1 /* 2 * Copyright (c) 1994, 2015, 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.Spliterator; 38 import java.util.StringJoiner; 39 import java.util.function.IntConsumer; 40 import java.util.regex.Matcher; 41 import java.util.regex.Pattern; 42 import java.util.regex.PatternSyntaxException; 43 import java.util.stream.IntStream; 44 import java.util.stream.StreamSupport; 45 46 /** 47 * The {@code String} class represents character strings. All 48 * string literals in Java programs, such as {@code "abc"}, are 49 * implemented as instances of this class. 50 * <p> 51 * Strings are constant; their values cannot be changed after they 52 * are created. String buffers support mutable strings. 53 * Because String objects are immutable they can be shared. For example: 54 * <blockquote><pre> 55 * String str = "abc"; 56 * </pre></blockquote><p> 57 * is equivalent to: 58 * <blockquote><pre> 59 * char data[] = {'a', 'b', 'c'}; 60 * String str = new String(data); 61 * </pre></blockquote><p> 62 * Here are some more examples of how strings can be used: 63 * <blockquote><pre> 64 * System.out.println("abc"); 65 * String cde = "cde"; 66 * System.out.println("abc" + cde); 67 * String c = "abc".substring(2,3); 68 * String d = cde.substring(1, 2); 69 * </pre></blockquote> 70 * <p> 71 * The class {@code String} includes methods for examining 72 * individual characters of the sequence, for comparing strings, for 73 * searching strings, for extracting substrings, and for creating a 74 * copy of a string with all characters translated to uppercase or to 75 * lowercase. Case mapping is based on the Unicode Standard version 76 * specified by the {@link java.lang.Character Character} class. 77 * <p> 78 * The Java language provides special support for the string 79 * concatenation operator ( + ), and for conversion of 80 * other objects to strings. String concatenation is implemented 81 * through the {@code StringBuilder}(or {@code StringBuffer}) 82 * class and its {@code append} method. 83 * String conversions are implemented through the method 84 * {@code toString}, defined by {@code Object} and 85 * inherited by all classes in Java. For additional information on 86 * string concatenation and conversion, see Gosling, Joy, and Steele, 87 * <i>The Java Language Specification</i>. 88 * 89 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor 90 * or method in this class will cause a {@link NullPointerException} to be 91 * thrown. 92 * 93 * <p>A {@code String} represents a string in the UTF-16 format 94 * in which <em>supplementary characters</em> are represented by <em>surrogate 95 * pairs</em> (see the section <a href="Character.html#unicode">Unicode 96 * Character Representations</a> in the {@code Character} class for 97 * more information). 98 * Index values refer to {@code char} code units, so a supplementary 99 * character uses two positions in a {@code String}. 100 * <p>The {@code String} class provides methods for dealing with 101 * Unicode code points (i.e., characters), in addition to those for 102 * dealing with Unicode code units (i.e., {@code char} values). 103 * 104 * @author Lee Boynton 105 * @author Arthur van Hoff 106 * @author Martin Buchholz 107 * @author Ulf Zibis 108 * @see java.lang.Object#toString() 109 * @see java.lang.StringBuffer 110 * @see java.lang.StringBuilder 111 * @see java.nio.charset.Charset 112 * @since 1.0 113 */ 114 115 public final class String 116 implements java.io.Serializable, Comparable<String>, CharSequence { 117 /** The value is used for character storage. */ 118 private final char value[]; 119 120 /** Cache the hash code for the string */ 121 private int hash; // Default to 0 122 123 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 124 private static final long serialVersionUID = -6849794470754667710L; 125 126 /** 127 * Class String is special cased within the Serialization Stream Protocol. 128 * 129 * A String instance is written into an ObjectOutputStream according to 130 * <a href="{@docRoot}/../platform/serialization/spec/output.html"> 131 * Object Serialization Specification, Section 6.2, "Stream Elements"</a> 132 */ 133 private static final ObjectStreamField[] serialPersistentFields = 134 new ObjectStreamField[0]; 135 136 /** 137 * Initializes a newly created {@code String} object so that it represents 138 * an empty character sequence. Note that use of this constructor is 139 * unnecessary since Strings are immutable. 140 */ 141 public String() { 142 this.value = "".value; 143 } 144 145 /** 146 * Initializes a newly created {@code String} object so that it represents 147 * the same sequence of characters as the argument; in other words, the 148 * newly created string is a copy of the argument string. Unless an 149 * explicit copy of {@code original} is needed, use of this constructor is 150 * unnecessary since Strings are immutable. 151 * 152 * @param original 153 * A {@code String} 154 */ 155 public String(String original) { 156 this.value = original.value; 157 this.hash = original.hash; 158 } 159 160 /** 161 * Allocates a new {@code String} so that it represents the sequence of 162 * characters currently contained in the character array argument. The 163 * contents of the character array are copied; subsequent modification of 164 * the character array does not affect the newly created string. 165 * 166 * @param value 167 * The initial value of the string 168 */ 169 public String(char value[]) { 170 this.value = Arrays.copyOf(value, value.length); 171 } 172 173 /** 174 * Allocates a new {@code String} that contains characters from a subarray 175 * of the character array argument. The {@code offset} argument is the 176 * index of the first character of the subarray and the {@code count} 177 * argument specifies the length of the subarray. The contents of the 178 * subarray are copied; subsequent modification of the character array does 179 * not affect the newly created string. 180 * 181 * @param value 182 * Array that is the source of characters 183 * 184 * @param offset 185 * The initial offset 186 * 187 * @param count 188 * The length 189 * 190 * @throws IndexOutOfBoundsException 191 * If {@code offset} is negative, {@code count} is negative, or 192 * {@code offset} is greater than {@code value.length - count} 193 */ 194 public String(char value[], int offset, int count) { 195 if (offset < 0) { 196 throw new StringIndexOutOfBoundsException(offset); 197 } 198 if (count <= 0) { 199 if (count < 0) { 200 throw new StringIndexOutOfBoundsException(count); 201 } 202 if (offset <= value.length) { 203 this.value = "".value; 204 return; 205 } 206 } 207 // Note: offset or count might be near -1>>>1. 208 if (offset > value.length - count) { 209 throw new StringIndexOutOfBoundsException(offset + count); 210 } 211 this.value = Arrays.copyOfRange(value, offset, offset + count); 212 } 213 214 /** 215 * Allocates a new {@code String} that contains characters from a subarray 216 * of the <a href="Character.html#unicode">Unicode code point</a> array 217 * argument. The {@code offset} argument is the index of the first code 218 * point of the subarray and the {@code count} argument specifies the 219 * length of the subarray. The contents of the subarray are converted to 220 * {@code char}s; subsequent modification of the {@code int} array does not 221 * affect the newly created string. 222 * 223 * @param codePoints 224 * Array that is the source of Unicode code points 225 * 226 * @param offset 227 * The initial offset 228 * 229 * @param count 230 * The length 231 * 232 * @throws IllegalArgumentException 233 * If any invalid Unicode code point is found in {@code 234 * codePoints} 235 * 236 * @throws IndexOutOfBoundsException 237 * If {@code offset} is negative, {@code count} is negative, or 238 * {@code offset} is greater than {@code codePoints.length - count} 239 * 240 * @since 1.5 241 */ 242 public String(int[] codePoints, int offset, int count) { 243 if (offset < 0) { 244 throw new StringIndexOutOfBoundsException(offset); 245 } 246 if (count <= 0) { 247 if (count < 0) { 248 throw new StringIndexOutOfBoundsException(count); 249 } 250 if (offset <= codePoints.length) { 251 this.value = "".value; 252 return; 253 } 254 } 255 // Note: offset or count might be near -1>>>1. 256 if (offset > codePoints.length - count) { 257 throw new StringIndexOutOfBoundsException(offset + count); 258 } 259 260 final int end = offset + count; 261 262 // Pass 1: Compute precise size of char[] 263 int n = count; 264 for (int i = offset; i < end; i++) { 265 int c = codePoints[i]; 266 if (Character.isBmpCodePoint(c)) 267 continue; 268 else if (Character.isValidCodePoint(c)) 269 n++; 270 else throw new IllegalArgumentException(Integer.toString(c)); 271 } 272 273 // Pass 2: Allocate and fill in char[] 274 final char[] v = new char[n]; 275 276 for (int i = offset, j = 0; i < end; i++, j++) { 277 int c = codePoints[i]; 278 if (Character.isBmpCodePoint(c)) 279 v[j] = (char)c; 280 else 281 Character.toSurrogates(c, v, j++); 282 } 283 284 this.value = v; 285 } 286 287 /** 288 * Allocates a new {@code String} constructed from a subarray of an array 289 * of 8-bit integer values. 290 * 291 * <p> The {@code offset} argument is the index of the first byte of the 292 * subarray, and the {@code count} argument specifies the length of the 293 * subarray. 294 * 295 * <p> Each {@code byte} in the subarray is converted to a {@code char} as 296 * specified in the method above. 297 * 298 * @deprecated This method does not properly convert bytes into characters. 299 * As of JDK 1.1, the preferred way to do this is via the 300 * {@code String} constructors that take a {@link 301 * java.nio.charset.Charset}, charset name, or that use the platform's 302 * default charset. 303 * 304 * @param ascii 305 * The bytes to be converted to characters 306 * 307 * @param hibyte 308 * The top 8 bits of each 16-bit Unicode code unit 309 * 310 * @param offset 311 * The initial offset 312 * @param count 313 * The length 314 * 315 * @throws IndexOutOfBoundsException 316 * If {@code offset} is negative, {@code count} is negative, or 317 * {@code offset} is greater than {@code ascii.length - count} 318 * 319 * @see #String(byte[], int) 320 * @see #String(byte[], int, int, java.lang.String) 321 * @see #String(byte[], int, int, java.nio.charset.Charset) 322 * @see #String(byte[], int, int) 323 * @see #String(byte[], java.lang.String) 324 * @see #String(byte[], java.nio.charset.Charset) 325 * @see #String(byte[]) 326 */ 327 @Deprecated 328 public String(byte ascii[], int hibyte, int offset, int count) { 329 checkBounds(ascii, offset, count); 330 char[] value = new char[count]; 331 332 if (hibyte == 0) { 333 for (int i = count; i-- > 0;) { 334 value[i] = (char)(ascii[i + offset] & 0xff); 335 } 336 } else { 337 hibyte <<= 8; 338 for (int i = count; i-- > 0;) { 339 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff)); 340 } 341 } 342 this.value = value; 343 } 344 345 /** 346 * Allocates a new {@code String} containing characters constructed from 347 * an array of 8-bit integer values. Each character <i>c</i>in the 348 * resulting string is constructed from the corresponding component 349 * <i>b</i> in the byte array such that: 350 * 351 * <blockquote><pre> 352 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8) 353 * | (<b><i>b</i></b> & 0xff)) 354 * </pre></blockquote> 355 * 356 * @deprecated This method does not properly convert bytes into 357 * characters. As of JDK 1.1, the preferred way to do this is via the 358 * {@code String} constructors that take a {@link 359 * java.nio.charset.Charset}, charset name, or that use the platform's 360 * default charset. 361 * 362 * @param ascii 363 * The bytes to be converted to characters 364 * 365 * @param hibyte 366 * The top 8 bits of each 16-bit Unicode code unit 367 * 368 * @see #String(byte[], int, int, java.lang.String) 369 * @see #String(byte[], int, int, java.nio.charset.Charset) 370 * @see #String(byte[], int, int) 371 * @see #String(byte[], java.lang.String) 372 * @see #String(byte[], java.nio.charset.Charset) 373 * @see #String(byte[]) 374 */ 375 @Deprecated 376 public String(byte ascii[], int hibyte) { 377 this(ascii, hibyte, 0, ascii.length); 378 } 379 380 /* Common private utility method used to bounds check the byte array 381 * and requested offset & length values used by the String(byte[],..) 382 * constructors. 383 */ 384 private static void checkBounds(byte[] bytes, int offset, int length) { 385 if (length < 0) 386 throw new StringIndexOutOfBoundsException(length); 387 if (offset < 0) 388 throw new StringIndexOutOfBoundsException(offset); 389 if (offset > bytes.length - length) 390 throw new StringIndexOutOfBoundsException(offset + length); 391 } 392 393 /** 394 * Constructs a new {@code String} by decoding the specified subarray of 395 * bytes using the specified charset. The length of the new {@code String} 396 * is a function of the charset, and hence may not be equal to the length 397 * of the subarray. 398 * 399 * <p> The behavior of this constructor when the given bytes are not valid 400 * in the given charset is unspecified. The {@link 401 * java.nio.charset.CharsetDecoder} class should be used when more control 402 * over the decoding process is required. 403 * 404 * @param bytes 405 * The bytes to be decoded into characters 406 * 407 * @param offset 408 * The index of the first byte to decode 409 * 410 * @param length 411 * The number of bytes to decode 412 413 * @param charsetName 414 * The name of a supported {@linkplain java.nio.charset.Charset 415 * charset} 416 * 417 * @throws UnsupportedEncodingException 418 * If the named charset is not supported 419 * 420 * @throws IndexOutOfBoundsException 421 * If {@code offset} is negative, {@code length} is negative, or 422 * {@code offset} is greater than {@code bytes.length - length} 423 * 424 * @since 1.1 425 */ 426 public String(byte bytes[], int offset, int length, String charsetName) 427 throws UnsupportedEncodingException { 428 if (charsetName == null) 429 throw new NullPointerException("charsetName"); 430 checkBounds(bytes, offset, length); 431 this.value = StringCoding.decode(charsetName, bytes, offset, length); 432 } 433 434 /** 435 * Constructs a new {@code String} by decoding the specified subarray of 436 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 437 * The length of the new {@code String} is a function of the charset, and 438 * hence may not be equal to the length of the subarray. 439 * 440 * <p> This method always replaces malformed-input and unmappable-character 441 * sequences with this charset's default replacement string. The {@link 442 * java.nio.charset.CharsetDecoder} class should be used when more control 443 * over the decoding process is required. 444 * 445 * @param bytes 446 * The bytes to be decoded into characters 447 * 448 * @param offset 449 * The index of the first byte to decode 450 * 451 * @param length 452 * The number of bytes to decode 453 * 454 * @param charset 455 * The {@linkplain java.nio.charset.Charset charset} to be used to 456 * decode the {@code bytes} 457 * 458 * @throws IndexOutOfBoundsException 459 * If {@code offset} is negative, {@code length} is negative, or 460 * {@code offset} is greater than {@code bytes.length - length} 461 * 462 * @since 1.6 463 */ 464 public String(byte bytes[], int offset, int length, Charset charset) { 465 if (charset == null) 466 throw new NullPointerException("charset"); 467 checkBounds(bytes, offset, length); 468 this.value = StringCoding.decode(charset, bytes, offset, length); 469 } 470 471 /** 472 * Constructs a new {@code String} by decoding the specified array of bytes 473 * using the specified {@linkplain java.nio.charset.Charset charset}. The 474 * length of the new {@code String} is a function of the charset, and hence 475 * may not be equal to the length of the byte array. 476 * 477 * <p> The behavior of this constructor when the given bytes are not valid 478 * in the given charset is unspecified. The {@link 479 * java.nio.charset.CharsetDecoder} class should be used when more control 480 * over the decoding process is required. 481 * 482 * @param bytes 483 * The bytes to be decoded into characters 484 * 485 * @param charsetName 486 * The name of a supported {@linkplain java.nio.charset.Charset 487 * charset} 488 * 489 * @throws UnsupportedEncodingException 490 * If the named charset is not supported 491 * 492 * @since 1.1 493 */ 494 public String(byte bytes[], String charsetName) 495 throws UnsupportedEncodingException { 496 this(bytes, 0, bytes.length, charsetName); 497 } 498 499 /** 500 * Constructs a new {@code String} by decoding the specified array of 501 * bytes using the specified {@linkplain java.nio.charset.Charset charset}. 502 * The length of the new {@code String} is a function of the charset, and 503 * hence may not be equal to the length of the byte array. 504 * 505 * <p> This method always replaces malformed-input and unmappable-character 506 * sequences with this charset's default replacement string. The {@link 507 * java.nio.charset.CharsetDecoder} class should be used when more control 508 * over the decoding process is required. 509 * 510 * @param bytes 511 * The bytes to be decoded into characters 512 * 513 * @param charset 514 * The {@linkplain java.nio.charset.Charset charset} to be used to 515 * decode the {@code bytes} 516 * 517 * @since 1.6 518 */ 519 public String(byte bytes[], Charset charset) { 520 this(bytes, 0, bytes.length, charset); 521 } 522 523 /** 524 * Constructs a new {@code String} by decoding the specified subarray of 525 * bytes using the platform's default charset. The length of the new 526 * {@code String} is a function of the charset, and hence may not be equal 527 * to the length of the subarray. 528 * 529 * <p> The behavior of this constructor when the given bytes are not valid 530 * in the default charset is unspecified. The {@link 531 * java.nio.charset.CharsetDecoder} class should be used when more control 532 * over the decoding process is required. 533 * 534 * @param bytes 535 * The bytes to be decoded into characters 536 * 537 * @param offset 538 * The index of the first byte to decode 539 * 540 * @param length 541 * The number of bytes to decode 542 * 543 * @throws IndexOutOfBoundsException 544 * If {@code offset} is negative, {@code length} is negative, or 545 * {@code offset} is greater than {@code bytes.length - length} 546 * 547 * @since 1.1 548 */ 549 public String(byte bytes[], int offset, int length) { 550 checkBounds(bytes, offset, length); 551 this.value = StringCoding.decode(bytes, offset, length); 552 } 553 554 /** 555 * Constructs a new {@code String} by decoding the specified array of bytes 556 * using the platform's default charset. The length of the new {@code 557 * String} is a function of the charset, and hence may not be equal to the 558 * length of the byte array. 559 * 560 * <p> The behavior of this constructor when the given bytes are not valid 561 * in the default charset is unspecified. The {@link 562 * java.nio.charset.CharsetDecoder} class should be used when more control 563 * over the decoding process is required. 564 * 565 * @param bytes 566 * The bytes to be decoded into characters 567 * 568 * @since 1.1 569 */ 570 public String(byte[] bytes) { 571 this(bytes, 0, bytes.length); 572 } 573 574 /** 575 * Allocates a new string that contains the sequence of characters 576 * currently contained in the string buffer argument. The contents of the 577 * string buffer are copied; subsequent modification of the string buffer 578 * does not affect the newly created string. 579 * 580 * @param buffer 581 * A {@code StringBuffer} 582 */ 583 public String(StringBuffer buffer) { 584 synchronized(buffer) { 585 this.value = Arrays.copyOf(buffer.getValue(), buffer.length()); 586 } 587 } 588 589 /** 590 * Allocates a new string that contains the sequence of characters 591 * currently contained in the string builder argument. The contents of the 592 * string builder are copied; subsequent modification of the string builder 593 * does not affect the newly created string. 594 * 595 * <p> This constructor is provided to ease migration to {@code 596 * StringBuilder}. Obtaining a string from a string builder via the {@code 597 * toString} method is likely to run faster and is generally preferred. 598 * 599 * @param builder 600 * A {@code StringBuilder} 601 * 602 * @since 1.5 603 */ 604 public String(StringBuilder builder) { 605 this.value = Arrays.copyOf(builder.getValue(), builder.length()); 606 } 607 608 /* 609 * Package private constructor which shares value array for speed. 610 * this constructor is always expected to be called with share==true. 611 * a separate constructor is needed because we already have a public 612 * String(char[]) constructor that makes a copy of the given char[]. 613 */ 614 String(char[] value, boolean share) { 615 // assert share : "unshared not supported"; 616 this.value = value; 617 } 618 619 /** 620 * Returns the length of this string. 621 * The length is equal to the number of <a href="Character.html#unicode">Unicode 622 * code units</a> in the string. 623 * 624 * @return the length of the sequence of characters represented by this 625 * object. 626 */ 627 public int length() { 628 return value.length; 629 } 630 631 /** 632 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}. 633 * 634 * @return {@code true} if {@link #length()} is {@code 0}, otherwise 635 * {@code false} 636 * 637 * @since 1.6 638 */ 639 public boolean isEmpty() { 640 return value.length == 0; 641 } 642 643 /** 644 * Returns the {@code char} value at the 645 * specified index. An index ranges from {@code 0} to 646 * {@code length() - 1}. The first {@code char} value of the sequence 647 * is at index {@code 0}, the next at index {@code 1}, 648 * and so on, as for array indexing. 649 * 650 * <p>If the {@code char} value specified by the index is a 651 * <a href="Character.html#unicode">surrogate</a>, the surrogate 652 * value is returned. 653 * 654 * @param index the index of the {@code char} value. 655 * @return the {@code char} value at the specified index of this string. 656 * The first {@code char} value is at index {@code 0}. 657 * @exception IndexOutOfBoundsException if the {@code index} 658 * argument is negative or not less than the length of this 659 * string. 660 */ 661 public char charAt(int index) { 662 if ((index < 0) || (index >= value.length)) { 663 throw new StringIndexOutOfBoundsException(index); 664 } 665 return value[index]; 666 } 667 668 /** 669 * Returns the character (Unicode code point) at the specified 670 * index. The index refers to {@code char} values 671 * (Unicode code units) and ranges from {@code 0} to 672 * {@link #length()}{@code - 1}. 673 * 674 * <p> If the {@code char} value specified at the given index 675 * is in the high-surrogate range, the following index is less 676 * than the length of this {@code String}, and the 677 * {@code char} value at the following index is in the 678 * low-surrogate range, then the supplementary code point 679 * corresponding to this surrogate pair is returned. Otherwise, 680 * the {@code char} value at the given index is returned. 681 * 682 * @param index the index to the {@code char} values 683 * @return the code point value of the character at the 684 * {@code index} 685 * @exception IndexOutOfBoundsException if the {@code index} 686 * argument is negative or not less than the length of this 687 * string. 688 * @since 1.5 689 */ 690 public int codePointAt(int index) { 691 if ((index < 0) || (index >= value.length)) { 692 throw new StringIndexOutOfBoundsException(index); 693 } 694 return Character.codePointAtImpl(value, index, value.length); 695 } 696 697 /** 698 * Returns the character (Unicode code point) before the specified 699 * index. The index refers to {@code char} values 700 * (Unicode code units) and ranges from {@code 1} to {@link 701 * CharSequence#length() length}. 702 * 703 * <p> If the {@code char} value at {@code (index - 1)} 704 * is in the low-surrogate range, {@code (index - 2)} is not 705 * negative, and the {@code char} value at {@code (index - 706 * 2)} is in the high-surrogate range, then the 707 * supplementary code point value of the surrogate pair is 708 * returned. If the {@code char} value at {@code index - 709 * 1} is an unpaired low-surrogate or a high-surrogate, the 710 * surrogate value is returned. 711 * 712 * @param index the index following the code point that should be returned 713 * @return the Unicode code point value before the given index. 714 * @exception IndexOutOfBoundsException if the {@code index} 715 * argument is less than 1 or greater than the length 716 * of this string. 717 * @since 1.5 718 */ 719 public int codePointBefore(int index) { 720 int i = index - 1; 721 if ((i < 0) || (i >= value.length)) { 722 throw new StringIndexOutOfBoundsException(index); 723 } 724 return Character.codePointBeforeImpl(value, index, 0); 725 } 726 727 /** 728 * Returns the number of Unicode code points in the specified text 729 * range of this {@code String}. The text range begins at the 730 * specified {@code beginIndex} and extends to the 731 * {@code char} at index {@code endIndex - 1}. Thus the 732 * length (in {@code char}s) of the text range is 733 * {@code endIndex-beginIndex}. Unpaired surrogates within 734 * the text range count as one code point each. 735 * 736 * @param beginIndex the index to the first {@code char} of 737 * the text range. 738 * @param endIndex the index after the last {@code char} of 739 * the text range. 740 * @return the number of Unicode code points in the specified text 741 * range 742 * @exception IndexOutOfBoundsException if the 743 * {@code beginIndex} is negative, or {@code endIndex} 744 * is larger than the length of this {@code String}, or 745 * {@code beginIndex} is larger than {@code endIndex}. 746 * @since 1.5 747 */ 748 public int codePointCount(int beginIndex, int endIndex) { 749 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) { 750 throw new IndexOutOfBoundsException(); 751 } 752 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex); 753 } 754 755 /** 756 * Returns the index within this {@code String} that is 757 * offset from the given {@code index} by 758 * {@code codePointOffset} code points. Unpaired surrogates 759 * within the text range given by {@code index} and 760 * {@code codePointOffset} count as one code point each. 761 * 762 * @param index the index to be offset 763 * @param codePointOffset the offset in code points 764 * @return the index within this {@code String} 765 * @exception IndexOutOfBoundsException if {@code index} 766 * is negative or larger then the length of this 767 * {@code String}, or if {@code codePointOffset} is positive 768 * and the substring starting with {@code index} has fewer 769 * than {@code codePointOffset} code points, 770 * or if {@code codePointOffset} is negative and the substring 771 * before {@code index} has fewer than the absolute value 772 * of {@code codePointOffset} code points. 773 * @since 1.5 774 */ 775 public int offsetByCodePoints(int index, int codePointOffset) { 776 if (index < 0 || index > value.length) { 777 throw new IndexOutOfBoundsException(); 778 } 779 return Character.offsetByCodePointsImpl(value, 0, value.length, 780 index, codePointOffset); 781 } 782 783 /** 784 * Copy characters from this string into dst starting at dstBegin. 785 * This method doesn't perform any range checking. 786 */ 787 void getChars(char dst[], int dstBegin) { 788 System.arraycopy(value, 0, dst, dstBegin, value.length); 789 } 790 791 /** 792 * Copies characters from this string into the destination character 793 * array. 794 * <p> 795 * The first character to be copied is at index {@code srcBegin}; 796 * the last character to be copied is at index {@code srcEnd-1} 797 * (thus the total number of characters to be copied is 798 * {@code srcEnd-srcBegin}). The characters are copied into the 799 * subarray of {@code dst} starting at index {@code dstBegin} 800 * and ending at index: 801 * <blockquote><pre> 802 * dstBegin + (srcEnd-srcBegin) - 1 803 * </pre></blockquote> 804 * 805 * @param srcBegin index of the first character in the string 806 * to copy. 807 * @param srcEnd index after the last character in the string 808 * to copy. 809 * @param dst the destination array. 810 * @param dstBegin the start offset in the destination array. 811 * @exception IndexOutOfBoundsException If any of the following 812 * is true: 813 * <ul><li>{@code srcBegin} is negative. 814 * <li>{@code srcBegin} is greater than {@code srcEnd} 815 * <li>{@code srcEnd} is greater than the length of this 816 * string 817 * <li>{@code dstBegin} is negative 818 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than 819 * {@code dst.length}</ul> 820 */ 821 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { 822 if (srcBegin < 0) { 823 throw new StringIndexOutOfBoundsException(srcBegin); 824 } 825 if (srcEnd > value.length) { 826 throw new StringIndexOutOfBoundsException(srcEnd); 827 } 828 if (srcBegin > srcEnd) { 829 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 830 } 831 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin); 832 } 833 834 /** 835 * Copies characters from this string into the destination byte array. Each 836 * byte receives the 8 low-order bits of the corresponding character. The 837 * eight high-order bits of each character are not copied and do not 838 * participate in the transfer in any way. 839 * 840 * <p> The first character to be copied is at index {@code srcBegin}; the 841 * last character to be copied is at index {@code srcEnd-1}. The total 842 * number of characters to be copied is {@code srcEnd-srcBegin}. The 843 * characters, converted to bytes, are copied into the subarray of {@code 844 * dst} starting at index {@code dstBegin} and ending at index: 845 * 846 * <blockquote><pre> 847 * dstBegin + (srcEnd-srcBegin) - 1 848 * </pre></blockquote> 849 * 850 * @deprecated This method does not properly convert characters into 851 * bytes. As of JDK 1.1, the preferred way to do this is via the 852 * {@link #getBytes()} method, which uses the platform's default charset. 853 * 854 * @param srcBegin 855 * Index of the first character in the string to copy 856 * 857 * @param srcEnd 858 * Index after the last character in the string to copy 859 * 860 * @param dst 861 * The destination array 862 * 863 * @param dstBegin 864 * The start offset in the destination array 865 * 866 * @throws IndexOutOfBoundsException 867 * If any of the following is true: 868 * <ul> 869 * <li> {@code srcBegin} is negative 870 * <li> {@code srcBegin} is greater than {@code srcEnd} 871 * <li> {@code srcEnd} is greater than the length of this String 872 * <li> {@code dstBegin} is negative 873 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code 874 * dst.length} 875 * </ul> 876 */ 877 @Deprecated 878 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) { 879 if (srcBegin < 0) { 880 throw new StringIndexOutOfBoundsException(srcBegin); 881 } 882 if (srcEnd > value.length) { 883 throw new StringIndexOutOfBoundsException(srcEnd); 884 } 885 if (srcBegin > srcEnd) { 886 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin); 887 } 888 Objects.requireNonNull(dst); 889 890 int j = dstBegin; 891 int n = srcEnd; 892 int i = srcBegin; 893 char[] val = value; /* avoid getfield opcode */ 894 895 while (i < n) { 896 dst[j++] = (byte)val[i++]; 897 } 898 } 899 900 /** 901 * Encodes this {@code String} into a sequence of bytes using the named 902 * charset, storing the result into a new byte array. 903 * 904 * <p> The behavior of this method when this string cannot be encoded in 905 * the given charset is unspecified. The {@link 906 * java.nio.charset.CharsetEncoder} class should be used when more control 907 * over the encoding process is required. 908 * 909 * @param charsetName 910 * The name of a supported {@linkplain java.nio.charset.Charset 911 * charset} 912 * 913 * @return The resultant byte array 914 * 915 * @throws UnsupportedEncodingException 916 * If the named charset is not supported 917 * 918 * @since 1.1 919 */ 920 public byte[] getBytes(String charsetName) 921 throws UnsupportedEncodingException { 922 if (charsetName == null) throw new NullPointerException(); 923 return StringCoding.encode(charsetName, value, 0, value.length); 924 } 925 926 /** 927 * Encodes this {@code String} into a sequence of bytes using the given 928 * {@linkplain java.nio.charset.Charset charset}, storing the result into a 929 * new byte array. 930 * 931 * <p> This method always replaces malformed-input and unmappable-character 932 * sequences with this charset's default replacement byte array. The 933 * {@link java.nio.charset.CharsetEncoder} class should be used when more 934 * control over the encoding process is required. 935 * 936 * @param charset 937 * The {@linkplain java.nio.charset.Charset} to be used to encode 938 * the {@code String} 939 * 940 * @return The resultant byte array 941 * 942 * @since 1.6 943 */ 944 public byte[] getBytes(Charset charset) { 945 if (charset == null) throw new NullPointerException(); 946 return StringCoding.encode(charset, value, 0, value.length); 947 } 948 949 /** 950 * Encodes this {@code String} into a sequence of bytes using the 951 * platform's default charset, storing the result into a new byte array. 952 * 953 * <p> The behavior of this method when this string cannot be encoded in 954 * the default charset is unspecified. The {@link 955 * java.nio.charset.CharsetEncoder} class should be used when more control 956 * over the encoding process is required. 957 * 958 * @return The resultant byte array 959 * 960 * @since 1.1 961 */ 962 public byte[] getBytes() { 963 return StringCoding.encode(value, 0, value.length); 964 } 965 966 /** 967 * Compares this string to the specified object. The result is {@code 968 * true} if and only if the argument is not {@code null} and is a {@code 969 * String} object that represents the same sequence of characters as this 970 * object. 971 * 972 * @param anObject 973 * The object to compare this {@code String} against 974 * 975 * @return {@code true} if the given object represents a {@code String} 976 * equivalent to this string, {@code false} otherwise 977 * 978 * @see #compareTo(String) 979 * @see #equalsIgnoreCase(String) 980 */ 981 public boolean equals(Object anObject) { 982 if (this == anObject) { 983 return true; 984 } 985 if (anObject instanceof String) { 986 char[] v1 = value; 987 char[] v2 = ((String)anObject).value; 988 int n = v1.length; 989 if (n == v2.length) { 990 int i = 0; 991 while (n-- != 0) { 992 if (v1[i] != v2[i]) 993 return false; 994 i++; 995 } 996 return true; 997 } 998 } 999 return false; 1000 } 1001 1002 /** 1003 * Compares this string to the specified {@code StringBuffer}. The result 1004 * is {@code true} if and only if this {@code String} represents the same 1005 * sequence of characters as the specified {@code StringBuffer}. This method 1006 * synchronizes on the {@code StringBuffer}. 1007 * 1008 * @param sb 1009 * The {@code StringBuffer} to compare this {@code String} against 1010 * 1011 * @return {@code true} if this {@code String} represents the same 1012 * sequence of characters as the specified {@code StringBuffer}, 1013 * {@code false} otherwise 1014 * 1015 * @since 1.4 1016 */ 1017 public boolean contentEquals(StringBuffer sb) { 1018 return contentEquals((CharSequence)sb); 1019 } 1020 1021 private boolean nonSyncContentEquals(AbstractStringBuilder sb) { 1022 char[] v1 = value; 1023 char[] v2 = sb.getValue(); 1024 int n = v1.length; 1025 if (n != sb.length()) { 1026 return false; 1027 } 1028 for (int i = 0; i < n; i++) { 1029 if (v1[i] != v2[i]) { 1030 return false; 1031 } 1032 } 1033 return true; 1034 } 1035 1036 /** 1037 * Compares this string to the specified {@code CharSequence}. The 1038 * result is {@code true} if and only if this {@code String} represents the 1039 * same sequence of char values as the specified sequence. Note that if the 1040 * {@code CharSequence} is a {@code StringBuffer} then the method 1041 * synchronizes on it. 1042 * 1043 * @param cs 1044 * The sequence to compare this {@code String} against 1045 * 1046 * @return {@code true} if this {@code String} represents the same 1047 * sequence of char values as the specified sequence, {@code 1048 * false} otherwise 1049 * 1050 * @since 1.5 1051 */ 1052 public boolean contentEquals(CharSequence cs) { 1053 // Argument is a StringBuffer, StringBuilder 1054 if (cs instanceof AbstractStringBuilder) { 1055 if (cs instanceof StringBuffer) { 1056 synchronized(cs) { 1057 return nonSyncContentEquals((AbstractStringBuilder)cs); 1058 } 1059 } else { 1060 return nonSyncContentEquals((AbstractStringBuilder)cs); 1061 } 1062 } 1063 // Argument is a String 1064 if (cs instanceof String) { 1065 return equals(cs); 1066 } 1067 // Argument is a generic CharSequence 1068 char[] v1 = value; 1069 int n = v1.length; 1070 if (n != cs.length()) { 1071 return false; 1072 } 1073 for (int i = 0; i < n; i++) { 1074 if (v1[i] != cs.charAt(i)) { 1075 return false; 1076 } 1077 } 1078 return true; 1079 } 1080 1081 /** 1082 * Compares this {@code String} to another {@code String}, ignoring case 1083 * considerations. Two strings are considered equal ignoring case if they 1084 * are of the same length and corresponding characters in the two strings 1085 * are equal ignoring case. 1086 * 1087 * <p> Two characters {@code c1} and {@code c2} are considered the same 1088 * ignoring case if at least one of the following is true: 1089 * <ul> 1090 * <li> The two characters are the same (as compared by the 1091 * {@code ==} operator) 1092 * <li> Applying the method {@link 1093 * java.lang.Character#toUpperCase(char)} to each character 1094 * produces the same result 1095 * <li> Applying the method {@link 1096 * java.lang.Character#toLowerCase(char)} to each character 1097 * produces the same result 1098 * </ul> 1099 * 1100 * @param anotherString 1101 * The {@code String} to compare this {@code String} against 1102 * 1103 * @return {@code true} if the argument is not {@code null} and it 1104 * represents an equivalent {@code String} ignoring case; {@code 1105 * false} otherwise 1106 * 1107 * @see #equals(Object) 1108 */ 1109 public boolean equalsIgnoreCase(String anotherString) { 1110 return (this == anotherString) ? true 1111 : (anotherString != null) 1112 && (anotherString.value.length == value.length) 1113 && regionMatches(true, 0, anotherString, 0, value.length); 1114 } 1115 1116 /** 1117 * Compares two strings lexicographically. 1118 * The comparison is based on the Unicode value of each character in 1119 * the strings. The character sequence represented by this 1120 * {@code String} object is compared lexicographically to the 1121 * character sequence represented by the argument string. The result is 1122 * a negative integer if this {@code String} object 1123 * lexicographically precedes the argument string. The result is a 1124 * positive integer if this {@code String} object lexicographically 1125 * follows the argument string. The result is zero if the strings 1126 * are equal; {@code compareTo} returns {@code 0} exactly when 1127 * the {@link #equals(Object)} method would return {@code true}. 1128 * <p> 1129 * This is the definition of lexicographic ordering. If two strings are 1130 * different, then either they have different characters at some index 1131 * that is a valid index for both strings, or their lengths are different, 1132 * or both. If they have different characters at one or more index 1133 * positions, let <i>k</i> be the smallest such index; then the string 1134 * whose character at position <i>k</i> has the smaller value, as 1135 * determined by using the < operator, lexicographically precedes the 1136 * other string. In this case, {@code compareTo} returns the 1137 * difference of the two character values at position {@code k} in 1138 * the two string -- that is, the value: 1139 * <blockquote><pre> 1140 * this.charAt(k)-anotherString.charAt(k) 1141 * </pre></blockquote> 1142 * If there is no index position at which they differ, then the shorter 1143 * string lexicographically precedes the longer string. In this case, 1144 * {@code compareTo} returns the difference of the lengths of the 1145 * strings -- that is, the value: 1146 * <blockquote><pre> 1147 * this.length()-anotherString.length() 1148 * </pre></blockquote> 1149 * 1150 * @param anotherString the {@code String} to be compared. 1151 * @return the value {@code 0} if the argument string is equal to 1152 * this string; a value less than {@code 0} if this string 1153 * is lexicographically less than the string argument; and a 1154 * value greater than {@code 0} if this string is 1155 * lexicographically greater than the string argument. 1156 */ 1157 public int compareTo(String anotherString) { 1158 char[] v1 = value; 1159 char[] v2 = anotherString.value; 1160 int len1 = v1.length; 1161 int len2 = v2.length; 1162 int lim = Math.min(len1, len2); 1163 1164 for (int k = 0; k < lim; k++) { 1165 char c1 = v1[k]; 1166 char c2 = v2[k]; 1167 if (c1 != c2) { 1168 return c1 - c2; 1169 } 1170 } 1171 return len1 - len2; 1172 } 1173 1174 /** 1175 * A Comparator that orders {@code String} objects as by 1176 * {@code compareToIgnoreCase}. This comparator is serializable. 1177 * <p> 1178 * Note that this Comparator does <em>not</em> take locale into account, 1179 * and will result in an unsatisfactory ordering for certain locales. 1180 * The java.text package provides <em>Collators</em> to allow 1181 * locale-sensitive ordering. 1182 * 1183 * @see java.text.Collator#compare(String, String) 1184 * @since 1.2 1185 */ 1186 public static final Comparator<String> CASE_INSENSITIVE_ORDER 1187 = new CaseInsensitiveComparator(); 1188 private static class CaseInsensitiveComparator 1189 implements Comparator<String>, java.io.Serializable { 1190 // use serialVersionUID from JDK 1.2.2 for interoperability 1191 private static final long serialVersionUID = 8575799808933029326L; 1192 1193 public int compare(String s1, String s2) { 1194 int n1 = s1.length(); 1195 int n2 = s2.length(); 1196 int min = Math.min(n1, n2); 1197 for (int i = 0; i < min; i++) { 1198 char c1 = s1.charAt(i); 1199 char c2 = s2.charAt(i); 1200 if (c1 != c2) { 1201 c1 = Character.toUpperCase(c1); 1202 c2 = Character.toUpperCase(c2); 1203 if (c1 != c2) { 1204 c1 = Character.toLowerCase(c1); 1205 c2 = Character.toLowerCase(c2); 1206 if (c1 != c2) { 1207 // No overflow because of numeric promotion 1208 return c1 - c2; 1209 } 1210 } 1211 } 1212 } 1213 return n1 - n2; 1214 } 1215 1216 /** Replaces the de-serialized object. */ 1217 private Object readResolve() { return CASE_INSENSITIVE_ORDER; } 1218 } 1219 1220 /** 1221 * Compares two strings lexicographically, ignoring case 1222 * differences. This method returns an integer whose sign is that of 1223 * calling {@code compareTo} with normalized versions of the strings 1224 * where case differences have been eliminated by calling 1225 * {@code Character.toLowerCase(Character.toUpperCase(character))} on 1226 * each character. 1227 * <p> 1228 * Note that this method does <em>not</em> take locale into account, 1229 * and will result in an unsatisfactory ordering for certain locales. 1230 * The java.text package provides <em>collators</em> to allow 1231 * locale-sensitive ordering. 1232 * 1233 * @param str the {@code String} to be compared. 1234 * @return a negative integer, zero, or a positive integer as the 1235 * specified String is greater than, equal to, or less 1236 * than this String, ignoring case considerations. 1237 * @see java.text.Collator#compare(String, String) 1238 * @since 1.2 1239 */ 1240 public int compareToIgnoreCase(String str) { 1241 return CASE_INSENSITIVE_ORDER.compare(this, str); 1242 } 1243 1244 /** 1245 * Tests if two string regions are equal. 1246 * <p> 1247 * A substring of this {@code String} object is compared to a substring 1248 * of the argument other. The result is true if these substrings 1249 * represent identical character sequences. The substring of this 1250 * {@code String} object to be compared begins at index {@code toffset} 1251 * and has length {@code len}. The substring of other to be compared 1252 * begins at index {@code ooffset} and has length {@code len}. The 1253 * result is {@code false} if and only if at least one of the following 1254 * is true: 1255 * <ul><li>{@code toffset} is negative. 1256 * <li>{@code ooffset} is negative. 1257 * <li>{@code toffset+len} is greater than the length of this 1258 * {@code String} object. 1259 * <li>{@code ooffset+len} is greater than the length of the other 1260 * argument. 1261 * <li>There is some nonnegative integer <i>k</i> less than {@code len} 1262 * such that: 1263 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + } 1264 * <i>k</i>{@code )} 1265 * </ul> 1266 * 1267 * @param toffset the starting offset of the subregion in this string. 1268 * @param other the string argument. 1269 * @param ooffset the starting offset of the subregion in the string 1270 * argument. 1271 * @param len the number of characters to compare. 1272 * @return {@code true} if the specified subregion of this string 1273 * exactly matches the specified subregion of the string argument; 1274 * {@code false} otherwise. 1275 */ 1276 public boolean regionMatches(int toffset, String other, int ooffset, 1277 int len) { 1278 char[] ta = value; 1279 int to = toffset; 1280 char[] pa = other.value; 1281 int po = ooffset; 1282 // Note: toffset, ooffset, or len might be near -1>>>1. 1283 if ((ooffset < 0) || (toffset < 0) 1284 || (toffset > (long)ta.length - len) 1285 || (ooffset > (long)pa.length - len)) { 1286 return false; 1287 } 1288 while (len-- > 0) { 1289 if (ta[to++] != pa[po++]) { 1290 return false; 1291 } 1292 } 1293 return true; 1294 } 1295 1296 /** 1297 * Tests if two string regions are equal. 1298 * <p> 1299 * A substring of this {@code String} object is compared to a substring 1300 * of the argument {@code other}. The result is {@code true} if these 1301 * substrings represent character sequences that are the same, ignoring 1302 * case if and only if {@code ignoreCase} is true. The substring of 1303 * this {@code String} object to be compared begins at index 1304 * {@code toffset} and has length {@code len}. The substring of 1305 * {@code other} to be compared begins at index {@code ooffset} and 1306 * has length {@code len}. The result is {@code false} if and only if 1307 * at least one of the following is true: 1308 * <ul><li>{@code toffset} is negative. 1309 * <li>{@code ooffset} is negative. 1310 * <li>{@code toffset+len} is greater than the length of this 1311 * {@code String} object. 1312 * <li>{@code ooffset+len} is greater than the length of the other 1313 * argument. 1314 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative 1315 * integer <i>k</i> less than {@code len} such that: 1316 * <blockquote><pre> 1317 * this.charAt(toffset+k) != other.charAt(ooffset+k) 1318 * </pre></blockquote> 1319 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative 1320 * integer <i>k</i> less than {@code len} such that: 1321 * <blockquote><pre> 1322 * Character.toLowerCase(this.charAt(toffset+k)) != 1323 Character.toLowerCase(other.charAt(ooffset+k)) 1324 * </pre></blockquote> 1325 * and: 1326 * <blockquote><pre> 1327 * Character.toUpperCase(this.charAt(toffset+k)) != 1328 * Character.toUpperCase(other.charAt(ooffset+k)) 1329 * </pre></blockquote> 1330 * </ul> 1331 * 1332 * @param ignoreCase if {@code true}, ignore case when comparing 1333 * characters. 1334 * @param toffset the starting offset of the subregion in this 1335 * string. 1336 * @param other the string argument. 1337 * @param ooffset the starting offset of the subregion in the string 1338 * argument. 1339 * @param len the number of characters to compare. 1340 * @return {@code true} if the specified subregion of this string 1341 * matches the specified subregion of the string argument; 1342 * {@code false} otherwise. Whether the matching is exact 1343 * or case insensitive depends on the {@code ignoreCase} 1344 * argument. 1345 */ 1346 public boolean regionMatches(boolean ignoreCase, int toffset, 1347 String other, int ooffset, int len) { 1348 char[] ta = value; 1349 int to = toffset; 1350 char[] pa = other.value; 1351 int po = ooffset; 1352 // Note: toffset, ooffset, or len might be near -1>>>1. 1353 if ((ooffset < 0) || (toffset < 0) 1354 || (toffset > (long)ta.length - len) 1355 || (ooffset > (long)pa.length - len)) { 1356 return false; 1357 } 1358 while (len-- > 0) { 1359 char c1 = ta[to++]; 1360 char c2 = pa[po++]; 1361 if (c1 == c2) { 1362 continue; 1363 } 1364 if (ignoreCase) { 1365 // If characters don't match but case may be ignored, 1366 // try converting both characters to uppercase. 1367 // If the results match, then the comparison scan should 1368 // continue. 1369 char u1 = Character.toUpperCase(c1); 1370 char u2 = Character.toUpperCase(c2); 1371 if (u1 == u2) { 1372 continue; 1373 } 1374 // Unfortunately, conversion to uppercase does not work properly 1375 // for the Georgian alphabet, which has strange rules about case 1376 // conversion. So we need to make one last check before 1377 // exiting. 1378 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) { 1379 continue; 1380 } 1381 } 1382 return false; 1383 } 1384 return true; 1385 } 1386 1387 /** 1388 * Tests if the substring of this string beginning at the 1389 * specified index starts with the specified prefix. 1390 * 1391 * @param prefix the prefix. 1392 * @param toffset where to begin looking in this string. 1393 * @return {@code true} if the character sequence represented by the 1394 * argument is a prefix of the substring of this object starting 1395 * at index {@code toffset}; {@code false} otherwise. 1396 * The result is {@code false} if {@code toffset} is 1397 * negative or greater than the length of this 1398 * {@code String} object; otherwise the result is the same 1399 * as the result of the expression 1400 * <pre> 1401 * this.substring(toffset).startsWith(prefix) 1402 * </pre> 1403 */ 1404 public boolean startsWith(String prefix, int toffset) { 1405 char[] ta = value; 1406 int to = toffset; 1407 char[] pa = prefix.value; 1408 int po = 0; 1409 int pc = pa.length; 1410 // Note: toffset might be near -1>>>1. 1411 if ((toffset < 0) || (toffset > ta.length - pc)) { 1412 return false; 1413 } 1414 while (--pc >= 0) { 1415 if (ta[to++] != pa[po++]) { 1416 return false; 1417 } 1418 } 1419 return true; 1420 } 1421 1422 /** 1423 * Tests if this string starts with the specified prefix. 1424 * 1425 * @param prefix the prefix. 1426 * @return {@code true} if the character sequence represented by the 1427 * argument is a prefix of the character sequence represented by 1428 * this string; {@code false} otherwise. 1429 * Note also that {@code true} will be returned if the 1430 * argument is an empty string or is equal to this 1431 * {@code String} object as determined by the 1432 * {@link #equals(Object)} method. 1433 * @since 1.0 1434 */ 1435 public boolean startsWith(String prefix) { 1436 return startsWith(prefix, 0); 1437 } 1438 1439 /** 1440 * Tests if this string ends with the specified suffix. 1441 * 1442 * @param suffix the suffix. 1443 * @return {@code true} if the character sequence represented by the 1444 * argument is a suffix of the character sequence represented by 1445 * this object; {@code false} otherwise. Note that the 1446 * result will be {@code true} if the argument is the 1447 * empty string or is equal to this {@code String} object 1448 * as determined by the {@link #equals(Object)} method. 1449 */ 1450 public boolean endsWith(String suffix) { 1451 return startsWith(suffix, value.length - suffix.value.length); 1452 } 1453 1454 /** 1455 * Returns a hash code for this string. The hash code for a 1456 * {@code String} object is computed as 1457 * <blockquote><pre> 1458 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1] 1459 * </pre></blockquote> 1460 * using {@code int} arithmetic, where {@code s[i]} is the 1461 * <i>i</i>th character of the string, {@code n} is the length of 1462 * the string, and {@code ^} indicates exponentiation. 1463 * (The hash value of the empty string is zero.) 1464 * 1465 * @return a hash code value for this object. 1466 */ 1467 public int hashCode() { 1468 int h = hash; 1469 if (h == 0) { 1470 for (char v : value) { 1471 h = 31 * h + v; 1472 } 1473 if (h != 0) { 1474 hash = h; 1475 } 1476 } 1477 return h; 1478 } 1479 1480 /** 1481 * Returns the index within this string of the first occurrence of 1482 * the specified character. If a character with value 1483 * {@code ch} occurs in the character sequence represented by 1484 * this {@code String} object, then the index (in Unicode 1485 * code units) of the first such occurrence is returned. For 1486 * values of {@code ch} in the range from 0 to 0xFFFF 1487 * (inclusive), this is the smallest value <i>k</i> such that: 1488 * <blockquote><pre> 1489 * this.charAt(<i>k</i>) == ch 1490 * </pre></blockquote> 1491 * is true. For other values of {@code ch}, it is the 1492 * smallest value <i>k</i> such that: 1493 * <blockquote><pre> 1494 * this.codePointAt(<i>k</i>) == ch 1495 * </pre></blockquote> 1496 * is true. In either case, if no such character occurs in this 1497 * string, then {@code -1} is returned. 1498 * 1499 * @param ch a character (Unicode code point). 1500 * @return the index of the first occurrence of the character in the 1501 * character sequence represented by this object, or 1502 * {@code -1} if the character does not occur. 1503 */ 1504 public int indexOf(int ch) { 1505 return indexOf(ch, 0); 1506 } 1507 1508 /** 1509 * Returns the index within this string of the first occurrence of the 1510 * specified character, starting the search at the specified index. 1511 * <p> 1512 * If a character with value {@code ch} occurs in the 1513 * character sequence represented by this {@code String} 1514 * object at an index no smaller than {@code fromIndex}, then 1515 * the index of the first such occurrence is returned. For values 1516 * of {@code ch} in the range from 0 to 0xFFFF (inclusive), 1517 * this is the smallest value <i>k</i> such that: 1518 * <blockquote><pre> 1519 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1520 * </pre></blockquote> 1521 * is true. For other values of {@code ch}, it is the 1522 * smallest value <i>k</i> such that: 1523 * <blockquote><pre> 1524 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex) 1525 * </pre></blockquote> 1526 * is true. In either case, if no such character occurs in this 1527 * string at or after position {@code fromIndex}, then 1528 * {@code -1} is returned. 1529 * 1530 * <p> 1531 * There is no restriction on the value of {@code fromIndex}. If it 1532 * is negative, it has the same effect as if it were zero: this entire 1533 * string may be searched. If it is greater than the length of this 1534 * string, it has the same effect as if it were equal to the length of 1535 * this string: {@code -1} is returned. 1536 * 1537 * <p>All indices are specified in {@code char} values 1538 * (Unicode code units). 1539 * 1540 * @param ch a character (Unicode code point). 1541 * @param fromIndex the index to start the search from. 1542 * @return the index of the first occurrence of the character in the 1543 * character sequence represented by this object that is greater 1544 * than or equal to {@code fromIndex}, or {@code -1} 1545 * if the character does not occur. 1546 */ 1547 public int indexOf(int ch, int fromIndex) { 1548 final int max = value.length; 1549 if (fromIndex < 0) { 1550 fromIndex = 0; 1551 } else if (fromIndex >= max) { 1552 // Note: fromIndex might be near -1>>>1. 1553 return -1; 1554 } 1555 1556 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1557 // handle most cases here (ch is a BMP code point or a 1558 // negative value (invalid code point)) 1559 final char[] value = this.value; 1560 for (int i = fromIndex; i < max; i++) { 1561 if (value[i] == ch) { 1562 return i; 1563 } 1564 } 1565 return -1; 1566 } else { 1567 return indexOfSupplementary(ch, fromIndex); 1568 } 1569 } 1570 1571 /** 1572 * Handles (rare) calls of indexOf with a supplementary character. 1573 */ 1574 private int indexOfSupplementary(int ch, int fromIndex) { 1575 if (Character.isValidCodePoint(ch)) { 1576 final char[] value = this.value; 1577 final char hi = Character.highSurrogate(ch); 1578 final char lo = Character.lowSurrogate(ch); 1579 final int max = value.length - 1; 1580 for (int i = fromIndex; i < max; i++) { 1581 if (value[i] == hi && value[i + 1] == lo) { 1582 return i; 1583 } 1584 } 1585 } 1586 return -1; 1587 } 1588 1589 /** 1590 * Returns the index within this string of the last occurrence of 1591 * the specified character. For values of {@code ch} in the 1592 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code 1593 * units) returned is the largest value <i>k</i> such that: 1594 * <blockquote><pre> 1595 * this.charAt(<i>k</i>) == ch 1596 * </pre></blockquote> 1597 * is true. For other values of {@code ch}, it is the 1598 * largest value <i>k</i> such that: 1599 * <blockquote><pre> 1600 * this.codePointAt(<i>k</i>) == ch 1601 * </pre></blockquote> 1602 * is true. In either case, if no such character occurs in this 1603 * string, then {@code -1} is returned. The 1604 * {@code String} is searched backwards starting at the last 1605 * character. 1606 * 1607 * @param ch a character (Unicode code point). 1608 * @return the index of the last occurrence of the character in the 1609 * character sequence represented by this object, or 1610 * {@code -1} if the character does not occur. 1611 */ 1612 public int lastIndexOf(int ch) { 1613 return lastIndexOf(ch, value.length - 1); 1614 } 1615 1616 /** 1617 * Returns the index within this string of the last occurrence of 1618 * the specified character, searching backward starting at the 1619 * specified index. For values of {@code ch} in the range 1620 * from 0 to 0xFFFF (inclusive), the index returned is the largest 1621 * value <i>k</i> such that: 1622 * <blockquote><pre> 1623 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1624 * </pre></blockquote> 1625 * is true. For other values of {@code ch}, it is the 1626 * largest value <i>k</i> such that: 1627 * <blockquote><pre> 1628 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex) 1629 * </pre></blockquote> 1630 * is true. In either case, if no such character occurs in this 1631 * string at or before position {@code fromIndex}, then 1632 * {@code -1} is returned. 1633 * 1634 * <p>All indices are specified in {@code char} values 1635 * (Unicode code units). 1636 * 1637 * @param ch a character (Unicode code point). 1638 * @param fromIndex the index to start the search from. There is no 1639 * restriction on the value of {@code fromIndex}. If it is 1640 * greater than or equal to the length of this string, it has 1641 * the same effect as if it were equal to one less than the 1642 * length of this string: this entire string may be searched. 1643 * If it is negative, it has the same effect as if it were -1: 1644 * -1 is returned. 1645 * @return the index of the last occurrence of the character in the 1646 * character sequence represented by this object that is less 1647 * than or equal to {@code fromIndex}, or {@code -1} 1648 * if the character does not occur before that point. 1649 */ 1650 public int lastIndexOf(int ch, int fromIndex) { 1651 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) { 1652 // handle most cases here (ch is a BMP code point or a 1653 // negative value (invalid code point)) 1654 final char[] value = this.value; 1655 int i = Math.min(fromIndex, value.length - 1); 1656 for (; i >= 0; i--) { 1657 if (value[i] == ch) { 1658 return i; 1659 } 1660 } 1661 return -1; 1662 } else { 1663 return lastIndexOfSupplementary(ch, fromIndex); 1664 } 1665 } 1666 1667 /** 1668 * Handles (rare) calls of lastIndexOf with a supplementary character. 1669 */ 1670 private int lastIndexOfSupplementary(int ch, int fromIndex) { 1671 if (Character.isValidCodePoint(ch)) { 1672 final char[] value = this.value; 1673 char hi = Character.highSurrogate(ch); 1674 char lo = Character.lowSurrogate(ch); 1675 int i = Math.min(fromIndex, value.length - 2); 1676 for (; i >= 0; i--) { 1677 if (value[i] == hi && value[i + 1] == lo) { 1678 return i; 1679 } 1680 } 1681 } 1682 return -1; 1683 } 1684 1685 /** 1686 * Returns the index within this string of the first occurrence of the 1687 * specified substring. 1688 * 1689 * <p>The returned index is the smallest value {@code k} for which: 1690 * <pre>{@code 1691 * this.startsWith(str, k) 1692 * }</pre> 1693 * If no such value of {@code k} exists, then {@code -1} is returned. 1694 * 1695 * @param str the substring to search for. 1696 * @return the index of the first occurrence of the specified substring, 1697 * or {@code -1} if there is no such occurrence. 1698 */ 1699 public int indexOf(String str) { 1700 return indexOf(str, 0); 1701 } 1702 1703 /** 1704 * Returns the index within this string of the first occurrence of the 1705 * specified substring, starting at the specified index. 1706 * 1707 * <p>The returned index is the smallest value {@code k} for which: 1708 * <pre>{@code 1709 * k >= Math.min(fromIndex, this.length()) && 1710 * this.startsWith(str, k) 1711 * }</pre> 1712 * If no such value of {@code k} exists, then {@code -1} is returned. 1713 * 1714 * @param str the substring to search for. 1715 * @param fromIndex the index from which to start the search. 1716 * @return the index of the first occurrence of the specified substring, 1717 * starting at the specified index, 1718 * or {@code -1} if there is no such occurrence. 1719 */ 1720 public int indexOf(String str, int fromIndex) { 1721 return indexOf(value, 0, value.length, 1722 str.value, 0, str.value.length, fromIndex); 1723 } 1724 1725 /** 1726 * Code shared by String and AbstractStringBuilder to do searches. The 1727 * source is the character array being searched, and the target 1728 * is the string being searched for. 1729 * 1730 * @param source the characters being searched. 1731 * @param sourceOffset offset of the source string. 1732 * @param sourceCount count of the source string. 1733 * @param target the characters being searched for. 1734 * @param fromIndex the index to begin searching from. 1735 */ 1736 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1737 String target, int fromIndex) { 1738 return indexOf(source, sourceOffset, sourceCount, 1739 target.value, 0, target.value.length, 1740 fromIndex); 1741 } 1742 1743 /** 1744 * Code shared by String and StringBuffer to do searches. The 1745 * source is the character array being searched, and the target 1746 * is the string being searched for. 1747 * 1748 * @param source the characters being searched. 1749 * @param sourceOffset offset of the source string. 1750 * @param sourceCount count of the source string. 1751 * @param target the characters being searched for. 1752 * @param targetOffset offset of the target string. 1753 * @param targetCount count of the target string. 1754 * @param fromIndex the index to begin searching from. 1755 */ 1756 static int indexOf(char[] source, int sourceOffset, int sourceCount, 1757 char[] target, int targetOffset, int targetCount, 1758 int fromIndex) { 1759 if (fromIndex >= sourceCount) { 1760 return (targetCount == 0 ? sourceCount : -1); 1761 } 1762 if (fromIndex < 0) { 1763 fromIndex = 0; 1764 } 1765 if (targetCount == 0) { 1766 return fromIndex; 1767 } 1768 1769 char first = target[targetOffset]; 1770 int max = sourceOffset + (sourceCount - targetCount); 1771 1772 for (int i = sourceOffset + fromIndex; i <= max; i++) { 1773 /* Look for first character. */ 1774 if (source[i] != first) { 1775 while (++i <= max && source[i] != first); 1776 } 1777 1778 /* Found first character, now look at the rest of v2 */ 1779 if (i <= max) { 1780 int j = i + 1; 1781 int end = j + targetCount - 1; 1782 for (int k = targetOffset + 1; j < end && source[j] 1783 == target[k]; j++, k++); 1784 1785 if (j == end) { 1786 /* Found whole string. */ 1787 return i - sourceOffset; 1788 } 1789 } 1790 } 1791 return -1; 1792 } 1793 1794 /** 1795 * Returns the index within this string of the last occurrence of the 1796 * specified substring. The last occurrence of the empty string "" 1797 * is considered to occur at the index value {@code this.length()}. 1798 * 1799 * <p>The returned index is the largest value {@code k} for which: 1800 * <pre>{@code 1801 * this.startsWith(str, k) 1802 * }</pre> 1803 * If no such value of {@code k} exists, then {@code -1} is returned. 1804 * 1805 * @param str the substring to search for. 1806 * @return the index of the last occurrence of the specified substring, 1807 * or {@code -1} if there is no such occurrence. 1808 */ 1809 public int lastIndexOf(String str) { 1810 return lastIndexOf(str, value.length); 1811 } 1812 1813 /** 1814 * Returns the index within this string of the last occurrence of the 1815 * specified substring, searching backward starting at the specified index. 1816 * 1817 * <p>The returned index is the largest value {@code k} for which: 1818 * <pre>{@code 1819 * k <= Math.min(fromIndex, this.length()) && 1820 * this.startsWith(str, k) 1821 * }</pre> 1822 * If no such value of {@code k} exists, then {@code -1} is returned. 1823 * 1824 * @param str the substring to search for. 1825 * @param fromIndex the index to start the search from. 1826 * @return the index of the last occurrence of the specified substring, 1827 * searching backward from the specified index, 1828 * or {@code -1} if there is no such occurrence. 1829 */ 1830 public int lastIndexOf(String str, int fromIndex) { 1831 return lastIndexOf(value, 0, value.length, 1832 str.value, 0, str.value.length, fromIndex); 1833 } 1834 1835 /** 1836 * Code shared by String and AbstractStringBuilder to do searches. The 1837 * source is the character array being searched, and the target 1838 * is the string being searched for. 1839 * 1840 * @param source the characters being searched. 1841 * @param sourceOffset offset of the source string. 1842 * @param sourceCount count of the source string. 1843 * @param target the characters being searched for. 1844 * @param fromIndex the index to begin searching from. 1845 */ 1846 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1847 String target, int fromIndex) { 1848 return lastIndexOf(source, sourceOffset, sourceCount, 1849 target.value, 0, target.value.length, 1850 fromIndex); 1851 } 1852 1853 /** 1854 * Code shared by String and StringBuffer to do searches. The 1855 * source is the character array being searched, and the target 1856 * is the string being searched for. 1857 * 1858 * @param source the characters being searched. 1859 * @param sourceOffset offset of the source string. 1860 * @param sourceCount count of the source string. 1861 * @param target the characters being searched for. 1862 * @param targetOffset offset of the target string. 1863 * @param targetCount count of the target string. 1864 * @param fromIndex the index to begin searching from. 1865 */ 1866 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount, 1867 char[] target, int targetOffset, int targetCount, 1868 int fromIndex) { 1869 /* 1870 * Check arguments; return immediately where possible. For 1871 * consistency, don't check for null str. 1872 */ 1873 int rightIndex = sourceCount - targetCount; 1874 if (fromIndex < 0) { 1875 return -1; 1876 } 1877 if (fromIndex > rightIndex) { 1878 fromIndex = rightIndex; 1879 } 1880 /* Empty string always matches. */ 1881 if (targetCount == 0) { 1882 return fromIndex; 1883 } 1884 1885 int strLastIndex = targetOffset + targetCount - 1; 1886 char strLastChar = target[strLastIndex]; 1887 int min = sourceOffset + targetCount - 1; 1888 int i = min + fromIndex; 1889 1890 startSearchForLastChar: 1891 while (true) { 1892 while (i >= min && source[i] != strLastChar) { 1893 i--; 1894 } 1895 if (i < min) { 1896 return -1; 1897 } 1898 int j = i - 1; 1899 int start = j - (targetCount - 1); 1900 int k = strLastIndex - 1; 1901 1902 while (j > start) { 1903 if (source[j--] != target[k--]) { 1904 i--; 1905 continue startSearchForLastChar; 1906 } 1907 } 1908 return start - sourceOffset + 1; 1909 } 1910 } 1911 1912 /** 1913 * Returns a string that is a substring of this string. The 1914 * substring begins with the character at the specified index and 1915 * extends to the end of this string. <p> 1916 * Examples: 1917 * <blockquote><pre> 1918 * "unhappy".substring(2) returns "happy" 1919 * "Harbison".substring(3) returns "bison" 1920 * "emptiness".substring(9) returns "" (an empty string) 1921 * </pre></blockquote> 1922 * 1923 * @param beginIndex the beginning index, inclusive. 1924 * @return the specified substring. 1925 * @exception IndexOutOfBoundsException if 1926 * {@code beginIndex} is negative or larger than the 1927 * length of this {@code String} object. 1928 */ 1929 public String substring(int beginIndex) { 1930 if (beginIndex <= 0) { 1931 if (beginIndex < 0) { 1932 throw new StringIndexOutOfBoundsException(beginIndex); 1933 } 1934 return this; 1935 } 1936 int subLen = value.length - beginIndex; 1937 if (subLen < 0) { 1938 throw new StringIndexOutOfBoundsException(subLen); 1939 } 1940 return new String(value, beginIndex, subLen); 1941 } 1942 1943 /** 1944 * Returns a string that is a substring of this string. The 1945 * substring begins at the specified {@code beginIndex} and 1946 * extends to the character at index {@code endIndex - 1}. 1947 * Thus the length of the substring is {@code endIndex-beginIndex}. 1948 * <p> 1949 * Examples: 1950 * <blockquote><pre> 1951 * "hamburger".substring(4, 8) returns "urge" 1952 * "smiles".substring(1, 5) returns "mile" 1953 * </pre></blockquote> 1954 * 1955 * @param beginIndex the beginning index, inclusive. 1956 * @param endIndex the ending index, exclusive. 1957 * @return the specified substring. 1958 * @exception IndexOutOfBoundsException if the 1959 * {@code beginIndex} is negative, or 1960 * {@code endIndex} is larger than the length of 1961 * this {@code String} object, or 1962 * {@code beginIndex} is larger than 1963 * {@code endIndex}. 1964 */ 1965 public String substring(int beginIndex, int endIndex) { 1966 if (beginIndex <= 0) { 1967 if (beginIndex < 0) { 1968 throw new StringIndexOutOfBoundsException(beginIndex); 1969 } 1970 if (endIndex == value.length) { 1971 return this; 1972 } 1973 } 1974 if (endIndex > value.length) { 1975 throw new StringIndexOutOfBoundsException(endIndex); 1976 } 1977 int subLen = endIndex - beginIndex; 1978 if (subLen < 0) { 1979 throw new StringIndexOutOfBoundsException(subLen); 1980 } 1981 return new String(value, beginIndex, subLen); 1982 } 1983 1984 /** 1985 * Returns a character sequence that is a subsequence of this sequence. 1986 * 1987 * <p> An invocation of this method of the form 1988 * 1989 * <blockquote><pre> 1990 * str.subSequence(begin, end)</pre></blockquote> 1991 * 1992 * behaves in exactly the same way as the invocation 1993 * 1994 * <blockquote><pre> 1995 * str.substring(begin, end)</pre></blockquote> 1996 * 1997 * @apiNote 1998 * This method is defined so that the {@code String} class can implement 1999 * the {@link CharSequence} interface. 2000 * 2001 * @param beginIndex the begin index, inclusive. 2002 * @param endIndex the end index, exclusive. 2003 * @return the specified subsequence. 2004 * 2005 * @throws IndexOutOfBoundsException 2006 * if {@code beginIndex} or {@code endIndex} is negative, 2007 * if {@code endIndex} is greater than {@code length()}, 2008 * or if {@code beginIndex} is greater than {@code endIndex} 2009 * 2010 * @since 1.4 2011 * @spec JSR-51 2012 */ 2013 public CharSequence subSequence(int beginIndex, int endIndex) { 2014 return this.substring(beginIndex, endIndex); 2015 } 2016 2017 /** 2018 * Concatenates the specified string to the end of this string. 2019 * <p> 2020 * If the length of the argument string is {@code 0}, then this 2021 * {@code String} object is returned. Otherwise, a 2022 * {@code String} object is returned that represents a character 2023 * sequence that is the concatenation of the character sequence 2024 * represented by this {@code String} object and the character 2025 * sequence represented by the argument string.<p> 2026 * Examples: 2027 * <blockquote><pre> 2028 * "cares".concat("s") returns "caress" 2029 * "to".concat("get").concat("her") returns "together" 2030 * </pre></blockquote> 2031 * 2032 * @param str the {@code String} that is concatenated to the end 2033 * of this {@code String}. 2034 * @return a string that represents the concatenation of this object's 2035 * characters followed by the string argument's characters. 2036 */ 2037 public String concat(String str) { 2038 int otherLen = str.length(); 2039 if (otherLen == 0) { 2040 return this; 2041 } 2042 int len = value.length; 2043 char[] buf = Arrays.copyOf(value, len + otherLen); 2044 str.getChars(buf, len); 2045 return new String(buf, true); 2046 } 2047 2048 /** 2049 * Returns a string resulting from replacing all occurrences of 2050 * {@code oldChar} in this string with {@code newChar}. 2051 * <p> 2052 * If the character {@code oldChar} does not occur in the 2053 * character sequence represented by this {@code String} object, 2054 * then a reference to this {@code String} object is returned. 2055 * Otherwise, a {@code String} object is returned that 2056 * represents a character sequence identical to the character sequence 2057 * represented by this {@code String} object, except that every 2058 * occurrence of {@code oldChar} is replaced by an occurrence 2059 * of {@code newChar}. 2060 * <p> 2061 * Examples: 2062 * <blockquote><pre> 2063 * "mesquite in your cellar".replace('e', 'o') 2064 * returns "mosquito in your collar" 2065 * "the war of baronets".replace('r', 'y') 2066 * returns "the way of bayonets" 2067 * "sparring with a purple porpoise".replace('p', 't') 2068 * returns "starring with a turtle tortoise" 2069 * "JonL".replace('q', 'x') returns "JonL" (no change) 2070 * </pre></blockquote> 2071 * 2072 * @param oldChar the old character. 2073 * @param newChar the new character. 2074 * @return a string derived from this string by replacing every 2075 * occurrence of {@code oldChar} with {@code newChar}. 2076 */ 2077 public String replace(char oldChar, char newChar) { 2078 if (oldChar != newChar) { 2079 char[] val = value; /* avoid getfield opcode */ 2080 int len = val.length; 2081 int i = -1; 2082 2083 while (++i < len) { 2084 if (val[i] == oldChar) { 2085 break; 2086 } 2087 } 2088 if (i < len) { 2089 char[] buf = new char[len]; 2090 for (int j = 0; j < i; j++) { 2091 buf[j] = val[j]; 2092 } 2093 while (i < len) { 2094 char c = val[i]; 2095 buf[i] = (c == oldChar) ? newChar : c; 2096 i++; 2097 } 2098 return new String(buf, true); 2099 } 2100 } 2101 return this; 2102 } 2103 2104 /** 2105 * Tells whether or not this string matches the given <a 2106 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2107 * 2108 * <p> An invocation of this method of the form 2109 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the 2110 * same result as the expression 2111 * 2112 * <blockquote> 2113 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence) 2114 * matches(<i>regex</i>, <i>str</i>)} 2115 * </blockquote> 2116 * 2117 * @param regex 2118 * the regular expression to which this string is to be matched 2119 * 2120 * @return {@code true} if, and only if, this string matches the 2121 * given regular expression 2122 * 2123 * @throws PatternSyntaxException 2124 * if the regular expression's syntax is invalid 2125 * 2126 * @see java.util.regex.Pattern 2127 * 2128 * @since 1.4 2129 * @spec JSR-51 2130 */ 2131 public boolean matches(String regex) { 2132 return Pattern.matches(regex, this); 2133 } 2134 2135 /** 2136 * Returns true if and only if this string contains the specified 2137 * sequence of char values. 2138 * 2139 * @param s the sequence to search for 2140 * @return true if this string contains {@code s}, false otherwise 2141 * @since 1.5 2142 */ 2143 public boolean contains(CharSequence s) { 2144 return indexOf(s.toString()) >= 0; 2145 } 2146 2147 /** 2148 * Replaces the first substring of this string that matches the given <a 2149 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2150 * given replacement. 2151 * 2152 * <p> An invocation of this method of the form 2153 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2154 * yields exactly the same result as the expression 2155 * 2156 * <blockquote> 2157 * <code> 2158 * {@link java.util.regex.Pattern}.{@link 2159 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2160 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2161 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>) 2162 * </code> 2163 * </blockquote> 2164 * 2165 *<p> 2166 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2167 * replacement string may cause the results to be different than if it were 2168 * being treated as a literal replacement string; see 2169 * {@link java.util.regex.Matcher#replaceFirst}. 2170 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2171 * meaning of these characters, if desired. 2172 * 2173 * @param regex 2174 * the regular expression to which this string is to be matched 2175 * @param replacement 2176 * the string to be substituted for the first match 2177 * 2178 * @return The resulting {@code String} 2179 * 2180 * @throws PatternSyntaxException 2181 * if the regular expression's syntax is invalid 2182 * 2183 * @see java.util.regex.Pattern 2184 * 2185 * @since 1.4 2186 * @spec JSR-51 2187 */ 2188 public String replaceFirst(String regex, String replacement) { 2189 return Pattern.compile(regex).matcher(this).replaceFirst(replacement); 2190 } 2191 2192 /** 2193 * Replaces each substring of this string that matches the given <a 2194 * href="../util/regex/Pattern.html#sum">regular expression</a> with the 2195 * given replacement. 2196 * 2197 * <p> An invocation of this method of the form 2198 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )} 2199 * yields exactly the same result as the expression 2200 * 2201 * <blockquote> 2202 * <code> 2203 * {@link java.util.regex.Pattern}.{@link 2204 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2205 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link 2206 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>) 2207 * </code> 2208 * </blockquote> 2209 * 2210 *<p> 2211 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the 2212 * replacement string may cause the results to be different than if it were 2213 * being treated as a literal replacement string; see 2214 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}. 2215 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special 2216 * meaning of these characters, if desired. 2217 * 2218 * @param regex 2219 * the regular expression to which this string is to be matched 2220 * @param replacement 2221 * the string to be substituted for each match 2222 * 2223 * @return The resulting {@code String} 2224 * 2225 * @throws PatternSyntaxException 2226 * if the regular expression's syntax is invalid 2227 * 2228 * @see java.util.regex.Pattern 2229 * 2230 * @since 1.4 2231 * @spec JSR-51 2232 */ 2233 public String replaceAll(String regex, String replacement) { 2234 return Pattern.compile(regex).matcher(this).replaceAll(replacement); 2235 } 2236 2237 /** 2238 * Replaces each substring of this string that matches the literal target 2239 * sequence with the specified literal replacement sequence. The 2240 * replacement proceeds from the beginning of the string to the end, for 2241 * example, replacing "aa" with "b" in the string "aaa" will result in 2242 * "ba" rather than "ab". 2243 * 2244 * @param target The sequence of char values to be replaced 2245 * @param replacement The replacement sequence of char values 2246 * @return The resulting string 2247 * @since 1.5 2248 */ 2249 public String replace(CharSequence target, CharSequence replacement) { 2250 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher( 2251 this).replaceAll(Matcher.quoteReplacement(replacement.toString())); 2252 } 2253 2254 /** 2255 * Splits this string around matches of the given 2256 * <a href="../util/regex/Pattern.html#sum">regular expression</a>. 2257 * 2258 * <p> The array returned by this method contains each substring of this 2259 * string that is terminated by another substring that matches the given 2260 * expression or is terminated by the end of the string. The substrings in 2261 * the array are in the order in which they occur in this string. If the 2262 * expression does not match any part of the input then the resulting array 2263 * has just one element, namely this string. 2264 * 2265 * <p> When there is a positive-width match at the beginning of this 2266 * string then an empty leading substring is included at the beginning 2267 * of the resulting array. A zero-width match at the beginning however 2268 * never produces such empty leading substring. 2269 * 2270 * <p> The {@code limit} parameter controls the number of times the 2271 * pattern is applied and therefore affects the length of the resulting 2272 * array. If the limit <i>n</i> is greater than zero then the pattern 2273 * will be applied at most <i>n</i> - 1 times, the array's 2274 * length will be no greater than <i>n</i>, and the array's last entry 2275 * will contain all input beyond the last matched delimiter. If <i>n</i> 2276 * is non-positive then the pattern will be applied as many times as 2277 * possible and the array can have any length. If <i>n</i> is zero then 2278 * the pattern will be applied as many times as possible, the array can 2279 * have any length, and trailing empty strings will be discarded. 2280 * 2281 * <p> The string {@code "boo:and:foo"}, for example, yields the 2282 * following results with these parameters: 2283 * 2284 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result"> 2285 * <tr> 2286 * <th>Regex</th> 2287 * <th>Limit</th> 2288 * <th>Result</th> 2289 * </tr> 2290 * <tr><td align=center>:</td> 2291 * <td align=center>2</td> 2292 * <td>{@code { "boo", "and:foo" }}</td></tr> 2293 * <tr><td align=center>:</td> 2294 * <td align=center>5</td> 2295 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2296 * <tr><td align=center>:</td> 2297 * <td align=center>-2</td> 2298 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2299 * <tr><td align=center>o</td> 2300 * <td align=center>5</td> 2301 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2302 * <tr><td align=center>o</td> 2303 * <td align=center>-2</td> 2304 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr> 2305 * <tr><td align=center>o</td> 2306 * <td align=center>0</td> 2307 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2308 * </table></blockquote> 2309 * 2310 * <p> An invocation of this method of the form 2311 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )} 2312 * yields the same result as the expression 2313 * 2314 * <blockquote> 2315 * <code> 2316 * {@link java.util.regex.Pattern}.{@link 2317 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link 2318 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>) 2319 * </code> 2320 * </blockquote> 2321 * 2322 * 2323 * @param regex 2324 * the delimiting regular expression 2325 * 2326 * @param limit 2327 * the result threshold, as described above 2328 * 2329 * @return the array of strings computed by splitting this string 2330 * around matches of the given regular expression 2331 * 2332 * @throws PatternSyntaxException 2333 * if the regular expression's syntax is invalid 2334 * 2335 * @see java.util.regex.Pattern 2336 * 2337 * @since 1.4 2338 * @spec JSR-51 2339 */ 2340 public String[] split(String regex, int limit) { 2341 /* fastpath if the regex is a 2342 (1)one-char String and this character is not one of the 2343 RegEx's meta characters ".$|()[{^?*+\\", or 2344 (2)two-char String and the first char is the backslash and 2345 the second is not the ascii digit or ascii letter. 2346 */ 2347 char ch = 0; 2348 if (((regex.value.length == 1 && 2349 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) || 2350 (regex.length() == 2 && 2351 regex.charAt(0) == '\\' && 2352 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 && 2353 ((ch-'a')|('z'-ch)) < 0 && 2354 ((ch-'A')|('Z'-ch)) < 0)) && 2355 (ch < Character.MIN_HIGH_SURROGATE || 2356 ch > Character.MAX_LOW_SURROGATE)) 2357 { 2358 int off = 0; 2359 int next = 0; 2360 boolean limited = limit > 0; 2361 ArrayList<String> list = new ArrayList<>(); 2362 while ((next = indexOf(ch, off)) != -1) { 2363 if (!limited || list.size() < limit - 1) { 2364 list.add(substring(off, next)); 2365 off = next + 1; 2366 } else { // last one 2367 //assert (list.size() == limit - 1); 2368 list.add(substring(off, value.length)); 2369 off = value.length; 2370 break; 2371 } 2372 } 2373 // If no match was found, return this 2374 if (off == 0) 2375 return new String[]{this}; 2376 2377 // Add remaining segment 2378 if (!limited || list.size() < limit) 2379 list.add(substring(off, value.length)); 2380 2381 // Construct result 2382 int resultSize = list.size(); 2383 if (limit == 0) { 2384 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) { 2385 resultSize--; 2386 } 2387 } 2388 String[] result = new String[resultSize]; 2389 return list.subList(0, resultSize).toArray(result); 2390 } 2391 return Pattern.compile(regex).split(this, limit); 2392 } 2393 2394 /** 2395 * Splits this string around matches of the given <a 2396 * href="../util/regex/Pattern.html#sum">regular expression</a>. 2397 * 2398 * <p> This method works as if by invoking the two-argument {@link 2399 * #split(String, int) split} method with the given expression and a limit 2400 * argument of zero. Trailing empty strings are therefore not included in 2401 * the resulting array. 2402 * 2403 * <p> The string {@code "boo:and:foo"}, for example, yields the following 2404 * results with these expressions: 2405 * 2406 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result"> 2407 * <tr> 2408 * <th>Regex</th> 2409 * <th>Result</th> 2410 * </tr> 2411 * <tr><td align=center>:</td> 2412 * <td>{@code { "boo", "and", "foo" }}</td></tr> 2413 * <tr><td align=center>o</td> 2414 * <td>{@code { "b", "", ":and:f" }}</td></tr> 2415 * </table></blockquote> 2416 * 2417 * 2418 * @param regex 2419 * the delimiting regular expression 2420 * 2421 * @return the array of strings computed by splitting this string 2422 * around matches of the given regular expression 2423 * 2424 * @throws PatternSyntaxException 2425 * if the regular expression's syntax is invalid 2426 * 2427 * @see java.util.regex.Pattern 2428 * 2429 * @since 1.4 2430 * @spec JSR-51 2431 */ 2432 public String[] split(String regex) { 2433 return split(regex, 0); 2434 } 2435 2436 /** 2437 * Returns a new String composed of copies of the 2438 * {@code CharSequence elements} joined together with a copy of 2439 * the specified {@code delimiter}. 2440 * 2441 * <blockquote>For example, 2442 * <pre>{@code 2443 * String message = String.join("-", "Java", "is", "cool"); 2444 * // message returned is: "Java-is-cool" 2445 * }</pre></blockquote> 2446 * 2447 * Note that if an element is null, then {@code "null"} is added. 2448 * 2449 * @param delimiter the delimiter that separates each element 2450 * @param elements the elements to join together. 2451 * 2452 * @return a new {@code String} that is composed of the {@code elements} 2453 * separated by the {@code delimiter} 2454 * 2455 * @throws NullPointerException If {@code delimiter} or {@code elements} 2456 * is {@code null} 2457 * 2458 * @see java.util.StringJoiner 2459 * @since 1.8 2460 */ 2461 public static String join(CharSequence delimiter, CharSequence... elements) { 2462 Objects.requireNonNull(delimiter); 2463 Objects.requireNonNull(elements); 2464 // Number of elements not likely worth Arrays.stream overhead. 2465 StringJoiner joiner = new StringJoiner(delimiter); 2466 for (CharSequence cs: elements) { 2467 joiner.add(cs); 2468 } 2469 return joiner.toString(); 2470 } 2471 2472 /** 2473 * Returns a new {@code String} composed of copies of the 2474 * {@code CharSequence elements} joined together with a copy of the 2475 * specified {@code delimiter}. 2476 * 2477 * <blockquote>For example, 2478 * <pre>{@code 2479 * List<String> strings = new LinkedList<>(); 2480 * strings.add("Java");strings.add("is"); 2481 * strings.add("cool"); 2482 * String message = String.join(" ", strings); 2483 * //message returned is: "Java is cool" 2484 * 2485 * Set<String> strings = new LinkedHashSet<>(); 2486 * strings.add("Java"); strings.add("is"); 2487 * strings.add("very"); strings.add("cool"); 2488 * String message = String.join("-", strings); 2489 * //message returned is: "Java-is-very-cool" 2490 * }</pre></blockquote> 2491 * 2492 * Note that if an individual element is {@code null}, then {@code "null"} is added. 2493 * 2494 * @param delimiter a sequence of characters that is used to separate each 2495 * of the {@code elements} in the resulting {@code String} 2496 * @param elements an {@code Iterable} that will have its {@code elements} 2497 * joined together. 2498 * 2499 * @return a new {@code String} that is composed from the {@code elements} 2500 * argument 2501 * 2502 * @throws NullPointerException If {@code delimiter} or {@code elements} 2503 * is {@code null} 2504 * 2505 * @see #join(CharSequence,CharSequence...) 2506 * @see java.util.StringJoiner 2507 * @since 1.8 2508 */ 2509 public static String join(CharSequence delimiter, 2510 Iterable<? extends CharSequence> elements) { 2511 Objects.requireNonNull(delimiter); 2512 Objects.requireNonNull(elements); 2513 StringJoiner joiner = new StringJoiner(delimiter); 2514 for (CharSequence cs: elements) { 2515 joiner.add(cs); 2516 } 2517 return joiner.toString(); 2518 } 2519 2520 /** 2521 * Converts all of the characters in this {@code String} to lower 2522 * case using the rules of the given {@code Locale}. Case mapping is based 2523 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2524 * class. Since case mappings are not always 1:1 char mappings, the resulting 2525 * {@code String} may be a different length than the original {@code String}. 2526 * <p> 2527 * Examples of lowercase mappings are in the following table: 2528 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description"> 2529 * <tr> 2530 * <th>Language Code of Locale</th> 2531 * <th>Upper Case</th> 2532 * <th>Lower Case</th> 2533 * <th>Description</th> 2534 * </tr> 2535 * <tr> 2536 * <td>tr (Turkish)</td> 2537 * <td>\u0130</td> 2538 * <td>\u0069</td> 2539 * <td>capital letter I with dot above -> small letter i</td> 2540 * </tr> 2541 * <tr> 2542 * <td>tr (Turkish)</td> 2543 * <td>\u0049</td> 2544 * <td>\u0131</td> 2545 * <td>capital letter I -> small letter dotless i </td> 2546 * </tr> 2547 * <tr> 2548 * <td>(all)</td> 2549 * <td>French Fries</td> 2550 * <td>french fries</td> 2551 * <td>lowercased all chars in String</td> 2552 * </tr> 2553 * <tr> 2554 * <td>(all)</td> 2555 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi"> 2556 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil"> 2557 * <img src="doc-files/capsigma.gif" alt="capsigma"></td> 2558 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi"> 2559 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon"> 2560 * <img src="doc-files/sigma1.gif" alt="sigma"></td> 2561 * <td>lowercased all chars in String</td> 2562 * </tr> 2563 * </table> 2564 * 2565 * @param locale use the case transformation rules for this locale 2566 * @return the {@code String}, converted to lowercase. 2567 * @see java.lang.String#toLowerCase() 2568 * @see java.lang.String#toUpperCase() 2569 * @see java.lang.String#toUpperCase(Locale) 2570 * @since 1.1 2571 */ 2572 public String toLowerCase(Locale locale) { 2573 if (locale == null) { 2574 throw new NullPointerException(); 2575 } 2576 int first; 2577 boolean hasSurr = false; 2578 final int len = value.length; 2579 2580 // Now check if there are any characters that need to be changed, or are surrogate 2581 for (first = 0 ; first < len; first++) { 2582 int cp = (int)value[first]; 2583 if (Character.isSurrogate((char)cp)) { 2584 hasSurr = true; 2585 break; 2586 } 2587 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR 2588 break; 2589 } 2590 } 2591 if (first == len) 2592 return this; 2593 char[] result = new char[len]; 2594 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2595 // lowerCase characters. 2596 String lang = locale.getLanguage(); 2597 if (lang == "tr" || lang == "az" || lang == "lt") { 2598 return toLowerCaseEx(result, first, locale, true); 2599 } 2600 if (hasSurr) { 2601 return toLowerCaseEx(result, first, locale, false); 2602 } 2603 for (int i = first; i < len; i++) { 2604 int cp = (int)value[i]; 2605 if (cp == '\u03A3' || // GREEK CAPITAL LETTER SIGMA 2606 Character.isSurrogate((char)cp)) { 2607 return toLowerCaseEx(result, i, locale, false); 2608 } 2609 if (cp == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE 2610 return toLowerCaseEx(result, i, locale, true); 2611 } 2612 cp = Character.toLowerCase(cp); 2613 if (!Character.isBmpCodePoint(cp)) { 2614 return toLowerCaseEx(result, i, locale, false); 2615 } 2616 result[i] = (char)cp; 2617 } 2618 return new String(result, true); 2619 } 2620 2621 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) { 2622 int resultOffset = first; 2623 int srcCount; 2624 for (int i = first; i < value.length; i += srcCount) { 2625 int srcChar = (int)value[i]; 2626 int lowerChar; 2627 char[] lowerCharArray; 2628 srcCount = 1; 2629 if (Character.isSurrogate((char)srcChar)) { 2630 srcChar = codePointAt(i); 2631 srcCount = Character.charCount(srcChar); 2632 } 2633 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA 2634 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale); 2635 } else { 2636 lowerChar = Character.toLowerCase(srcChar); 2637 } 2638 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp 2639 result[resultOffset++] = (char)lowerChar; 2640 } else { 2641 if (lowerChar == Character.ERROR) { 2642 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale); 2643 } else if (srcCount == 2) { 2644 resultOffset += Character.toChars(lowerChar, result, resultOffset); 2645 continue; 2646 } else { 2647 lowerCharArray = Character.toChars(lowerChar); 2648 } 2649 /* Grow result if needed */ 2650 int mapLen = lowerCharArray.length; 2651 if (mapLen > srcCount) { 2652 char[] result2 = new char[result.length + mapLen - srcCount]; 2653 System.arraycopy(result, 0, result2, 0, resultOffset); 2654 result = result2; 2655 } 2656 for (int x = 0; x < mapLen; ++x) { 2657 result[resultOffset++] = lowerCharArray[x]; 2658 } 2659 } 2660 } 2661 return new String(result, 0, resultOffset); 2662 } 2663 2664 /** 2665 * Converts all of the characters in this {@code String} to lower 2666 * case using the rules of the default locale. This is equivalent to calling 2667 * {@code toLowerCase(Locale.getDefault())}. 2668 * <p> 2669 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2670 * results if used for strings that are intended to be interpreted locale 2671 * independently. 2672 * Examples are programming language identifiers, protocol keys, and HTML 2673 * tags. 2674 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale 2675 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the 2676 * LATIN SMALL LETTER DOTLESS I character. 2677 * To obtain correct results for locale insensitive strings, use 2678 * {@code toLowerCase(Locale.ROOT)}. 2679 * 2680 * @return the {@code String}, converted to lowercase. 2681 * @see java.lang.String#toLowerCase(Locale) 2682 */ 2683 public String toLowerCase() { 2684 return toLowerCase(Locale.getDefault()); 2685 } 2686 2687 /** 2688 * Converts all of the characters in this {@code String} to upper 2689 * case using the rules of the given {@code Locale}. Case mapping is based 2690 * on the Unicode Standard version specified by the {@link java.lang.Character Character} 2691 * class. Since case mappings are not always 1:1 char mappings, the resulting 2692 * {@code String} may be a different length than the original {@code String}. 2693 * <p> 2694 * Examples of locale-sensitive and 1:M case mappings are in the following table. 2695 * 2696 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description."> 2697 * <tr> 2698 * <th>Language Code of Locale</th> 2699 * <th>Lower Case</th> 2700 * <th>Upper Case</th> 2701 * <th>Description</th> 2702 * </tr> 2703 * <tr> 2704 * <td>tr (Turkish)</td> 2705 * <td>\u0069</td> 2706 * <td>\u0130</td> 2707 * <td>small letter i -> capital letter I with dot above</td> 2708 * </tr> 2709 * <tr> 2710 * <td>tr (Turkish)</td> 2711 * <td>\u0131</td> 2712 * <td>\u0049</td> 2713 * <td>small letter dotless i -> capital letter I</td> 2714 * </tr> 2715 * <tr> 2716 * <td>(all)</td> 2717 * <td>\u00df</td> 2718 * <td>\u0053 \u0053</td> 2719 * <td>small letter sharp s -> two letters: SS</td> 2720 * </tr> 2721 * <tr> 2722 * <td>(all)</td> 2723 * <td>Fahrvergnügen</td> 2724 * <td>FAHRVERGNÜGEN</td> 2725 * <td></td> 2726 * </tr> 2727 * </table> 2728 * @param locale use the case transformation rules for this locale 2729 * @return the {@code String}, converted to uppercase. 2730 * @see java.lang.String#toUpperCase() 2731 * @see java.lang.String#toLowerCase() 2732 * @see java.lang.String#toLowerCase(Locale) 2733 * @since 1.1 2734 */ 2735 public String toUpperCase(Locale locale) { 2736 if (locale == null) { 2737 throw new NullPointerException(); 2738 } 2739 int first; 2740 boolean hasSurr = false; 2741 final int len = value.length; 2742 2743 // Now check if there are any characters that need to be changed, or are surrogate 2744 for (first = 0 ; first < len; first++ ) { 2745 int cp = (int)value[first]; 2746 if (Character.isSurrogate((char)cp)) { 2747 hasSurr = true; 2748 break; 2749 } 2750 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR 2751 break; 2752 } 2753 } 2754 if (first == len) { 2755 return this; 2756 } 2757 char[] result = new char[len]; 2758 System.arraycopy(value, 0, result, 0, first); // Just copy the first few 2759 // upperCase characters. 2760 String lang = locale.getLanguage(); 2761 if (lang == "tr" || lang == "az" || lang == "lt") { 2762 return toUpperCaseEx(result, first, locale, true); 2763 } 2764 if (hasSurr) { 2765 return toUpperCaseEx(result, first, locale, false); 2766 } 2767 for (int i = first; i < len; i++) { 2768 int cp = (int)value[i]; 2769 if (Character.isSurrogate((char)cp)) { 2770 return toUpperCaseEx(result, i, locale, false); 2771 } 2772 cp = Character.toUpperCaseEx(cp); 2773 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp 2774 return toUpperCaseEx(result, i, locale, false); 2775 } 2776 result[i] = (char)cp; 2777 } 2778 return new String(result, true); 2779 } 2780 2781 private String toUpperCaseEx(char[] result, int first, Locale locale, 2782 boolean localeDependent) { 2783 int resultOffset = first; 2784 int srcCount; 2785 for (int i = first; i < value.length; i += srcCount) { 2786 int srcChar = (int)value[i]; 2787 int upperChar; 2788 char[] upperCharArray; 2789 srcCount = 1; 2790 if (Character.isSurrogate((char)srcChar)) { 2791 srcChar = codePointAt(i); 2792 srcCount = Character.charCount(srcChar); 2793 } 2794 if (localeDependent) { 2795 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale); 2796 } else { 2797 upperChar = Character.toUpperCaseEx(srcChar); 2798 } 2799 if (Character.isBmpCodePoint(upperChar)) { 2800 result[resultOffset++] = (char)upperChar; 2801 } else { 2802 if (upperChar == Character.ERROR) { 2803 if (localeDependent) { 2804 upperCharArray = 2805 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale); 2806 } else { 2807 upperCharArray = Character.toUpperCaseCharArray(srcChar); 2808 } 2809 } else if (srcCount == 2) { 2810 resultOffset += Character.toChars(upperChar, result, resultOffset); 2811 continue; 2812 } else { 2813 upperCharArray = Character.toChars(upperChar); 2814 } 2815 /* Grow result if needed */ 2816 int mapLen = upperCharArray.length; 2817 if (mapLen > srcCount) { 2818 char[] result2 = new char[result.length + mapLen - srcCount]; 2819 System.arraycopy(result, 0, result2, 0, resultOffset); 2820 result = result2; 2821 } 2822 for (int x = 0; x < mapLen; ++x) { 2823 result[resultOffset++] = upperCharArray[x]; 2824 } 2825 } 2826 } 2827 return new String(result, 0, resultOffset); 2828 } 2829 2830 /** 2831 * Converts all of the characters in this {@code String} to upper 2832 * case using the rules of the default locale. This method is equivalent to 2833 * {@code toUpperCase(Locale.getDefault())}. 2834 * <p> 2835 * <b>Note:</b> This method is locale sensitive, and may produce unexpected 2836 * results if used for strings that are intended to be interpreted locale 2837 * independently. 2838 * Examples are programming language identifiers, protocol keys, and HTML 2839 * tags. 2840 * For instance, {@code "title".toUpperCase()} in a Turkish locale 2841 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the 2842 * LATIN CAPITAL LETTER I WITH DOT ABOVE character. 2843 * To obtain correct results for locale insensitive strings, use 2844 * {@code toUpperCase(Locale.ROOT)}. 2845 * 2846 * @return the {@code String}, converted to uppercase. 2847 * @see java.lang.String#toUpperCase(Locale) 2848 */ 2849 public String toUpperCase() { 2850 return toUpperCase(Locale.getDefault()); 2851 } 2852 2853 /** 2854 * Returns a string whose value is this string, with any leading and trailing 2855 * whitespace removed. 2856 * <p> 2857 * If this {@code String} object represents an empty character 2858 * sequence, or the first and last characters of character sequence 2859 * represented by this {@code String} object both have codes 2860 * greater than {@code '\u005Cu0020'} (the space character), then a 2861 * reference to this {@code String} object is returned. 2862 * <p> 2863 * Otherwise, if there is no character with a code greater than 2864 * {@code '\u005Cu0020'} in the string, then a 2865 * {@code String} object representing an empty string is 2866 * returned. 2867 * <p> 2868 * Otherwise, let <i>k</i> be the index of the first character in the 2869 * string whose code is greater than {@code '\u005Cu0020'}, and let 2870 * <i>m</i> be the index of the last character in the string whose code 2871 * is greater than {@code '\u005Cu0020'}. A {@code String} 2872 * object is returned, representing the substring of this string that 2873 * begins with the character at index <i>k</i> and ends with the 2874 * character at index <i>m</i>-that is, the result of 2875 * {@code this.substring(k, m + 1)}. 2876 * <p> 2877 * This method may be used to trim whitespace (as defined above) from 2878 * the beginning and end of a string. 2879 * 2880 * @return A string whose value is this string, with any leading and trailing white 2881 * space removed, or this string if it has no leading or 2882 * trailing white space. 2883 */ 2884 public String trim() { 2885 char[] val = value; /* avoid getfield opcode */ 2886 int end = val.length; 2887 int beg = 0; 2888 2889 while ((beg < end) && (val[beg] <= ' ')) { 2890 beg++; 2891 } 2892 while ((beg < end) && (val[end - 1] <= ' ')) { 2893 end--; 2894 } 2895 return substring(beg, end); 2896 } 2897 2898 /** 2899 * This object (which is already a string!) is itself returned. 2900 * 2901 * @return the string itself. 2902 */ 2903 public String toString() { 2904 return this; 2905 } 2906 2907 static class IntCharArraySpliterator implements Spliterator.OfInt { 2908 private final char[] array; 2909 private int index; // current index, modified on advance/split 2910 private final int fence; // one past last index 2911 private final int cs; 2912 2913 IntCharArraySpliterator(char[] array, int acs) { 2914 this(array, 0, array.length, acs); 2915 } 2916 2917 IntCharArraySpliterator(char[] array, int origin, int fence, int acs) { 2918 this.array = array; 2919 this.index = origin; 2920 this.fence = fence; 2921 this.cs = acs | Spliterator.ORDERED | Spliterator.SIZED 2922 | Spliterator.SUBSIZED; 2923 } 2924 2925 @Override 2926 public OfInt trySplit() { 2927 int lo = index, mid = (lo + fence) >>> 1; 2928 return (lo >= mid) 2929 ? null 2930 : new IntCharArraySpliterator(array, lo, index = mid, cs); 2931 } 2932 2933 @Override 2934 public void forEachRemaining(IntConsumer action) { 2935 char[] a; int i, hi; // hoist accesses and checks from loop 2936 if (action == null) 2937 throw new NullPointerException(); 2938 if ((a = array).length >= (hi = fence) && 2939 (i = index) >= 0 && i < (index = hi)) { 2940 do { action.accept(a[i]); } while (++i < hi); 2941 } 2942 } 2943 2944 @Override 2945 public boolean tryAdvance(IntConsumer action) { 2946 if (action == null) 2947 throw new NullPointerException(); 2948 if (index >= 0 && index < fence) { 2949 action.accept(array[index++]); 2950 return true; 2951 } 2952 return false; 2953 } 2954 2955 @Override 2956 public long estimateSize() { return (long)(fence - index); } 2957 2958 @Override 2959 public int characteristics() { 2960 return cs; 2961 } 2962 } 2963 2964 /** 2965 * Returns a stream of {@code int} zero-extending the {@code char} values 2966 * from this sequence. Any char which maps to a <a 2967 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code 2968 * point</a> is passed through uninterpreted. 2969 * 2970 * @return an IntStream of char values from this sequence 2971 * @since 1.9 2972 */ 2973 @Override 2974 public IntStream chars() { 2975 return StreamSupport.intStream( 2976 new IntCharArraySpliterator(value, Spliterator.IMMUTABLE), false); 2977 } 2978 2979 static class CodePointsSpliterator implements Spliterator.OfInt { 2980 private final char[] array; 2981 private int index; // current index, modified on advance/split 2982 private final int fence; // one past last index 2983 private final int cs; 2984 2985 CodePointsSpliterator(char[] array, int acs) { 2986 this(array, 0, array.length, acs); 2987 } 2988 2989 CodePointsSpliterator(char[] array, int origin, int fence, int acs) { 2990 this.array = array; 2991 this.index = origin; 2992 this.fence = fence; 2993 this.cs = acs | Spliterator.ORDERED; 2994 } 2995 2996 @Override 2997 public OfInt trySplit() { 2998 int lo = index, mid = (lo + fence) >>> 1; 2999 if (lo >= mid) 3000 return null; 3001 3002 int midOneLess; 3003 // If the mid-point intersects a surrogate pair 3004 if (Character.isLowSurrogate(array[mid]) && 3005 Character.isHighSurrogate(array[midOneLess = (mid -1)])) { 3006 // If there is only one pair it cannot be split 3007 if (lo >= midOneLess) 3008 return null; 3009 // Shift the mid-point to align with the surrogate pair 3010 return new CodePointsSpliterator(array, lo, index = midOneLess, cs); 3011 } 3012 return new CodePointsSpliterator(array, lo, index = mid, cs); 3013 } 3014 3015 @Override 3016 public void forEachRemaining(IntConsumer action) { 3017 char[] a; int i, hi; // hoist accesses and checks from loop 3018 if (action == null) 3019 throw new NullPointerException(); 3020 if ((a = array).length >= (hi = fence) && 3021 (i = index) >= 0 && i < (index = hi)) { 3022 do { 3023 i = advance(a, i, hi, action); 3024 } while (i < hi); 3025 } 3026 } 3027 3028 @Override 3029 public boolean tryAdvance(IntConsumer action) { 3030 if (action == null) 3031 throw new NullPointerException(); 3032 if (index >= 0 && index < fence) { 3033 index = advance(array, index, fence, action); 3034 return true; 3035 } 3036 return false; 3037 } 3038 3039 // Advance one code point from the index, i, and return the next 3040 // index to advance from 3041 private static int advance(char[] a, int i, int hi, IntConsumer action) { 3042 char c1 = a[i++]; 3043 int cp = c1; 3044 if (Character.isHighSurrogate(c1) && i < hi) { 3045 char c2 = a[i]; 3046 if (Character.isLowSurrogate(c2)) { 3047 i++; 3048 cp = Character.toCodePoint(c1, c2); 3049 } 3050 } 3051 action.accept(cp); 3052 return i; 3053 } 3054 3055 @Override 3056 public long estimateSize() { return (long)(fence - index); } 3057 3058 @Override 3059 public int characteristics() { 3060 return cs; 3061 } 3062 } 3063 3064 /** 3065 * Returns a stream of code point values from this sequence. Any surrogate 3066 * pairs encountered in the sequence are combined as if by {@linkplain 3067 * Character#toCodePoint Character.toCodePoint} and the result is passed 3068 * to the stream. Any other code units, including ordinary BMP characters, 3069 * unpaired surrogates, and undefined code units, are zero-extended to 3070 * {@code int} values which are then passed to the stream. 3071 * 3072 * @return an IntStream of Unicode code points from this sequence 3073 * @since 1.9 3074 */ 3075 @Override 3076 public IntStream codePoints() { 3077 return StreamSupport.intStream( 3078 new CodePointsSpliterator(value, Spliterator.IMMUTABLE), false); 3079 } 3080 3081 /** 3082 * Converts this string to a new character array. 3083 * 3084 * @return a newly allocated character array whose length is the length 3085 * of this string and whose contents are initialized to contain 3086 * the character sequence represented by this string. 3087 */ 3088 public char[] toCharArray() { 3089 // Cannot use Arrays.copyOf because of class initialization order issues 3090 char[] result = new char[value.length]; 3091 System.arraycopy(value, 0, result, 0, value.length); 3092 return result; 3093 } 3094 3095 /** 3096 * Returns a formatted string using the specified format string and 3097 * arguments. 3098 * 3099 * <p> The locale always used is the one returned by {@link 3100 * java.util.Locale#getDefault() Locale.getDefault()}. 3101 * 3102 * @param format 3103 * A <a href="../util/Formatter.html#syntax">format string</a> 3104 * 3105 * @param args 3106 * Arguments referenced by the format specifiers in the format 3107 * string. If there are more arguments than format specifiers, the 3108 * extra arguments are ignored. The number of arguments is 3109 * variable and may be zero. The maximum number of arguments is 3110 * limited by the maximum dimension of a Java array as defined by 3111 * <cite>The Java™ Virtual Machine Specification</cite>. 3112 * The behaviour on a 3113 * {@code null} argument depends on the <a 3114 * href="../util/Formatter.html#syntax">conversion</a>. 3115 * 3116 * @throws java.util.IllegalFormatException 3117 * If a format string contains an illegal syntax, a format 3118 * specifier that is incompatible with the given arguments, 3119 * insufficient arguments given the format string, or other 3120 * illegal conditions. For specification of all possible 3121 * formatting errors, see the <a 3122 * href="../util/Formatter.html#detail">Details</a> section of the 3123 * formatter class specification. 3124 * 3125 * @return A formatted string 3126 * 3127 * @see java.util.Formatter 3128 * @since 1.5 3129 */ 3130 public static String format(String format, Object... args) { 3131 return new Formatter().format(format, args).toString(); 3132 } 3133 3134 /** 3135 * Returns a formatted string using the specified locale, format string, 3136 * and arguments. 3137 * 3138 * @param l 3139 * The {@linkplain java.util.Locale locale} to apply during 3140 * formatting. If {@code l} is {@code null} then no localization 3141 * is applied. 3142 * 3143 * @param format 3144 * A <a href="../util/Formatter.html#syntax">format string</a> 3145 * 3146 * @param args 3147 * Arguments referenced by the format specifiers in the format 3148 * string. If there are more arguments than format specifiers, the 3149 * extra arguments are ignored. The number of arguments is 3150 * variable and may be zero. The maximum number of arguments is 3151 * limited by the maximum dimension of a Java array as defined by 3152 * <cite>The Java™ Virtual Machine Specification</cite>. 3153 * The behaviour on a 3154 * {@code null} argument depends on the 3155 * <a href="../util/Formatter.html#syntax">conversion</a>. 3156 * 3157 * @throws java.util.IllegalFormatException 3158 * If a format string contains an illegal syntax, a format 3159 * specifier that is incompatible with the given arguments, 3160 * insufficient arguments given the format string, or other 3161 * illegal conditions. For specification of all possible 3162 * formatting errors, see the <a 3163 * href="../util/Formatter.html#detail">Details</a> section of the 3164 * formatter class specification 3165 * 3166 * @return A formatted string 3167 * 3168 * @see java.util.Formatter 3169 * @since 1.5 3170 */ 3171 public static String format(Locale l, String format, Object... args) { 3172 return new Formatter(l).format(format, args).toString(); 3173 } 3174 3175 /** 3176 * Returns the string representation of the {@code Object} argument. 3177 * 3178 * @param obj an {@code Object}. 3179 * @return if the argument is {@code null}, then a string equal to 3180 * {@code "null"}; otherwise, the value of 3181 * {@code obj.toString()} is returned. 3182 * @see java.lang.Object#toString() 3183 */ 3184 public static String valueOf(Object obj) { 3185 return (obj == null) ? "null" : obj.toString(); 3186 } 3187 3188 /** 3189 * Returns the string representation of the {@code char} array 3190 * argument. The contents of the character array are copied; subsequent 3191 * modification of the character array does not affect the returned 3192 * string. 3193 * 3194 * @param data the character array. 3195 * @return a {@code String} that contains the characters of the 3196 * character array. 3197 */ 3198 public static String valueOf(char data[]) { 3199 return new String(data); 3200 } 3201 3202 /** 3203 * Returns the string representation of a specific subarray of the 3204 * {@code char} array argument. 3205 * <p> 3206 * The {@code offset} argument is the index of the first 3207 * character of the subarray. The {@code count} argument 3208 * specifies the length of the subarray. The contents of the subarray 3209 * are copied; subsequent modification of the character array does not 3210 * affect the returned string. 3211 * 3212 * @param data the character array. 3213 * @param offset initial offset of the subarray. 3214 * @param count length of the subarray. 3215 * @return a {@code String} that contains the characters of the 3216 * specified subarray of the character array. 3217 * @exception IndexOutOfBoundsException if {@code offset} is 3218 * negative, or {@code count} is negative, or 3219 * {@code offset+count} is larger than 3220 * {@code data.length}. 3221 */ 3222 public static String valueOf(char data[], int offset, int count) { 3223 return new String(data, offset, count); 3224 } 3225 3226 /** 3227 * Equivalent to {@link #valueOf(char[], int, int)}. 3228 * 3229 * @param data the character array. 3230 * @param offset initial offset of the subarray. 3231 * @param count length of the subarray. 3232 * @return a {@code String} that contains the characters of the 3233 * specified subarray of the character array. 3234 * @exception IndexOutOfBoundsException if {@code offset} is 3235 * negative, or {@code count} is negative, or 3236 * {@code offset+count} is larger than 3237 * {@code data.length}. 3238 */ 3239 public static String copyValueOf(char data[], int offset, int count) { 3240 return new String(data, offset, count); 3241 } 3242 3243 /** 3244 * Equivalent to {@link #valueOf(char[])}. 3245 * 3246 * @param data the character array. 3247 * @return a {@code String} that contains the characters of the 3248 * character array. 3249 */ 3250 public static String copyValueOf(char data[]) { 3251 return new String(data); 3252 } 3253 3254 /** 3255 * Returns the string representation of the {@code boolean} argument. 3256 * 3257 * @param b a {@code boolean}. 3258 * @return if the argument is {@code true}, a string equal to 3259 * {@code "true"} is returned; otherwise, a string equal to 3260 * {@code "false"} is returned. 3261 */ 3262 public static String valueOf(boolean b) { 3263 return b ? "true" : "false"; 3264 } 3265 3266 /** 3267 * Returns the string representation of the {@code char} 3268 * argument. 3269 * 3270 * @param c a {@code char}. 3271 * @return a string of length {@code 1} containing 3272 * as its single character the argument {@code c}. 3273 */ 3274 public static String valueOf(char c) { 3275 return new String(new char[]{c}, true); 3276 } 3277 3278 /** 3279 * Returns the string representation of the {@code int} argument. 3280 * <p> 3281 * The representation is exactly the one returned by the 3282 * {@code Integer.toString} method of one argument. 3283 * 3284 * @param i an {@code int}. 3285 * @return a string representation of the {@code int} argument. 3286 * @see java.lang.Integer#toString(int, int) 3287 */ 3288 public static String valueOf(int i) { 3289 return Integer.toString(i); 3290 } 3291 3292 /** 3293 * Returns the string representation of the {@code long} argument. 3294 * <p> 3295 * The representation is exactly the one returned by the 3296 * {@code Long.toString} method of one argument. 3297 * 3298 * @param l a {@code long}. 3299 * @return a string representation of the {@code long} argument. 3300 * @see java.lang.Long#toString(long) 3301 */ 3302 public static String valueOf(long l) { 3303 return Long.toString(l); 3304 } 3305 3306 /** 3307 * Returns the string representation of the {@code float} argument. 3308 * <p> 3309 * The representation is exactly the one returned by the 3310 * {@code Float.toString} method of one argument. 3311 * 3312 * @param f a {@code float}. 3313 * @return a string representation of the {@code float} argument. 3314 * @see java.lang.Float#toString(float) 3315 */ 3316 public static String valueOf(float f) { 3317 return Float.toString(f); 3318 } 3319 3320 /** 3321 * Returns the string representation of the {@code double} argument. 3322 * <p> 3323 * The representation is exactly the one returned by the 3324 * {@code Double.toString} method of one argument. 3325 * 3326 * @param d a {@code double}. 3327 * @return a string representation of the {@code double} argument. 3328 * @see java.lang.Double#toString(double) 3329 */ 3330 public static String valueOf(double d) { 3331 return Double.toString(d); 3332 } 3333 3334 /** 3335 * Returns a canonical representation for the string object. 3336 * <p> 3337 * A pool of strings, initially empty, is maintained privately by the 3338 * class {@code String}. 3339 * <p> 3340 * When the intern method is invoked, if the pool already contains a 3341 * string equal to this {@code String} object as determined by 3342 * the {@link #equals(Object)} method, then the string from the pool is 3343 * returned. Otherwise, this {@code String} object is added to the 3344 * pool and a reference to this {@code String} object is returned. 3345 * <p> 3346 * It follows that for any two strings {@code s} and {@code t}, 3347 * {@code s.intern() == t.intern()} is {@code true} 3348 * if and only if {@code s.equals(t)} is {@code true}. 3349 * <p> 3350 * All literal strings and string-valued constant expressions are 3351 * interned. String literals are defined in section 3.10.5 of the 3352 * <cite>The Java™ Language Specification</cite>. 3353 * 3354 * @return a string that has the same contents as this string, but is 3355 * guaranteed to be from a pool of unique strings. 3356 */ 3357 public native String intern(); 3358 }