @param charsetName 469 * The name of a supported {@linkplain java.nio.charset.Charset 470 * charset} 471 * 472 * @throws UnsupportedEncodingException 473 * If the named charset is not supported 474 * 475 * @since JDK1.1 476 */ 477 public String(byte bytes[], String charsetName) 478 throws UnsupportedEncodingException { 479 this(bytes, 0, bytes.length, charsetName); 480 } 481 482 /** 483 * Constructs a new {@code String} by decoding the specified array of 484 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 485 * The length of the new {@code String} is a function of the charset, and 486 * hence may not be equal to the length of the byte array. 487 * 488 * <p> This method always replaces malformed-input and unmappable-character 489 * sequences with this charset's default replacement string. The {@link 490 * java.nio.charset.CharsetDecoder} class should be used when more control 491 * over the decoding process is required. 492 * 493 * @param bytes 494 * The bytes to be decoded into characters 495 * 496 * @param charset 497 * The {@linkplain java.nio.charset.Charset charset} to be used to 498 * decode the {@code bytes} 499 * 500 * @since 1.6 501 */ 502 public String(byte bytes[], Charset charset) { 503 this(bytes, 0, bytes.length, charset); 504 } 505 506 /** 507 * Constructs a new {@code String} by decoding the specified subarray of 508 * bytes using the platform's default charset. The length of the new 509 * {@code String} is a function of the charset, and hence may not be equal 510 * to the length of the subarray. 511 * 512 * <p> The behavior of this constructor when the given bytes are not valid 513 * in the default charset is unspecified. The {@link 514 * java.nio.charset.CharsetDecoder} class should be used when more control 515 * over the decoding process is required. 516 * 517 * @param bytes 518 * The bytes to be decoded into characters 519 * 520 * @param offset 521 * The index of the first byte to decode 522 * 523 * @param length 524 * The number of bytes to decode 525 * 526 * @throws IndexOutOfBoundsException 527 * If the {@code offset} and the {@code length} arguments index 528 * characters outside the bounds of the {@code bytes} array 529 * 530 * @since JDK1.1 531 */ 532 public String(byte bytes[], int offset, int length) { 533 checkBounds(bytes, offset, length); 534 this.value = StringCoding.decode(bytes, offset, length); 535 } 536 537 /** 538 * Constructs a new {@code String} by decoding the specified array of bytes 539 * using the platform's default charset. The length of the new {@code 540 * String} is a function of the charset, and hence may not be equal to the 541 * length of the byte array. 542 * 543 * <p> The behavior of this constructor when the given bytes are not valid 544 * in the default charset is unspecified. The {@link 545 * java.nio.charset.CharsetDecoder} class should be used when more control 546 * over the decoding process is required. 547 * 548 * @param bytes 549 * The bytes to be decoded into characters 550 * 551 * @since JDK1.1 552 */ 553 public String(byte bytes[]) { 554 this(bytes, 0, bytes.length); 555 } 556 557 /** 558 * Allocates a new string that contains the sequence of characters 559 * currently contained in the string buffer argument. The contents of the 560 * string buffer are copied; subsequent modification of the string buffer 561 * does not affect the newly created string. 562 * 563 * @param buffer 564 * A {@code StringBuffer} 565 */ 566 public String(StringBuffer buffer) { 567 synchronized(buffer) { 568 this.value = Arrays.copyOf(buffer.getValue(), buffer.length()); 569 } 570 } 571 572 /** 573 * Allocates a new string that contains the sequence of characters 574 * currently contained in the string builder argument. The contents of the 575 * string builder are copied; subsequent modification of the string builder 576 * does not affect the newly created string. 577 * 578 * <p> This constructor is provided to ease migration to {@code 579 * StringBuilder}. Obtaining a string from a string builder via the {@code 580 * toString} method is likely to run faster and is generally preferred. 581 * 582 * @param builder 583 * A {@code StringBuilder} 584 * 585 * @since 1.5 586 */ 587 public String(StringBuilder builder) { 588 this.value = Arrays.copyOf(builder.getValue(), builder.length()); 589 } 590 591 /* 592 * Package private constructor which shares value array for speed. 593 * this constructor is always expected to be called with share==true. 594 * a separate constructor is needed because we already have a public 595 * String(char[]) constructor that makes a copy of the given char[]. 596 */ 597 String(char[] value, boolean share) { 598 // assert share : "unshared not supported"; 599 this.value = value; 600 } 601 602 /** 603 * Returns the length of this string. 604 * The length is equal to the number of <a href="Character.html#unicode">Unicode 605 * code units</a> in the string. 606 * 607 * @return the length of the sequence of characters represented by this 608 * object. 609 */ 610 public int length() { 611 return value.length; 612 } 613 614 /** 615 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 616 * 617 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 618 * {@code false} 619 * 620 * @since 1.6 621 */ 622 public boolean isEmpty() { 623 return value.length == 0; 624 } 625 626 /** 627 * Returns the {@code char} value at the 628 * specified index. An index ranges from {@code 0} to 629 * {@code length() - 1}. The first {@code char} value of the sequence 630 * is at index {@code 0}, the next at index {@code 1}, 631 * and so on, as for array indexing. 632 * 633 * <p>If the {@code char} value specified by the index is a 634 * <a href="Character.html#unicode">surrogate</a>, the surrogate 635 * value is returned. 636 * 637 * @param index the index of the {@code char} value. 638 * @return the {@code char} value at the specified index of this string. 639 * The first {@code char} value is at index {@code 0}. 640 * @exception IndexOutOfBoundsException if the {@code index} 641 * argument is negative or not less than the length of this 642 * string. 643 */ 644 public char charAt(int index) { 645 if ((index < 0) || (index >= value.length)) { 646 throw new StringIndexOutOfBoundsException(index); 647 } 648 return value[index]; 649 } 650 651 /** 652 * Returns the character (Unicode code point) at the specified 653 * index. The index refers to {@code char} values 654 * (Unicode code units) and ranges from {@code 0} to 655 * {@link #length()}{@code - 1}. 656 * 657 * <p> If the {@code char} value specified at the given index 658 * is in the high-surrogate range, the following index is less 659 * than the length of this {@code String}, and the 660 * {@code char} value at the following index is in the 661 * low-surrogate range, then the supplementary code point 662 * corresponding to this surrogate pair is returned. Otherwise, 663 * the {@code char} value at the given index is returned. 664 * 665 * @param index the index to the {@code char} values 666 * @return the code point value of the character at the 667 * {@code index} 668 * @exception IndexOutOfBoundsException if the {@code index} 669 * argument is negative or not less than the length of this 670 * string. 671 * @since 1.5 672 */ 673 public int codePointAt(int index) { 674 if ((index < 0) || (index >= value.length)) { 675 throw new StringIndexOutOfBoundsException(index); 676 } 677 return Character.codePointAtImpl(value, index, value.length); 678 } 679 680 /** 681 * Returns the character (Unicode code point) before the specified 682 * index. The index refers to {@code char} values 683 * (Unicode code units) and ranges from {@code 1} to {@link 684 * CharSequence#length() length}. 685 * 686 * <p> If the {@code char} value at {@code (index - 1)} 687 * is in the low-surrogate range, {@code (index - 2)} is not 688 * negative, and the {@code char} value at {@code (index - 689 * 2)} is in the high-surrogate range, then the 690 * supplementary code point value of the surrogate pair is 691 * returned. If the {@code char} value at {@code index - 692 * 1} is an unpaired low-surrogate or a high-surrogate, the 693 * surrogate value is returned. 694 * 695 * @param index the index following the code point that should be returned 696 * @return the Unicode code point value before the given index. 697 * @exception IndexOutOfBoundsException if the {@code index} 698 * argument is less than 1 or greater than the length 699 * of this string. 700 * @since 1.5 701 */ 702 public int codePointBefore(int index) { 703 int i = index - 1; 704 if ((i < 0) || (i >= value.length)) { 705 throw new StringIndexOutOfBoundsException(index); 706 } 707 return Character.codePointBeforeImpl(value, index, 0); 708 } 709 710 /** 711 * Returns the number of Unicode code points in the specified text 712 * range of this {@code String}. The text range begins at the 713 * specified {@code beginIndex} and extends to the 714 * {@code char} at index {@code endIndex - 1}. Thus the 715 * length (in {@code char}s) of the text range is 716 * {@code endIndex-beginIndex}. Unpaired surrogates within 717 * the text range count as one code point each. 718 * 719 * @param beginIndex the index to the first {@code char} of 720 * the text range. 721 * @param endIndex the index after the last {@code char} of 722 * the text range. 723 * @return the number of Unicode code points in the specified text 724 * range 725 * @exception IndexOutOfBoundsException if the 726 * {@code beginIndex} is negative, or {@code endIndex} 727 * is larger than the length of this {@code String}, or 728 * {@code beginIndex} is larger than {@code endIndex}. 729 * @since 1.5 730 */ 731 public int codePointCount(int beginIndex, int endIndex) { 732 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) { 733 throw new IndexOutOfBoundsException(); 734 } 735 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex); 736 } 737 738 /** 739 * Returns the index within this {@code String} that is 740 * offset from the given {@code index} by 741 * {@code codePointOffset} code points. Unpaired surrogates 742 * within the text range given by {@code index} and 743 * {@code codePointOffset} count as one code point each. 744 * 745 * @param index the index to be offset 746 * @param codePointOffset the offset in code points 747 * @return the index within this {@code String} 748 * @exception IndexOutOfBoundsException if {@code index} 749 * is negative or larger then the length of this 750 * {@code String}, or if {@code codePointOffset} is positive 751 * and the substring starting with {@code index} has fewer 752 * than {@code codePointOffset} code points, 753 * or if {@code codePointOffset} is negative and the substring 754 * before {@code index} has fewer than the absolute value 755 * of {@code codePointOffset} code points. 756 * @since 1.5 757 */ 758 public int offsetByCodePoints(int index, int codePointOffset) { 759 if (index < 0 || index > value.length) { 760 throw new IndexOutOfBoundsException(); 761 } 762 return Character.offsetByCodePointsImpl(value, 0, value.length, 763 index, codePointOffset); 764 } 765 766 /** 767 * Copy characters from this string into dst starting at dstBegin. 768 * This method doesn't perform any range checking. 769 */ 770 void getChars(char dst[], int dstBegin) { 771 System.arraycopy(value, 0, dst, dstBegin, value.length); 772 } 773 774 /** 775 * Copies characters from this string into the destination character 776 * array. 777 * <p> 778 * The first character to be copied is at index {@code srcBegin}; 779 * the last character to be copied is at index {@code srcEnd-1} 780 * (thus the total number of characters to be copied is 781 * {@code srcEnd-srcBegin}). The characters are copied into the 782 * subarray of {@code dst} starting at index {@code dstBegin} 783 * and ending at index: 784 * <blockquote><pre> 785 * dstbegin + (srcEnd-srcBegin) - 1 786 * </pre></blockquote> 787 * 788 * @param srcBegin index of the first character in the string 789 * to copy. 790 * @param srcEnd index after the last character in the string 791 * to copy. 792 * @param dst the destination array. 793 * @param dstBegin the start offset in the destination array. 794 * @exception IndexOutOfBoundsException If any of the following 795 * is true: 796 * <ul><li>{@code srcBegin} is negative. 797 * <li>{@code srcBegin} is greater than {@code srcEnd} 798 * <li>{@code srcEnd} is greater than the length of this 799 * string 800 * <li>{@code dstBegin} is negative 801 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 802 * {@code dst.length}</ul> 803 */ 804 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 805 if (srcBegin < 0) { 806 throw new StringIndexOutOfBoundsException(srcBegin); 807 } 808 if (srcEnd > value.length) { 809 throw new StringIndexOutOfBoundsException(srcEnd); 810 } 811 if (srcBegin > srcEnd) { 812 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 813 } 814 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin); 815 } 816 817 /** 818 * Copies characters from this string into the destination byte array. Each 819 * byte receives the 8 low-order bits of the corresponding character. The 820 * eight high-order bits of each character are not copied and do not 821 * participate in the transfer in any way. 822 * 823 * <p> The first character to be copied is at index {@code srcBegin}; the 824 * last character to be copied is at index {@code srcEnd-1}. The total 825 * number of characters to be copied is {@code srcEnd-srcBegin}. The 826 * characters, converted to bytes, are copied into the subarray of {@code 827 * dst} starting at index {@code dstBegin} and ending at index: 828 * 829 * <blockquote><pre> 830 * dstbegin + (srcEnd-srcBegin) - 1 831 * </pre></blockquote> 832 * 833 * @deprecated This method does not properly convert characters into 834 * bytes. As of JDK 1.1, the preferred way to do this is via the 835 * {@link #getBytes()} method, which uses the platform's default charset. 836 * 837 * @param srcBegin 838 * Index of the first character in the string to copy 839 * 840 * @param srcEnd 841 * Index after the last character in the string to copy 842 * 843 * @param dst 844 * The destination array 845 * 846 * @param dstBegin 847 * The start offset in the destination array 848 * 849 * @throws IndexOutOfBoundsException 850 * If any of the following is true: 851 * <ul> 852 * <li> {@code srcBegin} is negative 853 * <li> {@code srcBegin} is greater than {@code srcEnd} 854 * <li> {@code srcEnd} is greater than the length of this String 855 * <li> {@code dstBegin} is negative 856 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 857 * dst.length} 858 * </ul> 859 */ 860 @Deprecated 861 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 862 if (srcBegin < 0) { 863 throw new StringIndexOutOfBoundsException(srcBegin); 864 } 865 if (srcEnd > value.length) { 866 throw new StringIndexOutOfBoundsException(srcEnd); 867 } 868 if (srcBegin > srcEnd) { 869 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 870 } 871 Objects.requireNonNull(dst); 872 873 int j = dstBegin; 874 int n = srcEnd; 875 int i = srcBegin; 876 char[] val = value; /* avoid getfield opcode */ 877 878 while (i < n) { 879 dst[j++] = (byte)val[i++]; 880 } 881 } 882 883 /** 884 * Encodes this {@code String} into a sequence of bytes using the named 885 * charset, storing the result into a new byte array. 886 * 887 * <p> The behavior of this method when this string cannot be encoded in 888 * the given charset is unspecified. The {@link 889 * java.nio.charset.CharsetEncoder} class should be used when more control 890 * over the encoding process is required. 891 * 892 * @param charsetName 893 * The name of a supported {@linkplain java.nio.charset.Charset 894 * charset} 895 * 896 * @return The resultant byte array 897 * 898 * @throws UnsupportedEncodingException 899 * If the named charset is not supported 900 * 901 * @since JDK1.1 902 */ 903 public byte[] getBytes(String charsetName) 904 throws UnsupportedEncodingException { 905 if (charsetName == null) throw new NullPointerException(); 906 return StringCoding.encode(charsetName, value, 0, value.length); 907 } 908 909 /** 910 * Encodes this {@code String} into a sequence of bytes using the given 911 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 912 * new byte array. 913 * 914 * <p> This method always replaces malformed-input and unmappable-character 915 * sequences with this charset's default replacement byte array. The 916 * {@link java.nio.charset.CharsetEncoder} class should be used when more 917 * control over the encoding process is required. 918 * 919 * @param charset 920 * The {@linkplain java.nio.charset.Charset} to be used to encode 921 * the {@code String} 922 * 923 * @return The resultant byte array 924 * 925 * @since 1.6 926 */ 927 public byte[] getBytes(Charset charset) { 928 if (charset == null) throw new NullPointerException(); 929 return StringCoding.encode(charset, value, 0, value.length); 930 } 931 932 /** 933 * Encodes this {@code String} into a sequence of bytes using the 934 * platform's default charset, storing the result into a new byte array. 935 * 936 * <p> The behavior of this method when this string cannot be encoded in 937 * the default charset is unspecified. The {@link 938 * java.nio.charset.CharsetEncoder} class should be used when more control 939 * over the encoding process is required. 940 * 941 * @return The resultant byte array 942 * 943 * @since JDK1.1 944 */ 945 public byte[] getBytes() { 946 return StringCoding.encode(value, 0, value.length); 947 } 948 949 /** 950 * Compares this string to the specified object. The result is {@code 951 * true} if and only if the argument is not {@code null} and is a {@code 952 * String} object that represents the same sequence of characters as this 953 * object. 954 * 955 * @param anObject 956 * The object to compare this {@code String} against 957 * 958 * @return {@code true} if the given object represents a {@code String} 959 * equivalent to this string, {@code false} otherwise 960 * 961 * @see #compareTo(String) 962 * @see #equalsIgnoreCase(String) 963 */ 964 public boolean equals(Object anObject) { 965 if (this == anObject) { 966 return true; 967 } 968 if (anObject instanceof String) { 969 String anotherString = (String)anObject; 970 int n = value.length; 971 if (n == anotherString.value.length) { 972 char v1[] = value; 973 char v2[] = anotherString.value; 974 int i = 0; 975 while (n-- != 0) { 976 if (v1[i] != v2[i]) 977 return false; 978 i++; 979 } 980 return true; 981 } 982 } 983 return false; 984 } 985 986 /** 987 * Compares this string to the specified {@code StringBuffer}. The result 988 * is {@code true} if and only if this {@code String} represents the same 989 * sequence of characters as the specified {@code StringBuffer}. This method 990 * synchronizes on the {@code StringBuffer}. 991 * 992 * @param sb 993 * The {@code StringBuffer} to compare this {@code String} against 994 * 995 * @return {@code true} if this {@code String} represents the same 996 * sequence of characters as the specified {@code StringBuffer}, 997 * {@code false} otherwise 998 * 999 * @since 1.4 1000 */ 1001 public boolean contentEquals(StringBuffer sb) { 1002 return contentEquals((CharSequence)sb); 1003 } 1004 1005 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1006 char v1[] = value; 1007 char v2[] = sb.getValue(); 1008 int n = v1.length; 1009 if (n != sb.length()) { 1010 return false; 1011 } 1012 for (int i = 0; i < n; i++) { 1013 if (v1[i] != v2[i]) { 1014 return false; 1015 } 1016 } 1017 return true; 1018 } 1019 1020 /** 1021 * Compares this string to the specified {@code CharSequence}. The 1022 * result is {@code true} if and only if this {@code String} represents the 1023 * same sequence of char values as the specified sequence. Note that if the 1024 * {@code CharSequence} is a {@code StringBuffer} then the method 1025 * synchronizes on it. 1026 * 1027 * @param cs 1028 * The sequence to compare this {@code String} against 1029 * 1030 * @return {@code true} if this {@code String} represents the same 1031 * sequence of char values as the specified sequence, {@code 1032 * false} otherwise 1033 * 1034 * @since 1.5 1035 */ 1036 public boolean contentEquals(CharSequence cs) { 1037 // Argument is a StringBuffer, StringBuilder 1038 if (cs instanceof AbstractStringBuilder) { 1039 if (cs instanceof StringBuffer) { 1040 synchronized(cs) { 1041 return nonSyncContentEquals((AbstractStringBuilder)cs); 1042 } 1043 } else { 1044 return nonSyncContentEquals((AbstractStringBuilder)cs); 1045 } 1046 } 1047 // Argument is a String 1048 if (cs.equals(this)) 1049 return true; 1050 // Argument is a generic CharSequence 1051 char v1[] = value; 1052 int n = v1.length; 1053 if (n != cs.length()) { 1054 return false; 1055 } 1056 for (int i = 0; i < n; i++) { 1057 if (v1[i] != cs.charAt(i)) { 1058 return false; 1059 } 1060 } 1061 return true; 1062 } 1063 1064 /** 1065 * Compares this {@code String} to another {@code String}, ignoring case 1066 * considerations. Two strings are considered equal ignoring case if they 1067 * are of the same length and corresponding characters in the two strings 1068 * are equal ignoring case. 1069 * 1070 * <p> Two characters {@code c1} and {@code c2} are considered the same 1071 * ignoring case if at least one of the following is true: 1072 * <ul> 1073 * <li> The two characters are the same (as compared by the 1074 * {@code ==} operator) 1075 * <li> Applying the method {@link 1076 * java.lang.Character#toUpperCase(char)} to each character 1077 * produces the same result 1078 * <li> Applying the method {@link 1079 * java.lang.Character#toLowerCase(char)} to each character 1080 * produces the same result 1081 * </ul> 1082 * 1083 * @param anotherString 1084 * The {@code String} to compare this {@code String} against 1085 * 1086 * @return {@code true} if the argument is not {@code null} and it 1087 * represents an equivalent {@code String} ignoring case; {@code 1088 * false} otherwise 1089 * 1090 * @see #equals(Object) 1091 */ 1092 public boolean equalsIgnoreCase(String anotherString) { 1093 return (this == anotherString) ? true 1094 : (anotherString != null) 1095 && (anotherString.value.length == value.length) 1096 && regionMatches(true, 0, anotherString, 0, value.length); 1097 } 1098 1099 /** 1100 * Compares two strings lexicographically. 1101 * The comparison is based on the Unicode value of each character in 1102 * the strings. The character sequence represented by this 1103 * {@code String} object is compared lexicographically to the 1104 * character sequence represented by the argument string. The result is 1105 * a negative integer if this {@code String} object 1106 * lexicographically precedes the argument string. The result is a 1107 * positive integer if this {@code String} object lexicographically 1108 * follows the argument string. The result is zero if the strings 1109 * are equal; {@code compareTo} returns {@code 0} exactly when 1110 * the {@link #equals(Object)} method would return {@code true}. 1111 * <p> 1112 * This is the definition of lexicographic ordering. If two strings are 1113 * different, then either they have different characters at some index 1114 * that is a valid index for both strings, or their lengths are different, 1115 * or both. If they have different characters at one or more index 1116 * positions, let <i>k</i> be the smallest such index; then the string 1117 * whose character at position <i>k</i> has the smaller value, as 1118 * determined by using the < operator, lexicographically precedes the 1119 * other string. In this case, {@code compareTo} returns the 1120 * difference of the two character values at position {@code k} in 1121 * the two string -- that is, the value: 1122 * <blockquote><pre> 1123 * this.charAt(k)-anotherString.charAt(k) 1124 * </pre></blockquote> 1125 * If there is no index position at which they differ, then the shorter 1126 * string lexicographically precedes the longer string. In this case, 1127 * {@code compareTo} returns the difference of the lengths of the 1128 * strings -- that is, the value: 1129 * <blockquote><pre> 1130 * this.length()-anotherString.length() 1131 * </pre></blockquote> 1132 * 1133 * @param anotherString the {@code String} to be compared. 1134 * @return the value {@code 0} if the argument string is equal to 1135 * this string; a value less than {@code 0} if this string 1136 * is lexicographically less than the string argument; and a 1137 * value greater than {@code 0} if this string is 1138 * lexicographically greater than the string argument. 1139 */ 1140 public int compareTo(String anotherString) { 1141 int len1 = value.length; 1142 int len2 = anotherString.value.length; 1143 int lim = Math.min(len1, len2); 1144 char v1[] = value; 1145 char v2[] = anotherString.value; 1146 1147 int k = 0; 1148 while (k < lim) { 1149 char c1 = v1[k]; 1150 char c2 = v2[k]; 1151 if (c1 != c2) { 1152 return c1 - c2; 1153 } 1154 k++; 1155 } 1156 return len1 - len2; 1157 } 1158 1159 /** 1160 * A Comparator that orders {@code String} objects as by 1161 * {@code compareToIgnoreCase}. This comparator is serializable. 1162 * <p> 1163 * Note that this Comparator does <em>not</em> take locale into account, 1164 * and will result in an unsatisfactory ordering for certain locales. 1165 * The java.text package provides <em>Collators</em> to allow 1166 * locale-sensitive ordering. 1167 * 1168 * @see java.text.Collator#compare(String, String) 1169 * @since 1.2 1170 */ 1171 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1172 = new CaseInsensitiveComparator(); 1173 private static class CaseInsensitiveComparator 1174 implements Comparator<String>, java.io.Serializable { 1175 // use serialVersionUID from JDK 1.2.2 for interoperability 1176 private static final long serialVersionUID = 8575799808933029326L; 1177 1178 public int compare(String s1, String s2) { 1179 int n1 = s1.length(); 1180 int n2 = s2.length(); 1181 int min = Math.min(n1, n2); 1182 for (int i = 0; i < min; i++) { 1183 char c1 = s1.charAt(i); 1184 char c2 = s2.charAt(i); 1185 if (c1 != c2) { 1186 c1 = Character.toUpperCase(c1); 1187 c2 = Character.toUpperCase(c2); 1188 if (c1 != c2) { 1189 c1 = Character.toLowerCase(c1); 1190 c2 = Character.toLowerCase(c2); 1191 if (c1 != c2) { 1192 // No overflow because of numeric promotion 1193 return c1 - c2; 1194 } 1195 } 1196 } 1197 } 1198 return n1 - n2; 1199 } 1200 1201 /** Replaces the de-serialized object. */ 1202 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1203 } 1204 1205 /** 1206 * Compares two strings lexicographically, ignoring case 1207 * differences. This method returns an integer whose sign is that of 1208 * calling {@code compareTo} with normalized versions of the strings 1209 * where case differences have been eliminated by calling 1210 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1211 * each character. 1212 * <p> 1213 * Note that this method does <em>not</em> take locale into account, 1214 * and will result in an unsatisfactory ordering for certain locales. 1215 * The java.text package provides <em>collators</em> to allow 1216 * locale-sensitive ordering. 1217 * 1218 * @param str the {@code String} to be compared. 1219 * @return a negative integer, zero, or a positive integer as the 1220 * specified String is greater than, equal to, or less 1221 * than this String, ignoring case considerations. 1222 * @see java.text.Collator#compare(String, String) 1223 * @since 1.2 1224 */ 1225 public int compareToIgnoreCase(String str) { 1226 return CASE_INSENSITIVE_ORDER.compare(this, str); 1227 } 1228 1229 /** 1230 * Tests if two string regions are equal. 1231 * <p> 1232 * A substring of this {@code String} object is compared to a substring 1233 * of the argument other. The result is true if these substrings 1234 * represent identical character sequences. The substring of this 1235 * {@code String} object to be compared begins at index {@code toffset} 1236 * and has length {@code len}. The substring of other to be compared 1237 * begins at index {@code ooffset} and has length {@code len}. The 1238 * result is {@code false} if and only if at least one of the following 1239 * is true: 1240 * <ul><li>{@code toffset} is negative. 1241 * <li>{@code ooffset} is negative. 1242 * <li>{@code toffset+len} is greater than the length of this 1243 * {@code String} object. 1244 * <li>{@code ooffset+len} is greater than the length of the other 1245 * argument. 1246 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1247 * such that: 1248 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1249 * <i>k</i>{@code )} 1250 * </ul> 1251 * 1252 * @param toffset the starting offset of the subregion in this string. 1253 * @param other the string argument. 1254 * @param ooffset the starting offset of the subregion in the string 1255 * argument. 1256 * @param len the number of characters to compare. 1257 * @return {@code true} if the specified subregion of this string 1258 * exactly matches the specified subregion of the string argument; 1259 * {@code false} otherwise. 1260 */ 1261 public boolean regionMatches(int toffset, String other, int ooffset, 1262 int len) { 1263 char ta[] = value; 1264 int to = toffset; 1265 char pa[] = other.value; 1266 int po = ooffset; 1267 // Note: toffset, ooffset, or len might be near -1>>>1. 1268 if ((ooffset < 0) || (toffset < 0) 1269 || (toffset > (long)value.length - len) 1270 || (ooffset > (long)other.value.length - len)) { 1271 return false; 1272 } 1273 while (len-- > 0) { 1274 if (ta[to++] != pa[po++]) { 1275 return false; 1276 } 1277 } 1278 return true; 1279 } 1280 1281 /** 1282 * Tests if two string regions are equal. 1283 * <p> 1284 * A substring of this {@code String} object is compared to a substring 1285 * of the argument {@code other}. The result is {@code true} if these 1286 * substrings represent character sequences that are the same, ignoring 1287 * case if and only if {@code ignoreCase} is true. The substring of 1288 * this {@code String} object to be compared begins at index 1289 * {@code toffset} and has length {@code len}. The substring of 1290 * {@code other} to be compared begins at index {@code ooffset} and 1291 * has length {@code len}. The result is {@code false} if and only if 1292 * at least one of the following is true: 1293 * <ul><li>{@code toffset} is negative. 1294 * <li>{@code ooffset} is negative. 1295 * <li>{@code toffset+len} is greater than the length of this 1296 * {@code String} object. 1297 * <li>{@code ooffset+len} is greater than the length of the other 1298 * argument. 1299 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1300 * integer <i>k</i> less than {@code len} such that: 1301 * <blockquote><pre> 1302 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1303 * </pre></blockquote> 1304 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1305 * integer <i>k</i> less than {@code len} such that: 1306 * <blockquote><pre> 1307 * Character.toLowerCase(this.charAt(toffset+k)) != 1308 Character.toLowerCase(other.charAt(ooffset+k)) 1309 * </pre></blockquote> 1310 * and: 1311 * <blockquote><pre> 1312 * Character.toUpperCase(this.charAt(toffset+k)) != 1313 * Character.toUpperCase(other.charAt(ooffset+k)) 1314 * </pre></blockquote> 1315 * </ul> 1316 * 1317 * @param ignoreCase if {@code true}, ignore case when comparing 1318 * characters. 1319 * @param toffset the starting offset of the subregion in this 1320 * string. 1321 * @param other the string argument. 1322 * @param ooffset the starting offset of the subregion in the string 1323 * argument. 1324 * @param len the number of characters to compare. 1325 * @return {@code true} if the specified subregion of this string 1326 * matches the specified subregion of the string argument; 1327 * {@code false} otherwise. Whether the matching is exact 1328 * or case insensitive depends on the {@code ignoreCase} 1329 * argument. 1330 */ 1331 public boolean regionMatches(boolean ignoreCase, int toffset, 1332 String other, int ooffset, int len) { 1333 char ta[] = value; 1334 int to = toffset; 1335 char pa[] = other.value; 1336 int po = ooffset; 1337 // Note: toffset, ooffset, or len might be near -1>>>1. 1338 if ((ooffset < 0) || (toffset < 0) 1339 || (toffset > (long)value.length - len) 1340 || (ooffset > (long)other.value.length - len)) { 1341 return false; 1342 } 1343 while (len-- > 0) { 1344 char c1 = ta[to++]; 1345 char c2 = pa[po++]; 1346 if (c1 == c2) { 1347 continue; 1348 } 1349 if (ignoreCase) { 1350 // If characters don't match but case may be ignored, 1351 // try converting both characters to uppercase. 1352 // If the results match, then the comparison scan should 1353 // continue. 1354 char u1 = Character.toUpperCase(c1); 1355 char u2 = Character.toUpperCase(c2); 1356 if (u1 == u2) { 1357 continue; 1358 } 1359 // Unfortunately, conversion to uppercase does not work properly 1360 // for the Georgian alphabet, which has strange rules about case 1361 // conversion. So we need to make one last check before 1362 // exiting. 1363 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) { 1364 continue; 1365 } 1366 } 1367 return false; 1368 } 1369 return true; 1370 } 1371 1372 /** 1373 * Tests if the substring of this string beginning at the 1374 * specified index starts with the specified prefix. 1375 * 1376 * @param prefix the prefix. 1377 * @param toffset where to begin looking in this string. 1378 * @return {@code true} if the character sequence represented by the 1379 * argument is a prefix of the substring of this object starting 1380 * at index {@code toffset}; {@code false} otherwise. 1381 * The result is {@code false} if {@code toffset} is 1382 * negative or greater than the length of this 1383 * {@code String} object; otherwise the result is the same 1384 * as the result of the expression 1385 * <pre> 1386 * this.substring(toffset).startsWith(prefix) 1387 * </pre> 1388 */ 1389 public boolean startsWith(String prefix, int toffset) { 1390 char ta[] = value; 1391 int to = toffset; 1392 char pa[] = prefix.value; 1393 int po = 0; 1394 int pc = prefix.value.length; 1395 // Note: toffset might be near -1>>>1. 1396 if ((toffset < 0) || (toffset > value.length - pc)) { 1397 return false; 1398 } 1399 while (--pc >= 0) { 1400 if (ta[to++] != pa[po++]) { 1401 return false; 1402 } 1403 } 1404 return true; 1405 } 1406 1407 /** 1408 * Tests if this string starts with the specified prefix. 1409 * 1410 * @param prefix the prefix. 1411 * @return {@code true} if the character sequence represented by the 1412 * argument is a prefix of the character sequence represented by 1413 * this string; {@code false} otherwise. 1414 * Note also that {@code true} will be returned if the 1415 * argument is an empty string or is equal to this 1416 * {@code String} object as determined by the 1417 * {@link #equals(Object)} method. 1418 * @since 1. 0 1419 */ 1420 public boolean startsWith(String prefix) { 1421 return startsWith(prefix, 0); 1422 } 1423 1424 /** 1425 * Tests if this string ends with the specified suffix. 1426 * 1427 * @param suffix the suffix. 1428 * @return {@code true} if the character sequence represented by the 1429 * argument is a suffix of the character sequence represented by 1430 * this object; {@code false} otherwise. Note that the 1431 * result will be {@code true} if the argument is the 1432 * empty string or is equal to this {@code String} object 1433 * as determined by the {@link #equals(Object)} method. 1434 */ 1435 public boolean endsWith(String suffix) { 1436 return startsWith(suffix, value.length - suffix.value.length); 1437 } 1438 1439 /** 1440 * Returns a hash code for this string. The hash code for a 1441 * {@code String} object is computed as 1442 * <blockquote><pre> 1443 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1444 * </pre></blockquote> 1445 * using {@code int} arithmetic, where {@code s[i]} is the 1446 * <i>i</i>th character of the string, {@code n} is the length of 1447 * the string, and {@code ^} indicates exponentiation. 1448 * (The hash value of the empty string is zero.) 1449 * 1450 * @return a hash code value for this object. 1451 */ 1452 public int hashCode() { 1453 int h = hash; 1454 if (h == 0 && value.length > 0) { 1455 char val[] = value; 1456 1457 for (int i = 0; i < value.length; i++) { 1458 h = 31 * h + val[i]; 1459 } 1460 hash = h; 1461 } 1462 return h; 1463 } 1464 1465 /** 1466 * Returns the index within this string of the first occurrence of 1467 * the specified character. If a character with value 1468 * {@code ch} occurs in the character sequence represented by 1469 * this {@code String} object, then the index (in Unicode 1470 * code units) of the first such occurrence is returned. For 1471 * values of {@code ch} in the range from 0 to 0xFFFF 1472 * (inclusive), this is the smallest value <i>k</i> such that: 1473 * <blockquote><pre> 1474 * this.charAt(<i>k</i>) == ch 1475 * </pre></blockquote> 1476 * is true. For other values of {@code ch}, it is the 1477 * smallest value <i>k</i> such that: 1478 * <blockquote><pre> 1479 * this.codePointAt(<i>k</i>) == ch 1480 * </pre></blockquote> 1481 * is true. In either case, if no such character occurs in this 1482 * string, then {@code -1} is returned. 1483 * 1484 * @param ch a character (Unicode code point). 1485 * @return the index of the first occurrence of the character in the 1486 * character sequence represented by this object, or 1487 * {@code -1} if the character does not occur. 1488 */ 1489 public int indexOf(int ch) { 1490 return indexOf(ch, 0); 1491 } 1492 1493 /** 1494 * Returns the index within this string of the first occurrence of the 1495 * specified character, starting the search at the specified index. 1496 * <p> 1497 * If a character with value {@code ch} occurs in the 1498 * character sequence represented by this {@code String} 1499 * object at an index no smaller than {@code fromIndex}, then 1500 * the index of the first such occurrence is returned. For values 1501 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1502 * this is the smallest value <i>k</i> such that: 1503 * <blockquote><pre> 1504 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1505 * </pre></blockquote> 1506 * is true. For other values of {@code ch}, it is the 1507 * smallest value <i>k</i> such that: 1508 * <blockquote><pre> 1509 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1510 * </pre></blockquote> 1511 * is true. In either case, if no such character occurs in this 1512 * string at or after position {@code fromIndex}, then 1513 * {@code -1} is returned. 1514 * 1515 * <p> 1516 * There is no restriction on the value of {@code fromIndex}. If it 1517 * is negative, it has the same effect as if it were zero: this entire 1518 * string may be searched. If it is greater than the length of this 1519 * string, it has the same effect as if it were equal to the length of 1520 * this string: {@code -1} is returned. 1521 * 1522 * <p>All indices are specified in {@code char} values 1523 * (Unicode code units). 1524 * 1525 * @param ch a character (Unicode code point). 1526 * @param fromIndex the index to start the search from. 1527 * @return the index of the first occurrence of the character in the 1528 * character sequence represented by this object that is greater 1529 * than or equal to {@code fromIndex}, or {@code -1} 1530 * if the character does not occur. 1531 */ 1532 public int indexOf(int ch, int fromIndex) { 1533 final int max = value.length; 1534 if (fromIndex < 0) { 1535 fromIndex = 0; 1536 } else if (fromIndex >= max) { 1537 // Note: fromIndex might be near -1>>>1. 1538 return -1; 1539 } 1540 1541 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1542 // handle most cases here (ch is a BMP code point or a 1543 // negative value (invalid code point)) 1544 final char[] value = this.value; 1545 for (int i = fromIndex; i < max; i++) { 1546 if (value[i] == ch) { 1547 return i; 1548 } 1549 } 1550 return -1; 1551 } else { 1552 return indexOfSupplementary(ch, fromIndex); 1553 } 1554 } 1555 1556 /** 1557 * Handles (rare) calls of indexOf with a supplementary character. 1558 */ 1559 private int indexOfSupplementary(int ch, int fromIndex) { 1560 if (Character.isValidCodePoint(ch)) { 1561 final char[] value = this.value; 1562 final char hi = Character.highSurrogate(ch); 1563 final char lo = Character.lowSurrogate(ch); 1564 final int max = value.length - 1; 1565 for (int i = fromIndex; i < max; i++) { 1566 if (value[i] == hi && value[i + 1] == lo) { 1567 return i; 1568 } 1569 } 1570 } 1571 return -1; 1572 } 1573 1574 /** 1575 * Returns the index within this string of the last occurrence of 1576 * the specified character. For values of {@code ch} in the 1577 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1578 * units) returned is the largest value <i>k</i> such that: 1579 * <blockquote><pre> 1580 * this.charAt(<i>k</i>) == ch 1581 * </pre></blockquote> 1582 * is true. For other values of {@code ch}, it is the 1583 * largest value <i>k</i> such that: 1584 * <blockquote><pre> 1585 * this.codePointAt(<i>k</i>) == ch 1586 * </pre></blockquote> 1587 * is true. In either case, if no such character occurs in this 1588 * string, then {@code -1} is returned. The 1589 * {@code String} is searched backwards starting at the last 1590 * character. 1591 * 1592 * @param ch a character (Unicode code point). 1593 * @return the index of the last occurrence of the character in the 1594 * character sequence represented by this object, or 1595 * {@code -1} if the character does not occur. 1596 */ 1597 public int lastIndexOf(int ch) { 1598 return lastIndexOf(ch, value.length - 1); 1599 } 1600 1601 /** 1602 * Returns the index within this string of the last occurrence of 1603 * the specified character, searching backward starting at the 1604 * specified index. For values of {@code ch} in the range 1605 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1606 * value <i>k</i> such that: 1607 * <blockquote><pre> 1608 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1609 * </pre></blockquote> 1610 * is true. For other values of {@code ch}, it is the 1611 * largest value <i>k</i> such that: 1612 * <blockquote><pre> 1613 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1614 * </pre></blockquote> 1615 * is true. In either case, if no such character occurs in this 1616 * string at or before position {@code fromIndex}, then 1617 * {@code -1} is returned. 1618 * 1619 * <p>All indices are specified in {@code char} values 1620 * (Unicode code units). 1621 * 1622 * @param ch a character (Unicode code point). 1623 * @param fromIndex the index to start the search from. There is no 1624 * restriction on the value of {@code fromIndex}. If it is 1625 * greater than or equal to the length of this string, it has 1626 * the same effect as if it were equal to one less than the 1627 * length of this string: this entire string may be searched. 1628 * If it is negative, it has the same effect as if it were -1: 1629 * -1 is returned. 1630 * @return the index of the last occurrence of the character in the 1631 * character sequence represented by this object that is less 1632 * than or equal to {@code fromIndex}, or {@code -1} 1633 * if the character does not occur before that point. 1634 */ 1635 public int lastIndexOf(int ch, int fromIndex) { 1636 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1637 // handle most cases here (ch is a BMP code point or a 1638 // negative value (invalid code point)) 1639 final char[] value = this.value; 1640 int i = Math.min(fromIndex, value.length - 1); 1641 for (; i >= 0; i--) { 1642 if (value[i] == ch) { 1643 return i; 1644 } 1645 } 1646 return -1; 1647 } else { 1648 return lastIndexOfSupplementary(ch, fromIndex); 1649 } 1650 } 1651 1652 /** 1653 * Handles (rare) calls of lastIndexOf with a supplementary character. 1654 */ 1655 private int lastIndexOfSupplementary(int ch, int fromIndex) { 1656 if (Character.isValidCodePoint(ch)) { 1657 final char[] value = this.value; 1658 char hi = Character.highSurrogate(ch); 1659 char lo = Character.lowSurrogate(ch); 1660 int i = Math.min(fromIndex, value.length - 2); 1661 for (; i >= 0; i--) { 1662 if (value[i] == hi && value[i + 1] == lo) { 1663 return i; 1664 } 1665 } 1666 } 1667 return -1; 1668 } 1669 1670 /** 1671 * Returns the index within this string of the first occurrence of the 1672 * specified substring. 1673 * 1674 * <p>The returned index is the smallest value {@code k} for which: 1675 * <pre>{@code 1676 * this.startsWith(str, k) 1677 * }</pre> 1678 * If no such value of {@code k} exists, then {@code -1} is returned. 1679 * 1680 * @param str the substring to search for. 1681 * @return the index of the first occurrence of the specified substring, 1682 * or {@code -1} if there is no such occurrence. 1683 */ 1684 public int indexOf(String str) { 1685 return indexOf(str, 0); 1686 } 1687 1688 /** 1689 * Returns the index within this string of the first occurrence of the 1690 * specified substring, starting at the specified index. 1691 * 1692 * <p>The returned index is the smallest value {@code k} for which: 1693 * <pre>{@code 1694 * k >= Math.min(fromIndex, this.length()) && 1695 * this.startsWith(str, k) 1696 * }</pre> 1697 * If no such value of {@code k} exists, then {@code -1} is returned. 1698 * 1699 * @param str the substring to search for. 1700 * @param fromIndex the index from which to start the search. 1701 * @return the index of the first occurrence of the specified substring, 1702 * starting at the specified index, 1703 * or {@code -1} if there is no such occurrence. 1704 */ 1705 public int indexOf(String str, int fromIndex) { 1706 return indexOf(value, 0, value.length, 1707 str.value, 0, str.value.length, fromIndex); 1708 } 1709 1710 /** 1711 * Code shared by String and AbstractStringBuilder to do searches. The 1712 * source is the character array being searched, and the target 1713 * is the string being searched for. 1714 * 1715 * @param source the characters being searched. 1716 * @param sourceOffset offset of the source string. 1717 * @param sourceCount count of the source string. 1718 * @param target the characters being searched for. 1719 * @param fromIndex the index to begin searching from. 1720 */ 1721 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1722 String target, int fromIndex) { 1723 return indexOf(source, sourceOffset, sourceCount, 1724 target.value, 0, target.value.length, 1725 fromIndex); 1726 } 1727 1728 /** 1729 * Code shared by String and StringBuffer to do searches. The 1730 * source is the character array being searched, and the target 1731 * is the string being searched for. 1732 * 1733 * @param source the characters being searched. 1734 * @param sourceOffset offset of the source string. 1735 * @param sourceCount count of the source string. 1736 * @param target the characters being searched for. 1737 * @param targetOffset offset of the target string. 1738 * @param targetCount count of the target string. 1739 * @param fromIndex the index to begin searching from. 1740 */ 1741 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1742 char[] target, int targetOffset, int targetCount, 1743 int fromIndex) { 1744 if (fromIndex >= sourceCount) { 1745 return (targetCount == 0 ? sourceCount : -1); 1746 } 1747 if (fromIndex < 0) { 1748 fromIndex = 0; 1749 } 1750 if (targetCount == 0) { 1751 return fromIndex; 1752 } 1753 1754 char first = target[targetOffset]; 1755 char second = 0; 1756 if (targetCount != 1) { 1757 second = target[targetOffset + 1]; 1758 } 1759 int max = sourceOffset + (sourceCount - targetCount); 1760 1761 for (int i = sourceOffset + fromIndex; i <= max; i++) { 1762 /* Look for first character. */ 1763 if (source[i] != first) { 1764 while (++i <= max && source[i] != first); 1765 } 1766 if (targetCount == 1) { 1767 return (i <= max) ? i - sourceOffset : -1; 1768 } 1769 /* Found first character, now look at the rest of v2 */ 1770 if (i <= max && source[i + 1] == second) { 1771 int j = i + 2; 1772 int end = i + targetCount; 1773 for (int k = targetOffset + 2; j < end && source[j] 1774 == target[k]; j++, k++); 1775 1776 if (j == end) { 1777 /* Found whole string. */ 1778 return i - sourceOffset; 1779 } 1780 } 1781 } 1782 return -1; 1783 } 1784 1785 /** 1786 * Returns the index within this string of the last occurrence of the 1787 * specified substring. The last occurrence of the empty string "" 1788 * is considered to occur at the index value {@code this.length()}. 1789 * 1790 * <p>The returned index is the largest value {@code k} for which: 1791 * <pre>{@code 1792 * this.startsWith(str, k) 1793 * }</pre> 1794 * If no such value of {@code k} exists, then {@code -1} is returned. 1795 * 1796 * @param str the substring to search for. 1797 * @return the index of the last occurrence of the specified substring, 1798 * or {@code -1} if there is no such occurrence. 1799 */ 1800 public int lastIndexOf(String str) { 1801 return lastIndexOf(str, value.length); 1802 } 1803 1804 /** 1805 * Returns the index within this string of the last occurrence of the 1806 * specified substring, searching backward starting at the specified index. 1807 * 1808 * <p>The returned index is the largest value {@code k} for which: 1809 * <pre>{@code 1810 * k <= Math.min(fromIndex, this.length()) && 1811 * this.startsWith(str, k) 1812 * }</pre> 1813 * If no such value of {@code k} exists, then {@code -1} is returned. 1814 * 1815 * @param str the substring to search for. 1816 * @param fromIndex the index to start the search from. 1817 * @return the index of the last occurrence of the specified substring, 1818 * searching backward from the specified index, 1819 * or {@code -1} if there is no such occurrence. 1820 */ 1821 public int lastIndexOf(String str, int fromIndex) { 1822 return lastIndexOf(value, 0, value.length, 1823 str.value, 0, str.value.length, fromIndex); 1824 } 1825 1826 /** 1827 * Code shared by String and AbstractStringBuilder to do searches. The 1828 * source is the character array being searched, and the target 1829 * is the string being searched for. 1830 * 1831 * @param source the characters being searched. 1832 * @param sourceOffset offset of the source string. 1833 * @param sourceCount count of the source string. 1834 * @param target the characters being searched for. 1835 * @param fromIndex the index to begin searching from. 1836 */ 1837 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1838 String target, int fromIndex) { 1839 return lastIndexOf(source, sourceOffset, sourceCount, 1840 target.value, 0, target.value.length, 1841 fromIndex); 1842 } 1843 1844 /** 1845 * Code shared by String and StringBuffer to do searches. The 1846 * source is the character array being searched, and the target 1847 * is the string being searched for. 1848 * 1849 * @param source the characters being searched. 1850 * @param sourceOffset offset of the source string. 1851 * @param sourceCount count of the source string. 1852 * @param target the characters being searched for. 1853 * @param targetOffset offset of the target string. 1854 * @param targetCount count of the target string. 1855 * @param fromIndex the index to begin searching from. 1856 */ 1857 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1858 char[] target, int targetOffset, int targetCount, 1859 int fromIndex) { 1860 /* 1861 * Check arguments; return immediately where possible. For 1862 * consistency, don't check for null str. 1863 */ 1864 int rightIndex = sourceCount - targetCount; 1865 if (fromIndex < 0) { 1866 return -1; 1867 } 1868 if (fromIndex > rightIndex) { 1869 fromIndex = rightIndex; 1870 } 1871 /* Empty string always matches. */ 1872 if (targetCount == 0) { 1873 return fromIndex; 1874 } 1875 1876 int strLastIndex = targetOffset + targetCount - 1; 1877 char strLastChar = target[strLastIndex]; 1878 int min = sourceOffset + targetCount - 1; 1879 int i = min + fromIndex; 1880 1881 startSearchForLastChar: 1882 while (true) { 1883 while (i >= min && source[i] != strLastChar) { 1884 i--; 1885 } 1886 if (i < min) { 1887 return -1; 1888 } 1889 int j = i - 1; 1890 int start = j - (targetCount - 1); 1891 int k = strLastIndex - 1; 1892 1893 while (j > start) { 1894 if (source[j--] != target[k--]) { 1895 i--; 1896 continue startSearchForLastChar; 1897 } 1898 } 1899 return start - sourceOffset + 1; 1900 } 1901 } 1902 1903 /** 1904 * Returns a string that is a substring of this string. The 1905 * substring begins with the character at the specified index and 1906 * extends to the end of this string. <p> 1907 * Examples: 1908 * <blockquote><pre> 1909 * "unhappy".substring(2) returns "happy" 1910 * "Harbison".substring(3) returns "bison" 1911 * "emptiness".substring(9) returns "" (an empty string) 1912 * </pre></blockquote> 1913 * 1914 * @param beginIndex the beginning index, inclusive. 1915 * @return the specified substring. 1916 * @exception IndexOutOfBoundsException if 1917 * {@code beginIndex} is negative or larger than the 1918 * length of this {@code String} object. 1919 */ 1920 public String substring(int beginIndex) { 1921 if (beginIndex < 0) { 1922 throw new StringIndexOutOfBoundsException(beginIndex); 1923 } 1924 int subLen = value.length - beginIndex; 1925 if (subLen < 0) { 1926 throw new StringIndexOutOfBoundsException(subLen); 1927 } 1928 return (beginIndex == 0) ? this : new String(value, beginIndex, subLen); 1929 } 1930 1931 /** 1932 * Returns a string that is a substring of this string. The 1933 * substring begins at the specified {@code beginIndex} and 1934 * extends to the character at index {@code endIndex - 1}. 1935 * Thus the length of the substring is {@code endIndex-beginIndex}. 1936 * <p> 1937 * Examples: 1938 * <blockquote><pre> 1939 * "hamburger".substring(4, 8) returns "urge" 1940 * "smiles".substring(1, 5) returns "mile" 1941 * </pre></blockquote> 1942 * 1943 * @param beginIndex the beginning index, inclusive. 1944 * @param endIndex the ending index, exclusive. 1945 * @return the specified substring. 1946 * @exception IndexOutOfBoundsException if the 1947 * {@code beginIndex} is negative, or 1948 * {@code endIndex} is larger than the length of 1949 * this {@code String} object, or 1950 * {@code beginIndex} is larger than 1951 * {@code endIndex}. 1952 */ 1953 public String substring(int beginIndex, int endIndex) { 1954 if (beginIndex < 0) { 1955 throw new StringIndexOutOfBoundsException(beginIndex); 1956 } 1957 if (endIndex > value.length) { 1958 throw new StringIndexOutOfBoundsException(endIndex); 1959 } 1960 int subLen = endIndex - beginIndex; 1961 if (subLen < 0) { 1962 throw new StringIndexOutOfBoundsException(subLen); 1963 } 1964 return ((beginIndex == 0) && (endIndex == value.length)) ? this 1965 : new String(value, beginIndex, subLen); 1966 } 1967 1968 /** 1969 * Returns a character sequence that is a subsequence of this sequence. 1970 * 1971 * <p> An invocation of this method of the form 1972 * 1973 * <blockquote><pre> 1974 * str.subSequence(begin, end)</pre></blockquote> 1975 * 1976 * behaves in exactly the same way as the invocation 1977 * 1978 * <blockquote><pre> 1979 * str.substring(begin, end)</pre></blockquote> 1980 * 1981 * @apiNote 1982 * This method is defined so that the {@code String} class can implement 1983 * the {@link CharSequence} interface. 1984 * 1985 * @param beginIndex the begin index, inclusive. 1986 * @param endIndex the end index, exclusive. 1987 * @return the specified subsequence. 1988 * 1989 * @throws IndexOutOfBoundsException 1990 * if {@code beginIndex} or {@code endIndex} is negative, 1991 * if {@code endIndex} is greater than {@code length()}, 1992 * or if {@code beginIndex} is greater than {@code endIndex} 1993 * 1994 * @since 1.4 1995 * @spec JSR-51 1996 */ 1997 public CharSequence subSequence(int beginIndex, int endIndex) { 1998 return this.substring(beginIndex, endIndex); 1999 } 2000 2001 /** 2002 * Concatenates the specified string to the end of this string. 2003 * <p> 2004 * If the length of the argument string is {@code 0}, then this 2005 * {@code String} object is returned. Otherwise, a 2006 * {@code String} object is returned that represents a character 2007 * sequence that is the concatenation of the character sequence 2008 * represented by this {@code String} object and the character 2009 * sequence represented by the argument string.<p> 2010 * Examples: 2011 * <blockquote><pre> 2012 * "cares".concat("s") returns "caress" 2013 * "to".concat("get").concat("her") returns "together" 2014 * </pre></blockquote> 2015 * 2016 * @param str the {@code String} that is concatenated to the end 2017 * of this {@code String}. 2018 * @return a string that represents the concatenation of this object's 2019 * characters followed by the string argument's characters. 2020 */ 2021 public String concat(String str) { 2022 int otherLen = str.length(); 2023 if (otherLen == 0) { 2024 return this; 2025 } 2026 int len = value.length; 2027 char buf[] = Arrays.copyOf(value, len + otherLen); 2028 str.getChars(buf, len); 2029 return new String(buf, true); 2030 } 2031 2032 /** 2033 * Returns a string resulting from replacing all occurrences of 2034 * {@code oldChar} in this string with {@code newChar}. 2035 * <p> 2036 * If the character {@code oldChar} does not occur in the 2037 * character sequence represented by this {@code String} object, 2038 * then a reference to this {@code String} object is returned. 2039 * Otherwise, a {@code String} object is returned that 2040 * represents a character sequence identical to the character sequence 2041 * represented by this {@code String} object, except that every 2042 * occurrence of {@code oldChar} is replaced by an occurrence 2043 * of {@code newChar}. 2044 * <p> 2045 * Examples: 2046 * <blockquote><pre> 2047 * "mesquite in your cellar".replace('e', 'o') 2048 * returns "mosquito in your collar" 2049 * "the war of baronets".replace('r', 'y') 2050 * returns "the way of bayonets" 2051 * "sparring with a purple porpoise".replace('p', 't') 2052 * returns "starring with a turtle tortoise" 2053 * "JonL".replace('q', 'x') returns "JonL" (no change) 2054 * </pre></blockquote> 2055 * 2056 * @param oldChar the old character. 2057 * @param newChar the new character. 2058 * @return a string derived from this string by replacing every 2059 * occurrence of {@code oldChar} with {@code newChar}. 2060 */ 2061 public String replace(char oldChar, char newChar) { 2062 if (oldChar != newChar) { 2063 int len = value.length; 2064 int i = -1; 2065 char[] val = value; /* avoid getfield opcode */ 2066 2067 while (++i < len) { 2068 if (val[i] == oldChar) { 2069 break; 2070 } 2071 } 2072 if (i < len) { 2073 char buf[] = new char[len]; 2074 for (int j = 0; j < i; j++) { 2075 buf[j] = val[j]; 2076 } 2077 while (i < len) { 2078 char c = val[i]; 2079 buf[i] = (c == oldChar) ? newChar : c; 2080 i++; 2081 } 2082 return new String(buf, true); 2083 } 2084 } 2085 return this; 2086 } 2087 2088 /** 2089 * Tells whether or not this string matches the given <a 2090 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2091 * 2092 * <p> An invocation of this method of the form 2093 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2094 * same result as the expression 2095 * 2096 * <blockquote> 2097 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2098 * matches(<i>regex</i>, <i>str</i>)} 2099 * </blockquote> 2100 * 2101 * @param regex 2102 * the regular expression to which this string is to be matched 2103 * 2104 * @return {@code true} if, and only if, this string matches the 2105 * given regular expression 2106 * 2107 * @throws PatternSyntaxException 2108 * if the regular expression's syntax is invalid 2109 * 2110 * @see java.util.regex.Pattern 2111 * 2112 * @since 1.4 2113 * @spec JSR-51 2114 */ 2115 public boolean matches(String regex) { 2116 return Pattern.matches(regex, this); 2117 } 2118 2119 /** 2120 * Returns true if and only if this string contains the specified 2121 * sequence of char values. 2122 * 2123 * @param s the sequence to search for 2124 * @return true if this string contains {@code s}, false otherwise 2125 * @since 1.5 2126 */ 2127 public boolean contains(CharSequence s) { 2128 return indexOf(s.toString()) > -1; 2129 } 2130 2131 /** 2132 * Replaces the first substring of this string that matches the given <a 2133 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2134 * given replacement. 2135 * 2136 * <p> An invocation of this method of the form 2137 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2138 * yields exactly the same result as the expression 2139 * 2140 * <blockquote> 2141 * <code> 2142 * {@link java.util.regex.Pattern}.{@link 2143 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2144 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2145 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>) 2146 * </code> 2147 * </blockquote> 2148 * 2149 *<p> 2150 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2151 * replacement string may cause the results to be different than if it were 2152 * being treated as a literal replacement string; see 2153 * {@link java.util.regex.Matcher#replaceFirst}. 2154 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2155 * meaning of these characters, if desired. 2156 * 2157 * @param regex 2158 * the regular expression to which this string is to be matched 2159 * @param replacement 2160 * the string to be substituted for the first match 2161 * 2162 * @return The resulting {@code String} 2163 * 2164 * @throws PatternSyntaxException 2165 * if the regular expression's syntax is invalid 2166 * 2167 * @see java.util.regex.Pattern 2168 * 2169 * @since 1.4 2170 * @spec JSR-51 2171 */ 2172 public String replaceFirst(String regex, String replacement) { 2173 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2174 } 2175 2176 /** 2177 * Replaces each substring of this string that matches the given <a 2178 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2179 * given replacement. 2180 * 2181 * <p> An invocation of this method of the form 2182 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2183 * yields exactly the same result as the expression 2184 * 2185 * <blockquote> 2186 * <code> 2187 * {@link java.util.regex.Pattern}.{@link 2188 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2189 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2190 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2191 * </code> 2192 * </blockquote> 2193 * 2194 *<p> 2195 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2196 * replacement string may cause the results to be different than if it were 2197 * being treated as a literal replacement string; see 2198 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2199 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2200 * meaning of these characters, if desired. 2201 * 2202 * @param regex 2203 * the regular expression to which this string is to be matched 2204 * @param replacement 2205 * the string to be substituted for each match 2206 * 2207 * @return The resulting {@code String} 2208 * 2209 * @throws PatternSyntaxException 2210 * if the regular expression's syntax is invalid 2211 * 2212 * @see java.util.regex.Pattern 2213 * 2214 * @since 1.4 2215 * @spec JSR-51 2216 */ 2217 public String replaceAll(String regex, String replacement) { 2218 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2219 } 2220 2221 /** 2222 * Replaces each substring of this string that matches the literal target 2223 * sequence with the specified literal replacement sequence. The 2224 * replacement proceeds from the beginning of the string to the end, for 2225 * example, replacing "aa" with "b" in the string "aaa" will result in 2226 * "ba" rather than "ab". 2227 * 2228 * @param target The sequence of char values to be replaced 2229 * @param replacement The replacement sequence of char values 2230 * @return The resulting string 2231 * @since 1.5 2232 */ 2233 public String replace(CharSequence target, CharSequence replacement) { 2234 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher( 2235 this).replaceAll(Matcher.quoteReplacement(replacement.toString())); 2236 } 2237 2238 /** 2239 * Splits this string around matches of the given 2240 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2241 * 2242 * <p> The array returned by this method contains each substring of this 2243 * string that is terminated by another substring that matches the given 2244 * expression or is terminated by the end of the string. The substrings in 2245 * the array are in the order in which they occur in this string. If the 2246 * expression does not match any part of the input then the resulting array 2247 * has just one element, namely this string. 2248 * 2249 * <p> When there is a positive-width match at the beginning of this 2250 * string then an empty leading substring is included at the beginning 2251 * of the resulting array. A zero-width match at the beginning however 2252 * never produces such empty leading substring. 2253 * 2254 * <p> The {@code limit} parameter controls the number of times the 2255 * pattern is applied and therefore affects the length of the resulting 2256 * array. If the limit <i>n</i> is greater than zero then the pattern 2257 * will be applied at most <i>n</i> - 1 times, the array's 2258 * length will be no greater than <i>n</i>, and the array's last entry 2259 * will contain all input beyond the last matched delimiter. If <i>n</i> 2260 * is non-positive then the pattern will be applied as many times as 2261 * possible and the array can have any length. If <i>n</i> is zero then 2262 * the pattern will be applied as many times as possible, the array can 2263 * have any length, and trailing empty strings will be discarded. 2264 * 2265 * <p> The string {@code "boo:and:foo"}, for example, yields the 2266 * following results with these parameters: 2267 * 2268 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2269 * <tr> 2270 * <th>Regex</th> 2271 * <th>Limit</th> 2272 * <th>Result</th> 2273 * </tr> 2274 * <tr><td align=center>:</td> 2275 * <td align=center>2</td> 2276 * <td>{@code { "boo", "and:foo" }}</td></tr> 2277 * <tr><td align=center>:</td> 2278 * <td align=center>5</td> 2279 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2280 * <tr><td align=center>:</td> 2281 * <td align=center>-2</td> 2282 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2283 * <tr><td align=center>o</td> 2284 * <td align=center>5</td> 2285 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2286 * <tr><td align=center>o</td> 2287 * <td align=center>-2</td> 2288 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2289 * <tr><td align=center>o</td> 2290 * <td align=center>0</td> 2291 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2292 * </table></blockquote> 2293 * 2294 * <p> An invocation of this method of the form 2295 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2296 * yields the same result as the expression 2297 * 2298 * <blockquote> 2299 * <code> 2300 * {@link java.util.regex.Pattern}.{@link 2301 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2302 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2303 * </code> 2304 * </blockquote> 2305 * 2306 * 2307 * @param regex 2308 * the delimiting regular expression 2309 * 2310 * @param limit 2311 * the result threshold, as described above 2312 * 2313 * @return the array of strings computed by splitting this string 2314 * around matches of the given regular expression 2315 * 2316 * @throws PatternSyntaxException 2317 * if the regular expression's syntax is invalid 2318 * 2319 * @see java.util.regex.Pattern 2320 * 2321 * @since 1.4 2322 * @spec JSR-51 2323 */ 2324 public String[] split(String regex, int limit) { 2325 /* fastpath if the regex is a 2326 (1)one-char String and this character is not one of the 2327 RegEx's meta characters ".$|()[{^?*+\\", or 2328 (2)two-char String and the first char is the backslash and 2329 the second is not the ascii digit or ascii letter. 2330 */ 2331 char ch = 0; 2332 if (((regex.value.length == 1 && 2333 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2334 (regex.length() == 2 && 2335 regex.charAt(0) == '\\' && 2336 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2337 ((ch-'a')|('z'-ch)) < 0 && 2338 ((ch-'A')|('Z'-ch)) < 0)) && 2339 (ch < Character.MIN_HIGH_SURROGATE || 2340 ch > Character.MAX_LOW_SURROGATE)) 2341 { 2342 int off = 0; 2343 int next = 0; 2344 boolean limited = limit > 0; 2345 ArrayList<String> list = new ArrayList<>(); 2346 while ((next = indexOf(ch, off)) != -1) { 2347 if (!limited || list.size() < limit - 1) { 2348 list.add(substring(off, next)); 2349 off = next + 1; 2350 } else { // last one 2351 //assert (list.size() == limit - 1); 2352 list.add(substring(off, value.length)); 2353 off = value.length; 2354 break; 2355 } 2356 } 2357 // If no match was found, return this 2358 if (off == 0) 2359 return new String[]{this}; 2360 2361 // Add remaining segment 2362 if (!limited || list.size() < limit) 2363 list.add(substring(off, value.length)); 2364 2365 // Construct result 2366 int resultSize = list.size(); 2367 if (limit == 0) { 2368 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) { 2369 resultSize--; 2370 } 2371 } 2372 String[] result = new String[resultSize]; 2373 return list.subList(0, resultSize).toArray(result); 2374 } 2375 return Pattern.compile(regex).split(this, limit); 2376 } 2377 2378 /** 2379 * Splits this string around matches of the given <a 2380 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2381 * 2382 * <p> This method works as if by invoking the two-argument {@link 2383 * #split(String, int) split} method with the given expression and a limit 2384 * argument of zero. Trailing empty strings are therefore not included in 2385 * the resulting array. 2386 * 2387 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2388 * results with these expressions: 2389 * 2390 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2391 * <tr> 2392 * <th>Regex</th> 2393 * <th>Result</th> 2394 * </tr> 2395 * <tr><td align=center>:</td> 2396 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2397 * <tr><td align=center>o</td> 2398 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2399 * </table></blockquote> 2400 * 2401 * 2402 * @param regex 2403 * the delimiting regular expression 2404 * 2405 * @return the array of strings computed by splitting this string 2406 * around matches of the given regular expression 2407 * 2408 * @throws PatternSyntaxException 2409 * if the regular expression's syntax is invalid 2410 * 2411 * @see java.util.regex.Pattern 2412 * 2413 * @since 1.4 2414 * @spec JSR-51 2415 */ 2416 public String[] split(String regex) { 2417 return split(regex, 0); 2418 } 2419 2420 /** 2421 * Returns a new String composed of copies of the 2422 * {@code CharSequence elements} joined together with a copy of 2423 * the specified {@code delimiter}. 2424 * 2425 * <blockquote>For example, 2426 * <pre>{@code 2427 * String message = String.join("-", "Java", "is", "cool"); 2428 * // message returned is: "Java-is-cool" 2429 * }</pre></blockquote> 2430 * 2431 * Note that if an element is null, then {@code "null"} is added. 2432 * 2433 * @param delimiter the delimiter that separates each element 2434 * @param elements the elements to join together. 2435 * 2436 * @return a new {@code String} that is composed of the {@code elements} 2437 * separated by the {@code delimiter} 2438 * 2439 * @throws NullPointerException If {@code delimiter} or {@code elements} 2440 * is {@code null} 2441 * 2442 * @see java.util.StringJoiner 2443 * @since 1.8 2444 */ 2445 public static String join(CharSequence delimiter, CharSequence... elements) { 2446 Objects.requireNonNull(delimiter); 2447 Objects.requireNonNull(elements); 2448 // Number of elements not likely worth Arrays.stream overhead. 2449 StringJoiner joiner = new StringJoiner(delimiter); 2450 for (CharSequence cs: elements) { 2451 joiner.add(cs); 2452 } 2453 return joiner.toString(); 2454 } 2455 2456 /** 2457 * Returns a new {@code String} composed of copies of the 2458 * {@code CharSequence elements} joined together with a copy of the 2459 * specified {@code delimiter}. 2460 * 2461 * <blockquote>For example, 2462 * <pre>{@code 2463 * List<String> strings = new LinkedList<>(); 2464 * strings.add("Java");strings.add("is"); 2465 * strings.add("cool"); 2466 * String message = String.join(" ", strings); 2467 * //message returned is: "Java is cool" 2468 * 2469 * Set<String> strings = new LinkedHashSet<>(); 2470 * strings.add("Java"); strings.add("is"); 2471 * strings.add("very"); strings.add("cool"); 2472 * String message = String.join("-", strings); 2473 * //message returned is: "Java-is-very-cool" 2474 * }</pre></blockquote> 2475 * 2476 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2477 * 2478 * @param delimiter a sequence of characters that is used to separate each 2479 * of the {@code elements} in the resulting {@code String} 2480 * @param elements an {@code Iterable} that will have its {@code elements} 2481 * joined together. 2482 * 2483 * @return a new {@code String} that is composed from the {@code elements} 2484 * argument 2485 * 2486 * @throws NullPointerException If {@code delimiter} or {@code elements} 2487 * is {@code null} 2488 * 2489 * @see #join(CharSequence,CharSequence...) 2490 * @see java.util.StringJoiner 2491 * @since 1.8 2492 */ 2493 public static String join(CharSequence delimiter, 2494 Iterable<? extends CharSequence> elements) { 2495 Objects.requireNonNull(delimiter); 2496 Objects.requireNonNull(elements); 2497 StringJoiner joiner = new StringJoiner(delimiter); 2498 for (CharSequence cs: elements) { 2499 joiner.add(cs); 2500 } 2501 return joiner.toString(); 2502 } 2503 2504 /** 2505 * Converts all of the characters in this {@code String} to lower 2506 * case using the rules of the given {@code Locale}. Case mapping is based 2507 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2508 * class. Since case mappings are not always 1:1 char mappings, the resulting 2509 * {@code String} may be a different length than the original {@code String}. 2510 * <p> 2511 * Examples of lowercase mappings are in the following table: 2512 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2513 * <tr> 2514 * <th>Language Code of Locale</th> 2515 * <th>Upper Case</th> 2516 * <th>Lower Case</th> 2517 * <th>Description</th> 2518 * </tr> 2519 * <tr> 2520 * <td>tr (Turkish)</td> 2521 * <td>\u0130</td> 2522 * <td>\u0069</td> 2523 * <td>capital letter I with dot above -> small letter i</td> 2524 * </tr> 2525 * <tr> 2526 * <td>tr (Turkish)</td> 2527 * <td>\u0049</td> 2528 * <td>\u0131</td> 2529 * <td>capital letter I -> small letter dotless i </td> 2530 * </tr> 2531 * <tr> 2532 * <td>(all)</td> 2533 * <td>French Fries</td> 2534 * <td>french fries</td> 2535 * <td>lowercased all chars in String</td> 2536 * </tr> 2537 * <tr> 2538 * <td>(all)</td> 2539 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2540 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2541 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2542 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2543 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2544 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2545 * <td>lowercased all chars in String</td> 2546 * </tr> 2547 * </table> 2548 * 2549 * @param locale use the case transformation rules for this locale 2550 * @return the {@code String}, converted to lowercase. 2551 * @see java.lang.String#toLowerCase() 2552 * @see java.lang.String#toUpperCase() 2553 * @see java.lang.String#toUpperCase(Locale) 2554 * @since 1.1 2555 */ 2556 public String toLowerCase(Locale locale) { 2557 if (locale == null) { 2558 throw new NullPointerException(); 2559 } 2560 int first; 2561 boolean hasSurr = false; 2562 final int len = value.length; 2563 2564 // Now check if there are any characters that need to be changed, or are surrogate 2565 for (first = 0 ; first < len; first++) { 2566 int cp = (int)value[first]; 2567 if (Character.isSurrogate((char)cp)) { 2568 hasSurr = true; 2569 break; 2570 } 2571 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR 2572 break; 2573 } 2574 } 2575 if (first == len) 2576 return this; 2577 char[] result = new char[len]; 2578 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2579 // lowerCase characters. 2580 String lang = locale.getLanguage(); 2581 if (lang == "tr" || lang == "az" || lang == "lt") { 2582 return toLowerCaseEx(result, first, locale, true); 2583 } 2584 if (hasSurr) { 2585 return toLowerCaseEx(result, first, locale, false); 2586 } 2587 for (int i = first; i < len; i++) { 2588 int cp = (int)value[i]; 2589 if (cp == '\u03A3') { // GREEK CAPITAL LETTER SIGMA 2590 return toLowerCaseEx(result, i, locale, false); 2591 } 2592 cp = Character.toLowerCase(cp); 2593 if (!Character.isBmpCodePoint(cp)) { 2594 return toLowerCaseEx(result, i, locale, false); 2595 } 2596 result[i] = (char)cp; 2597 } 2598 return new String(result, true); 2599 } 2600 2601 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) { 2602 int resultOffset = first; 2603 int srcCount; 2604 for (int i = first; i < value.length; i += srcCount) { 2605 int srcChar = (int)value[i]; 2606 int lowerChar; 2607 char[] lowerCharArray; 2608 srcCount = 1; 2609 if (Character.isSurrogate((char)srcChar)) { 2610 srcChar = codePointAt(i); 2611 srcCount = Character.charCount(srcChar); 2612 } 2613 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA 2614 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale); 2615 } else { 2616 lowerChar = Character.toLowerCase(srcChar); 2617 } 2618 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp 2619 result[resultOffset++] = (char)lowerChar; 2620 } else { 2621 if (lowerChar == Character.ERROR) { 2622 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale); 2623 } else if (srcCount == 2) { 2624 resultOffset += Character.toChars(lowerChar, result, resultOffset); 2625 continue; 2626 } else { 2627 lowerCharArray = Character.toChars(lowerChar); 2628 } 2629 /* Grow result if needed */ 2630 int mapLen = lowerCharArray.length; 2631 if (mapLen > srcCount) { 2632 char[] result2 = new char[result.length + mapLen - srcCount]; 2633 System.arraycopy(result, 0, result2, 0, resultOffset); 2634 result = result2; 2635 } 2636 for (int x = 0; x < mapLen; ++x) { 2637 result[resultOffset++] = lowerCharArray[x]; 2638 } 2639 } 2640 } 2641 return new String(result, 0, resultOffset); 2642 } 2643 2644 /** 2645 * Converts all of the characters in this {@code String} to lower 2646 * case using the rules of the default locale. This is equivalent to calling 2647 * {@code toLowerCase(Locale.getDefault())}. 2648 * <p> 2649 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2650 * results if used for strings that are intended to be interpreted locale 2651 * independently. 2652 * Examples are programming language identifiers, protocol keys, and HTML 2653 * tags. 2654 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2655 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2656 * LATIN SMALL LETTER DOTLESS I character. 2657 * To obtain correct results for locale insensitive strings, use 2658 * {@code toLowerCase(Locale.ROOT)}. 2659 * <p> 2660 * @return the {@code String}, converted to lowercase. 2661 * @see java.lang.String#toLowerCase(Locale) 2662 */ 2663 public String toLowerCase() { 2664 return toLowerCase(Locale.getDefault()); 2665 } 2666 2667 /** 2668 * Converts all of the characters in this {@code String} to upper 2669 * case using the rules of the given {@code Locale}. Case mapping is based 2670 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2671 * class. Since case mappings are not always 1:1 char mappings, the resulting 2672 * {@code String} may be a different length than the original {@code String}. 2673 * <p> 2674 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2675 * 2676 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2677 * <tr> 2678 * <th>Language Code of Locale</th> 2679 * <th>Lower Case</th> 2680 * <th>Upper Case</th> 2681 * <th>Description</th> 2682 * </tr> 2683 * <tr> 2684 * <td>tr (Turkish)</td> 2685 * <td>\u0069</td> 2686 * <td>\u0130</td> 2687 * <td>small letter i -> capital letter I with dot above</td> 2688 * </tr> 2689 * <tr> 2690 * <td>tr (Turkish)</td> 2691 * <td>\u0131</td> 2692 * <td>\u0049</td> 2693 * <td>small letter dotless i -> capital letter I</td> 2694 * </tr> 2695 * <tr> 2696 * <td>(all)</td> 2697 * <td>\u00df</td> 2698 * <td>\u0053 \u0053</td> 2699 * <td>small letter sharp s -> two letters: SS</td> 2700 * </tr> 2701 * <tr> 2702 * <td>(all)</td> 2703 * <td>Fahrvergnügen</td> 2704 * <td>FAHRVERGNÜGEN</td> 2705 * <td></td> 2706 * </tr> 2707 * </table> 2708 * @param locale use the case transformation rules for this locale 2709 * @return the {@code String}, converted to uppercase. 2710 * @see java.lang.String#toUpperCase() 2711 * @see java.lang.String#toLowerCase() 2712 * @see java.lang.String#toLowerCase(Locale) 2713 * @since 1.1 2714 */ 2715 public String toUpperCase(Locale locale) { 2716 if (locale == null) { 2717 throw new NullPointerException(); 2718 } 2719 int first; 2720 boolean hasSurr = false; 2721 final int len = value.length; 2722 2723 // Now check if there are any characters that need to be changed, or are surrogate 2724 for (first = 0 ; first < len; first++ ) { 2725 int cp = (int)value[first]; 2726 if (Character.isSurrogate((char)cp)) { 2727 hasSurr = true; 2728 break; 2729 } 2730 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR 2731 break; 2732 } 2733 } 2734 if (first == len) { 2735 return this; 2736 } 2737 char[] result = new char[len]; 2738 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2739 // upperCase characters. 2740 String lang = locale.getLanguage(); 2741 if (lang == "tr" || lang == "az" || lang == "lt") { 2742 return toUpperCaseEx(result, first, locale, true); 2743 } 2744 if (hasSurr) { 2745 return toUpperCaseEx(result, first, locale, false); 2746 } 2747 for (int i = first; i < len; i++) { 2748 int cp = Character.toUpperCaseEx((int)value[i]); 2749 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp 2750 return toUpperCaseEx(result, i, locale, false); 2751 } 2752 result[i] = (char)cp; 2753 } 2754 return new String(result, true); 2755 } 2756 2757 private String toUpperCaseEx(char[] result, int first, Locale locale, 2758 boolean localeDependent) { 2759 int resultOffset = first; 2760 int srcCount; 2761 for (int i = first; i < value.length; i += srcCount) { 2762 int srcChar = (int)value[i]; 2763 int upperChar; 2764 char[] upperCharArray; 2765 srcCount = 1; 2766 if (Character.isSurrogate((char)srcChar)) { 2767 srcChar = codePointAt(i); 2768 srcCount = Character.charCount(srcChar); 2769 } 2770 if (localeDependent) { 2771 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale); 2772 } else { 2773 upperChar = Character.toUpperCaseEx(srcChar); 2774 } 2775 if (Character.isBmpCodePoint(upperChar)) { 2776 result[resultOffset++] = (char)upperChar; 2777 } else { 2778 if (upperChar == Character.ERROR) { 2779 if (localeDependent) { 2780 upperCharArray = 2781 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale); 2782 } else { 2783 upperCharArray = Character.toUpperCaseCharArray(srcChar); 2784 } 2785 } else if (srcCount == 2) { 2786 resultOffset += Character.toChars(upperChar, result, resultOffset); 2787 continue; 2788 } else { 2789 upperCharArray = Character.toChars(upperChar); 2790 } 2791 /* Grow result if needed */ 2792 int mapLen = upperCharArray.length; 2793 if (mapLen > srcCount) { 2794 char[] result2 = new char[result.length + mapLen - srcCount]; 2795 System.arraycopy(result, 0, result2, 0, resultOffset); 2796 result = result2; 2797 } 2798 for (int x = 0; x < mapLen; ++x) { 2799 result[resultOffset++] = upperCharArray[x]; 2800 } 2801 } 2802 } 2803 return new String(result, 0, resultOffset); 2804 } 2805 2806 /** 2807 * Converts all of the characters in this {@code String} to upper 2808 * case using the rules of the default locale. This method is equivalent to 2809 * {@code toUpperCase(Locale.getDefault())}. 2810 * <p> 2811 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2812 * results if used for strings that are intended to be interpreted locale 2813 * independently. 2814 * Examples are programming language identifiers, protocol keys, and HTML 2815 * tags. 2816 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2817 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2818 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2819 * To obtain correct results for locale insensitive strings, use 2820 * {@code toUpperCase(Locale.ROOT)}. 2821 * <p> 2822 * @return the {@code String}, converted to uppercase. 2823 * @see java.lang.String#toUpperCase(Locale) 2824 */ 2825 public String toUpperCase() { 2826 return toUpperCase(Locale.getDefault()); 2827 } 2828 2829 /** 2830 * Returns a string whose value is this string, with any leading and trailing 2831 * whitespace removed. 2832 * <p> 2833 * If this {@code String} object represents an empty character 2834 * sequence, or the first and last characters of character sequence 2835 * represented by this {@code String} object both have codes 2836 * greater than {@code '\u005Cu0020'} (the space character), then a 2837 * reference to this {@code String} object is returned. 2838 * <p> 2839 * Otherwise, if there is no character with a code greater than 2840 * {@code '\u005Cu0020'} in the string, then a 2841 * {@code String} object representing an empty string is 2842 * returned. 2843 * <p> 2844 * Otherwise, let <i>k</i> be the index of the first character in the 2845 * string whose code is greater than {@code '\u005Cu0020'}, and let 2846 * <i>m</i> be the index of the last character in the string whose code 2847 * is greater than {@code '\u005Cu0020'}. A {@code String} 2848 * object is returned, representing the substring of this string that 2849 * begins with the character at index <i>k</i> and ends with the 2850 * character at index <i>m</i>-that is, the result of 2851 * {@code this.substring(k, m + 1)}. 2852 * <p> 2853 * This method may be used to trim whitespace (as defined above) from 2854 * the beginning and end of a string. 2855 * 2856 * @return A string whose value is this string, with any leading and trailing white 2857 * space removed, or this string if it has no leading or 2858 * trailing white space. 2859 */ 2860 public String trim() { 2861 int len = value.length; 2862 int st = 0; 2863 char[] val = value; /* avoid getfield opcode */ 2864 2865 while ((st < len) && (val[st] <= ' ')) { 2866 st++; 2867 } 2868 while ((st < len) && (val[len - 1] <= ' ')) { 2869 len--; 2870 } 2871 return ((st > 0) || (len < value.length)) ? substring(st, len) : this; 2872 } 2873 2874 /** 2875 * This object (which is already a string!) is itself returned. 2876 * 2877 * @return the string itself. 2878 */ 2879 public String toString() { 2880 return this; 2881 } 2882 2883 /** 2884 * Converts this string to a new character array. 2885 * 2886 * @return a newly allocated character array whose length is the length 2887 * of this string and whose contents are initialized to contain 2888 * the character sequence represented by this string. 2889 */ 2890 public char[] toCharArray() { 2891 // Cannot use Arrays.copyOf because of class initialization order issues 2892 char result[] = new char[value.length]; 2893 System.arraycopy(value, 0, result, 0, value.length); 2894 return result; 2895 } 2896 2897 /** 2898 * Returns a formatted string using the specified format string and 2899 * arguments. 2900 * 2901 * <p> The locale always used is the one returned by {@link 2902 * java.util.Locale#getDefault() Locale.getDefault()}. 2903 * 2904 * @param format 2905 * A <a href="../util/Formatter.html#syntax">format string</a> 2906 * 2907 * @param args 2908 * Arguments referenced by the format specifiers in the format 2909 * string. If there are more arguments than format specifiers, the 2910 * extra arguments are ignored. The number of arguments is 2911 * variable and may be zero. The maximum number of arguments is 2912 * limited by the maximum dimension of a Java array as defined by 2913 * <cite>The Java™ Virtual Machine Specification</cite>. 2914 * The behaviour on a 2915 * {@code null} argument depends on the <a 2916 * href="../util/Formatter.html#syntax">conversion</a>. 2917 * 2918 * @throws java.util.IllegalFormatException 2919 * If a format string contains an illegal syntax, a format 2920 * specifier that is incompatible with the given arguments, 2921 * insufficient arguments given the format string, or other 2922 * illegal conditions. For specification of all possible 2923 * formatting errors, see the <a 2924 * href="../util/Formatter.html#detail">Details</a> section of the 2925 * formatter class specification. 2926 * 2927 * @return A formatted string 2928 * 2929 * @see java.util.Formatter 2930 * @since 1.5 2931 */ 2932 public static String format(String format, Object... args) { 2933 return new Formatter().format(format, args).toString(); 2934 } 2935 2936 /** 2937 * Returns a formatted string using the specified locale, format string, 2938 * and arguments. 2939 * 2940 * @param l 2941 * The {@linkplain java.util.Locale locale} to apply during 2942 * formatting. If {@code l} is {@code null} then no localization 2943 * is applied. 2944 * 2945 * @param format 2946 * A <a href="../util/Formatter.html#syntax">format string</a> 2947 * 2948 * @param args 2949 * Arguments referenced by the format specifiers in the format 2950 * string. If there are more arguments than format specifiers, the 2951 * extra arguments are ignored. The number of arguments is 2952 * variable and may be zero. The maximum number of arguments is 2953 * limited by the maximum dimension of a Java array as defined by 2954 * <cite>The Java™ Virtual Machine Specification</cite>. 2955 * The behaviour on a 2956 * {@code null} argument depends on the 2957 * <a href="../util/Formatter.html#syntax">conversion</a>. 2958 * 2959 * @throws java.util.IllegalFormatException 2960 * If a format string contains an illegal syntax, a format 2961 * specifier that is incompatible with the given arguments, 2962 * insufficient arguments given the format string, or other 2963 * illegal conditions. For specification of all possible 2964 * formatting errors, see the <a 2965 * href="../util/Formatter.html#detail">Details</a> section of the 2966 * formatter class specification 2967 * 2968 * @return A formatted string 2969 * 2970 * @see java.util.Formatter 2971 * @since 1.5 2972 */ 2973 public static String format(Locale l, String format, Object... args) { 2974 return new Formatter(l).format(format, args).toString(); 2975 } 2976 2977 /** 2978 * Returns the string representation of the {@code Object} argument. 2979 * 2980 * @param obj an {@code Object}. 2981 * @return if the argument is {@code null}, then a string equal to 2982 * {@code "null"}; otherwise, the value of 2983 * {@code obj.toString()} is returned. 2984 * @see java.lang.Object#toString() 2985 */ 2986 public static String valueOf(Object obj) { 2987 return (obj == null) ? "null" : obj.toString(); 2988 } 2989 2990 /** 2991 * Returns the string representation of the {@code char} array 2992 * argument. The contents of the character array are copied; subsequent 2993 * modification of the character array does not affect the returned 2994 * string. 2995 * 2996 * @param data the character array. 2997 * @return a {@code String} that contains the characters of the 2998 * character array. 2999 */ 3000 public static String valueOf(char data[]) { 3001 return new String(data); 3002 } 3003 3004 /** 3005 * Returns the string representation of a specific subarray of the 3006 * {@code char} array argument. 3007 * <p> 3008 * The {@code offset} argument is the index of the first 3009 * character of the subarray. The {@code count} argument 3010 * specifies the length of the subarray. The contents of the subarray 3011 * are copied; subsequent modification of the character array does not 3012 * affect the returned string. 3013 * 3014 * @param data the character array. 3015 * @param offset initial offset of the subarray. 3016 * @param count length of the subarray. 3017 * @return a {@code String} that contains the characters of the 3018 * specified subarray of the character array. 3019 * @exception IndexOutOfBoundsException if {@code offset} is 3020 * negative, or {@code count} is negative, or 3021 * {@code offset+count} is larger than 3022 * {@code data.length}. 3023 */ 3024 public static String valueOf(char data[], int offset, int count) { 3025 return new String(data, offset, count); 3026 } 3027 3028 /** 3029 * Equivalent to {@link #valueOf(char[], int, int)}. 3030 * 3031 * @param data the character array. 3032 * @param offset initial offset of the subarray. 3033 * @param count length of the subarray. 3034 * @return a {@code String} that contains the characters of the 3035 * specified subarray of the character array. 3036 * @exception IndexOutOfBoundsException if {@code offset} is 3037 * negative, or {@code count} is negative, or 3038 * {@code offset+count} is larger than 3039 * {@code data.length}. 3040 */ 3041 public static String copyValueOf(char data[], int offset, int count) { 3042 return new String(data, offset, count); 3043 } 3044 3045 /** 3046 * Equivalent to {@link #valueOf(char[])}. 3047 * 3048 * @param data the character array. 3049 * @return a {@code String} that contains the characters of the 3050 * character array. 3051 */ 3052 public static String copyValueOf(char data[]) { 3053 return new String(data); 3054 } 3055 3056 /** 3057 * Returns the string representation of the {@code boolean} argument. 3058 * 3059 * @param b a {@code boolean}. 3060 * @return if the argument is {@code true}, a string equal to 3061 * {@code "true"} is returned; otherwise, a string equal to 3062 * {@code "false"} is returned. 3063 */ 3064 public static String valueOf(boolean b) { 3065 return b ? "true" : "false"; 3066 } 3067 3068 /** 3069 * Returns the string representation of the {@code char} 3070 * argument. 3071 * 3072 * @param c a {@code char}. 3073 * @return a string of length {@code 1} containing 3074 * as its single character the argument {@code c}. 3075 */ 3076 public static String valueOf(char c) { 3077 char data[] = {c}; 3078 return new String(data, true); 3079 } 3080 3081 /** 3082 * Returns the string representation of the {@code int} argument. 3083 * <p> 3084 * The representation is exactly the one returned by the 3085 * {@code Integer.toString} method of one argument. 3086 * 3087 * @param i an {@code int}. 3088 * @return a string representation of the {@code int} argument. 3089 * @see java.lang.Integer#toString(int, int) 3090 */ 3091 public static String valueOf(int i) { 3092 return Integer.toString(i); 3093 } 3094 3095 /** 3096 * Returns the string representation of the {@code long} argument. 3097 * <p> 3098 * The representation is exactly the one returned by the 3099 * {@code Long.toString} method of one argument. 3100 * 3101 * @param l a {@code long}. 3102 * @return a string representation of the {@code long} argument. 3103 * @see java.lang.Long#toString(long) 3104 */ 3105 public static String valueOf(long l) { 3106 return Long.toString(l); 3107 } 3108 3109 /** 3110 * Returns the string representation of the {@code float} argument. 3111 * <p> 3112 * The representation is exactly the one returned by the 3113 * {@code Float.toString} method of one argument. 3114 * 3115 * @param f a {@code float}. 3116 * @return a string representation of the {@code float} argument. 3117 * @see java.lang.Float#toString(float) 3118 */ 3119 public static String valueOf(float f) { 3120 return Float.toString(f); 3121 } 3122 3123 /** 3124 * Returns the string representation of the {@code double} argument. 3125 * <p> 3126 * The representation is exactly the one returned by the 3127 * {@code Double.toString} method of one argument. 3128 * 3129 * @param d a {@code double}. 3130 * @return a string representation of the {@code double} argument. 3131 * @see java.lang.Double#toString(double) 3132 */ 3133 public static String valueOf(double d) { 3134 return Double.toString(d); 3135 } 3136 3137 /** 3138 * Returns a canonical representation for the string object. 3139 * <p> 3140 * A pool of strings, initially empty, is maintained privately by the 3141 * class {@code String}. 3142 * <p> 3143 * When the intern method is invoked, if the pool already contains a 3144 * string equal to this {@code String} object as determined by 3145 * the {@link #equals(Object)} method, then the string from the pool is 3146 * returned. Otherwise, this {@code String} object is added to the 3147 * pool and a reference to this {@code String} object is returned. 3148 * <p> 3149 * It follows that for any two strings {@code s} and {@code t}, 3150 * {@code s.intern() == t.intern()} is {@code true} 3151 * if and only if {@code s.equals(t)} is {@code true}. 3152 * <p> 3153 * All literal strings and string-valued constant expressions are 3154 * interned. String literals are defined in section 3.10.5 of the 3155 * <cite>The Java™ Language Specification</cite>. 3156 * 3157 * @return a string that has the same contents as this string, but is 3158 * guaranteed to be from a pool of unique strings. 3159 */ 3160 public native String intern(); 3161 }