1 /* 2 * Copyright (c) 1994, 2014, Oracle and/or its affiliates. All rights reserved. 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4 * 5 * This code is free software; you can redistribute it and/or modify it 6 * under the terms of the GNU General Public License version 2 only, as 7 * published by the Free Software Foundation. Oracle designates this 8 * particular file as subject to the "Classpath" exception as provided 9 * by Oracle in the LICENSE file that accompanied this code. 10 * 11 * This code is distributed in the hope that it will be useful, but WITHOUT 12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 14 * version 2 for more details (a copy is included in the LICENSE file that 15 * accompanied this code). 16 * 17 * You should have received a copy of the GNU General Public License version 18 * 2 along with this work; if not, write to the Free Software Foundation, 19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 20 * 21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 22 * or visit www.oracle.com if you need additional information or have any 23 * questions. 24 */ 25 26 package java.lang; 27 28 import java.io.ObjectStreamField; 29 import java.io.UnsupportedEncodingException; 30 import java.nio.charset.Charset; 31 import java.util.ArrayList; 32 import java.util.Arrays; 33 import java.util.Comparator; 34 import java.util.Formatter; 35 import java.util.Locale; 36 import java.util.Objects; 37 import java.util.StringJoiner; 38 import java.util.regex.Matcher; 39 import java.util.regex.Pattern; 40 import java.util.regex.PatternSyntaxException; 41 42 /** 43 * The {@code String} class represents character strings. All 44 * string literals in Java programs, such as {@code "abc"}, are 45 * implemented as instances of this class. 46 * <p> 47 * Strings are constant; their values cannot be changed after they 48 * are created. String buffers support mutable strings. 49 * Because String objects are immutable they can be shared. For example: 50 * <blockquote><pre> 51 * String str = "abc"; 52 * </pre></blockquote><p> 53 * is equivalent to: 54 * <blockquote><pre> 55 * char data[] = {'a', 'b', 'c'}; 56 * String str = new String(data); 57 * </pre></blockquote><p> 58 * Here are some more examples of how strings can be used: 59 * <blockquote><pre> 60 * System.out.println("abc"); 61 * String cde = "cde"; 62 * System.out.println("abc" + cde); 63 * String c = "abc".substring(2,3); 64 * String d = cde.substring(1, 2); 65 * </pre></blockquote> 66 * <p> 67 * The class {@code String} includes methods for examining 68 * individual characters of the sequence, for comparing strings, for 69 * searching strings, for extracting substrings, and for creating a 70 * copy of a string with all characters translated to uppercase or to 71 * lowercase. Case mapping is based on the Unicode Standard version 72 * specified by the {@link java.lang.Character Character} class. 73 * <p> 74 * The Java language provides special support for the string 75 * concatenation operator ( + ), and for conversion of 76 * other objects to strings. String concatenation is implemented 77 * through the {@code StringBuilder}(or {@code StringBuffer}) 78 * class and its {@code append} method. 79 * String conversions are implemented through the method 80 * {@code toString}, defined by {@code Object} and 81 * inherited by all classes in Java. For additional information on 82 * string concatenation and conversion, see Gosling, Joy, and Steele, 83 * <i>The Java Language Specification</i>. 84 * 85 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor 86 * or method in this class will cause a {@link NullPointerException} to be 87 * thrown. 88 * 89 * <p>A {@code String} represents a string in the UTF-16 format 90 * in which <em>supplementary characters</em> are represented by <em>surrogate 91 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 92 * Character Representations</a> in the {@code Character} class for 93 * more information). 94 * Index values refer to {@code char} code units, so a supplementary 95 * character uses two positions in a {@code String}. 96 * <p>The {@code String} class provides methods for dealing with 97 * Unicode code points (i.e., characters), in addition to those for 98 * dealing with Unicode code units (i.e., {@code char} values). 99 * 100 * @author Lee Boynton 101 * @author Arthur van Hoff 102 * @author Martin Buchholz 103 * @author Ulf Zibis 104 * @see java.lang.Object#toString() 105 * @see java.lang.StringBuffer 106 * @see java.lang.StringBuilder 107 * @see java.nio.charset.Charset 108 * @since 1.0 109 */ 110 111 public final class String 112 implements java.io.Serializable, Comparable<String>, CharSequence { 113 /** The value is used for character storage. */ 114 private final char value[]; 115 116 /** Cache the hash code for the string */ 117 private int hash; // Default to 0 118 119 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 120 private static final long serialVersionUID = -6849794470754667710L; 121 122 /** 123 * Class String is special cased within the Serialization Stream Protocol. 124 * 125 * A String instance is written into an ObjectOutputStream according to 126 * <a href="{@docRoot}/../platform/serialization/spec/output.html"> 127 * Object Serialization Specification, Section 6.2, "Stream Elements"</a> 128 */ 129 private static final ObjectStreamField[] serialPersistentFields = 130 new ObjectStreamField[0]; 131 132 /** 133 * 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 = "".value; 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 {@code offset} is negative, {@code count} is negative, or 188 * {@code offset} is greater than {@code value.length - count} 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 if (count == 0) { 196 this.value = "".value; 197 return; 198 } 199 throw new StringIndexOutOfBoundsException(count); 200 } 201 // Note: offset or count might be near -1>>>1. 202 if (offset > value.length - count) { 203 throw new StringIndexOutOfBoundsException(offset + count); 204 } 205 this.value = Arrays.copyOfRange(value, offset, offset+count); 206 } 207 208 /** 209 * Allocates a new {@code String} that contains characters from a subarray 210 * of the <a href="Character.html#unicode">Unicode code point</a> array 211 * argument. The {@code offset} argument is the index of the first code 212 * point of the subarray and the {@code count} argument specifies the 213 * length of the subarray. The contents of the subarray are converted to 214 * {@code char}s; subsequent modification of the {@code int} array does not 215 * affect the newly created string. 216 * 217 * @param codePoints 218 * Array that is the source of Unicode code points 219 * 220 * @param offset 221 * The initial offset 222 * 223 * @param count 224 * The length 225 * 226 * @throws IllegalArgumentException 227 * If any invalid Unicode code point is found in {@code 228 * codePoints} 229 * 230 * @throws IndexOutOfBoundsException 231 * If {@code offset} is negative, {@code count} is negative, or 232 * {@code offset} is greater than {@code codePoints.length - count} 233 * 234 * @since 1.5 235 */ 236 public String(int[] codePoints, int offset, int count) { 237 if (offset < 0) { 238 throw new StringIndexOutOfBoundsException(offset); 239 } 240 if (count <= 0) { 241 if (count == 0) { 242 this.value = "".value; 243 return; 244 } 245 throw new StringIndexOutOfBoundsException(count); 246 } 247 // Note: offset or count might be near -1>>>1. 248 if (offset > codePoints.length - count) { 249 throw new StringIndexOutOfBoundsException(offset + count); 250 } 251 252 final int end = offset + count; 253 254 // Pass 1: Compute precise size of char[] 255 int n = count; 256 for (int i = offset; i < end; i++) { 257 int c = codePoints[i]; 258 if (Character.isBmpCodePoint(c)) 259 continue; 260 else if (Character.isValidCodePoint(c)) 261 n++; 262 else throw new IllegalArgumentException(Integer.toString(c)); 263 } 264 265 // Pass 2: Allocate and fill in char[] 266 final char[] v = new char[n]; 267 268 for (int i = offset, j = 0; i < end; i++, j++) { 269 int c = codePoints[i]; 270 if (Character.isBmpCodePoint(c)) 271 v[j] = (char)c; 272 else 273 Character.toSurrogates(c, v, j++); 274 } 275 276 this.value = v; 277 } 278 279 /** 280 * Allocates a new {@code String} constructed from a subarray of an array 281 * of 8-bit integer values. 282 * 283 * <p> The {@code offset} argument is the index of the first byte of the 284 * subarray, and the {@code count} argument specifies the length of the 285 * subarray. 286 * 287 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 288 * specified in the method above. 289 * 290 * @deprecated This method does not properly convert bytes into characters. 291 * As of JDK 1.1, the preferred way to do this is via the 292 * {@code String} constructors that take a {@link 293 * java.nio.charset.Charset}, charset name, or that use the platform's 294 * default charset. 295 * 296 * @param ascii 297 * The bytes to be converted to characters 298 * 299 * @param hibyte 300 * The top 8 bits of each 16-bit Unicode code unit 301 * 302 * @param offset 303 * The initial offset 304 * @param count 305 * The length 306 * 307 * @throws IndexOutOfBoundsException 308 * If {@code offset} is negative, {@code count} is negative, or 309 * {@code offset} is greater than {@code ascii.length - count} 310 * 311 * @see #String(byte[], int) 312 * @see #String(byte[], int, int, java.lang.String) 313 * @see #String(byte[], int, int, java.nio.charset.Charset) 314 * @see #String(byte[], int, int) 315 * @see #String(byte[], java.lang.String) 316 * @see #String(byte[], java.nio.charset.Charset) 317 * @see #String(byte[]) 318 */ 319 @Deprecated 320 public String(byte ascii[], int hibyte, int offset, int count) { 321 checkBounds(ascii, offset, count); 322 char value[] = new char[count]; 323 324 if (hibyte == 0) { 325 for (int i = count; i-- > 0;) { 326 value[i] = (char)(ascii[i + offset] & 0xff); 327 } 328 } else { 329 hibyte <<= 8; 330 for (int i = count; i-- > 0;) { 331 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff)); 332 } 333 } 334 this.value = value; 335 } 336 337 /** 338 * Allocates a new {@code String} containing characters constructed from 339 * an array of 8-bit integer values. Each character <i>c</i>in the 340 * resulting string is constructed from the corresponding component 341 * <i>b</i> in the byte array such that: 342 * 343 * <blockquote><pre> 344 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 345 * | (<b><i>b</i></b> & 0xff)) 346 * </pre></blockquote> 347 * 348 * @deprecated This method does not properly convert bytes into 349 * characters. As of JDK 1.1, the preferred way to do this is via the 350 * {@code String} constructors that take a {@link 351 * java.nio.charset.Charset}, charset name, or that use the platform's 352 * default charset. 353 * 354 * @param ascii 355 * The bytes to be converted to characters 356 * 357 * @param hibyte 358 * The top 8 bits of each 16-bit Unicode code unit 359 * 360 * @see #String(byte[], int, int, java.lang.String) 361 * @see #String(byte[], int, int, java.nio.charset.Charset) 362 * @see #String(byte[], int, int) 363 * @see #String(byte[], java.lang.String) 364 * @see #String(byte[], java.nio.charset.Charset) 365 * @see #String(byte[]) 366 */ 367 @Deprecated 368 public String(byte ascii[], int hibyte) { 369 this(ascii, hibyte, 0, ascii.length); 370 } 371 372 /* Common private utility method used to bounds check the byte array 373 * and requested offset & length values used by the String(byte[],..) 374 * constructors. 375 */ 376 private static void checkBounds(byte[] bytes, int offset, int length) { 377 if (length < 0) 378 throw new StringIndexOutOfBoundsException(length); 379 if (offset < 0) 380 throw new StringIndexOutOfBoundsException(offset); 381 if (offset > bytes.length - length) 382 throw new StringIndexOutOfBoundsException(offset + length); 383 } 384 385 /** 386 * Constructs a new {@code String} by decoding the specified subarray of 387 * bytes using the specified charset. The length of the new {@code String} 388 * is a function of the charset, and hence may not be equal to the length 389 * of the subarray. 390 * 391 * <p> The behavior of this constructor when the given bytes are not valid 392 * in the given charset is unspecified. The {@link 393 * java.nio.charset.CharsetDecoder} class should be used when more control 394 * over the decoding process is required. 395 * 396 * @param bytes 397 * The bytes to be decoded into characters 398 * 399 * @param offset 400 * The index of the first byte to decode 401 * 402 * @param length 403 * The number of bytes to decode 404 405 * @param charsetName 406 * The name of a supported {@linkplain java.nio.charset.Charset 407 * charset} 408 * 409 * @throws UnsupportedEncodingException 410 * If the named charset is not supported 411 * 412 * @throws IndexOutOfBoundsException 413 * If {@code offset} is negative, {@code length} is negative, or 414 * {@code offset} is greater than {@code bytes.length - length} 415 * 416 * @since 1.1 417 */ 418 public String(byte bytes[], int offset, int length, String charsetName) 419 throws UnsupportedEncodingException { 420 if (charsetName == null) 421 throw new NullPointerException("charsetName"); 422 checkBounds(bytes, offset, length); 423 this.value = StringCoding.decode(charsetName, bytes, offset, length); 424 } 425 426 /** 427 * Constructs a new {@code String} by decoding the specified subarray of 428 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 429 * The length of the new {@code String} is a function of the charset, and 430 * hence may not be equal to the length of the subarray. 431 * 432 * <p> This method always replaces malformed-input and unmappable-character 433 * sequences with this charset's default replacement string. The {@link 434 * java.nio.charset.CharsetDecoder} class should be used when more control 435 * over the decoding process is required. 436 * 437 * @param bytes 438 * The bytes to be decoded into characters 439 * 440 * @param offset 441 * The index of the first byte to decode 442 * 443 * @param length 444 * The number of bytes to decode 445 * 446 * @param charset 447 * The {@linkplain java.nio.charset.Charset charset} to be used to 448 * decode the {@code bytes} 449 * 450 * @throws IndexOutOfBoundsException 451 * If {@code offset} is negative, {@code length} is negative, or 452 * {@code offset} is greater than {@code bytes.length - length} 453 * 454 * @since 1.6 455 */ 456 public String(byte bytes[], int offset, int length, Charset charset) { 457 if (charset == null) 458 throw new NullPointerException("charset"); 459 checkBounds(bytes, offset, length); 460 this.value = StringCoding.decode(charset, bytes, offset, length); 461 } 462 463 /** 464 * Constructs a new {@code String} by decoding the specified array of bytes 465 * using the specified {@linkplain java.nio.charset.Charset charset}. The 466 * length of the new {@code String} is a function of the charset, and hence 467 * may not be equal to the length of the byte array. 468 * 469 * <p> The behavior of this constructor when the given bytes are not valid 470 * in the given charset is unspecified. The {@link 471 * java.nio.charset.CharsetDecoder} class should be used when more control 472 * over the decoding process is required. 473 * 474 * @param bytes 475 * The bytes to be decoded into characters 476 * 477 * @param charsetName 478 * The name of a supported {@linkplain java.nio.charset.Charset 479 * charset} 480 * 481 * @throws UnsupportedEncodingException 482 * If the named charset is not supported 483 * 484 * @since 1.1 485 */ 486 public String(byte bytes[], String charsetName) 487 throws UnsupportedEncodingException { 488 this(bytes, 0, bytes.length, charsetName); 489 } 490 491 /** 492 * Constructs a new {@code String} by decoding the specified array of 493 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 494 * The length of the new {@code String} is a function of the charset, and 495 * hence may not be equal to the length of the byte array. 496 * 497 * <p> This method always replaces malformed-input and unmappable-character 498 * sequences with this charset's default replacement string. The {@link 499 * java.nio.charset.CharsetDecoder} class should be used when more control 500 * over the decoding process is required. 501 * 502 * @param bytes 503 * The bytes to be decoded into characters 504 * 505 * @param charset 506 * The {@linkplain java.nio.charset.Charset charset} to be used to 507 * decode the {@code bytes} 508 * 509 * @since 1.6 510 */ 511 public String(byte bytes[], Charset charset) { 512 this(bytes, 0, bytes.length, charset); 513 } 514 515 /** 516 * Constructs a new {@code String} by decoding the specified subarray of 517 * bytes using the platform's default charset. The length of the new 518 * {@code String} is a function of the charset, and hence may not be equal 519 * to the length of the subarray. 520 * 521 * <p> The behavior of this constructor when the given bytes are not valid 522 * in the default charset is unspecified. The {@link 523 * java.nio.charset.CharsetDecoder} class should be used when more control 524 * over the decoding process is required. 525 * 526 * @param bytes 527 * The bytes to be decoded into characters 528 * 529 * @param offset 530 * The index of the first byte to decode 531 * 532 * @param length 533 * The number of bytes to decode 534 * 535 * @throws IndexOutOfBoundsException 536 * If {@code offset} is negative, {@code length} is negative, or 537 * {@code offset} is greater than {@code bytes.length - length} 538 * 539 * @since 1.1 540 */ 541 public String(byte bytes[], int offset, int length) { 542 checkBounds(bytes, offset, length); 543 this.value = StringCoding.decode(bytes, offset, length); 544 } 545 546 /** 547 * Constructs a new {@code String} by decoding the specified array of bytes 548 * using the platform's default charset. The length of the new {@code 549 * String} is a function of the charset, and hence may not be equal to the 550 * length of the byte array. 551 * 552 * <p> The behavior of this constructor when the given bytes are not valid 553 * in the default charset is unspecified. The {@link 554 * java.nio.charset.CharsetDecoder} class should be used when more control 555 * over the decoding process is required. 556 * 557 * @param bytes 558 * The bytes to be decoded into characters 559 * 560 * @since 1.1 561 */ 562 public String(byte bytes[]) { 563 this(bytes, 0, bytes.length); 564 } 565 566 /** 567 * Allocates a new string that contains the sequence of characters 568 * currently contained in the string buffer argument. The contents of the 569 * string buffer are copied; subsequent modification of the string buffer 570 * does not affect the newly created string. 571 * 572 * @param buffer 573 * A {@code StringBuffer} 574 */ 575 public String(StringBuffer buffer) { 576 synchronized(buffer) { 577 this.value = Arrays.copyOf(buffer.getValue(), buffer.length()); 578 } 579 } 580 581 /** 582 * Allocates a new string that contains the sequence of characters 583 * currently contained in the string builder argument. The contents of the 584 * string builder are copied; subsequent modification of the string builder 585 * does not affect the newly created string. 586 * 587 * <p> This constructor is provided to ease migration to {@code 588 * StringBuilder}. Obtaining a string from a string builder via the {@code 589 * toString} method is likely to run faster and is generally preferred. 590 * 591 * @param builder 592 * A {@code StringBuilder} 593 * 594 * @since 1.5 595 */ 596 public String(StringBuilder builder) { 597 this.value = Arrays.copyOf(builder.getValue(), builder.length()); 598 } 599 600 /* 601 * Package private constructor which shares value array for speed. 602 * this constructor is always expected to be called with share==true. 603 * a separate constructor is needed because we already have a public 604 * String(char[]) constructor that makes a copy of the given char[]. 605 */ 606 String(char[] value, boolean share) { 607 // assert share : "unshared not supported"; 608 this.value = value; 609 } 610 611 /** 612 * Returns the length of this string. 613 * The length is equal to the number of <a href="Character.html#unicode">Unicode 614 * code units</a> in the string. 615 * 616 * @return the length of the sequence of characters represented by this 617 * object. 618 */ 619 public int length() { 620 return value.length; 621 } 622 623 /** 624 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 625 * 626 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 627 * {@code false} 628 * 629 * @since 1.6 630 */ 631 public boolean isEmpty() { 632 return value.length == 0; 633 } 634 635 /** 636 * Returns the {@code char} value at the 637 * specified index. An index ranges from {@code 0} to 638 * {@code length() - 1}. The first {@code char} value of the sequence 639 * is at index {@code 0}, the next at index {@code 1}, 640 * and so on, as for array indexing. 641 * 642 * <p>If the {@code char} value specified by the index is a 643 * <a href="Character.html#unicode">surrogate</a>, the surrogate 644 * value is returned. 645 * 646 * @param index the index of the {@code char} value. 647 * @return the {@code char} value at the specified index of this string. 648 * The first {@code char} value is at index {@code 0}. 649 * @exception IndexOutOfBoundsException if the {@code index} 650 * argument is negative or not less than the length of this 651 * string. 652 */ 653 public char charAt(int index) { 654 if ((index < 0) || (index >= value.length)) { 655 throw new StringIndexOutOfBoundsException(index); 656 } 657 return value[index]; 658 } 659 660 /** 661 * Returns the character (Unicode code point) at the specified 662 * index. The index refers to {@code char} values 663 * (Unicode code units) and ranges from {@code 0} to 664 * {@link #length()}{@code - 1}. 665 * 666 * <p> If the {@code char} value specified at the given index 667 * is in the high-surrogate range, the following index is less 668 * than the length of this {@code String}, and the 669 * {@code char} value at the following index is in the 670 * low-surrogate range, then the supplementary code point 671 * corresponding to this surrogate pair is returned. Otherwise, 672 * the {@code char} value at the given index is returned. 673 * 674 * @param index the index to the {@code char} values 675 * @return the code point value of the character at the 676 * {@code index} 677 * @exception IndexOutOfBoundsException if the {@code index} 678 * argument is negative or not less than the length of this 679 * string. 680 * @since 1.5 681 */ 682 public int codePointAt(int index) { 683 if ((index < 0) || (index >= value.length)) { 684 throw new StringIndexOutOfBoundsException(index); 685 } 686 return Character.codePointAtImpl(value, index, value.length); 687 } 688 689 /** 690 * Returns the character (Unicode code point) before the specified 691 * index. The index refers to {@code char} values 692 * (Unicode code units) and ranges from {@code 1} to {@link 693 * CharSequence#length() length}. 694 * 695 * <p> If the {@code char} value at {@code (index - 1)} 696 * is in the low-surrogate range, {@code (index - 2)} is not 697 * negative, and the {@code char} value at {@code (index - 698 * 2)} is in the high-surrogate range, then the 699 * supplementary code point value of the surrogate pair is 700 * returned. If the {@code char} value at {@code index - 701 * 1} is an unpaired low-surrogate or a high-surrogate, the 702 * surrogate value is returned. 703 * 704 * @param index the index following the code point that should be returned 705 * @return the Unicode code point value before the given index. 706 * @exception IndexOutOfBoundsException if the {@code index} 707 * argument is less than 1 or greater than the length 708 * of this string. 709 * @since 1.5 710 */ 711 public int codePointBefore(int index) { 712 int i = index - 1; 713 if ((i < 0) || (i >= value.length)) { 714 throw new StringIndexOutOfBoundsException(index); 715 } 716 return Character.codePointBeforeImpl(value, index, 0); 717 } 718 719 /** 720 * Returns the number of Unicode code points in the specified text 721 * range of this {@code String}. The text range begins at the 722 * specified {@code beginIndex} and extends to the 723 * {@code char} at index {@code endIndex - 1}. Thus the 724 * length (in {@code char}s) of the text range is 725 * {@code endIndex-beginIndex}. Unpaired surrogates within 726 * the text range count as one code point each. 727 * 728 * @param beginIndex the index to the first {@code char} of 729 * the text range. 730 * @param endIndex the index after the last {@code char} of 731 * the text range. 732 * @return the number of Unicode code points in the specified text 733 * range 734 * @exception IndexOutOfBoundsException if the 735 * {@code beginIndex} is negative, or {@code endIndex} 736 * is larger than the length of this {@code String}, or 737 * {@code beginIndex} is larger than {@code endIndex}. 738 * @since 1.5 739 */ 740 public int codePointCount(int beginIndex, int endIndex) { 741 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) { 742 throw new IndexOutOfBoundsException(); 743 } 744 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex); 745 } 746 747 /** 748 * Returns the index within this {@code String} that is 749 * offset from the given {@code index} by 750 * {@code codePointOffset} code points. Unpaired surrogates 751 * within the text range given by {@code index} and 752 * {@code codePointOffset} count as one code point each. 753 * 754 * @param index the index to be offset 755 * @param codePointOffset the offset in code points 756 * @return the index within this {@code String} 757 * @exception IndexOutOfBoundsException if {@code index} 758 * is negative or larger then the length of this 759 * {@code String}, or if {@code codePointOffset} is positive 760 * and the substring starting with {@code index} has fewer 761 * than {@code codePointOffset} code points, 762 * or if {@code codePointOffset} is negative and the substring 763 * before {@code index} has fewer than the absolute value 764 * of {@code codePointOffset} code points. 765 * @since 1.5 766 */ 767 public int offsetByCodePoints(int index, int codePointOffset) { 768 if (index < 0 || index > value.length) { 769 throw new IndexOutOfBoundsException(); 770 } 771 return Character.offsetByCodePointsImpl(value, 0, value.length, 772 index, codePointOffset); 773 } 774 775 /** 776 * Copy characters from this string into dst starting at dstBegin. 777 * This method doesn't perform any range checking. 778 */ 779 void getChars(char dst[], int dstBegin) { 780 System.arraycopy(value, 0, dst, dstBegin, value.length); 781 } 782 783 /** 784 * Copies characters from this string into the destination character 785 * array. 786 * <p> 787 * The first character to be copied is at index {@code srcBegin}; 788 * the last character to be copied is at index {@code srcEnd-1} 789 * (thus the total number of characters to be copied is 790 * {@code srcEnd-srcBegin}). The characters are copied into the 791 * subarray of {@code dst} starting at index {@code dstBegin} 792 * and ending at index: 793 * <blockquote><pre> 794 * dstbegin + (srcEnd-srcBegin) - 1 795 * </pre></blockquote> 796 * 797 * @param srcBegin index of the first character in the string 798 * to copy. 799 * @param srcEnd index after the last character in the string 800 * to copy. 801 * @param dst the destination array. 802 * @param dstBegin the start offset in the destination array. 803 * @exception IndexOutOfBoundsException If any of the following 804 * is true: 805 * <ul><li>{@code srcBegin} is negative. 806 * <li>{@code srcBegin} is greater than {@code srcEnd} 807 * <li>{@code srcEnd} is greater than the length of this 808 * string 809 * <li>{@code dstBegin} is negative 810 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 811 * {@code dst.length}</ul> 812 */ 813 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 814 if (srcBegin < 0) { 815 throw new StringIndexOutOfBoundsException(srcBegin); 816 } 817 if (srcEnd > value.length) { 818 throw new StringIndexOutOfBoundsException(srcEnd); 819 } 820 if (srcBegin > srcEnd) { 821 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 822 } 823 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin); 824 } 825 826 /** 827 * Copies characters from this string into the destination byte array. Each 828 * byte receives the 8 low-order bits of the corresponding character. The 829 * eight high-order bits of each character are not copied and do not 830 * participate in the transfer in any way. 831 * 832 * <p> The first character to be copied is at index {@code srcBegin}; the 833 * last character to be copied is at index {@code srcEnd-1}. The total 834 * number of characters to be copied is {@code srcEnd-srcBegin}. The 835 * characters, converted to bytes, are copied into the subarray of {@code 836 * dst} starting at index {@code dstBegin} and ending at index: 837 * 838 * <blockquote><pre> 839 * dstbegin + (srcEnd-srcBegin) - 1 840 * </pre></blockquote> 841 * 842 * @deprecated This method does not properly convert characters into 843 * bytes. As of JDK 1.1, the preferred way to do this is via the 844 * {@link #getBytes()} method, which uses the platform's default charset. 845 * 846 * @param srcBegin 847 * Index of the first character in the string to copy 848 * 849 * @param srcEnd 850 * Index after the last character in the string to copy 851 * 852 * @param dst 853 * The destination array 854 * 855 * @param dstBegin 856 * The start offset in the destination array 857 * 858 * @throws IndexOutOfBoundsException 859 * If any of the following is true: 860 * <ul> 861 * <li> {@code srcBegin} is negative 862 * <li> {@code srcBegin} is greater than {@code srcEnd} 863 * <li> {@code srcEnd} is greater than the length of this String 864 * <li> {@code dstBegin} is negative 865 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 866 * dst.length} 867 * </ul> 868 */ 869 @Deprecated 870 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 871 if (srcBegin < 0) { 872 throw new StringIndexOutOfBoundsException(srcBegin); 873 } 874 if (srcEnd > value.length) { 875 throw new StringIndexOutOfBoundsException(srcEnd); 876 } 877 if (srcBegin > srcEnd) { 878 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 879 } 880 Objects.requireNonNull(dst); 881 882 int j = dstBegin; 883 int n = srcEnd; 884 int i = srcBegin; 885 char[] val = value; /* avoid getfield opcode */ 886 887 while (i < n) { 888 dst[j++] = (byte)val[i++]; 889 } 890 } 891 892 /** 893 * Encodes this {@code String} into a sequence of bytes using the named 894 * charset, storing the result into a new byte array. 895 * 896 * <p> The behavior of this method when this string cannot be encoded in 897 * the given charset is unspecified. The {@link 898 * java.nio.charset.CharsetEncoder} class should be used when more control 899 * over the encoding process is required. 900 * 901 * @param charsetName 902 * The name of a supported {@linkplain java.nio.charset.Charset 903 * charset} 904 * 905 * @return The resultant byte array 906 * 907 * @throws UnsupportedEncodingException 908 * If the named charset is not supported 909 * 910 * @since 1.1 911 */ 912 public byte[] getBytes(String charsetName) 913 throws UnsupportedEncodingException { 914 if (charsetName == null) throw new NullPointerException(); 915 return StringCoding.encode(charsetName, value, 0, value.length); 916 } 917 918 /** 919 * Encodes this {@code String} into a sequence of bytes using the given 920 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 921 * new byte array. 922 * 923 * <p> This method always replaces malformed-input and unmappable-character 924 * sequences with this charset's default replacement byte array. The 925 * {@link java.nio.charset.CharsetEncoder} class should be used when more 926 * control over the encoding process is required. 927 * 928 * @param charset 929 * The {@linkplain java.nio.charset.Charset} to be used to encode 930 * the {@code String} 931 * 932 * @return The resultant byte array 933 * 934 * @since 1.6 935 */ 936 public byte[] getBytes(Charset charset) { 937 if (charset == null) throw new NullPointerException(); 938 return StringCoding.encode(charset, value, 0, value.length); 939 } 940 941 /** 942 * Encodes this {@code String} into a sequence of bytes using the 943 * platform's default charset, storing the result into a new byte array. 944 * 945 * <p> The behavior of this method when this string cannot be encoded in 946 * the default charset is unspecified. The {@link 947 * java.nio.charset.CharsetEncoder} class should be used when more control 948 * over the encoding process is required. 949 * 950 * @return The resultant byte array 951 * 952 * @since 1.1 953 */ 954 public byte[] getBytes() { 955 return StringCoding.encode(value, 0, value.length); 956 } 957 958 /** 959 * Compares this string to the specified object. The result is {@code 960 * true} if and only if the argument is not {@code null} and is a {@code 961 * String} object that represents the same sequence of characters as this 962 * object. 963 * 964 * @param anObject 965 * The object to compare this {@code String} against 966 * 967 * @return {@code true} if the given object represents a {@code String} 968 * equivalent to this string, {@code false} otherwise 969 * 970 * @see #compareTo(String) 971 * @see #equalsIgnoreCase(String) 972 */ 973 public boolean equals(Object anObject) { 974 if (this == anObject) { 975 return true; 976 } 977 if (anObject instanceof String) { 978 String anotherString = (String)anObject; 979 int n = value.length; 980 if (n == anotherString.value.length) { 981 char v1[] = value; 982 char v2[] = anotherString.value; 983 int i = 0; 984 while (n-- != 0) { 985 if (v1[i] != v2[i]) 986 return false; 987 i++; 988 } 989 return true; 990 } 991 } 992 return false; 993 } 994 995 /** 996 * Compares this string to the specified {@code StringBuffer}. The result 997 * is {@code true} if and only if this {@code String} represents the same 998 * sequence of characters as the specified {@code StringBuffer}. This method 999 * synchronizes on the {@code StringBuffer}. 1000 * 1001 * @param sb 1002 * The {@code StringBuffer} to compare this {@code String} against 1003 * 1004 * @return {@code true} if this {@code String} represents the same 1005 * sequence of characters as the specified {@code StringBuffer}, 1006 * {@code false} otherwise 1007 * 1008 * @since 1.4 1009 */ 1010 public boolean contentEquals(StringBuffer sb) { 1011 return contentEquals((CharSequence)sb); 1012 } 1013 1014 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1015 char v1[] = value; 1016 char v2[] = sb.getValue(); 1017 int n = v1.length; 1018 if (n != sb.length()) { 1019 return false; 1020 } 1021 for (int i = 0; i < n; i++) { 1022 if (v1[i] != v2[i]) { 1023 return false; 1024 } 1025 } 1026 return true; 1027 } 1028 1029 /** 1030 * Compares this string to the specified {@code CharSequence}. The 1031 * result is {@code true} if and only if this {@code String} represents the 1032 * same sequence of char values as the specified sequence. Note that if the 1033 * {@code CharSequence} is a {@code StringBuffer} then the method 1034 * synchronizes on it. 1035 * 1036 * @param cs 1037 * The sequence to compare this {@code String} against 1038 * 1039 * @return {@code true} if this {@code String} represents the same 1040 * sequence of char values as the specified sequence, {@code 1041 * false} otherwise 1042 * 1043 * @since 1.5 1044 */ 1045 public boolean contentEquals(CharSequence cs) { 1046 // Argument is a StringBuffer, StringBuilder 1047 if (cs instanceof AbstractStringBuilder) { 1048 if (cs instanceof StringBuffer) { 1049 synchronized(cs) { 1050 return nonSyncContentEquals((AbstractStringBuilder)cs); 1051 } 1052 } else { 1053 return nonSyncContentEquals((AbstractStringBuilder)cs); 1054 } 1055 } 1056 // Argument is a String 1057 if (cs instanceof String) { 1058 return equals(cs); 1059 } 1060 // Argument is a generic CharSequence 1061 char v1[] = value; 1062 int n = v1.length; 1063 if (n != cs.length()) { 1064 return false; 1065 } 1066 for (int i = 0; i < n; i++) { 1067 if (v1[i] != cs.charAt(i)) { 1068 return false; 1069 } 1070 } 1071 return true; 1072 } 1073 1074 /** 1075 * Compares this {@code String} to another {@code String}, ignoring case 1076 * considerations. Two strings are considered equal ignoring case if they 1077 * are of the same length and corresponding characters in the two strings 1078 * are equal ignoring case. 1079 * 1080 * <p> Two characters {@code c1} and {@code c2} are considered the same 1081 * ignoring case if at least one of the following is true: 1082 * <ul> 1083 * <li> The two characters are the same (as compared by the 1084 * {@code ==} operator) 1085 * <li> Applying the method {@link 1086 * java.lang.Character#toUpperCase(char)} to each character 1087 * produces the same result 1088 * <li> Applying the method {@link 1089 * java.lang.Character#toLowerCase(char)} to each character 1090 * produces the same result 1091 * </ul> 1092 * 1093 * @param anotherString 1094 * The {@code String} to compare this {@code String} against 1095 * 1096 * @return {@code true} if the argument is not {@code null} and it 1097 * represents an equivalent {@code String} ignoring case; {@code 1098 * false} otherwise 1099 * 1100 * @see #equals(Object) 1101 */ 1102 public boolean equalsIgnoreCase(String anotherString) { 1103 return (this == anotherString) ? true 1104 : (anotherString != null) 1105 && (anotherString.value.length == value.length) 1106 && regionMatches(true, 0, anotherString, 0, value.length); 1107 } 1108 1109 /** 1110 * Compares two strings lexicographically. 1111 * The comparison is based on the Unicode value of each character in 1112 * the strings. The character sequence represented by this 1113 * {@code String} object is compared lexicographically to the 1114 * character sequence represented by the argument string. The result is 1115 * a negative integer if this {@code String} object 1116 * lexicographically precedes the argument string. The result is a 1117 * positive integer if this {@code String} object lexicographically 1118 * follows the argument string. The result is zero if the strings 1119 * are equal; {@code compareTo} returns {@code 0} exactly when 1120 * the {@link #equals(Object)} method would return {@code true}. 1121 * <p> 1122 * This is the definition of lexicographic ordering. If two strings are 1123 * different, then either they have different characters at some index 1124 * that is a valid index for both strings, or their lengths are different, 1125 * or both. If they have different characters at one or more index 1126 * positions, let <i>k</i> be the smallest such index; then the string 1127 * whose character at position <i>k</i> has the smaller value, as 1128 * determined by using the < operator, lexicographically precedes the 1129 * other string. In this case, {@code compareTo} returns the 1130 * difference of the two character values at position {@code k} in 1131 * the two string -- that is, the value: 1132 * <blockquote><pre> 1133 * this.charAt(k)-anotherString.charAt(k) 1134 * </pre></blockquote> 1135 * If there is no index position at which they differ, then the shorter 1136 * string lexicographically precedes the longer string. In this case, 1137 * {@code compareTo} returns the difference of the lengths of the 1138 * strings -- that is, the value: 1139 * <blockquote><pre> 1140 * this.length()-anotherString.length() 1141 * </pre></blockquote> 1142 * 1143 * @param anotherString the {@code String} to be compared. 1144 * @return the value {@code 0} if the argument string is equal to 1145 * this string; a value less than {@code 0} if this string 1146 * is lexicographically less than the string argument; and a 1147 * value greater than {@code 0} if this string is 1148 * lexicographically greater than the string argument. 1149 */ 1150 public int compareTo(String anotherString) { 1151 int len1 = value.length; 1152 int len2 = anotherString.value.length; 1153 int lim = Math.min(len1, len2); 1154 char v1[] = value; 1155 char v2[] = anotherString.value; 1156 1157 int k = 0; 1158 while (k < lim) { 1159 char c1 = v1[k]; 1160 char c2 = v2[k]; 1161 if (c1 != c2) { 1162 return c1 - c2; 1163 } 1164 k++; 1165 } 1166 return len1 - len2; 1167 } 1168 1169 /** 1170 * A Comparator that orders {@code String} objects as by 1171 * {@code compareToIgnoreCase}. This comparator is serializable. 1172 * <p> 1173 * Note that this Comparator does <em>not</em> take locale into account, 1174 * and will result in an unsatisfactory ordering for certain locales. 1175 * The java.text package provides <em>Collators</em> to allow 1176 * locale-sensitive ordering. 1177 * 1178 * @see java.text.Collator#compare(String, String) 1179 * @since 1.2 1180 */ 1181 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1182 = new CaseInsensitiveComparator(); 1183 private static class CaseInsensitiveComparator 1184 implements Comparator<String>, java.io.Serializable { 1185 // use serialVersionUID from JDK 1.2.2 for interoperability 1186 private static final long serialVersionUID = 8575799808933029326L; 1187 1188 public int compare(String s1, String s2) { 1189 int n1 = s1.length(); 1190 int n2 = s2.length(); 1191 int min = Math.min(n1, n2); 1192 for (int i = 0; i < min; i++) { 1193 char c1 = s1.charAt(i); 1194 char c2 = s2.charAt(i); 1195 if (c1 != c2) { 1196 c1 = Character.toUpperCase(c1); 1197 c2 = Character.toUpperCase(c2); 1198 if (c1 != c2) { 1199 c1 = Character.toLowerCase(c1); 1200 c2 = Character.toLowerCase(c2); 1201 if (c1 != c2) { 1202 // No overflow because of numeric promotion 1203 return c1 - c2; 1204 } 1205 } 1206 } 1207 } 1208 return n1 - n2; 1209 } 1210 1211 /** Replaces the de-serialized object. */ 1212 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1213 } 1214 1215 /** 1216 * Compares two strings lexicographically, ignoring case 1217 * differences. This method returns an integer whose sign is that of 1218 * calling {@code compareTo} with normalized versions of the strings 1219 * where case differences have been eliminated by calling 1220 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1221 * each character. 1222 * <p> 1223 * Note that this method does <em>not</em> take locale into account, 1224 * and will result in an unsatisfactory ordering for certain locales. 1225 * The java.text package provides <em>collators</em> to allow 1226 * locale-sensitive ordering. 1227 * 1228 * @param str the {@code String} to be compared. 1229 * @return a negative integer, zero, or a positive integer as the 1230 * specified String is greater than, equal to, or less 1231 * than this String, ignoring case considerations. 1232 * @see java.text.Collator#compare(String, String) 1233 * @since 1.2 1234 */ 1235 public int compareToIgnoreCase(String str) { 1236 return CASE_INSENSITIVE_ORDER.compare(this, str); 1237 } 1238 1239 /** 1240 * Tests if two string regions are equal. 1241 * <p> 1242 * A substring of this {@code String} object is compared to a substring 1243 * of the argument other. The result is true if these substrings 1244 * represent identical character sequences. The substring of this 1245 * {@code String} object to be compared begins at index {@code toffset} 1246 * and has length {@code len}. The substring of other to be compared 1247 * begins at index {@code ooffset} and has length {@code len}. The 1248 * result is {@code false} if and only if at least one of the following 1249 * is true: 1250 * <ul><li>{@code toffset} is negative. 1251 * <li>{@code ooffset} is negative. 1252 * <li>{@code toffset+len} is greater than the length of this 1253 * {@code String} object. 1254 * <li>{@code ooffset+len} is greater than the length of the other 1255 * argument. 1256 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1257 * such that: 1258 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1259 * <i>k</i>{@code )} 1260 * </ul> 1261 * 1262 * @param toffset the starting offset of the subregion in this string. 1263 * @param other the string argument. 1264 * @param ooffset the starting offset of the subregion in the string 1265 * argument. 1266 * @param len the number of characters to compare. 1267 * @return {@code true} if the specified subregion of this string 1268 * exactly matches the specified subregion of the string argument; 1269 * {@code false} otherwise. 1270 */ 1271 public boolean regionMatches(int toffset, String other, int ooffset, 1272 int len) { 1273 char ta[] = value; 1274 int to = toffset; 1275 char pa[] = other.value; 1276 int po = ooffset; 1277 // Note: toffset, ooffset, or len might be near -1>>>1. 1278 if ((ooffset < 0) || (toffset < 0) 1279 || (toffset > (long)value.length - len) 1280 || (ooffset > (long)other.value.length - len)) { 1281 return false; 1282 } 1283 while (len-- > 0) { 1284 if (ta[to++] != pa[po++]) { 1285 return false; 1286 } 1287 } 1288 return true; 1289 } 1290 1291 /** 1292 * Tests if two string regions are equal. 1293 * <p> 1294 * A substring of this {@code String} object is compared to a substring 1295 * of the argument {@code other}. The result is {@code true} if these 1296 * substrings represent character sequences that are the same, ignoring 1297 * case if and only if {@code ignoreCase} is true. The substring of 1298 * this {@code String} object to be compared begins at index 1299 * {@code toffset} and has length {@code len}. The substring of 1300 * {@code other} to be compared begins at index {@code ooffset} and 1301 * has length {@code len}. The result is {@code false} if and only if 1302 * at least one of the following is true: 1303 * <ul><li>{@code toffset} is negative. 1304 * <li>{@code ooffset} is negative. 1305 * <li>{@code toffset+len} is greater than the length of this 1306 * {@code String} object. 1307 * <li>{@code ooffset+len} is greater than the length of the other 1308 * argument. 1309 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1310 * integer <i>k</i> less than {@code len} such that: 1311 * <blockquote><pre> 1312 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1313 * </pre></blockquote> 1314 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1315 * integer <i>k</i> less than {@code len} such that: 1316 * <blockquote><pre> 1317 * Character.toLowerCase(this.charAt(toffset+k)) != 1318 Character.toLowerCase(other.charAt(ooffset+k)) 1319 * </pre></blockquote> 1320 * and: 1321 * <blockquote><pre> 1322 * Character.toUpperCase(this.charAt(toffset+k)) != 1323 * Character.toUpperCase(other.charAt(ooffset+k)) 1324 * </pre></blockquote> 1325 * </ul> 1326 * 1327 * @param ignoreCase if {@code true}, ignore case when comparing 1328 * characters. 1329 * @param toffset the starting offset of the subregion in this 1330 * string. 1331 * @param other the string argument. 1332 * @param ooffset the starting offset of the subregion in the string 1333 * argument. 1334 * @param len the number of characters to compare. 1335 * @return {@code true} if the specified subregion of this string 1336 * matches the specified subregion of the string argument; 1337 * {@code false} otherwise. Whether the matching is exact 1338 * or case insensitive depends on the {@code ignoreCase} 1339 * argument. 1340 */ 1341 public boolean regionMatches(boolean ignoreCase, int toffset, 1342 String other, int ooffset, int len) { 1343 char ta[] = value; 1344 int to = toffset; 1345 char pa[] = other.value; 1346 int po = ooffset; 1347 // Note: toffset, ooffset, or len might be near -1>>>1. 1348 if ((ooffset < 0) || (toffset < 0) 1349 || (toffset > (long)value.length - len) 1350 || (ooffset > (long)other.value.length - len)) { 1351 return false; 1352 } 1353 while (len-- > 0) { 1354 char c1 = ta[to++]; 1355 char c2 = pa[po++]; 1356 if (c1 == c2) { 1357 continue; 1358 } 1359 if (ignoreCase) { 1360 // If characters don't match but case may be ignored, 1361 // try converting both characters to uppercase. 1362 // If the results match, then the comparison scan should 1363 // continue. 1364 char u1 = Character.toUpperCase(c1); 1365 char u2 = Character.toUpperCase(c2); 1366 if (u1 == u2) { 1367 continue; 1368 } 1369 // Unfortunately, conversion to uppercase does not work properly 1370 // for the Georgian alphabet, which has strange rules about case 1371 // conversion. So we need to make one last check before 1372 // exiting. 1373 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) { 1374 continue; 1375 } 1376 } 1377 return false; 1378 } 1379 return true; 1380 } 1381 1382 /** 1383 * Tests if the substring of this string beginning at the 1384 * specified index starts with the specified prefix. 1385 * 1386 * @param prefix the prefix. 1387 * @param toffset where to begin looking in this string. 1388 * @return {@code true} if the character sequence represented by the 1389 * argument is a prefix of the substring of this object starting 1390 * at index {@code toffset}; {@code false} otherwise. 1391 * The result is {@code false} if {@code toffset} is 1392 * negative or greater than the length of this 1393 * {@code String} object; otherwise the result is the same 1394 * as the result of the expression 1395 * <pre> 1396 * this.substring(toffset).startsWith(prefix) 1397 * </pre> 1398 */ 1399 public boolean startsWith(String prefix, int toffset) { 1400 char ta[] = value; 1401 int to = toffset; 1402 char pa[] = prefix.value; 1403 int po = 0; 1404 int pc = prefix.value.length; 1405 // Note: toffset might be near -1>>>1. 1406 if ((toffset < 0) || (toffset > value.length - pc)) { 1407 return false; 1408 } 1409 while (--pc >= 0) { 1410 if (ta[to++] != pa[po++]) { 1411 return false; 1412 } 1413 } 1414 return true; 1415 } 1416 1417 /** 1418 * Tests if this string starts with the specified prefix. 1419 * 1420 * @param prefix the prefix. 1421 * @return {@code true} if the character sequence represented by the 1422 * argument is a prefix of the character sequence represented by 1423 * this string; {@code false} otherwise. 1424 * Note also that {@code true} will be returned if the 1425 * argument is an empty string or is equal to this 1426 * {@code String} object as determined by the 1427 * {@link #equals(Object)} method. 1428 * @since 1.0 1429 */ 1430 public boolean startsWith(String prefix) { 1431 return startsWith(prefix, 0); 1432 } 1433 1434 /** 1435 * Tests if this string ends with the specified suffix. 1436 * 1437 * @param suffix the suffix. 1438 * @return {@code true} if the character sequence represented by the 1439 * argument is a suffix of the character sequence represented by 1440 * this object; {@code false} otherwise. Note that the 1441 * result will be {@code true} if the argument is the 1442 * empty string or is equal to this {@code String} object 1443 * as determined by the {@link #equals(Object)} method. 1444 */ 1445 public boolean endsWith(String suffix) { 1446 return startsWith(suffix, value.length - suffix.value.length); 1447 } 1448 1449 /** 1450 * Returns a hash code for this string. The hash code for a 1451 * {@code String} object is computed as 1452 * <blockquote><pre> 1453 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1454 * </pre></blockquote> 1455 * using {@code int} arithmetic, where {@code s[i]} is the 1456 * <i>i</i>th character of the string, {@code n} is the length of 1457 * the string, and {@code ^} indicates exponentiation. 1458 * (The hash value of the empty string is zero.) 1459 * 1460 * @return a hash code value for this object. 1461 */ 1462 public int hashCode() { 1463 int h = hash; 1464 if (h == 0) { 1465 for (char v : value) { 1466 h = 31 * h + v; 1467 } 1468 hash = h; 1469 } 1470 return h; 1471 } 1472 1473 /** 1474 * Returns the index within this string of the first occurrence of 1475 * the specified character. If a character with value 1476 * {@code ch} occurs in the character sequence represented by 1477 * this {@code String} object, then the index (in Unicode 1478 * code units) of the first such occurrence is returned. For 1479 * values of {@code ch} in the range from 0 to 0xFFFF 1480 * (inclusive), this is the smallest value <i>k</i> such that: 1481 * <blockquote><pre> 1482 * this.charAt(<i>k</i>) == ch 1483 * </pre></blockquote> 1484 * is true. For other values of {@code ch}, it is the 1485 * smallest value <i>k</i> such that: 1486 * <blockquote><pre> 1487 * this.codePointAt(<i>k</i>) == ch 1488 * </pre></blockquote> 1489 * is true. In either case, if no such character occurs in this 1490 * string, then {@code -1} is returned. 1491 * 1492 * @param ch a character (Unicode code point). 1493 * @return the index of the first occurrence of the character in the 1494 * character sequence represented by this object, or 1495 * {@code -1} if the character does not occur. 1496 */ 1497 public int indexOf(int ch) { 1498 return indexOf(ch, 0); 1499 } 1500 1501 /** 1502 * Returns the index within this string of the first occurrence of the 1503 * specified character, starting the search at the specified index. 1504 * <p> 1505 * If a character with value {@code ch} occurs in the 1506 * character sequence represented by this {@code String} 1507 * object at an index no smaller than {@code fromIndex}, then 1508 * the index of the first such occurrence is returned. For values 1509 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1510 * this is the smallest value <i>k</i> such that: 1511 * <blockquote><pre> 1512 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1513 * </pre></blockquote> 1514 * is true. For other values of {@code ch}, it is the 1515 * smallest value <i>k</i> such that: 1516 * <blockquote><pre> 1517 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1518 * </pre></blockquote> 1519 * is true. In either case, if no such character occurs in this 1520 * string at or after position {@code fromIndex}, then 1521 * {@code -1} is returned. 1522 * 1523 * <p> 1524 * There is no restriction on the value of {@code fromIndex}. If it 1525 * is negative, it has the same effect as if it were zero: this entire 1526 * string may be searched. If it is greater than the length of this 1527 * string, it has the same effect as if it were equal to the length of 1528 * this string: {@code -1} is returned. 1529 * 1530 * <p>All indices are specified in {@code char} values 1531 * (Unicode code units). 1532 * 1533 * @param ch a character (Unicode code point). 1534 * @param fromIndex the index to start the search from. 1535 * @return the index of the first occurrence of the character in the 1536 * character sequence represented by this object that is greater 1537 * than or equal to {@code fromIndex}, or {@code -1} 1538 * if the character does not occur. 1539 */ 1540 public int indexOf(int ch, int fromIndex) { 1541 final int max = value.length; 1542 if (fromIndex < 0) { 1543 fromIndex = 0; 1544 } else if (fromIndex >= max) { 1545 // Note: fromIndex might be near -1>>>1. 1546 return -1; 1547 } 1548 1549 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1550 // handle most cases here (ch is a BMP code point or a 1551 // negative value (invalid code point)) 1552 final char[] value = this.value; 1553 for (int i = fromIndex; i < max; i++) { 1554 if (value[i] == ch) { 1555 return i; 1556 } 1557 } 1558 return -1; 1559 } else { 1560 return indexOfSupplementary(ch, fromIndex); 1561 } 1562 } 1563 1564 /** 1565 * Handles (rare) calls of indexOf with a supplementary character. 1566 */ 1567 private int indexOfSupplementary(int ch, int fromIndex) { 1568 if (Character.isValidCodePoint(ch)) { 1569 final char[] value = this.value; 1570 final char hi = Character.highSurrogate(ch); 1571 final char lo = Character.lowSurrogate(ch); 1572 final int max = value.length - 1; 1573 for (int i = fromIndex; i < max; i++) { 1574 if (value[i] == hi && value[i + 1] == lo) { 1575 return i; 1576 } 1577 } 1578 } 1579 return -1; 1580 } 1581 1582 /** 1583 * Returns the index within this string of the last occurrence of 1584 * the specified character. For values of {@code ch} in the 1585 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1586 * units) returned is the largest value <i>k</i> such that: 1587 * <blockquote><pre> 1588 * this.charAt(<i>k</i>) == ch 1589 * </pre></blockquote> 1590 * is true. For other values of {@code ch}, it is the 1591 * largest value <i>k</i> such that: 1592 * <blockquote><pre> 1593 * this.codePointAt(<i>k</i>) == ch 1594 * </pre></blockquote> 1595 * is true. In either case, if no such character occurs in this 1596 * string, then {@code -1} is returned. The 1597 * {@code String} is searched backwards starting at the last 1598 * character. 1599 * 1600 * @param ch a character (Unicode code point). 1601 * @return the index of the last occurrence of the character in the 1602 * character sequence represented by this object, or 1603 * {@code -1} if the character does not occur. 1604 */ 1605 public int lastIndexOf(int ch) { 1606 return lastIndexOf(ch, value.length - 1); 1607 } 1608 1609 /** 1610 * Returns the index within this string of the last occurrence of 1611 * the specified character, searching backward starting at the 1612 * specified index. For values of {@code ch} in the range 1613 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1614 * value <i>k</i> such that: 1615 * <blockquote><pre> 1616 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1617 * </pre></blockquote> 1618 * is true. For other values of {@code ch}, it is the 1619 * largest value <i>k</i> such that: 1620 * <blockquote><pre> 1621 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1622 * </pre></blockquote> 1623 * is true. In either case, if no such character occurs in this 1624 * string at or before position {@code fromIndex}, then 1625 * {@code -1} is returned. 1626 * 1627 * <p>All indices are specified in {@code char} values 1628 * (Unicode code units). 1629 * 1630 * @param ch a character (Unicode code point). 1631 * @param fromIndex the index to start the search from. There is no 1632 * restriction on the value of {@code fromIndex}. If it is 1633 * greater than or equal to the length of this string, it has 1634 * the same effect as if it were equal to one less than the 1635 * length of this string: this entire string may be searched. 1636 * If it is negative, it has the same effect as if it were -1: 1637 * -1 is returned. 1638 * @return the index of the last occurrence of the character in the 1639 * character sequence represented by this object that is less 1640 * than or equal to {@code fromIndex}, or {@code -1} 1641 * if the character does not occur before that point. 1642 */ 1643 public int lastIndexOf(int ch, int fromIndex) { 1644 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1645 // handle most cases here (ch is a BMP code point or a 1646 // negative value (invalid code point)) 1647 final char[] value = this.value; 1648 int i = Math.min(fromIndex, value.length - 1); 1649 for (; i >= 0; i--) { 1650 if (value[i] == ch) { 1651 return i; 1652 } 1653 } 1654 return -1; 1655 } else { 1656 return lastIndexOfSupplementary(ch, fromIndex); 1657 } 1658 } 1659 1660 /** 1661 * Handles (rare) calls of lastIndexOf with a supplementary character. 1662 */ 1663 private int lastIndexOfSupplementary(int ch, int fromIndex) { 1664 if (Character.isValidCodePoint(ch)) { 1665 final char[] value = this.value; 1666 char hi = Character.highSurrogate(ch); 1667 char lo = Character.lowSurrogate(ch); 1668 int i = Math.min(fromIndex, value.length - 2); 1669 for (; i >= 0; i--) { 1670 if (value[i] == hi && value[i + 1] == lo) { 1671 return i; 1672 } 1673 } 1674 } 1675 return -1; 1676 } 1677 1678 /** 1679 * Returns the index within this string of the first occurrence of the 1680 * specified substring. 1681 * 1682 * <p>The returned index is the smallest value {@code k} for which: 1683 * <pre>{@code 1684 * this.startsWith(str, k) 1685 * }</pre> 1686 * If no such value of {@code k} exists, then {@code -1} is returned. 1687 * 1688 * @param str the substring to search for. 1689 * @return the index of the first occurrence of the specified substring, 1690 * or {@code -1} if there is no such occurrence. 1691 */ 1692 public int indexOf(String str) { 1693 return indexOf(str, 0); 1694 } 1695 1696 /** 1697 * Returns the index within this string of the first occurrence of the 1698 * specified substring, starting at the specified index. 1699 * 1700 * <p>The returned index is the smallest value {@code k} for which: 1701 * <pre>{@code 1702 * k >= Math.min(fromIndex, this.length()) && 1703 * this.startsWith(str, k) 1704 * }</pre> 1705 * If no such value of {@code k} exists, then {@code -1} is returned. 1706 * 1707 * @param str the substring to search for. 1708 * @param fromIndex the index from which to start the search. 1709 * @return the index of the first occurrence of the specified substring, 1710 * starting at the specified index, 1711 * or {@code -1} if there is no such occurrence. 1712 */ 1713 public int indexOf(String str, int fromIndex) { 1714 return indexOf(value, 0, value.length, 1715 str.value, 0, str.value.length, fromIndex); 1716 } 1717 1718 /** 1719 * Code shared by String and AbstractStringBuilder to do searches. The 1720 * source is the character array being searched, and the target 1721 * is the string being searched for. 1722 * 1723 * @param source the characters being searched. 1724 * @param sourceOffset offset of the source string. 1725 * @param sourceCount count of the source string. 1726 * @param target the characters being searched for. 1727 * @param fromIndex the index to begin searching from. 1728 */ 1729 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1730 String target, int fromIndex) { 1731 return indexOf(source, sourceOffset, sourceCount, 1732 target.value, 0, target.value.length, 1733 fromIndex); 1734 } 1735 1736 /** 1737 * Code shared by String and StringBuffer to do searches. The 1738 * source is the character array being searched, and the target 1739 * is the string being searched for. 1740 * 1741 * @param source the characters being searched. 1742 * @param sourceOffset offset of the source string. 1743 * @param sourceCount count of the source string. 1744 * @param target the characters being searched for. 1745 * @param targetOffset offset of the target string. 1746 * @param targetCount count of the target string. 1747 * @param fromIndex the index to begin searching from. 1748 */ 1749 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1750 char[] target, int targetOffset, int targetCount, 1751 int fromIndex) { 1752 if (fromIndex >= sourceCount) { 1753 return (targetCount == 0 ? sourceCount : -1); 1754 } 1755 if (fromIndex < 0) { 1756 fromIndex = 0; 1757 } 1758 if (targetCount == 0) { 1759 return fromIndex; 1760 } 1761 1762 char first = target[targetOffset]; 1763 int max = sourceOffset + (sourceCount - targetCount); 1764 1765 for (int i = sourceOffset + fromIndex; i <= max; i++) { 1766 /* Look for first character. */ 1767 if (source[i] != first) { 1768 while (++i <= max && source[i] != first); 1769 } 1770 1771 /* Found first character, now look at the rest of v2 */ 1772 if (i <= max) { 1773 int j = i + 1; 1774 int end = j + targetCount - 1; 1775 for (int k = targetOffset + 1; j < end && source[j] 1776 == target[k]; j++, k++); 1777 1778 if (j == end) { 1779 /* Found whole string. */ 1780 return i - sourceOffset; 1781 } 1782 } 1783 } 1784 return -1; 1785 } 1786 1787 /** 1788 * Returns the index within this string of the last occurrence of the 1789 * specified substring. The last occurrence of the empty string "" 1790 * is considered to occur at the index value {@code this.length()}. 1791 * 1792 * <p>The returned index is the largest value {@code k} for which: 1793 * <pre>{@code 1794 * this.startsWith(str, k) 1795 * }</pre> 1796 * If no such value of {@code k} exists, then {@code -1} is returned. 1797 * 1798 * @param str the substring to search for. 1799 * @return the index of the last occurrence of the specified substring, 1800 * or {@code -1} if there is no such occurrence. 1801 */ 1802 public int lastIndexOf(String str) { 1803 return lastIndexOf(str, value.length); 1804 } 1805 1806 /** 1807 * Returns the index within this string of the last occurrence of the 1808 * specified substring, searching backward starting at the specified index. 1809 * 1810 * <p>The returned index is the largest value {@code k} for which: 1811 * <pre>{@code 1812 * k <= Math.min(fromIndex, this.length()) && 1813 * this.startsWith(str, k) 1814 * }</pre> 1815 * If no such value of {@code k} exists, then {@code -1} is returned. 1816 * 1817 * @param str the substring to search for. 1818 * @param fromIndex the index to start the search from. 1819 * @return the index of the last occurrence of the specified substring, 1820 * searching backward from the specified index, 1821 * or {@code -1} if there is no such occurrence. 1822 */ 1823 public int lastIndexOf(String str, int fromIndex) { 1824 return lastIndexOf(value, 0, value.length, 1825 str.value, 0, str.value.length, fromIndex); 1826 } 1827 1828 /** 1829 * Code shared by String and AbstractStringBuilder to do searches. The 1830 * source is the character array being searched, and the target 1831 * is the string being searched for. 1832 * 1833 * @param source the characters being searched. 1834 * @param sourceOffset offset of the source string. 1835 * @param sourceCount count of the source string. 1836 * @param target the characters being searched for. 1837 * @param fromIndex the index to begin searching from. 1838 */ 1839 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1840 String target, int fromIndex) { 1841 return lastIndexOf(source, sourceOffset, sourceCount, 1842 target.value, 0, target.value.length, 1843 fromIndex); 1844 } 1845 1846 /** 1847 * Code shared by String and StringBuffer to do searches. The 1848 * source is the character array being searched, and the target 1849 * is the string being searched for. 1850 * 1851 * @param source the characters being searched. 1852 * @param sourceOffset offset of the source string. 1853 * @param sourceCount count of the source string. 1854 * @param target the characters being searched for. 1855 * @param targetOffset offset of the target string. 1856 * @param targetCount count of the target string. 1857 * @param fromIndex the index to begin searching from. 1858 */ 1859 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1860 char[] target, int targetOffset, int targetCount, 1861 int fromIndex) { 1862 /* 1863 * Check arguments; return immediately where possible. For 1864 * consistency, don't check for null str. 1865 */ 1866 int rightIndex = sourceCount - targetCount; 1867 if (fromIndex < 0) { 1868 return -1; 1869 } 1870 if (fromIndex > rightIndex) { 1871 fromIndex = rightIndex; 1872 } 1873 /* Empty string always matches. */ 1874 if (targetCount == 0) { 1875 return fromIndex; 1876 } 1877 1878 int strLastIndex = targetOffset + targetCount - 1; 1879 char strLastChar = target[strLastIndex]; 1880 int min = sourceOffset + targetCount - 1; 1881 int i = min + fromIndex; 1882 1883 startSearchForLastChar: 1884 while (true) { 1885 while (i >= min && source[i] != strLastChar) { 1886 i--; 1887 } 1888 if (i < min) { 1889 return -1; 1890 } 1891 int j = i - 1; 1892 int start = j - (targetCount - 1); 1893 int k = strLastIndex - 1; 1894 1895 while (j > start) { 1896 if (source[j--] != target[k--]) { 1897 i--; 1898 continue startSearchForLastChar; 1899 } 1900 } 1901 return start - sourceOffset + 1; 1902 } 1903 } 1904 1905 /** 1906 * Returns a string that is a substring of this string. The 1907 * substring begins with the character at the specified index and 1908 * extends to the end of this string. <p> 1909 * Examples: 1910 * <blockquote><pre> 1911 * "unhappy".substring(2) returns "happy" 1912 * "Harbison".substring(3) returns "bison" 1913 * "emptiness".substring(9) returns "" (an empty string) 1914 * </pre></blockquote> 1915 * 1916 * @param beginIndex the beginning index, inclusive. 1917 * @return the specified substring. 1918 * @exception IndexOutOfBoundsException if 1919 * {@code beginIndex} is negative or larger than the 1920 * length of this {@code String} object. 1921 */ 1922 public String substring(int beginIndex) { 1923 if (beginIndex < 0) { 1924 throw new StringIndexOutOfBoundsException(beginIndex); 1925 } 1926 int subLen = value.length - beginIndex; 1927 if (subLen < 0) { 1928 throw new StringIndexOutOfBoundsException(subLen); 1929 } 1930 return (beginIndex == 0) ? this : new String(value, beginIndex, subLen); 1931 } 1932 1933 /** 1934 * Returns a string that is a substring of this string. The 1935 * substring begins at the specified {@code beginIndex} and 1936 * extends to the character at index {@code endIndex - 1}. 1937 * Thus the length of the substring is {@code endIndex-beginIndex}. 1938 * <p> 1939 * Examples: 1940 * <blockquote><pre> 1941 * "hamburger".substring(4, 8) returns "urge" 1942 * "smiles".substring(1, 5) returns "mile" 1943 * </pre></blockquote> 1944 * 1945 * @param beginIndex the beginning index, inclusive. 1946 * @param endIndex the ending index, exclusive. 1947 * @return the specified substring. 1948 * @exception IndexOutOfBoundsException if the 1949 * {@code beginIndex} is negative, or 1950 * {@code endIndex} is larger than the length of 1951 * this {@code String} object, or 1952 * {@code beginIndex} is larger than 1953 * {@code endIndex}. 1954 */ 1955 public String substring(int beginIndex, int endIndex) { 1956 if (beginIndex < 0) { 1957 throw new StringIndexOutOfBoundsException(beginIndex); 1958 } 1959 if (endIndex > value.length) { 1960 throw new StringIndexOutOfBoundsException(endIndex); 1961 } 1962 int subLen = endIndex - beginIndex; 1963 if (subLen < 0) { 1964 throw new StringIndexOutOfBoundsException(subLen); 1965 } 1966 return ((beginIndex == 0) && (endIndex == value.length)) ? this 1967 : new String(value, beginIndex, subLen); 1968 } 1969 1970 /** 1971 * Returns a character sequence that is a subsequence of this sequence. 1972 * 1973 * <p> An invocation of this method of the form 1974 * 1975 * <blockquote><pre> 1976 * str.subSequence(begin, end)</pre></blockquote> 1977 * 1978 * behaves in exactly the same way as the invocation 1979 * 1980 * <blockquote><pre> 1981 * str.substring(begin, end)</pre></blockquote> 1982 * 1983 * @apiNote 1984 * This method is defined so that the {@code String} class can implement 1985 * the {@link CharSequence} interface. 1986 * 1987 * @param beginIndex the begin index, inclusive. 1988 * @param endIndex the end index, exclusive. 1989 * @return the specified subsequence. 1990 * 1991 * @throws IndexOutOfBoundsException 1992 * if {@code beginIndex} or {@code endIndex} is negative, 1993 * if {@code endIndex} is greater than {@code length()}, 1994 * or if {@code beginIndex} is greater than {@code endIndex} 1995 * 1996 * @since 1.4 1997 * @spec JSR-51 1998 */ 1999 public CharSequence subSequence(int beginIndex, int endIndex) { 2000 return this.substring(beginIndex, endIndex); 2001 } 2002 2003 /** 2004 * Concatenates the specified string to the end of this string. 2005 * <p> 2006 * If the length of the argument string is {@code 0}, then this 2007 * {@code String} object is returned. Otherwise, a 2008 * {@code String} object is returned that represents a character 2009 * sequence that is the concatenation of the character sequence 2010 * represented by this {@code String} object and the character 2011 * sequence represented by the argument string.<p> 2012 * Examples: 2013 * <blockquote><pre> 2014 * "cares".concat("s") returns "caress" 2015 * "to".concat("get").concat("her") returns "together" 2016 * </pre></blockquote> 2017 * 2018 * @param str the {@code String} that is concatenated to the end 2019 * of this {@code String}. 2020 * @return a string that represents the concatenation of this object's 2021 * characters followed by the string argument's characters. 2022 */ 2023 public String concat(String str) { 2024 int otherLen = str.length(); 2025 if (otherLen == 0) { 2026 return this; 2027 } 2028 int len = value.length; 2029 char buf[] = Arrays.copyOf(value, len + otherLen); 2030 str.getChars(buf, len); 2031 return new String(buf, true); 2032 } 2033 2034 /** 2035 * Returns a string resulting from replacing all occurrences of 2036 * {@code oldChar} in this string with {@code newChar}. 2037 * <p> 2038 * If the character {@code oldChar} does not occur in the 2039 * character sequence represented by this {@code String} object, 2040 * then a reference to this {@code String} object is returned. 2041 * Otherwise, a {@code String} object is returned that 2042 * represents a character sequence identical to the character sequence 2043 * represented by this {@code String} object, except that every 2044 * occurrence of {@code oldChar} is replaced by an occurrence 2045 * of {@code newChar}. 2046 * <p> 2047 * Examples: 2048 * <blockquote><pre> 2049 * "mesquite in your cellar".replace('e', 'o') 2050 * returns "mosquito in your collar" 2051 * "the war of baronets".replace('r', 'y') 2052 * returns "the way of bayonets" 2053 * "sparring with a purple porpoise".replace('p', 't') 2054 * returns "starring with a turtle tortoise" 2055 * "JonL".replace('q', 'x') returns "JonL" (no change) 2056 * </pre></blockquote> 2057 * 2058 * @param oldChar the old character. 2059 * @param newChar the new character. 2060 * @return a string derived from this string by replacing every 2061 * occurrence of {@code oldChar} with {@code newChar}. 2062 */ 2063 public String replace(char oldChar, char newChar) { 2064 if (oldChar != newChar) { 2065 int len = value.length; 2066 int i = -1; 2067 char[] val = value; /* avoid getfield opcode */ 2068 2069 while (++i < len) { 2070 if (val[i] == oldChar) { 2071 break; 2072 } 2073 } 2074 if (i < len) { 2075 char buf[] = new char[len]; 2076 for (int j = 0; j < i; j++) { 2077 buf[j] = val[j]; 2078 } 2079 while (i < len) { 2080 char c = val[i]; 2081 buf[i] = (c == oldChar) ? newChar : c; 2082 i++; 2083 } 2084 return new String(buf, true); 2085 } 2086 } 2087 return this; 2088 } 2089 2090 /** 2091 * Tells whether or not this string matches the given <a 2092 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2093 * 2094 * <p> An invocation of this method of the form 2095 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2096 * same result as the expression 2097 * 2098 * <blockquote> 2099 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2100 * matches(<i>regex</i>, <i>str</i>)} 2101 * </blockquote> 2102 * 2103 * @param regex 2104 * the regular expression to which this string is to be matched 2105 * 2106 * @return {@code true} if, and only if, this string matches the 2107 * given regular expression 2108 * 2109 * @throws PatternSyntaxException 2110 * if the regular expression's syntax is invalid 2111 * 2112 * @see java.util.regex.Pattern 2113 * 2114 * @since 1.4 2115 * @spec JSR-51 2116 */ 2117 public boolean matches(String regex) { 2118 return Pattern.matches(regex, this); 2119 } 2120 2121 /** 2122 * Returns true if and only if this string contains the specified 2123 * sequence of char values. 2124 * 2125 * @param s the sequence to search for 2126 * @return true if this string contains {@code s}, false otherwise 2127 * @since 1.5 2128 */ 2129 public boolean contains(CharSequence s) { 2130 return indexOf(s.toString()) >= 0; 2131 } 2132 2133 /** 2134 * Replaces the first substring of this string that matches the given <a 2135 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2136 * given replacement. 2137 * 2138 * <p> An invocation of this method of the form 2139 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2140 * yields exactly the same result as the expression 2141 * 2142 * <blockquote> 2143 * <code> 2144 * {@link java.util.regex.Pattern}.{@link 2145 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2146 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2147 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>) 2148 * </code> 2149 * </blockquote> 2150 * 2151 *<p> 2152 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2153 * replacement string may cause the results to be different than if it were 2154 * being treated as a literal replacement string; see 2155 * {@link java.util.regex.Matcher#replaceFirst}. 2156 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2157 * meaning of these characters, if desired. 2158 * 2159 * @param regex 2160 * the regular expression to which this string is to be matched 2161 * @param replacement 2162 * the string to be substituted for the first match 2163 * 2164 * @return The resulting {@code String} 2165 * 2166 * @throws PatternSyntaxException 2167 * if the regular expression's syntax is invalid 2168 * 2169 * @see java.util.regex.Pattern 2170 * 2171 * @since 1.4 2172 * @spec JSR-51 2173 */ 2174 public String replaceFirst(String regex, String replacement) { 2175 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2176 } 2177 2178 /** 2179 * Replaces each substring of this string that matches the given <a 2180 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2181 * given replacement. 2182 * 2183 * <p> An invocation of this method of the form 2184 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2185 * yields exactly the same result as the expression 2186 * 2187 * <blockquote> 2188 * <code> 2189 * {@link java.util.regex.Pattern}.{@link 2190 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2191 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2192 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2193 * </code> 2194 * </blockquote> 2195 * 2196 *<p> 2197 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2198 * replacement string may cause the results to be different than if it were 2199 * being treated as a literal replacement string; see 2200 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2201 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2202 * meaning of these characters, if desired. 2203 * 2204 * @param regex 2205 * the regular expression to which this string is to be matched 2206 * @param replacement 2207 * the string to be substituted for each match 2208 * 2209 * @return The resulting {@code String} 2210 * 2211 * @throws PatternSyntaxException 2212 * if the regular expression's syntax is invalid 2213 * 2214 * @see java.util.regex.Pattern 2215 * 2216 * @since 1.4 2217 * @spec JSR-51 2218 */ 2219 public String replaceAll(String regex, String replacement) { 2220 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2221 } 2222 2223 /** 2224 * Replaces each substring of this string that matches the literal target 2225 * sequence with the specified literal replacement sequence. The 2226 * replacement proceeds from the beginning of the string to the end, for 2227 * example, replacing "aa" with "b" in the string "aaa" will result in 2228 * "ba" rather than "ab". 2229 * 2230 * @param target The sequence of char values to be replaced 2231 * @param replacement The replacement sequence of char values 2232 * @return The resulting string 2233 * @since 1.5 2234 */ 2235 public String replace(CharSequence target, CharSequence replacement) { 2236 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher( 2237 this).replaceAll(Matcher.quoteReplacement(replacement.toString())); 2238 } 2239 2240 /** 2241 * Splits this string around matches of the given 2242 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2243 * 2244 * <p> The array returned by this method contains each substring of this 2245 * string that is terminated by another substring that matches the given 2246 * expression or is terminated by the end of the string. The substrings in 2247 * the array are in the order in which they occur in this string. If the 2248 * expression does not match any part of the input then the resulting array 2249 * has just one element, namely this string. 2250 * 2251 * <p> When there is a positive-width match at the beginning of this 2252 * string then an empty leading substring is included at the beginning 2253 * of the resulting array. A zero-width match at the beginning however 2254 * never produces such empty leading substring. 2255 * 2256 * <p> The {@code limit} parameter controls the number of times the 2257 * pattern is applied and therefore affects the length of the resulting 2258 * array. If the limit <i>n</i> is greater than zero then the pattern 2259 * will be applied at most <i>n</i> - 1 times, the array's 2260 * length will be no greater than <i>n</i>, and the array's last entry 2261 * will contain all input beyond the last matched delimiter. If <i>n</i> 2262 * is non-positive then the pattern will be applied as many times as 2263 * possible and the array can have any length. If <i>n</i> is zero then 2264 * the pattern will be applied as many times as possible, the array can 2265 * have any length, and trailing empty strings will be discarded. 2266 * 2267 * <p> The string {@code "boo:and:foo"}, for example, yields the 2268 * following results with these parameters: 2269 * 2270 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2271 * <tr> 2272 * <th>Regex</th> 2273 * <th>Limit</th> 2274 * <th>Result</th> 2275 * </tr> 2276 * <tr><td align=center>:</td> 2277 * <td align=center>2</td> 2278 * <td>{@code { "boo", "and:foo" }}</td></tr> 2279 * <tr><td align=center>:</td> 2280 * <td align=center>5</td> 2281 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2282 * <tr><td align=center>:</td> 2283 * <td align=center>-2</td> 2284 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2285 * <tr><td align=center>o</td> 2286 * <td align=center>5</td> 2287 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2288 * <tr><td align=center>o</td> 2289 * <td align=center>-2</td> 2290 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2291 * <tr><td align=center>o</td> 2292 * <td align=center>0</td> 2293 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2294 * </table></blockquote> 2295 * 2296 * <p> An invocation of this method of the form 2297 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2298 * yields the same result as the expression 2299 * 2300 * <blockquote> 2301 * <code> 2302 * {@link java.util.regex.Pattern}.{@link 2303 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2304 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2305 * </code> 2306 * </blockquote> 2307 * 2308 * 2309 * @param regex 2310 * the delimiting regular expression 2311 * 2312 * @param limit 2313 * the result threshold, as described above 2314 * 2315 * @return the array of strings computed by splitting this string 2316 * around matches of the given regular expression 2317 * 2318 * @throws PatternSyntaxException 2319 * if the regular expression's syntax is invalid 2320 * 2321 * @see java.util.regex.Pattern 2322 * 2323 * @since 1.4 2324 * @spec JSR-51 2325 */ 2326 public String[] split(String regex, int limit) { 2327 /* fastpath if the regex is a 2328 (1)one-char String and this character is not one of the 2329 RegEx's meta characters ".$|()[{^?*+\\", or 2330 (2)two-char String and the first char is the backslash and 2331 the second is not the ascii digit or ascii letter. 2332 */ 2333 char ch = 0; 2334 if (((regex.value.length == 1 && 2335 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2336 (regex.length() == 2 && 2337 regex.charAt(0) == '\\' && 2338 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2339 ((ch-'a')|('z'-ch)) < 0 && 2340 ((ch-'A')|('Z'-ch)) < 0)) && 2341 (ch < Character.MIN_HIGH_SURROGATE || 2342 ch > Character.MAX_LOW_SURROGATE)) 2343 { 2344 int off = 0; 2345 int next = 0; 2346 boolean limited = limit > 0; 2347 ArrayList<String> list = new ArrayList<>(); 2348 while ((next = indexOf(ch, off)) != -1) { 2349 if (!limited || list.size() < limit - 1) { 2350 list.add(substring(off, next)); 2351 off = next + 1; 2352 } else { // last one 2353 //assert (list.size() == limit - 1); 2354 list.add(substring(off, value.length)); 2355 off = value.length; 2356 break; 2357 } 2358 } 2359 // If no match was found, return this 2360 if (off == 0) 2361 return new String[]{this}; 2362 2363 // Add remaining segment 2364 if (!limited || list.size() < limit) 2365 list.add(substring(off, value.length)); 2366 2367 // Construct result 2368 int resultSize = list.size(); 2369 if (limit == 0) { 2370 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) { 2371 resultSize--; 2372 } 2373 } 2374 String[] result = new String[resultSize]; 2375 return list.subList(0, resultSize).toArray(result); 2376 } 2377 return Pattern.compile(regex).split(this, limit); 2378 } 2379 2380 /** 2381 * Splits this string around matches of the given <a 2382 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2383 * 2384 * <p> This method works as if by invoking the two-argument {@link 2385 * #split(String, int) split} method with the given expression and a limit 2386 * argument of zero. Trailing empty strings are therefore not included in 2387 * the resulting array. 2388 * 2389 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2390 * results with these expressions: 2391 * 2392 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2393 * <tr> 2394 * <th>Regex</th> 2395 * <th>Result</th> 2396 * </tr> 2397 * <tr><td align=center>:</td> 2398 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2399 * <tr><td align=center>o</td> 2400 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2401 * </table></blockquote> 2402 * 2403 * 2404 * @param regex 2405 * the delimiting regular expression 2406 * 2407 * @return the array of strings computed by splitting this string 2408 * around matches of the given regular expression 2409 * 2410 * @throws PatternSyntaxException 2411 * if the regular expression's syntax is invalid 2412 * 2413 * @see java.util.regex.Pattern 2414 * 2415 * @since 1.4 2416 * @spec JSR-51 2417 */ 2418 public String[] split(String regex) { 2419 return split(regex, 0); 2420 } 2421 2422 /** 2423 * Returns a new String composed of copies of the 2424 * {@code CharSequence elements} joined together with a copy of 2425 * the specified {@code delimiter}. 2426 * 2427 * <blockquote>For example, 2428 * <pre>{@code 2429 * String message = String.join("-", "Java", "is", "cool"); 2430 * // message returned is: "Java-is-cool" 2431 * }</pre></blockquote> 2432 * 2433 * Note that if an element is null, then {@code "null"} is added. 2434 * 2435 * @param delimiter the delimiter that separates each element 2436 * @param elements the elements to join together. 2437 * 2438 * @return a new {@code String} that is composed of the {@code elements} 2439 * separated by the {@code delimiter} 2440 * 2441 * @throws NullPointerException If {@code delimiter} or {@code elements} 2442 * is {@code null} 2443 * 2444 * @see java.util.StringJoiner 2445 * @since 1.8 2446 */ 2447 public static String join(CharSequence delimiter, CharSequence... elements) { 2448 Objects.requireNonNull(delimiter); 2449 Objects.requireNonNull(elements); 2450 // Number of elements not likely worth Arrays.stream overhead. 2451 StringJoiner joiner = new StringJoiner(delimiter); 2452 for (CharSequence cs: elements) { 2453 joiner.add(cs); 2454 } 2455 return joiner.toString(); 2456 } 2457 2458 /** 2459 * Returns a new {@code String} composed of copies of the 2460 * {@code CharSequence elements} joined together with a copy of the 2461 * specified {@code delimiter}. 2462 * 2463 * <blockquote>For example, 2464 * <pre>{@code 2465 * List<String> strings = new LinkedList<>(); 2466 * strings.add("Java");strings.add("is"); 2467 * strings.add("cool"); 2468 * String message = String.join(" ", strings); 2469 * //message returned is: "Java is cool" 2470 * 2471 * Set<String> strings = new LinkedHashSet<>(); 2472 * strings.add("Java"); strings.add("is"); 2473 * strings.add("very"); strings.add("cool"); 2474 * String message = String.join("-", strings); 2475 * //message returned is: "Java-is-very-cool" 2476 * }</pre></blockquote> 2477 * 2478 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2479 * 2480 * @param delimiter a sequence of characters that is used to separate each 2481 * of the {@code elements} in the resulting {@code String} 2482 * @param elements an {@code Iterable} that will have its {@code elements} 2483 * joined together. 2484 * 2485 * @return a new {@code String} that is composed from the {@code elements} 2486 * argument 2487 * 2488 * @throws NullPointerException If {@code delimiter} or {@code elements} 2489 * is {@code null} 2490 * 2491 * @see #join(CharSequence,CharSequence...) 2492 * @see java.util.StringJoiner 2493 * @since 1.8 2494 */ 2495 public static String join(CharSequence delimiter, 2496 Iterable<? extends CharSequence> elements) { 2497 Objects.requireNonNull(delimiter); 2498 Objects.requireNonNull(elements); 2499 StringJoiner joiner = new StringJoiner(delimiter); 2500 for (CharSequence cs: elements) { 2501 joiner.add(cs); 2502 } 2503 return joiner.toString(); 2504 } 2505 2506 /** 2507 * Converts all of the characters in this {@code String} to lower 2508 * case using the rules of the given {@code Locale}. Case mapping is based 2509 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2510 * class. Since case mappings are not always 1:1 char mappings, the resulting 2511 * {@code String} may be a different length than the original {@code String}. 2512 * <p> 2513 * Examples of lowercase mappings are in the following table: 2514 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2515 * <tr> 2516 * <th>Language Code of Locale</th> 2517 * <th>Upper Case</th> 2518 * <th>Lower Case</th> 2519 * <th>Description</th> 2520 * </tr> 2521 * <tr> 2522 * <td>tr (Turkish)</td> 2523 * <td>\u0130</td> 2524 * <td>\u0069</td> 2525 * <td>capital letter I with dot above -> small letter i</td> 2526 * </tr> 2527 * <tr> 2528 * <td>tr (Turkish)</td> 2529 * <td>\u0049</td> 2530 * <td>\u0131</td> 2531 * <td>capital letter I -> small letter dotless i </td> 2532 * </tr> 2533 * <tr> 2534 * <td>(all)</td> 2535 * <td>French Fries</td> 2536 * <td>french fries</td> 2537 * <td>lowercased all chars in String</td> 2538 * </tr> 2539 * <tr> 2540 * <td>(all)</td> 2541 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2542 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2543 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2544 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2545 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2546 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2547 * <td>lowercased all chars in String</td> 2548 * </tr> 2549 * </table> 2550 * 2551 * @param locale use the case transformation rules for this locale 2552 * @return the {@code String}, converted to lowercase. 2553 * @see java.lang.String#toLowerCase() 2554 * @see java.lang.String#toUpperCase() 2555 * @see java.lang.String#toUpperCase(Locale) 2556 * @since 1.1 2557 */ 2558 public String toLowerCase(Locale locale) { 2559 if (locale == null) { 2560 throw new NullPointerException(); 2561 } 2562 int first; 2563 boolean hasSurr = false; 2564 final int len = value.length; 2565 2566 // Now check if there are any characters that need to be changed, or are surrogate 2567 for (first = 0 ; first < len; first++) { 2568 int cp = (int)value[first]; 2569 if (Character.isSurrogate((char)cp)) { 2570 hasSurr = true; 2571 break; 2572 } 2573 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR 2574 break; 2575 } 2576 } 2577 if (first == len) 2578 return this; 2579 char[] result = new char[len]; 2580 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2581 // lowerCase characters. 2582 String lang = locale.getLanguage(); 2583 if (lang == "tr" || lang == "az" || lang == "lt") { 2584 return toLowerCaseEx(result, first, locale, true); 2585 } 2586 if (hasSurr) { 2587 return toLowerCaseEx(result, first, locale, false); 2588 } 2589 for (int i = first; i < len; i++) { 2590 int cp = (int)value[i]; 2591 if (cp == '\u03A3' || // GREEK CAPITAL LETTER SIGMA 2592 Character.isSurrogate((char)cp)) { 2593 return toLowerCaseEx(result, i, locale, false); 2594 } 2595 if (cp == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE 2596 return toLowerCaseEx(result, i, locale, true); 2597 } 2598 cp = Character.toLowerCase(cp); 2599 if (!Character.isBmpCodePoint(cp)) { 2600 return toLowerCaseEx(result, i, locale, false); 2601 } 2602 result[i] = (char)cp; 2603 } 2604 return new String(result, true); 2605 } 2606 2607 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) { 2608 int resultOffset = first; 2609 int srcCount; 2610 for (int i = first; i < value.length; i += srcCount) { 2611 int srcChar = (int)value[i]; 2612 int lowerChar; 2613 char[] lowerCharArray; 2614 srcCount = 1; 2615 if (Character.isSurrogate((char)srcChar)) { 2616 srcChar = codePointAt(i); 2617 srcCount = Character.charCount(srcChar); 2618 } 2619 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA 2620 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale); 2621 } else { 2622 lowerChar = Character.toLowerCase(srcChar); 2623 } 2624 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp 2625 result[resultOffset++] = (char)lowerChar; 2626 } else { 2627 if (lowerChar == Character.ERROR) { 2628 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale); 2629 } else if (srcCount == 2) { 2630 resultOffset += Character.toChars(lowerChar, result, resultOffset); 2631 continue; 2632 } else { 2633 lowerCharArray = Character.toChars(lowerChar); 2634 } 2635 /* Grow result if needed */ 2636 int mapLen = lowerCharArray.length; 2637 if (mapLen > srcCount) { 2638 char[] result2 = new char[result.length + mapLen - srcCount]; 2639 System.arraycopy(result, 0, result2, 0, resultOffset); 2640 result = result2; 2641 } 2642 for (int x = 0; x < mapLen; ++x) { 2643 result[resultOffset++] = lowerCharArray[x]; 2644 } 2645 } 2646 } 2647 return new String(result, 0, resultOffset); 2648 } 2649 2650 /** 2651 * Converts all of the characters in this {@code String} to lower 2652 * case using the rules of the default locale. This is equivalent to calling 2653 * {@code toLowerCase(Locale.getDefault())}. 2654 * <p> 2655 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2656 * results if used for strings that are intended to be interpreted locale 2657 * independently. 2658 * Examples are programming language identifiers, protocol keys, and HTML 2659 * tags. 2660 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2661 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2662 * LATIN SMALL LETTER DOTLESS I character. 2663 * To obtain correct results for locale insensitive strings, use 2664 * {@code toLowerCase(Locale.ROOT)}. 2665 * 2666 * @return the {@code String}, converted to lowercase. 2667 * @see java.lang.String#toLowerCase(Locale) 2668 */ 2669 public String toLowerCase() { 2670 return toLowerCase(Locale.getDefault()); 2671 } 2672 2673 /** 2674 * Converts all of the characters in this {@code String} to upper 2675 * case using the rules of the given {@code Locale}. Case mapping is based 2676 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2677 * class. Since case mappings are not always 1:1 char mappings, the resulting 2678 * {@code String} may be a different length than the original {@code String}. 2679 * <p> 2680 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2681 * 2682 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2683 * <tr> 2684 * <th>Language Code of Locale</th> 2685 * <th>Lower Case</th> 2686 * <th>Upper Case</th> 2687 * <th>Description</th> 2688 * </tr> 2689 * <tr> 2690 * <td>tr (Turkish)</td> 2691 * <td>\u0069</td> 2692 * <td>\u0130</td> 2693 * <td>small letter i -> capital letter I with dot above</td> 2694 * </tr> 2695 * <tr> 2696 * <td>tr (Turkish)</td> 2697 * <td>\u0131</td> 2698 * <td>\u0049</td> 2699 * <td>small letter dotless i -> capital letter I</td> 2700 * </tr> 2701 * <tr> 2702 * <td>(all)</td> 2703 * <td>\u00df</td> 2704 * <td>\u0053 \u0053</td> 2705 * <td>small letter sharp s -> two letters: SS</td> 2706 * </tr> 2707 * <tr> 2708 * <td>(all)</td> 2709 * <td>Fahrvergnügen</td> 2710 * <td>FAHRVERGNÜGEN</td> 2711 * <td></td> 2712 * </tr> 2713 * </table> 2714 * @param locale use the case transformation rules for this locale 2715 * @return the {@code String}, converted to uppercase. 2716 * @see java.lang.String#toUpperCase() 2717 * @see java.lang.String#toLowerCase() 2718 * @see java.lang.String#toLowerCase(Locale) 2719 * @since 1.1 2720 */ 2721 public String toUpperCase(Locale locale) { 2722 if (locale == null) { 2723 throw new NullPointerException(); 2724 } 2725 int first; 2726 boolean hasSurr = false; 2727 final int len = value.length; 2728 2729 // Now check if there are any characters that need to be changed, or are surrogate 2730 for (first = 0 ; first < len; first++ ) { 2731 int cp = (int)value[first]; 2732 if (Character.isSurrogate((char)cp)) { 2733 hasSurr = true; 2734 break; 2735 } 2736 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR 2737 break; 2738 } 2739 } 2740 if (first == len) { 2741 return this; 2742 } 2743 char[] result = new char[len]; 2744 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2745 // upperCase characters. 2746 String lang = locale.getLanguage(); 2747 if (lang == "tr" || lang == "az" || lang == "lt") { 2748 return toUpperCaseEx(result, first, locale, true); 2749 } 2750 if (hasSurr) { 2751 return toUpperCaseEx(result, first, locale, false); 2752 } 2753 for (int i = first; i < len; i++) { 2754 int cp = (int)value[i]; 2755 if (Character.isSurrogate((char)cp)) { 2756 return toUpperCaseEx(result, i, locale, false); 2757 } 2758 cp = Character.toUpperCaseEx(cp); 2759 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp 2760 return toUpperCaseEx(result, i, locale, false); 2761 } 2762 result[i] = (char)cp; 2763 } 2764 return new String(result, true); 2765 } 2766 2767 private String toUpperCaseEx(char[] result, int first, Locale locale, 2768 boolean localeDependent) { 2769 int resultOffset = first; 2770 int srcCount; 2771 for (int i = first; i < value.length; i += srcCount) { 2772 int srcChar = (int)value[i]; 2773 int upperChar; 2774 char[] upperCharArray; 2775 srcCount = 1; 2776 if (Character.isSurrogate((char)srcChar)) { 2777 srcChar = codePointAt(i); 2778 srcCount = Character.charCount(srcChar); 2779 } 2780 if (localeDependent) { 2781 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale); 2782 } else { 2783 upperChar = Character.toUpperCaseEx(srcChar); 2784 } 2785 if (Character.isBmpCodePoint(upperChar)) { 2786 result[resultOffset++] = (char)upperChar; 2787 } else { 2788 if (upperChar == Character.ERROR) { 2789 if (localeDependent) { 2790 upperCharArray = 2791 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale); 2792 } else { 2793 upperCharArray = Character.toUpperCaseCharArray(srcChar); 2794 } 2795 } else if (srcCount == 2) { 2796 resultOffset += Character.toChars(upperChar, result, resultOffset); 2797 continue; 2798 } else { 2799 upperCharArray = Character.toChars(upperChar); 2800 } 2801 /* Grow result if needed */ 2802 int mapLen = upperCharArray.length; 2803 if (mapLen > srcCount) { 2804 char[] result2 = new char[result.length + mapLen - srcCount]; 2805 System.arraycopy(result, 0, result2, 0, resultOffset); 2806 result = result2; 2807 } 2808 for (int x = 0; x < mapLen; ++x) { 2809 result[resultOffset++] = upperCharArray[x]; 2810 } 2811 } 2812 } 2813 return new String(result, 0, resultOffset); 2814 } 2815 2816 /** 2817 * Converts all of the characters in this {@code String} to upper 2818 * case using the rules of the default locale. This method is equivalent to 2819 * {@code toUpperCase(Locale.getDefault())}. 2820 * <p> 2821 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2822 * results if used for strings that are intended to be interpreted locale 2823 * independently. 2824 * Examples are programming language identifiers, protocol keys, and HTML 2825 * tags. 2826 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2827 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2828 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2829 * To obtain correct results for locale insensitive strings, use 2830 * {@code toUpperCase(Locale.ROOT)}. 2831 * 2832 * @return the {@code String}, converted to uppercase. 2833 * @see java.lang.String#toUpperCase(Locale) 2834 */ 2835 public String toUpperCase() { 2836 return toUpperCase(Locale.getDefault()); 2837 } 2838 2839 /** 2840 * Returns a string whose value is this string, with any leading and trailing 2841 * whitespace removed. 2842 * <p> 2843 * If this {@code String} object represents an empty character 2844 * sequence, or the first and last characters of character sequence 2845 * represented by this {@code String} object both have codes 2846 * greater than {@code '\u005Cu0020'} (the space character), then a 2847 * reference to this {@code String} object is returned. 2848 * <p> 2849 * Otherwise, if there is no character with a code greater than 2850 * {@code '\u005Cu0020'} in the string, then a 2851 * {@code String} object representing an empty string is 2852 * returned. 2853 * <p> 2854 * Otherwise, let <i>k</i> be the index of the first character in the 2855 * string whose code is greater than {@code '\u005Cu0020'}, and let 2856 * <i>m</i> be the index of the last character in the string whose code 2857 * is greater than {@code '\u005Cu0020'}. A {@code String} 2858 * object is returned, representing the substring of this string that 2859 * begins with the character at index <i>k</i> and ends with the 2860 * character at index <i>m</i>-that is, the result of 2861 * {@code this.substring(k, m + 1)}. 2862 * <p> 2863 * This method may be used to trim whitespace (as defined above) from 2864 * the beginning and end of a string. 2865 * 2866 * @return A string whose value is this string, with any leading and trailing white 2867 * space removed, or this string if it has no leading or 2868 * trailing white space. 2869 */ 2870 public String trim() { 2871 int len = value.length; 2872 int st = 0; 2873 char[] val = value; /* avoid getfield opcode */ 2874 2875 while ((st < len) && (val[st] <= ' ')) { 2876 st++; 2877 } 2878 while ((st < len) && (val[len - 1] <= ' ')) { 2879 len--; 2880 } 2881 return ((st > 0) || (len < value.length)) ? substring(st, len) : this; 2882 } 2883 2884 /** 2885 * This object (which is already a string!) is itself returned. 2886 * 2887 * @return the string itself. 2888 */ 2889 public String toString() { 2890 return this; 2891 } 2892 2893 /** 2894 * Converts this string to a new character array. 2895 * 2896 * @return a newly allocated character array whose length is the length 2897 * of this string and whose contents are initialized to contain 2898 * the character sequence represented by this string. 2899 */ 2900 public char[] toCharArray() { 2901 // Cannot use Arrays.copyOf because of class initialization order issues 2902 char result[] = new char[value.length]; 2903 System.arraycopy(value, 0, result, 0, value.length); 2904 return result; 2905 } 2906 2907 /** 2908 * Returns a formatted string using the specified format string and 2909 * arguments. 2910 * 2911 * <p> The locale always used is the one returned by {@link 2912 * java.util.Locale#getDefault() Locale.getDefault()}. 2913 * 2914 * @param format 2915 * A <a href="../util/Formatter.html#syntax">format string</a> 2916 * 2917 * @param args 2918 * Arguments referenced by the format specifiers in the format 2919 * string. If there are more arguments than format specifiers, the 2920 * extra arguments are ignored. The number of arguments is 2921 * variable and may be zero. The maximum number of arguments is 2922 * limited by the maximum dimension of a Java array as defined by 2923 * <cite>The Java™ Virtual Machine Specification</cite>. 2924 * The behaviour on a 2925 * {@code null} argument depends on the <a 2926 * href="../util/Formatter.html#syntax">conversion</a>. 2927 * 2928 * @throws java.util.IllegalFormatException 2929 * If a format string contains an illegal syntax, a format 2930 * specifier that is incompatible with the given arguments, 2931 * insufficient arguments given the format string, or other 2932 * illegal conditions. For specification of all possible 2933 * formatting errors, see the <a 2934 * href="../util/Formatter.html#detail">Details</a> section of the 2935 * formatter class specification. 2936 * 2937 * @return A formatted string 2938 * 2939 * @see java.util.Formatter 2940 * @since 1.5 2941 */ 2942 public static String format(String format, Object... args) { 2943 return new Formatter().format(format, args).toString(); 2944 } 2945 2946 /** 2947 * Returns a formatted string using the specified locale, format string, 2948 * and arguments. 2949 * 2950 * @param l 2951 * The {@linkplain java.util.Locale locale} to apply during 2952 * formatting. If {@code l} is {@code null} then no localization 2953 * is applied. 2954 * 2955 * @param format 2956 * A <a href="../util/Formatter.html#syntax">format string</a> 2957 * 2958 * @param args 2959 * Arguments referenced by the format specifiers in the format 2960 * string. If there are more arguments than format specifiers, the 2961 * extra arguments are ignored. The number of arguments is 2962 * variable and may be zero. The maximum number of arguments is 2963 * limited by the maximum dimension of a Java array as defined by 2964 * <cite>The Java™ Virtual Machine Specification</cite>. 2965 * The behaviour on a 2966 * {@code null} argument depends on the 2967 * <a href="../util/Formatter.html#syntax">conversion</a>. 2968 * 2969 * @throws java.util.IllegalFormatException 2970 * If a format string contains an illegal syntax, a format 2971 * specifier that is incompatible with the given arguments, 2972 * insufficient arguments given the format string, or other 2973 * illegal conditions. For specification of all possible 2974 * formatting errors, see the <a 2975 * href="../util/Formatter.html#detail">Details</a> section of the 2976 * formatter class specification 2977 * 2978 * @return A formatted string 2979 * 2980 * @see java.util.Formatter 2981 * @since 1.5 2982 */ 2983 public static String format(Locale l, String format, Object... args) { 2984 return new Formatter(l).format(format, args).toString(); 2985 } 2986 2987 /** 2988 * Returns the string representation of the {@code Object} argument. 2989 * 2990 * @param obj an {@code Object}. 2991 * @return if the argument is {@code null}, then a string equal to 2992 * {@code "null"}; otherwise, the value of 2993 * {@code obj.toString()} is returned. 2994 * @see java.lang.Object#toString() 2995 */ 2996 public static String valueOf(Object obj) { 2997 return (obj == null) ? "null" : obj.toString(); 2998 } 2999 3000 /** 3001 * Returns the string representation of the {@code char} array 3002 * argument. The contents of the character array are copied; subsequent 3003 * modification of the character array does not affect the returned 3004 * string. 3005 * 3006 * @param data the character array. 3007 * @return a {@code String} that contains the characters of the 3008 * character array. 3009 */ 3010 public static String valueOf(char data[]) { 3011 return new String(data); 3012 } 3013 3014 /** 3015 * Returns the string representation of a specific subarray of the 3016 * {@code char} array argument. 3017 * <p> 3018 * The {@code offset} argument is the index of the first 3019 * character of the subarray. The {@code count} argument 3020 * specifies the length of the subarray. The contents of the subarray 3021 * are copied; subsequent modification of the character array does not 3022 * affect the returned string. 3023 * 3024 * @param data the character array. 3025 * @param offset initial offset of the subarray. 3026 * @param count length of the subarray. 3027 * @return a {@code String} that contains the characters of the 3028 * specified subarray of the character array. 3029 * @exception IndexOutOfBoundsException if {@code offset} is 3030 * negative, or {@code count} is negative, or 3031 * {@code offset+count} is larger than 3032 * {@code data.length}. 3033 */ 3034 public static String valueOf(char data[], int offset, int count) { 3035 return new String(data, offset, count); 3036 } 3037 3038 /** 3039 * Equivalent to {@link #valueOf(char[], int, int)}. 3040 * 3041 * @param data the character array. 3042 * @param offset initial offset of the subarray. 3043 * @param count length of the subarray. 3044 * @return a {@code String} that contains the characters of the 3045 * specified subarray of the character array. 3046 * @exception IndexOutOfBoundsException if {@code offset} is 3047 * negative, or {@code count} is negative, or 3048 * {@code offset+count} is larger than 3049 * {@code data.length}. 3050 */ 3051 public static String copyValueOf(char data[], int offset, int count) { 3052 return new String(data, offset, count); 3053 } 3054 3055 /** 3056 * Equivalent to {@link #valueOf(char[])}. 3057 * 3058 * @param data the character array. 3059 * @return a {@code String} that contains the characters of the 3060 * character array. 3061 */ 3062 public static String copyValueOf(char data[]) { 3063 return new String(data); 3064 } 3065 3066 /** 3067 * Returns the string representation of the {@code boolean} argument. 3068 * 3069 * @param b a {@code boolean}. 3070 * @return if the argument is {@code true}, a string equal to 3071 * {@code "true"} is returned; otherwise, a string equal to 3072 * {@code "false"} is returned. 3073 */ 3074 public static String valueOf(boolean b) { 3075 return b ? "true" : "false"; 3076 } 3077 3078 /** 3079 * Returns the string representation of the {@code char} 3080 * argument. 3081 * 3082 * @param c a {@code char}. 3083 * @return a string of length {@code 1} containing 3084 * as its single character the argument {@code c}. 3085 */ 3086 public static String valueOf(char c) { 3087 char data[] = {c}; 3088 return new String(data, true); 3089 } 3090 3091 /** 3092 * Returns the string representation of the {@code int} argument. 3093 * <p> 3094 * The representation is exactly the one returned by the 3095 * {@code Integer.toString} method of one argument. 3096 * 3097 * @param i an {@code int}. 3098 * @return a string representation of the {@code int} argument. 3099 * @see java.lang.Integer#toString(int, int) 3100 */ 3101 public static String valueOf(int i) { 3102 return Integer.toString(i); 3103 } 3104 3105 /** 3106 * Returns the string representation of the {@code long} argument. 3107 * <p> 3108 * The representation is exactly the one returned by the 3109 * {@code Long.toString} method of one argument. 3110 * 3111 * @param l a {@code long}. 3112 * @return a string representation of the {@code long} argument. 3113 * @see java.lang.Long#toString(long) 3114 */ 3115 public static String valueOf(long l) { 3116 return Long.toString(l); 3117 } 3118 3119 /** 3120 * Returns the string representation of the {@code float} argument. 3121 * <p> 3122 * The representation is exactly the one returned by the 3123 * {@code Float.toString} method of one argument. 3124 * 3125 * @param f a {@code float}. 3126 * @return a string representation of the {@code float} argument. 3127 * @see java.lang.Float#toString(float) 3128 */ 3129 public static String valueOf(float f) { 3130 return Float.toString(f); 3131 } 3132 3133 /** 3134 * Returns the string representation of the {@code double} argument. 3135 * <p> 3136 * The representation is exactly the one returned by the 3137 * {@code Double.toString} method of one argument. 3138 * 3139 * @param d a {@code double}. 3140 * @return a string representation of the {@code double} argument. 3141 * @see java.lang.Double#toString(double) 3142 */ 3143 public static String valueOf(double d) { 3144 return Double.toString(d); 3145 } 3146 3147 /** 3148 * Returns a canonical representation for the string object. 3149 * <p> 3150 * A pool of strings, initially empty, is maintained privately by the 3151 * class {@code String}. 3152 * <p> 3153 * When the intern method is invoked, if the pool already contains a 3154 * string equal to this {@code String} object as determined by 3155 * the {@link #equals(Object)} method, then the string from the pool is 3156 * returned. Otherwise, this {@code String} object is added to the 3157 * pool and a reference to this {@code String} object is returned. 3158 * <p> 3159 * It follows that for any two strings {@code s} and {@code t}, 3160 * {@code s.intern() == t.intern()} is {@code true} 3161 * if and only if {@code s.equals(t)} is {@code true}. 3162 * <p> 3163 * All literal strings and string-valued constant expressions are 3164 * interned. String literals are defined in section 3.10.5 of the 3165 * <cite>The Java™ Language Specification</cite>. 3166 * 3167 * @return a string that has the same contents as this string, but is 3168 * guaranteed to be from a pool of unique strings. 3169 */ 3170 public native String intern(); 3171 }