2 * Copyright (c) 1994, 2010, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
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.
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).
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.
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
28 import java.io.ObjectStreamClass;
29 import java.io.ObjectStreamField;
30 import java.io.UnsupportedEncodingException;
31 import java.nio.charset.Charset;
32 import java.util.ArrayList;
33 import java.util.Arrays;
34 import java.util.Comparator;
35 import java.util.Formatter;
36 import java.util.Locale;
37 import java.util.regex.Matcher;
38 import java.util.regex.Pattern;
39 import java.util.regex.PatternSyntaxException;
42 * The <code>String</code> class represents character strings. All
43 * string literals in Java programs, such as <code>"abc"</code>, are
44 * implemented as instances of this class.
46 * Strings are constant; their values cannot be changed after they
47 * are created. String buffers support mutable strings.
48 * Because String objects are immutable they can be shared. For example:
49 * <p><blockquote><pre>
51 * </pre></blockquote><p>
53 * <p><blockquote><pre>
54 * char data[] = {'a', 'b', 'c'};
55 * String str = new String(data);
56 * </pre></blockquote><p>
57 * Here are some more examples of how strings can be used:
58 * <p><blockquote><pre>
59 * System.out.println("abc");
61 * System.out.println("abc" + cde);
62 * String c = "abc".substring(2,3);
63 * String d = cde.substring(1, 2);
66 * The class <code>String</code> includes methods for examining
67 * individual characters of the sequence, for comparing strings, for
68 * searching strings, for extracting substrings, and for creating a
69 * copy of a string with all characters translated to uppercase or to
70 * lowercase. Case mapping is based on the Unicode Standard version
71 * specified by the {@link java.lang.Character Character} class.
73 * The Java language provides special support for the string
74 * concatenation operator ( + ), and for conversion of
75 * other objects to strings. String concatenation is implemented
76 * through the <code>StringBuilder</code>(or <code>StringBuffer</code>)
77 * class and its <code>append</code> method.
78 * String conversions are implemented through the method
79 * <code>toString</code>, defined by <code>Object</code> and
80 * inherited by all classes in Java. For additional information on
81 * string concatenation and conversion, see Gosling, Joy, and Steele,
82 * <i>The Java Language Specification</i>.
84 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
85 * or method in this class will cause a {@link NullPointerException} to be
88 * <p>A <code>String</code> represents a string in the UTF-16 format
89 * in which <em>supplementary characters</em> are represented by <em>surrogate
90 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
91 * Character Representations</a> in the <code>Character</code> class for
93 * Index values refer to <code>char</code> code units, so a supplementary
94 * character uses two positions in a <code>String</code>.
95 * <p>The <code>String</code> class provides methods for dealing with
96 * Unicode code points (i.e., characters), in addition to those for
97 * dealing with Unicode code units (i.e., <code>char</code> values).
100 * @author Arthur van Hoff
101 * @author Martin Buchholz
103 * @see java.lang.Object#toString()
104 * @see java.lang.StringBuffer
105 * @see java.lang.StringBuilder
106 * @see java.nio.charset.Charset
110 public final class String
111 implements java.io.Serializable, Comparable<String>, CharSequence
113 /** The value is used for character storage. */
114 private final char value[];
116 /** The offset is the first index of the storage that is used. */
117 private final int offset;
119 /** The count is the number of characters in the String. */
120 private final int count;
122 /** Cache the hash code for the string */
123 private int hash; // Default to 0
125 /** use serialVersionUID from JDK 1.0.2 for interoperability */
126 private static final long serialVersionUID = -6849794470754667710L;
129 * Class String is special cased within the Serialization Stream Protocol.
131 * A String instance is written initially into an ObjectOutputStream in the
134 * <code>TC_STRING</code> (utf String)
136 * The String is written by method <code>DataOutput.writeUTF</code>.
137 * A new handle is generated to refer to all future references to the
138 * string instance within the stream.
140 private static final ObjectStreamField[] serialPersistentFields =
141 new ObjectStreamField[0];
144 * Initializes a newly created {@code String} object so that it represents
145 * an empty character sequence. Note that use of this constructor is
146 * unnecessary since Strings are immutable.
151 this.value = new char[0];
155 * Initializes a newly created {@code String} object so that it represents
156 * the same sequence of characters as the argument; in other words, the
157 * newly created string is a copy of the argument string. Unless an
158 * explicit copy of {@code original} is needed, use of this constructor is
159 * unnecessary since Strings are immutable.
164 public String(String original) {
165 int size = original.count;
166 char[] originalValue = original.value;
168 if (originalValue.length > size) {
169 // The array representing the String is bigger than the new
170 // String itself. Perhaps this constructor is being called
171 // in order to trim the baggage, so make a copy of the array.
172 int off = original.offset;
173 v = Arrays.copyOfRange(originalValue, off, off+size);
175 // The array representing the String is the same
176 // size as the String, so no point in making a copy.
185 * Allocates a new {@code String} so that it represents the sequence of
186 * characters currently contained in the character array argument. The
187 * contents of the character array are copied; subsequent modification of
188 * the character array does not affect the newly created string.
191 * The initial value of the string
193 public String(char value[]) {
194 int size = value.length;
197 this.value = Arrays.copyOf(value, size);
201 * Allocates a new {@code String} that contains characters from a subarray
202 * of the character array argument. The {@code offset} argument is the
203 * index of the first character of the subarray and the {@code count}
204 * argument specifies the length of the subarray. The contents of the
205 * subarray are copied; subsequent modification of the character array does
206 * not affect the newly created string.
209 * Array that is the source of characters
217 * @throws IndexOutOfBoundsException
218 * If the {@code offset} and {@code count} arguments index
219 * characters outside the bounds of the {@code value} array
221 public String(char value[], int offset, int count) {
223 throw new StringIndexOutOfBoundsException(offset);
226 throw new StringIndexOutOfBoundsException(count);
228 // Note: offset or count might be near -1>>>1.
229 if (offset > value.length - count) {
230 throw new StringIndexOutOfBoundsException(offset + count);
234 this.value = Arrays.copyOfRange(value, offset, offset+count);
238 * Allocates a new {@code String} that contains characters from a subarray
239 * of the <a href="Character.html#unicode">Unicode code point</a> array
240 * argument. The {@code offset} argument is the index of the first code
241 * point of the subarray and the {@code count} argument specifies the
242 * length of the subarray. The contents of the subarray are converted to
243 * {@code char}s; subsequent modification of the {@code int} array does not
244 * affect the newly created string.
247 * Array that is the source of Unicode code points
255 * @throws IllegalArgumentException
256 * If any invalid Unicode code point is found in {@code
259 * @throws IndexOutOfBoundsException
260 * If the {@code offset} and {@code count} arguments index
261 * characters outside the bounds of the {@code codePoints} array
265 public String(int[] codePoints, int offset, int count) {
267 throw new StringIndexOutOfBoundsException(offset);
270 throw new StringIndexOutOfBoundsException(count);
272 // Note: offset or count might be near -1>>>1.
273 if (offset > codePoints.length - count) {
274 throw new StringIndexOutOfBoundsException(offset + count);
277 final int end = offset + count;
279 // Pass 1: Compute precise size of char[]
281 for (int i = offset; i < end; i++) {
282 int c = codePoints[i];
283 if (Character.isBmpCodePoint(c))
285 else if (Character.isValidCodePoint(c))
287 else throw new IllegalArgumentException(Integer.toString(c));
290 // Pass 2: Allocate and fill in char[]
291 final char[] v = new char[n];
293 for (int i = offset, j = 0; i < end; i++, j++) {
294 int c = codePoints[i];
295 if (Character.isBmpCodePoint(c))
298 Character.toSurrogates(c, v, j++);
307 * Allocates a new {@code String} constructed from a subarray of an array
308 * of 8-bit integer values.
310 * <p> The {@code offset} argument is the index of the first byte of the
311 * subarray, and the {@code count} argument specifies the length of the
314 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
315 * specified in the method above.
317 * @deprecated This method does not properly convert bytes into characters.
318 * As of JDK 1.1, the preferred way to do this is via the
319 * {@code String} constructors that take a {@link
320 * java.nio.charset.Charset}, charset name, or that use the platform's
324 * The bytes to be converted to characters
327 * The top 8 bits of each 16-bit Unicode code unit
334 * @throws IndexOutOfBoundsException
335 * If the {@code offset} or {@code count} argument is invalid
337 * @see #String(byte[], int)
338 * @see #String(byte[], int, int, java.lang.String)
339 * @see #String(byte[], int, int, java.nio.charset.Charset)
340 * @see #String(byte[], int, int)
341 * @see #String(byte[], java.lang.String)
342 * @see #String(byte[], java.nio.charset.Charset)
343 * @see #String(byte[])
346 public String(byte ascii[], int hibyte, int offset, int count) {
347 checkBounds(ascii, offset, count);
348 char value[] = new char[count];
351 for (int i = count ; i-- > 0 ;) {
352 value[i] = (char) (ascii[i + offset] & 0xff);
356 for (int i = count ; i-- > 0 ;) {
357 value[i] = (char) (hibyte | (ascii[i + offset] & 0xff));
366 * Allocates a new {@code String} containing characters constructed from
367 * an array of 8-bit integer values. Each character <i>c</i>in the
368 * resulting string is constructed from the corresponding component
369 * <i>b</i> in the byte array such that:
372 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
373 * | (<b><i>b</i></b> & 0xff))
374 * </pre></blockquote>
376 * @deprecated This method does not properly convert bytes into
377 * characters. As of JDK 1.1, the preferred way to do this is via the
378 * {@code String} constructors that take a {@link
379 * java.nio.charset.Charset}, charset name, or that use the platform's
383 * The bytes to be converted to characters
386 * The top 8 bits of each 16-bit Unicode code unit
388 * @see #String(byte[], int, int, java.lang.String)
389 * @see #String(byte[], int, int, java.nio.charset.Charset)
390 * @see #String(byte[], int, int)
391 * @see #String(byte[], java.lang.String)
392 * @see #String(byte[], java.nio.charset.Charset)
393 * @see #String(byte[])
396 public String(byte ascii[], int hibyte) {
397 this(ascii, hibyte, 0, ascii.length);
400 /* Common private utility method used to bounds check the byte array
401 * and requested offset & length values used by the String(byte[],..)
404 private static void checkBounds(byte[] bytes, int offset, int length) {
406 throw new StringIndexOutOfBoundsException(length);
408 throw new StringIndexOutOfBoundsException(offset);
409 if (offset > bytes.length - length)
410 throw new StringIndexOutOfBoundsException(offset + length);
414 * Constructs a new {@code String} by decoding the specified subarray of
415 * bytes using the specified charset. The length of the new {@code String}
416 * is a function of the charset, and hence may not be equal to the length
419 * <p> The behavior of this constructor when the given bytes are not valid
420 * in the given charset is unspecified. The {@link
421 * java.nio.charset.CharsetDecoder} class should be used when more control
422 * over the decoding process is required.
425 * The bytes to be decoded into characters
428 * The index of the first byte to decode
431 * The number of bytes to decode
434 * The name of a supported {@linkplain java.nio.charset.Charset
437 * @throws UnsupportedEncodingException
438 * If the named charset is not supported
440 * @throws IndexOutOfBoundsException
441 * If the {@code offset} and {@code length} arguments index
442 * characters outside the bounds of the {@code bytes} array
446 public String(byte bytes[], int offset, int length, String charsetName)
447 throws UnsupportedEncodingException
449 if (charsetName == null)
450 throw new NullPointerException("charsetName");
451 checkBounds(bytes, offset, length);
452 char[] v = StringCoding.decode(charsetName, bytes, offset, length);
454 this.count = v.length;
459 * Constructs a new {@code String} by decoding the specified subarray of
460 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
461 * The length of the new {@code String} is a function of the charset, and
462 * hence may not be equal to the length of the subarray.
464 * <p> This method always replaces malformed-input and unmappable-character
465 * sequences with this charset's default replacement string. The {@link
466 * java.nio.charset.CharsetDecoder} class should be used when more control
467 * over the decoding process is required.
470 * The bytes to be decoded into characters
473 * The index of the first byte to decode
476 * The number of bytes to decode
479 * The {@linkplain java.nio.charset.Charset charset} to be used to
480 * decode the {@code bytes}
482 * @throws IndexOutOfBoundsException
483 * If the {@code offset} and {@code length} arguments index
484 * characters outside the bounds of the {@code bytes} array
488 public String(byte bytes[], int offset, int length, Charset charset) {
490 throw new NullPointerException("charset");
491 checkBounds(bytes, offset, length);
492 char[] v = StringCoding.decode(charset, bytes, offset, length);
494 this.count = v.length;
499 * Constructs a new {@code String} by decoding the specified array of bytes
500 * using the specified {@linkplain java.nio.charset.Charset charset}. The
501 * length of the new {@code String} is a function of the charset, and hence
502 * may not be equal to the length of the byte array.
504 * <p> The behavior of this constructor when the given bytes are not valid
505 * in the given charset is unspecified. The {@link
506 * java.nio.charset.CharsetDecoder} class should be used when more control
507 * over the decoding process is required.
510 * The bytes to be decoded into characters
513 * The name of a supported {@linkplain java.nio.charset.Charset
516 * @throws UnsupportedEncodingException
517 * If the named charset is not supported
521 public String(byte bytes[], String charsetName)
522 throws UnsupportedEncodingException
524 this(bytes, 0, bytes.length, charsetName);
528 * Constructs a new {@code String} by decoding the specified array of
529 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
530 * The length of the new {@code String} is a function of the charset, and
531 * hence may not be equal to the length of the byte array.
533 * <p> This method always replaces malformed-input and unmappable-character
534 * sequences with this charset's default replacement string. The {@link
535 * java.nio.charset.CharsetDecoder} class should be used when more control
536 * over the decoding process is required.
539 * The bytes to be decoded into characters
542 * The {@linkplain java.nio.charset.Charset charset} to be used to
543 * decode the {@code bytes}
547 public String(byte bytes[], Charset charset) {
548 this(bytes, 0, bytes.length, charset);
552 * Constructs a new {@code String} by decoding the specified subarray of
553 * bytes using the platform's default charset. The length of the new
554 * {@code String} is a function of the charset, and hence may not be equal
555 * to the length of the subarray.
557 * <p> The behavior of this constructor when the given bytes are not valid
558 * in the default charset is unspecified. The {@link
559 * java.nio.charset.CharsetDecoder} class should be used when more control
560 * over the decoding process is required.
563 * The bytes to be decoded into characters
566 * The index of the first byte to decode
569 * The number of bytes to decode
571 * @throws IndexOutOfBoundsException
572 * If the {@code offset} and the {@code length} arguments index
573 * characters outside the bounds of the {@code bytes} array
577 public String(byte bytes[], int offset, int length) {
578 checkBounds(bytes, offset, length);
579 char[] v = StringCoding.decode(bytes, offset, length);
581 this.count = v.length;
586 * Constructs a new {@code String} by decoding the specified array of bytes
587 * using the platform's default charset. The length of the new {@code
588 * String} is a function of the charset, and hence may not be equal to the
589 * length of the byte array.
591 * <p> The behavior of this constructor when the given bytes are not valid
592 * in the default charset is unspecified. The {@link
593 * java.nio.charset.CharsetDecoder} class should be used when more control
594 * over the decoding process is required.
597 * The bytes to be decoded into characters
601 public String(byte bytes[]) {
602 this(bytes, 0, bytes.length);
606 * Allocates a new string that contains the sequence of characters
607 * currently contained in the string buffer argument. The contents of the
608 * string buffer are copied; subsequent modification of the string buffer
609 * does not affect the newly created string.
612 * A {@code StringBuffer}
614 public String(StringBuffer buffer) {
615 String result = buffer.toString();
616 this.value = result.value;
617 this.count = result.count;
618 this.offset = result.offset;
622 * Allocates a new string that contains the sequence of characters
623 * currently contained in the string builder argument. The contents of the
624 * string builder are copied; subsequent modification of the string builder
625 * does not affect the newly created string.
627 * <p> This constructor is provided to ease migration to {@code
628 * StringBuilder}. Obtaining a string from a string builder via the {@code
629 * toString} method is likely to run faster and is generally preferred.
632 * A {@code StringBuilder}
636 public String(StringBuilder builder) {
637 String result = builder.toString();
638 this.value = result.value;
639 this.count = result.count;
640 this.offset = result.offset;
644 // Package private constructor which shares value array for speed.
645 String(int offset, int count, char value[]) {
647 this.offset = offset;
652 * Returns the length of this string.
653 * The length is equal to the number of <a href="Character.html#unicode">Unicode
654 * code units</a> in the string.
656 * @return the length of the sequence of characters represented by this
659 public int length() {
664 * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>.
666 * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise
671 public boolean isEmpty() {
676 * Returns the <code>char</code> value at the
677 * specified index. An index ranges from <code>0</code> to
678 * <code>length() - 1</code>. The first <code>char</code> value of the sequence
679 * is at index <code>0</code>, the next at index <code>1</code>,
680 * and so on, as for array indexing.
682 * <p>If the <code>char</code> value specified by the index is a
683 * <a href="Character.html#unicode">surrogate</a>, the surrogate
686 * @param index the index of the <code>char</code> value.
687 * @return the <code>char</code> value at the specified index of this string.
688 * The first <code>char</code> value is at index <code>0</code>.
689 * @exception IndexOutOfBoundsException if the <code>index</code>
690 * argument is negative or not less than the length of this
693 public char charAt(int index) {
694 if ((index < 0) || (index >= count)) {
695 throw new StringIndexOutOfBoundsException(index);
697 return value[index + offset];
701 * Returns the character (Unicode code point) at the specified
702 * index. The index refers to <code>char</code> values
703 * (Unicode code units) and ranges from <code>0</code> to
704 * {@link #length()}<code> - 1</code>.
706 * <p> If the <code>char</code> value specified at the given index
707 * is in the high-surrogate range, the following index is less
708 * than the length of this <code>String</code>, and the
709 * <code>char</code> value at the following index is in the
710 * low-surrogate range, then the supplementary code point
711 * corresponding to this surrogate pair is returned. Otherwise,
712 * the <code>char</code> value at the given index is returned.
714 * @param index the index to the <code>char</code> values
715 * @return the code point value of the character at the
717 * @exception IndexOutOfBoundsException if the <code>index</code>
718 * argument is negative or not less than the length of this
722 public int codePointAt(int index) {
723 if ((index < 0) || (index >= count)) {
724 throw new StringIndexOutOfBoundsException(index);
726 return Character.codePointAtImpl(value, offset + index, offset + count);
730 * Returns the character (Unicode code point) before the specified
731 * index. The index refers to <code>char</code> values
732 * (Unicode code units) and ranges from <code>1</code> to {@link
733 * CharSequence#length() length}.
735 * <p> If the <code>char</code> value at <code>(index - 1)</code>
736 * is in the low-surrogate range, <code>(index - 2)</code> is not
737 * negative, and the <code>char</code> value at <code>(index -
738 * 2)</code> is in the high-surrogate range, then the
739 * supplementary code point value of the surrogate pair is
740 * returned. If the <code>char</code> value at <code>index -
741 * 1</code> is an unpaired low-surrogate or a high-surrogate, the
742 * surrogate value is returned.
744 * @param index the index following the code point that should be returned
745 * @return the Unicode code point value before the given index.
746 * @exception IndexOutOfBoundsException if the <code>index</code>
747 * argument is less than 1 or greater than the length
751 public int codePointBefore(int index) {
753 if ((i < 0) || (i >= count)) {
754 throw new StringIndexOutOfBoundsException(index);
756 return Character.codePointBeforeImpl(value, offset + index, offset);
760 * Returns the number of Unicode code points in the specified text
761 * range of this <code>String</code>. The text range begins at the
762 * specified <code>beginIndex</code> and extends to the
763 * <code>char</code> at index <code>endIndex - 1</code>. Thus the
764 * length (in <code>char</code>s) of the text range is
765 * <code>endIndex-beginIndex</code>. Unpaired surrogates within
766 * the text range count as one code point each.
768 * @param beginIndex the index to the first <code>char</code> of
770 * @param endIndex the index after the last <code>char</code> of
772 * @return the number of Unicode code points in the specified text
774 * @exception IndexOutOfBoundsException if the
775 * <code>beginIndex</code> is negative, or <code>endIndex</code>
776 * is larger than the length of this <code>String</code>, or
777 * <code>beginIndex</code> is larger than <code>endIndex</code>.
780 public int codePointCount(int beginIndex, int endIndex) {
781 if (beginIndex < 0 || endIndex > count || beginIndex > endIndex) {
782 throw new IndexOutOfBoundsException();
784 return Character.codePointCountImpl(value, offset+beginIndex, endIndex-beginIndex);
788 * Returns the index within this <code>String</code> that is
789 * offset from the given <code>index</code> by
790 * <code>codePointOffset</code> code points. Unpaired surrogates
791 * within the text range given by <code>index</code> and
792 * <code>codePointOffset</code> count as one code point each.
794 * @param index the index to be offset
795 * @param codePointOffset the offset in code points
796 * @return the index within this <code>String</code>
797 * @exception IndexOutOfBoundsException if <code>index</code>
798 * is negative or larger then the length of this
799 * <code>String</code>, or if <code>codePointOffset</code> is positive
800 * and the substring starting with <code>index</code> has fewer
801 * than <code>codePointOffset</code> code points,
802 * or if <code>codePointOffset</code> is negative and the substring
803 * before <code>index</code> has fewer than the absolute value
804 * of <code>codePointOffset</code> code points.
807 public int offsetByCodePoints(int index, int codePointOffset) {
808 if (index < 0 || index > count) {
809 throw new IndexOutOfBoundsException();
811 return Character.offsetByCodePointsImpl(value, offset, count,
812 offset+index, codePointOffset) - offset;
816 * Copy characters from this string into dst starting at dstBegin.
817 * This method doesn't perform any range checking.
819 void getChars(char dst[], int dstBegin) {
820 System.arraycopy(value, offset, dst, dstBegin, count);
824 * Copies characters from this string into the destination character
827 * The first character to be copied is at index <code>srcBegin</code>;
828 * the last character to be copied is at index <code>srcEnd-1</code>
829 * (thus the total number of characters to be copied is
830 * <code>srcEnd-srcBegin</code>). The characters are copied into the
831 * subarray of <code>dst</code> starting at index <code>dstBegin</code>
832 * and ending at index:
833 * <p><blockquote><pre>
834 * dstbegin + (srcEnd-srcBegin) - 1
835 * </pre></blockquote>
837 * @param srcBegin index of the first character in the string
839 * @param srcEnd index after the last character in the string
841 * @param dst the destination array.
842 * @param dstBegin the start offset in the destination array.
843 * @exception IndexOutOfBoundsException If any of the following
845 * <ul><li><code>srcBegin</code> is negative.
846 * <li><code>srcBegin</code> is greater than <code>srcEnd</code>
847 * <li><code>srcEnd</code> is greater than the length of this
849 * <li><code>dstBegin</code> is negative
850 * <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
851 * <code>dst.length</code></ul>
853 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
855 throw new StringIndexOutOfBoundsException(srcBegin);
857 if (srcEnd > count) {
858 throw new StringIndexOutOfBoundsException(srcEnd);
860 if (srcBegin > srcEnd) {
861 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
863 System.arraycopy(value, offset + srcBegin, dst, dstBegin,
868 * Copies characters from this string into the destination byte array. Each
869 * byte receives the 8 low-order bits of the corresponding character. The
870 * eight high-order bits of each character are not copied and do not
871 * participate in the transfer in any way.
873 * <p> The first character to be copied is at index {@code srcBegin}; the
874 * last character to be copied is at index {@code srcEnd-1}. The total
875 * number of characters to be copied is {@code srcEnd-srcBegin}. The
876 * characters, converted to bytes, are copied into the subarray of {@code
877 * dst} starting at index {@code dstBegin} and ending at index:
880 * dstbegin + (srcEnd-srcBegin) - 1
881 * </pre></blockquote>
883 * @deprecated This method does not properly convert characters into
884 * bytes. As of JDK 1.1, the preferred way to do this is via the
885 * {@link #getBytes()} method, which uses the platform's default charset.
888 * Index of the first character in the string to copy
891 * Index after the last character in the string to copy
894 * The destination array
897 * The start offset in the destination array
899 * @throws IndexOutOfBoundsException
900 * If any of the following is true:
902 * <li> {@code srcBegin} is negative
903 * <li> {@code srcBegin} is greater than {@code srcEnd}
904 * <li> {@code srcEnd} is greater than the length of this String
905 * <li> {@code dstBegin} is negative
906 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
911 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
913 throw new StringIndexOutOfBoundsException(srcBegin);
915 if (srcEnd > count) {
916 throw new StringIndexOutOfBoundsException(srcEnd);
918 if (srcBegin > srcEnd) {
919 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
922 int n = offset + srcEnd;
923 int i = offset + srcBegin;
924 char[] val = value; /* avoid getfield opcode */
927 dst[j++] = (byte)val[i++];
932 * Encodes this {@code String} into a sequence of bytes using the named
933 * charset, storing the result into a new byte array.
935 * <p> The behavior of this method when this string cannot be encoded in
936 * the given charset is unspecified. The {@link
937 * java.nio.charset.CharsetEncoder} class should be used when more control
938 * over the encoding process is required.
941 * The name of a supported {@linkplain java.nio.charset.Charset
944 * @return The resultant byte array
946 * @throws UnsupportedEncodingException
947 * If the named charset is not supported
951 public byte[] getBytes(String charsetName)
952 throws UnsupportedEncodingException
954 if (charsetName == null) throw new NullPointerException();
955 return StringCoding.encode(charsetName, value, offset, count);
959 * Encodes this {@code String} into a sequence of bytes using the given
960 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
963 * <p> This method always replaces malformed-input and unmappable-character
964 * sequences with this charset's default replacement byte array. The
965 * {@link java.nio.charset.CharsetEncoder} class should be used when more
966 * control over the encoding process is required.
969 * The {@linkplain java.nio.charset.Charset} to be used to encode
972 * @return The resultant byte array
976 public byte[] getBytes(Charset charset) {
977 if (charset == null) throw new NullPointerException();
978 return StringCoding.encode(charset, value, offset, count);
982 * Encodes this {@code String} into a sequence of bytes using the
983 * platform's default charset, storing the result into a new byte array.
985 * <p> The behavior of this method when this string cannot be encoded in
986 * the default charset is unspecified. The {@link
987 * java.nio.charset.CharsetEncoder} class should be used when more control
988 * over the encoding process is required.
990 * @return The resultant byte array
994 public byte[] getBytes() {
995 return StringCoding.encode(value, offset, count);
999 * Compares this string to the specified object. The result is {@code
1000 * true} if and only if the argument is not {@code null} and is a {@code
1001 * String} object that represents the same sequence of characters as this
1005 * The object to compare this {@code String} against
1007 * @return {@code true} if the given object represents a {@code String}
1008 * equivalent to this string, {@code false} otherwise
1010 * @see #compareTo(String)
1011 * @see #equalsIgnoreCase(String)
1013 public boolean equals(Object anObject) {
1014 if (this == anObject) {
1017 if (anObject instanceof String) {
1018 String anotherString = (String)anObject;
1020 if (n == anotherString.count) {
1022 char v2[] = anotherString.value;
1024 int j = anotherString.offset;
1026 if (v1[i++] != v2[j++])
1036 * Compares this string to the specified {@code StringBuffer}. The result
1037 * is {@code true} if and only if this {@code String} represents the same
1038 * sequence of characters as the specified {@code StringBuffer}.
1041 * The {@code StringBuffer} to compare this {@code String} against
1043 * @return {@code true} if this {@code String} represents the same
1044 * sequence of characters as the specified {@code StringBuffer},
1045 * {@code false} otherwise
1049 public boolean contentEquals(StringBuffer sb) {
1051 return contentEquals((CharSequence)sb);
1056 * Compares this string to the specified {@code CharSequence}. The result
1057 * is {@code true} if and only if this {@code String} represents the same
1058 * sequence of char values as the specified sequence.
1061 * The sequence to compare this {@code String} against
1063 * @return {@code true} if this {@code String} represents the same
1064 * sequence of char values as the specified sequence, {@code
1069 public boolean contentEquals(CharSequence cs) {
1070 if (count != cs.length())
1072 // Argument is a StringBuffer, StringBuilder
1073 if (cs instanceof AbstractStringBuilder) {
1075 char v2[] = ((AbstractStringBuilder)cs).getValue();
1080 if (v1[i++] != v2[j++])
1085 // Argument is a String
1086 if (cs.equals(this))
1088 // Argument is a generic CharSequence
1094 if (v1[i++] != cs.charAt(j++))
1101 * Compares this {@code String} to another {@code String}, ignoring case
1102 * considerations. Two strings are considered equal ignoring case if they
1103 * are of the same length and corresponding characters in the two strings
1104 * are equal ignoring case.
1106 * <p> Two characters {@code c1} and {@code c2} are considered the same
1107 * ignoring case if at least one of the following is true:
1109 * <li> The two characters are the same (as compared by the
1110 * {@code ==} operator)
1111 * <li> Applying the method {@link
1112 * java.lang.Character#toUpperCase(char)} to each character
1113 * produces the same result
1114 * <li> Applying the method {@link
1115 * java.lang.Character#toLowerCase(char)} to each character
1116 * produces the same result
1119 * @param anotherString
1120 * The {@code String} to compare this {@code String} against
1122 * @return {@code true} if the argument is not {@code null} and it
1123 * represents an equivalent {@code String} ignoring case; {@code
1126 * @see #equals(Object)
1128 public boolean equalsIgnoreCase(String anotherString) {
1129 return (this == anotherString) ? true :
1130 (anotherString != null) && (anotherString.count == count) &&
1131 regionMatches(true, 0, anotherString, 0, count);
1135 * Compares two strings lexicographically.
1136 * The comparison is based on the Unicode value of each character in
1137 * the strings. The character sequence represented by this
1138 * <code>String</code> object is compared lexicographically to the
1139 * character sequence represented by the argument string. The result is
1140 * a negative integer if this <code>String</code> object
1141 * lexicographically precedes the argument string. The result is a
1142 * positive integer if this <code>String</code> object lexicographically
1143 * follows the argument string. The result is zero if the strings
1144 * are equal; <code>compareTo</code> returns <code>0</code> exactly when
1145 * the {@link #equals(Object)} method would return <code>true</code>.
1147 * This is the definition of lexicographic ordering. If two strings are
1148 * different, then either they have different characters at some index
1149 * that is a valid index for both strings, or their lengths are different,
1150 * or both. If they have different characters at one or more index
1151 * positions, let <i>k</i> be the smallest such index; then the string
1152 * whose character at position <i>k</i> has the smaller value, as
1153 * determined by using the < operator, lexicographically precedes the
1154 * other string. In this case, <code>compareTo</code> returns the
1155 * difference of the two character values at position <code>k</code> in
1156 * the two string -- that is, the value:
1158 * this.charAt(k)-anotherString.charAt(k)
1159 * </pre></blockquote>
1160 * If there is no index position at which they differ, then the shorter
1161 * string lexicographically precedes the longer string. In this case,
1162 * <code>compareTo</code> returns the difference of the lengths of the
1163 * strings -- that is, the value:
1165 * this.length()-anotherString.length()
1166 * </pre></blockquote>
1168 * @param anotherString the <code>String</code> to be compared.
1169 * @return the value <code>0</code> if the argument string is equal to
1170 * this string; a value less than <code>0</code> if this string
1171 * is lexicographically less than the string argument; and a
1172 * value greater than <code>0</code> if this string is
1173 * lexicographically greater than the string argument.
1175 public int compareTo(String anotherString) {
1177 int len2 = anotherString.count;
1178 int n = Math.min(len1, len2);
1180 char v2[] = anotherString.value;
1182 int j = anotherString.offset;
1208 * A Comparator that orders <code>String</code> objects as by
1209 * <code>compareToIgnoreCase</code>. This comparator is serializable.
1211 * Note that this Comparator does <em>not</em> take locale into account,
1212 * and will result in an unsatisfactory ordering for certain locales.
1213 * The java.text package provides <em>Collators</em> to allow
1214 * locale-sensitive ordering.
1216 * @see java.text.Collator#compare(String, String)
1219 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1220 = new CaseInsensitiveComparator();
1221 private static class CaseInsensitiveComparator
1222 implements Comparator<String>, java.io.Serializable {
1223 // use serialVersionUID from JDK 1.2.2 for interoperability
1224 private static final long serialVersionUID = 8575799808933029326L;
1226 public int compare(String s1, String s2) {
1227 int n1 = s1.length();
1228 int n2 = s2.length();
1229 int min = Math.min(n1, n2);
1230 for (int i = 0; i < min; i++) {
1231 char c1 = s1.charAt(i);
1232 char c2 = s2.charAt(i);
1234 c1 = Character.toUpperCase(c1);
1235 c2 = Character.toUpperCase(c2);
1237 c1 = Character.toLowerCase(c1);
1238 c2 = Character.toLowerCase(c2);
1240 // No overflow because of numeric promotion
1251 * Compares two strings lexicographically, ignoring case
1252 * differences. This method returns an integer whose sign is that of
1253 * calling <code>compareTo</code> with normalized versions of the strings
1254 * where case differences have been eliminated by calling
1255 * <code>Character.toLowerCase(Character.toUpperCase(character))</code> on
1258 * Note that this method does <em>not</em> take locale into account,
1259 * and will result in an unsatisfactory ordering for certain locales.
1260 * The java.text package provides <em>collators</em> to allow
1261 * locale-sensitive ordering.
1263 * @param str the <code>String</code> to be compared.
1264 * @return a negative integer, zero, or a positive integer as the
1265 * specified String is greater than, equal to, or less
1266 * than this String, ignoring case considerations.
1267 * @see java.text.Collator#compare(String, String)
1270 public int compareToIgnoreCase(String str) {
1271 return CASE_INSENSITIVE_ORDER.compare(this, str);
1275 * Tests if two string regions are equal.
1277 * A substring of this <tt>String</tt> object is compared to a substring
1278 * of the argument other. The result is true if these substrings
1279 * represent identical character sequences. The substring of this
1280 * <tt>String</tt> object to be compared begins at index <tt>toffset</tt>
1281 * and has length <tt>len</tt>. The substring of other to be compared
1282 * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The
1283 * result is <tt>false</tt> if and only if at least one of the following
1285 * <ul><li><tt>toffset</tt> is negative.
1286 * <li><tt>ooffset</tt> is negative.
1287 * <li><tt>toffset+len</tt> is greater than the length of this
1288 * <tt>String</tt> object.
1289 * <li><tt>ooffset+len</tt> is greater than the length of the other
1291 * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt>
1293 * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt>
1296 * @param toffset the starting offset of the subregion in this string.
1297 * @param other the string argument.
1298 * @param ooffset the starting offset of the subregion in the string
1300 * @param len the number of characters to compare.
1301 * @return <code>true</code> if the specified subregion of this string
1302 * exactly matches the specified subregion of the string argument;
1303 * <code>false</code> otherwise.
1305 public boolean regionMatches(int toffset, String other, int ooffset,
1308 int to = offset + toffset;
1309 char pa[] = other.value;
1310 int po = other.offset + ooffset;
1311 // Note: toffset, ooffset, or len might be near -1>>>1.
1312 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len)
1313 || (ooffset > (long)other.count - len)) {
1317 if (ta[to++] != pa[po++]) {
1325 * Tests if two string regions are equal.
1327 * A substring of this <tt>String</tt> object is compared to a substring
1328 * of the argument <tt>other</tt>. The result is <tt>true</tt> if these
1329 * substrings represent character sequences that are the same, ignoring
1330 * case if and only if <tt>ignoreCase</tt> is true. The substring of
1331 * this <tt>String</tt> object to be compared begins at index
1332 * <tt>toffset</tt> and has length <tt>len</tt>. The substring of
1333 * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and
1334 * has length <tt>len</tt>. The result is <tt>false</tt> if and only if
1335 * at least one of the following is true:
1336 * <ul><li><tt>toffset</tt> is negative.
1337 * <li><tt>ooffset</tt> is negative.
1338 * <li><tt>toffset+len</tt> is greater than the length of this
1339 * <tt>String</tt> object.
1340 * <li><tt>ooffset+len</tt> is greater than the length of the other
1342 * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative
1343 * integer <i>k</i> less than <tt>len</tt> such that:
1345 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1346 * </pre></blockquote>
1347 * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative
1348 * integer <i>k</i> less than <tt>len</tt> such that:
1350 * Character.toLowerCase(this.charAt(toffset+k)) !=
1351 Character.toLowerCase(other.charAt(ooffset+k))
1352 * </pre></blockquote>
1355 * Character.toUpperCase(this.charAt(toffset+k)) !=
1356 * Character.toUpperCase(other.charAt(ooffset+k))
1357 * </pre></blockquote>
1360 * @param ignoreCase if <code>true</code>, ignore case when comparing
1362 * @param toffset the starting offset of the subregion in this
1364 * @param other the string argument.
1365 * @param ooffset the starting offset of the subregion in the string
1367 * @param len the number of characters to compare.
1368 * @return <code>true</code> if the specified subregion of this string
1369 * matches the specified subregion of the string argument;
1370 * <code>false</code> otherwise. Whether the matching is exact
1371 * or case insensitive depends on the <code>ignoreCase</code>
1374 public boolean regionMatches(boolean ignoreCase, int toffset,
1375 String other, int ooffset, int len) {
1377 int to = offset + toffset;
1378 char pa[] = other.value;
1379 int po = other.offset + ooffset;
1380 // Note: toffset, ooffset, or len might be near -1>>>1.
1381 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) ||
1382 (ooffset > (long)other.count - len)) {
1392 // If characters don't match but case may be ignored,
1393 // try converting both characters to uppercase.
1394 // If the results match, then the comparison scan should
1396 char u1 = Character.toUpperCase(c1);
1397 char u2 = Character.toUpperCase(c2);
1401 // Unfortunately, conversion to uppercase does not work properly
1402 // for the Georgian alphabet, which has strange rules about case
1403 // conversion. So we need to make one last check before
1405 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1415 * Tests if the substring of this string beginning at the
1416 * specified index starts with the specified prefix.
1418 * @param prefix the prefix.
1419 * @param toffset where to begin looking in this string.
1420 * @return <code>true</code> if the character sequence represented by the
1421 * argument is a prefix of the substring of this object starting
1422 * at index <code>toffset</code>; <code>false</code> otherwise.
1423 * The result is <code>false</code> if <code>toffset</code> is
1424 * negative or greater than the length of this
1425 * <code>String</code> object; otherwise the result is the same
1426 * as the result of the expression
1428 * this.substring(toffset).startsWith(prefix)
1431 public boolean startsWith(String prefix, int toffset) {
1433 int to = offset + toffset;
1434 char pa[] = prefix.value;
1435 int po = prefix.offset;
1436 int pc = prefix.count;
1437 // Note: toffset might be near -1>>>1.
1438 if ((toffset < 0) || (toffset > count - pc)) {
1442 if (ta[to++] != pa[po++]) {
1450 * Tests if this string starts with the specified prefix.
1452 * @param prefix the prefix.
1453 * @return <code>true</code> if the character sequence represented by the
1454 * argument is a prefix of the character sequence represented by
1455 * this string; <code>false</code> otherwise.
1456 * Note also that <code>true</code> will be returned if the
1457 * argument is an empty string or is equal to this
1458 * <code>String</code> object as determined by the
1459 * {@link #equals(Object)} method.
1462 public boolean startsWith(String prefix) {
1463 return startsWith(prefix, 0);
1467 * Tests if this string ends with the specified suffix.
1469 * @param suffix the suffix.
1470 * @return <code>true</code> if the character sequence represented by the
1471 * argument is a suffix of the character sequence represented by
1472 * this object; <code>false</code> otherwise. Note that the
1473 * result will be <code>true</code> if the argument is the
1474 * empty string or is equal to this <code>String</code> object
1475 * as determined by the {@link #equals(Object)} method.
1477 public boolean endsWith(String suffix) {
1478 return startsWith(suffix, count - suffix.count);
1482 * Returns a hash code for this string. The hash code for a
1483 * <code>String</code> object is computed as
1485 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1486 * </pre></blockquote>
1487 * using <code>int</code> arithmetic, where <code>s[i]</code> is the
1488 * <i>i</i>th character of the string, <code>n</code> is the length of
1489 * the string, and <code>^</code> indicates exponentiation.
1490 * (The hash value of the empty string is zero.)
1492 * @return a hash code value for this object.
1494 public int hashCode() {
1496 if (h == 0 && count > 0) {
1501 for (int i = 0; i < len; i++) {
1502 h = 31*h + val[off++];
1510 * Returns the index within this string of the first occurrence of
1511 * the specified character. If a character with value
1512 * <code>ch</code> occurs in the character sequence represented by
1513 * this <code>String</code> object, then the index (in Unicode
1514 * code units) of the first such occurrence is returned. For
1515 * values of <code>ch</code> in the range from 0 to 0xFFFF
1516 * (inclusive), this is the smallest value <i>k</i> such that:
1518 * this.charAt(<i>k</i>) == ch
1519 * </pre></blockquote>
1520 * is true. For other values of <code>ch</code>, it is the
1521 * smallest value <i>k</i> such that:
1523 * this.codePointAt(<i>k</i>) == ch
1524 * </pre></blockquote>
1525 * is true. In either case, if no such character occurs in this
1526 * string, then <code>-1</code> is returned.
1528 * @param ch a character (Unicode code point).
1529 * @return the index of the first occurrence of the character in the
1530 * character sequence represented by this object, or
1531 * <code>-1</code> if the character does not occur.
1533 public int indexOf(int ch) {
1534 return indexOf(ch, 0);
1538 * Returns the index within this string of the first occurrence of the
1539 * specified character, starting the search at the specified index.
1541 * If a character with value <code>ch</code> occurs in the
1542 * character sequence represented by this <code>String</code>
1543 * object at an index no smaller than <code>fromIndex</code>, then
1544 * the index of the first such occurrence is returned. For values
1545 * of <code>ch</code> in the range from 0 to 0xFFFF (inclusive),
1546 * this is the smallest value <i>k</i> such that:
1548 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1549 * </pre></blockquote>
1550 * is true. For other values of <code>ch</code>, it is the
1551 * smallest value <i>k</i> such that:
1553 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1554 * </pre></blockquote>
1555 * is true. In either case, if no such character occurs in this
1556 * string at or after position <code>fromIndex</code>, then
1557 * <code>-1</code> is returned.
1560 * There is no restriction on the value of <code>fromIndex</code>. If it
1561 * is negative, it has the same effect as if it were zero: this entire
1562 * string may be searched. If it is greater than the length of this
1563 * string, it has the same effect as if it were equal to the length of
1564 * this string: <code>-1</code> is returned.
1566 * <p>All indices are specified in <code>char</code> values
1567 * (Unicode code units).
1569 * @param ch a character (Unicode code point).
1570 * @param fromIndex the index to start the search from.
1571 * @return the index of the first occurrence of the character in the
1572 * character sequence represented by this object that is greater
1573 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1574 * if the character does not occur.
1576 public int indexOf(int ch, int fromIndex) {
1577 if (fromIndex < 0) {
1579 } else if (fromIndex >= count) {
1580 // Note: fromIndex might be near -1>>>1.
1584 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1585 // handle most cases here (ch is a BMP code point or a
1586 // negative value (invalid code point))
1587 final char[] value = this.value;
1588 final int offset = this.offset;
1589 final int max = offset + count;
1590 for (int i = offset + fromIndex; i < max ; i++) {
1591 if (value[i] == ch) {
1597 return indexOfSupplementary(ch, fromIndex);
1602 * Handles (rare) calls of indexOf with a supplementary character.
1604 private int indexOfSupplementary(int ch, int fromIndex) {
1605 if (Character.isValidCodePoint(ch)) {
1606 final char[] value = this.value;
1607 final int offset = this.offset;
1608 final char hi = Character.highSurrogate(ch);
1609 final char lo = Character.lowSurrogate(ch);
1610 final int max = offset + count - 1;
1611 for (int i = offset + fromIndex; i < max; i++) {
1612 if (value[i] == hi && value[i+1] == lo) {
1621 * Returns the index within this string of the last occurrence of
1622 * the specified character. For values of <code>ch</code> in the
1623 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1624 * units) returned is the largest value <i>k</i> such that:
1626 * this.charAt(<i>k</i>) == ch
1627 * </pre></blockquote>
1628 * is true. For other values of <code>ch</code>, it is the
1629 * largest value <i>k</i> such that:
1631 * this.codePointAt(<i>k</i>) == ch
1632 * </pre></blockquote>
1633 * is true. In either case, if no such character occurs in this
1634 * string, then <code>-1</code> is returned. The
1635 * <code>String</code> is searched backwards starting at the last
1638 * @param ch a character (Unicode code point).
1639 * @return the index of the last occurrence of the character in the
1640 * character sequence represented by this object, or
1641 * <code>-1</code> if the character does not occur.
1643 public int lastIndexOf(int ch) {
1644 return lastIndexOf(ch, count - 1);
1648 * Returns the index within this string of the last occurrence of
1649 * the specified character, searching backward starting at the
1650 * specified index. For values of <code>ch</code> in the range
1651 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1652 * value <i>k</i> such that:
1654 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1655 * </pre></blockquote>
1656 * is true. For other values of <code>ch</code>, it is the
1657 * largest value <i>k</i> such that:
1659 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1660 * </pre></blockquote>
1661 * is true. In either case, if no such character occurs in this
1662 * string at or before position <code>fromIndex</code>, then
1663 * <code>-1</code> is returned.
1665 * <p>All indices are specified in <code>char</code> values
1666 * (Unicode code units).
1668 * @param ch a character (Unicode code point).
1669 * @param fromIndex the index to start the search from. There is no
1670 * restriction on the value of <code>fromIndex</code>. If it is
1671 * greater than or equal to the length of this string, it has
1672 * the same effect as if it were equal to one less than the
1673 * length of this string: this entire string may be searched.
1674 * If it is negative, it has the same effect as if it were -1:
1676 * @return the index of the last occurrence of the character in the
1677 * character sequence represented by this object that is less
1678 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1679 * if the character does not occur before that point.
1681 public int lastIndexOf(int ch, int fromIndex) {
1682 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1683 // handle most cases here (ch is a BMP code point or a
1684 // negative value (invalid code point))
1685 final char[] value = this.value;
1686 final int offset = this.offset;
1687 int i = offset + Math.min(fromIndex, count - 1);
1688 for (; i >= offset ; i--) {
1689 if (value[i] == ch) {
1695 return lastIndexOfSupplementary(ch, fromIndex);
1700 * Handles (rare) calls of lastIndexOf with a supplementary character.
1702 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1703 if (Character.isValidCodePoint(ch)) {
1704 final char[] value = this.value;
1705 final int offset = this.offset;
1706 char hi = Character.highSurrogate(ch);
1707 char lo = Character.lowSurrogate(ch);
1708 int i = offset + Math.min(fromIndex, count - 2);
1709 for (; i >= offset; i--) {
1710 if (value[i] == hi && value[i+1] == lo) {
1719 * Returns the index within this string of the first occurrence of the
1720 * specified substring.
1722 * <p>The returned index is the smallest value <i>k</i> for which:
1724 * this.startsWith(str, <i>k</i>)
1725 * </pre></blockquote>
1726 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1728 * @param str the substring to search for.
1729 * @return the index of the first occurrence of the specified substring,
1730 * or {@code -1} if there is no such occurrence.
1732 public int indexOf(String str) {
1733 return indexOf(str, 0);
1737 * Returns the index within this string of the first occurrence of the
1738 * specified substring, starting at the specified index.
1740 * <p>The returned index is the smallest value <i>k</i> for which:
1742 * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>)
1743 * </pre></blockquote>
1744 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1746 * @param str the substring to search for.
1747 * @param fromIndex the index from which to start the search.
1748 * @return the index of the first occurrence of the specified substring,
1749 * starting at the specified index,
1750 * or {@code -1} if there is no such occurrence.
1752 public int indexOf(String str, int fromIndex) {
1753 return indexOf(value, offset, count,
1754 str.value, str.offset, str.count, fromIndex);
1758 * Code shared by String and StringBuffer to do searches. The
1759 * source is the character array being searched, and the target
1760 * is the string being searched for.
1762 * @param source the characters being searched.
1763 * @param sourceOffset offset of the source string.
1764 * @param sourceCount count of the source string.
1765 * @param target the characters being searched for.
1766 * @param targetOffset offset of the target string.
1767 * @param targetCount count of the target string.
1768 * @param fromIndex the index to begin searching from.
1770 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1771 char[] target, int targetOffset, int targetCount,
1773 if (fromIndex >= sourceCount) {
1774 return (targetCount == 0 ? sourceCount : -1);
1776 if (fromIndex < 0) {
1779 if (targetCount == 0) {
1783 char first = target[targetOffset];
1784 int max = sourceOffset + (sourceCount - targetCount);
1786 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1787 /* Look for first character. */
1788 if (source[i] != first) {
1789 while (++i <= max && source[i] != first);
1792 /* Found first character, now look at the rest of v2 */
1795 int end = j + targetCount - 1;
1796 for (int k = targetOffset + 1; j < end && source[j] ==
1797 target[k]; j++, k++);
1800 /* Found whole string. */
1801 return i - sourceOffset;
1809 * Returns the index within this string of the last occurrence of the
1810 * specified substring. The last occurrence of the empty string ""
1811 * is considered to occur at the index value {@code this.length()}.
1813 * <p>The returned index is the largest value <i>k</i> for which:
1815 * this.startsWith(str, <i>k</i>)
1816 * </pre></blockquote>
1817 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1819 * @param str the substring to search for.
1820 * @return the index of the last occurrence of the specified substring,
1821 * or {@code -1} if there is no such occurrence.
1823 public int lastIndexOf(String str) {
1824 return lastIndexOf(str, count);
1828 * Returns the index within this string of the last occurrence of the
1829 * specified substring, searching backward starting at the specified index.
1831 * <p>The returned index is the largest value <i>k</i> for which:
1833 * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>)
1834 * </pre></blockquote>
1835 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1837 * @param str the substring to search for.
1838 * @param fromIndex the index to start the search from.
1839 * @return the index of the last occurrence of the specified substring,
1840 * searching backward from the specified index,
1841 * or {@code -1} if there is no such occurrence.
1843 public int lastIndexOf(String str, int fromIndex) {
1844 return lastIndexOf(value, offset, count,
1845 str.value, str.offset, str.count, fromIndex);
1849 * Code shared by String and StringBuffer to do searches. The
1850 * source is the character array being searched, and the target
1851 * is the string being searched for.
1853 * @param source the characters being searched.
1854 * @param sourceOffset offset of the source string.
1855 * @param sourceCount count of the source string.
1856 * @param target the characters being searched for.
1857 * @param targetOffset offset of the target string.
1858 * @param targetCount count of the target string.
1859 * @param fromIndex the index to begin searching from.
1861 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1862 char[] target, int targetOffset, int targetCount,
1865 * Check arguments; return immediately where possible. For
1866 * consistency, don't check for null str.
1868 int rightIndex = sourceCount - targetCount;
1869 if (fromIndex < 0) {
1872 if (fromIndex > rightIndex) {
1873 fromIndex = rightIndex;
1875 /* Empty string always matches. */
1876 if (targetCount == 0) {
1880 int strLastIndex = targetOffset + targetCount - 1;
1881 char strLastChar = target[strLastIndex];
1882 int min = sourceOffset + targetCount - 1;
1883 int i = min + fromIndex;
1885 startSearchForLastChar:
1887 while (i >= min && source[i] != strLastChar) {
1894 int start = j - (targetCount - 1);
1895 int k = strLastIndex - 1;
1898 if (source[j--] != target[k--]) {
1900 continue startSearchForLastChar;
1903 return start - sourceOffset + 1;
1908 * Returns a new string that is a substring of this string. The
1909 * substring begins with the character at the specified index and
1910 * extends to the end of this string. <p>
1913 * "unhappy".substring(2) returns "happy"
1914 * "Harbison".substring(3) returns "bison"
1915 * "emptiness".substring(9) returns "" (an empty string)
1916 * </pre></blockquote>
1918 * @param beginIndex the beginning index, inclusive.
1919 * @return the specified substring.
1920 * @exception IndexOutOfBoundsException if
1921 * <code>beginIndex</code> is negative or larger than the
1922 * length of this <code>String</code> object.
1924 public String substring(int beginIndex) {
1925 return substring(beginIndex, count);
1929 * Returns a new string that is a substring of this string. The
1930 * substring begins at the specified <code>beginIndex</code> and
1931 * extends to the character at index <code>endIndex - 1</code>.
1932 * Thus the length of the substring is <code>endIndex-beginIndex</code>.
1936 * "hamburger".substring(4, 8) returns "urge"
1937 * "smiles".substring(1, 5) returns "mile"
1938 * </pre></blockquote>
1940 * @param beginIndex the beginning index, inclusive.
1941 * @param endIndex the ending index, exclusive.
1942 * @return the specified substring.
1943 * @exception IndexOutOfBoundsException if the
1944 * <code>beginIndex</code> is negative, or
1945 * <code>endIndex</code> is larger than the length of
1946 * this <code>String</code> object, or
1947 * <code>beginIndex</code> is larger than
1948 * <code>endIndex</code>.
1950 public String substring(int beginIndex, int endIndex) {
1951 if (beginIndex < 0) {
1952 throw new StringIndexOutOfBoundsException(beginIndex);
1954 if (endIndex > count) {
1955 throw new StringIndexOutOfBoundsException(endIndex);
1957 if (beginIndex > endIndex) {
1958 throw new StringIndexOutOfBoundsException(endIndex - beginIndex);
1960 return ((beginIndex == 0) && (endIndex == count)) ? this :
1961 new String(offset + beginIndex, endIndex - beginIndex, value);
1965 * Returns a new character sequence that is a subsequence of this sequence.
1967 * <p> An invocation of this method of the form
1970 * str.subSequence(begin, end)</pre></blockquote>
1972 * behaves in exactly the same way as the invocation
1975 * str.substring(begin, end)</pre></blockquote>
1977 * This method is defined so that the <tt>String</tt> class can implement
1978 * the {@link CharSequence} interface. </p>
1980 * @param beginIndex the begin index, inclusive.
1981 * @param endIndex the end index, exclusive.
1982 * @return the specified subsequence.
1984 * @throws IndexOutOfBoundsException
1985 * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative,
1986 * if <tt>endIndex</tt> is greater than <tt>length()</tt>,
1987 * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt>
1992 public CharSequence subSequence(int beginIndex, int endIndex) {
1993 return this.substring(beginIndex, endIndex);
1997 * Concatenates the specified string to the end of this string.
1999 * If the length of the argument string is <code>0</code>, then this
2000 * <code>String</code> object is returned. Otherwise, a new
2001 * <code>String</code> object is created, representing a character
2002 * sequence that is the concatenation of the character sequence
2003 * represented by this <code>String</code> object and the character
2004 * sequence represented by the argument string.<p>
2007 * "cares".concat("s") returns "caress"
2008 * "to".concat("get").concat("her") returns "together"
2009 * </pre></blockquote>
2011 * @param str the <code>String</code> that is concatenated to the end
2012 * of this <code>String</code>.
2013 * @return a string that represents the concatenation of this object's
2014 * characters followed by the string argument's characters.
2016 public String concat(String str) {
2017 int otherLen = str.length();
2018 if (otherLen == 0) {
2021 char buf[] = new char[count + otherLen];
2022 getChars(0, count, buf, 0);
2023 str.getChars(0, otherLen, buf, count);
2024 return new String(0, count + otherLen, buf);
2028 * Returns a new string resulting from replacing all occurrences of
2029 * <code>oldChar</code> in this string with <code>newChar</code>.
2031 * If the character <code>oldChar</code> does not occur in the
2032 * character sequence represented by this <code>String</code> object,
2033 * then a reference to this <code>String</code> object is returned.
2034 * Otherwise, a new <code>String</code> object is created that
2035 * represents a character sequence identical to the character sequence
2036 * represented by this <code>String</code> object, except that every
2037 * occurrence of <code>oldChar</code> is replaced by an occurrence
2038 * of <code>newChar</code>.
2042 * "mesquite in your cellar".replace('e', 'o')
2043 * returns "mosquito in your collar"
2044 * "the war of baronets".replace('r', 'y')
2045 * returns "the way of bayonets"
2046 * "sparring with a purple porpoise".replace('p', 't')
2047 * returns "starring with a turtle tortoise"
2048 * "JonL".replace('q', 'x') returns "JonL" (no change)
2049 * </pre></blockquote>
2051 * @param oldChar the old character.
2052 * @param newChar the new character.
2053 * @return a string derived from this string by replacing every
2054 * occurrence of <code>oldChar</code> with <code>newChar</code>.
2056 public String replace(char oldChar, char newChar) {
2057 if (oldChar != newChar) {
2060 char[] val = value; /* avoid getfield opcode */
2061 int off = offset; /* avoid getfield opcode */
2064 if (val[off + i] == oldChar) {
2069 char buf[] = new char[len];
2070 for (int j = 0 ; j < i ; j++) {
2071 buf[j] = val[off+j];
2074 char c = val[off + i];
2075 buf[i] = (c == oldChar) ? newChar : c;
2078 return new String(0, len, buf);
2085 * Tells whether or not this string matches the given <a
2086 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2088 * <p> An invocation of this method of the form
2089 * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the
2090 * same result as the expression
2092 * <blockquote><tt> {@link java.util.regex.Pattern}.{@link
2093 * java.util.regex.Pattern#matches(String,CharSequence)
2094 * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote>
2097 * the regular expression to which this string is to be matched
2099 * @return <tt>true</tt> if, and only if, this string matches the
2100 * given regular expression
2102 * @throws PatternSyntaxException
2103 * if the regular expression's syntax is invalid
2105 * @see java.util.regex.Pattern
2110 public boolean matches(String regex) {
2111 return Pattern.matches(regex, this);
2115 * Returns true if and only if this string contains the specified
2116 * sequence of char values.
2118 * @param s the sequence to search for
2119 * @return true if this string contains <code>s</code>, false otherwise
2120 * @throws NullPointerException if <code>s</code> is <code>null</code>
2123 public boolean contains(CharSequence s) {
2124 return indexOf(s.toString()) > -1;
2128 * Replaces the first substring of this string that matches the given <a
2129 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2130 * given replacement.
2132 * <p> An invocation of this method of the form
2133 * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2134 * yields exactly the same result as the expression
2137 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2138 * compile}(</tt><i>regex</i><tt>).{@link
2139 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2140 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst
2141 * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote>
2144 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2145 * replacement string may cause the results to be different than if it were
2146 * being treated as a literal replacement string; see
2147 * {@link java.util.regex.Matcher#replaceFirst}.
2148 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2149 * meaning of these characters, if desired.
2152 * the regular expression to which this string is to be matched
2153 * @param replacement
2154 * the string to be substituted for the first match
2156 * @return The resulting <tt>String</tt>
2158 * @throws PatternSyntaxException
2159 * if the regular expression's syntax is invalid
2161 * @see java.util.regex.Pattern
2166 public String replaceFirst(String regex, String replacement) {
2167 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2171 * Replaces each substring of this string that matches the given <a
2172 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2173 * given replacement.
2175 * <p> An invocation of this method of the form
2176 * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2177 * yields exactly the same result as the expression
2180 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2181 * compile}(</tt><i>regex</i><tt>).{@link
2182 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2183 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll
2184 * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote>
2187 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2188 * replacement string may cause the results to be different than if it were
2189 * being treated as a literal replacement string; see
2190 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2191 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2192 * meaning of these characters, if desired.
2195 * the regular expression to which this string is to be matched
2196 * @param replacement
2197 * the string to be substituted for each match
2199 * @return The resulting <tt>String</tt>
2201 * @throws PatternSyntaxException
2202 * if the regular expression's syntax is invalid
2204 * @see java.util.regex.Pattern
2209 public String replaceAll(String regex, String replacement) {
2210 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2214 * Replaces each substring of this string that matches the literal target
2215 * sequence with the specified literal replacement sequence. The
2216 * replacement proceeds from the beginning of the string to the end, for
2217 * example, replacing "aa" with "b" in the string "aaa" will result in
2218 * "ba" rather than "ab".
2220 * @param target The sequence of char values to be replaced
2221 * @param replacement The replacement sequence of char values
2222 * @return The resulting string
2223 * @throws NullPointerException if <code>target</code> or
2224 * <code>replacement</code> is <code>null</code>.
2227 public String replace(CharSequence target, CharSequence replacement) {
2228 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
2229 this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
2233 * Splits this string around matches of the given
2234 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2236 * <p> The array returned by this method contains each substring of this
2237 * string that is terminated by another substring that matches the given
2238 * expression or is terminated by the end of the string. The substrings in
2239 * the array are in the order in which they occur in this string. If the
2240 * expression does not match any part of the input then the resulting array
2241 * has just one element, namely this string.
2243 * <p> The <tt>limit</tt> parameter controls the number of times the
2244 * pattern is applied and therefore affects the length of the resulting
2245 * array. If the limit <i>n</i> is greater than zero then the pattern
2246 * will be applied at most <i>n</i> - 1 times, the array's
2247 * length will be no greater than <i>n</i>, and the array's last entry
2248 * will contain all input beyond the last matched delimiter. If <i>n</i>
2249 * is non-positive then the pattern will be applied as many times as
2250 * possible and the array can have any length. If <i>n</i> is zero then
2251 * the pattern will be applied as many times as possible, the array can
2252 * have any length, and trailing empty strings will be discarded.
2254 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the
2255 * following results with these parameters:
2257 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2263 * <tr><td align=center>:</td>
2264 * <td align=center>2</td>
2265 * <td><tt>{ "boo", "and:foo" }</tt></td></tr>
2266 * <tr><td align=center>:</td>
2267 * <td align=center>5</td>
2268 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2269 * <tr><td align=center>:</td>
2270 * <td align=center>-2</td>
2271 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2272 * <tr><td align=center>o</td>
2273 * <td align=center>5</td>
2274 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2275 * <tr><td align=center>o</td>
2276 * <td align=center>-2</td>
2277 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2278 * <tr><td align=center>o</td>
2279 * <td align=center>0</td>
2280 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2281 * </table></blockquote>
2283 * <p> An invocation of this method of the form
2284 * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt>
2285 * yields the same result as the expression
2288 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2289 * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link
2290 * java.util.regex.Pattern#split(java.lang.CharSequence,int)
2291 * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt>
2296 * the delimiting regular expression
2299 * the result threshold, as described above
2301 * @return the array of strings computed by splitting this string
2302 * around matches of the given regular expression
2304 * @throws PatternSyntaxException
2305 * if the regular expression's syntax is invalid
2307 * @see java.util.regex.Pattern
2312 public String[] split(String regex, int limit) {
2313 /* fastpath if the regex is a
2314 (1)one-char String and this character is not one of the
2315 RegEx's meta characters ".$|()[{^?*+\\", or
2316 (2)two-char String and the first char is the backslash and
2317 the second is not the ascii digit or ascii letter.
2320 if (((regex.count == 1 &&
2321 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2322 (regex.length() == 2 &&
2323 regex.charAt(0) == '\\' &&
2324 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2325 ((ch-'a')|('z'-ch)) < 0 &&
2326 ((ch-'A')|('Z'-ch)) < 0)) &&
2327 (ch < Character.MIN_HIGH_SURROGATE ||
2328 ch > Character.MAX_LOW_SURROGATE))
2332 boolean limited = limit > 0;
2333 ArrayList<String> list = new ArrayList<>();
2334 while ((next = indexOf(ch, off)) != -1) {
2335 if (!limited || list.size() < limit - 1) {
2336 list.add(substring(off, next));
2338 } else { // last one
2339 //assert (list.size() == limit - 1);
2340 list.add(substring(off, count));
2345 // If no match was found, return this
2347 return new String[] { this };
2349 // Add remaining segment
2350 if (!limited || list.size() < limit)
2351 list.add(substring(off, count));
2354 int resultSize = list.size();
2356 while (resultSize > 0 && list.get(resultSize-1).length() == 0)
2358 String[] result = new String[resultSize];
2359 return list.subList(0, resultSize).toArray(result);
2361 return Pattern.compile(regex).split(this, limit);
2365 * Splits this string around matches of the given <a
2366 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2368 * <p> This method works as if by invoking the two-argument {@link
2369 * #split(String, int) split} method with the given expression and a limit
2370 * argument of zero. Trailing empty strings are therefore not included in
2371 * the resulting array.
2373 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the following
2374 * results with these expressions:
2376 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2381 * <tr><td align=center>:</td>
2382 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2383 * <tr><td align=center>o</td>
2384 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2385 * </table></blockquote>
2389 * the delimiting regular expression
2391 * @return the array of strings computed by splitting this string
2392 * around matches of the given regular expression
2394 * @throws PatternSyntaxException
2395 * if the regular expression's syntax is invalid
2397 * @see java.util.regex.Pattern
2402 public String[] split(String regex) {
2403 return split(regex, 0);
2407 * Converts all of the characters in this <code>String</code> to lower
2408 * case using the rules of the given <code>Locale</code>. Case mapping is based
2409 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2410 * class. Since case mappings are not always 1:1 char mappings, the resulting
2411 * <code>String</code> may be a different length than the original <code>String</code>.
2413 * Examples of lowercase mappings are in the following table:
2414 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2416 * <th>Language Code of Locale</th>
2417 * <th>Upper Case</th>
2418 * <th>Lower Case</th>
2419 * <th>Description</th>
2422 * <td>tr (Turkish)</td>
2423 * <td>\u0130</td>
2424 * <td>\u0069</td>
2425 * <td>capital letter I with dot above -> small letter i</td>
2428 * <td>tr (Turkish)</td>
2429 * <td>\u0049</td>
2430 * <td>\u0131</td>
2431 * <td>capital letter I -> small letter dotless i </td>
2435 * <td>French Fries</td>
2436 * <td>french fries</td>
2437 * <td>lowercased all chars in String</td>
2441 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2442 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2443 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2444 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2445 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2446 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2447 * <td>lowercased all chars in String</td>
2451 * @param locale use the case transformation rules for this locale
2452 * @return the <code>String</code>, converted to lowercase.
2453 * @see java.lang.String#toLowerCase()
2454 * @see java.lang.String#toUpperCase()
2455 * @see java.lang.String#toUpperCase(Locale)
2458 public String toLowerCase(Locale locale) {
2459 if (locale == null) {
2460 throw new NullPointerException();
2465 /* Now check if there are any characters that need to be changed. */
2467 for (firstUpper = 0 ; firstUpper < count; ) {
2468 char c = value[offset+firstUpper];
2469 if ((c >= Character.MIN_HIGH_SURROGATE) &&
2470 (c <= Character.MAX_HIGH_SURROGATE)) {
2471 int supplChar = codePointAt(firstUpper);
2472 if (supplChar != Character.toLowerCase(supplChar)) {
2475 firstUpper += Character.charCount(supplChar);
2477 if (c != Character.toLowerCase(c)) {
2486 char[] result = new char[count];
2487 int resultOffset = 0; /* result may grow, so i+resultOffset
2488 * is the write location in result */
2490 /* Just copy the first few lowerCase characters. */
2491 System.arraycopy(value, offset, result, 0, firstUpper);
2493 String lang = locale.getLanguage();
2494 boolean localeDependent =
2495 (lang == "tr" || lang == "az" || lang == "lt");
2496 char[] lowerCharArray;
2500 for (int i = firstUpper; i < count; i += srcCount) {
2501 srcChar = (int)value[offset+i];
2502 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2503 (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2504 srcChar = codePointAt(i);
2505 srcCount = Character.charCount(srcChar);
2509 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2510 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2511 } else if (srcChar == '\u0130') { // LATIN CAPITAL LETTER I DOT
2512 lowerChar = Character.ERROR;
2514 lowerChar = Character.toLowerCase(srcChar);
2516 if ((lowerChar == Character.ERROR) ||
2517 (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2518 if (lowerChar == Character.ERROR) {
2519 if (!localeDependent && srcChar == '\u0130') {
2521 ConditionalSpecialCasing.toLowerCaseCharArray(this, i, Locale.ENGLISH);
2524 ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2526 } else if (srcCount == 2) {
2527 resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount;
2530 lowerCharArray = Character.toChars(lowerChar);
2533 /* Grow result if needed */
2534 int mapLen = lowerCharArray.length;
2535 if (mapLen > srcCount) {
2536 char[] result2 = new char[result.length + mapLen - srcCount];
2537 System.arraycopy(result, 0, result2, 0,
2541 for (int x=0; x<mapLen; ++x) {
2542 result[i+resultOffset+x] = lowerCharArray[x];
2544 resultOffset += (mapLen - srcCount);
2546 result[i+resultOffset] = (char)lowerChar;
2549 return new String(0, count+resultOffset, result);
2553 * Converts all of the characters in this <code>String</code> to lower
2554 * case using the rules of the default locale. This is equivalent to calling
2555 * <code>toLowerCase(Locale.getDefault())</code>.
2557 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2558 * results if used for strings that are intended to be interpreted locale
2560 * Examples are programming language identifiers, protocol keys, and HTML
2562 * For instance, <code>"TITLE".toLowerCase()</code> in a Turkish locale
2563 * returns <code>"t\u005Cu0131tle"</code>, where '\u005Cu0131' is the
2564 * LATIN SMALL LETTER DOTLESS I character.
2565 * To obtain correct results for locale insensitive strings, use
2566 * <code>toLowerCase(Locale.ENGLISH)</code>.
2568 * @return the <code>String</code>, converted to lowercase.
2569 * @see java.lang.String#toLowerCase(Locale)
2571 public String toLowerCase() {
2572 return toLowerCase(Locale.getDefault());
2576 * Converts all of the characters in this <code>String</code> to upper
2577 * case using the rules of the given <code>Locale</code>. Case mapping is based
2578 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2579 * class. Since case mappings are not always 1:1 char mappings, the resulting
2580 * <code>String</code> may be a different length than the original <code>String</code>.
2582 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2584 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2586 * <th>Language Code of Locale</th>
2587 * <th>Lower Case</th>
2588 * <th>Upper Case</th>
2589 * <th>Description</th>
2592 * <td>tr (Turkish)</td>
2593 * <td>\u0069</td>
2594 * <td>\u0130</td>
2595 * <td>small letter i -> capital letter I with dot above</td>
2598 * <td>tr (Turkish)</td>
2599 * <td>\u0131</td>
2600 * <td>\u0049</td>
2601 * <td>small letter dotless i -> capital letter I</td>
2605 * <td>\u00df</td>
2606 * <td>\u0053 \u0053</td>
2607 * <td>small letter sharp s -> two letters: SS</td>
2611 * <td>Fahrvergnügen</td>
2612 * <td>FAHRVERGNÜGEN</td>
2616 * @param locale use the case transformation rules for this locale
2617 * @return the <code>String</code>, converted to uppercase.
2618 * @see java.lang.String#toUpperCase()
2619 * @see java.lang.String#toLowerCase()
2620 * @see java.lang.String#toLowerCase(Locale)
2623 public String toUpperCase(Locale locale) {
2624 if (locale == null) {
2625 throw new NullPointerException();
2630 /* Now check if there are any characters that need to be changed. */
2632 for (firstLower = 0 ; firstLower < count; ) {
2633 int c = (int)value[offset+firstLower];
2635 if ((c >= Character.MIN_HIGH_SURROGATE) &&
2636 (c <= Character.MAX_HIGH_SURROGATE)) {
2637 c = codePointAt(firstLower);
2638 srcCount = Character.charCount(c);
2642 int upperCaseChar = Character.toUpperCaseEx(c);
2643 if ((upperCaseChar == Character.ERROR) ||
2644 (c != upperCaseChar)) {
2647 firstLower += srcCount;
2652 char[] result = new char[count]; /* may grow */
2653 int resultOffset = 0; /* result may grow, so i+resultOffset
2654 * is the write location in result */
2656 /* Just copy the first few upperCase characters. */
2657 System.arraycopy(value, offset, result, 0, firstLower);
2659 String lang = locale.getLanguage();
2660 boolean localeDependent =
2661 (lang == "tr" || lang == "az" || lang == "lt");
2662 char[] upperCharArray;
2666 for (int i = firstLower; i < count; i += srcCount) {
2667 srcChar = (int)value[offset+i];
2668 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2669 (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2670 srcChar = codePointAt(i);
2671 srcCount = Character.charCount(srcChar);
2675 if (localeDependent) {
2676 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2678 upperChar = Character.toUpperCaseEx(srcChar);
2680 if ((upperChar == Character.ERROR) ||
2681 (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2682 if (upperChar == Character.ERROR) {
2683 if (localeDependent) {
2685 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
2687 upperCharArray = Character.toUpperCaseCharArray(srcChar);
2689 } else if (srcCount == 2) {
2690 resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount;
2693 upperCharArray = Character.toChars(upperChar);
2696 /* Grow result if needed */
2697 int mapLen = upperCharArray.length;
2698 if (mapLen > srcCount) {
2699 char[] result2 = new char[result.length + mapLen - srcCount];
2700 System.arraycopy(result, 0, result2, 0,
2704 for (int x=0; x<mapLen; ++x) {
2705 result[i+resultOffset+x] = upperCharArray[x];
2707 resultOffset += (mapLen - srcCount);
2709 result[i+resultOffset] = (char)upperChar;
2712 return new String(0, count+resultOffset, result);
2716 * Converts all of the characters in this <code>String</code> to upper
2717 * case using the rules of the default locale. This method is equivalent to
2718 * <code>toUpperCase(Locale.getDefault())</code>.
2720 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2721 * results if used for strings that are intended to be interpreted locale
2723 * Examples are programming language identifiers, protocol keys, and HTML
2725 * For instance, <code>"title".toUpperCase()</code> in a Turkish locale
2726 * returns <code>"T\u005Cu0130TLE"</code>, where '\u005Cu0130' is the
2727 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2728 * To obtain correct results for locale insensitive strings, use
2729 * <code>toUpperCase(Locale.ENGLISH)</code>.
2731 * @return the <code>String</code>, converted to uppercase.
2732 * @see java.lang.String#toUpperCase(Locale)
2734 public String toUpperCase() {
2735 return toUpperCase(Locale.getDefault());
2739 * Returns a copy of the string, with leading and trailing whitespace
2742 * If this <code>String</code> object represents an empty character
2743 * sequence, or the first and last characters of character sequence
2744 * represented by this <code>String</code> object both have codes
2745 * greater than <code>'\u0020'</code> (the space character), then a
2746 * reference to this <code>String</code> object is returned.
2748 * Otherwise, if there is no character with a code greater than
2749 * <code>'\u0020'</code> in the string, then a new
2750 * <code>String</code> object representing an empty string is created
2753 * Otherwise, let <i>k</i> be the index of the first character in the
2754 * string whose code is greater than <code>'\u0020'</code>, and let
2755 * <i>m</i> be the index of the last character in the string whose code
2756 * is greater than <code>'\u0020'</code>. A new <code>String</code>
2757 * object is created, representing the substring of this string that
2758 * begins with the character at index <i>k</i> and ends with the
2759 * character at index <i>m</i>-that is, the result of
2760 * <code>this.substring(<i>k</i>, <i>m</i>+1)</code>.
2762 * This method may be used to trim whitespace (as defined above) from
2763 * the beginning and end of a string.
2765 * @return A copy of this string with leading and trailing white
2766 * space removed, or this string if it has no leading or
2767 * trailing white space.
2769 public String trim() {
2772 int off = offset; /* avoid getfield opcode */
2773 char[] val = value; /* avoid getfield opcode */
2775 while ((st < len) && (val[off + st] <= ' ')) {
2778 while ((st < len) && (val[off + len - 1] <= ' ')) {
2781 return ((st > 0) || (len < count)) ? substring(st, len) : this;
2785 * This object (which is already a string!) is itself returned.
2787 * @return the string itself.
2789 public String toString() {
2794 * Converts this string to a new character array.
2796 * @return a newly allocated character array whose length is the length
2797 * of this string and whose contents are initialized to contain
2798 * the character sequence represented by this string.
2800 public char[] toCharArray() {
2801 char result[] = new char[count];
2802 getChars(0, count, result, 0);
2807 * Returns a formatted string using the specified format string and
2810 * <p> The locale always used is the one returned by {@link
2811 * java.util.Locale#getDefault() Locale.getDefault()}.
2814 * A <a href="../util/Formatter.html#syntax">format string</a>
2817 * Arguments referenced by the format specifiers in the format
2818 * string. If there are more arguments than format specifiers, the
2819 * extra arguments are ignored. The number of arguments is
2820 * variable and may be zero. The maximum number of arguments is
2821 * limited by the maximum dimension of a Java array as defined by
2822 * <cite>The Java™ Virtual Machine Specification</cite>.
2823 * The behaviour on a
2824 * <tt>null</tt> argument depends on the <a
2825 * href="../util/Formatter.html#syntax">conversion</a>.
2827 * @throws IllegalFormatException
2828 * If a format string contains an illegal syntax, a format
2829 * specifier that is incompatible with the given arguments,
2830 * insufficient arguments given the format string, or other
2831 * illegal conditions. For specification of all possible
2832 * formatting errors, see the <a
2833 * href="../util/Formatter.html#detail">Details</a> section of the
2834 * formatter class specification.
2836 * @throws NullPointerException
2837 * If the <tt>format</tt> is <tt>null</tt>
2839 * @return A formatted string
2841 * @see java.util.Formatter
2844 public static String format(String format, Object ... args) {
2845 return new Formatter().format(format, args).toString();
2849 * Returns a formatted string using the specified locale, format string,
2853 * The {@linkplain java.util.Locale locale} to apply during
2854 * formatting. If <tt>l</tt> is <tt>null</tt> then no localization
2858 * A <a href="../util/Formatter.html#syntax">format string</a>
2861 * Arguments referenced by the format specifiers in the format
2862 * string. If there are more arguments than format specifiers, the
2863 * extra arguments are ignored. The number of arguments is
2864 * variable and may be zero. The maximum number of arguments is
2865 * limited by the maximum dimension of a Java array as defined by
2866 * <cite>The Java™ Virtual Machine Specification</cite>.
2867 * The behaviour on a
2868 * <tt>null</tt> argument depends on the <a
2869 * href="../util/Formatter.html#syntax">conversion</a>.
2871 * @throws IllegalFormatException
2872 * If a format string contains an illegal syntax, a format
2873 * specifier that is incompatible with the given arguments,
2874 * insufficient arguments given the format string, or other
2875 * illegal conditions. For specification of all possible
2876 * formatting errors, see the <a
2877 * href="../util/Formatter.html#detail">Details</a> section of the
2878 * formatter class specification
2880 * @throws NullPointerException
2881 * If the <tt>format</tt> is <tt>null</tt>
2883 * @return A formatted string
2885 * @see java.util.Formatter
2888 public static String format(Locale l, String format, Object ... args) {
2889 return new Formatter(l).format(format, args).toString();
2893 * Returns the string representation of the <code>Object</code> argument.
2895 * @param obj an <code>Object</code>.
2896 * @return if the argument is <code>null</code>, then a string equal to
2897 * <code>"null"</code>; otherwise, the value of
2898 * <code>obj.toString()</code> is returned.
2899 * @see java.lang.Object#toString()
2901 public static String valueOf(Object obj) {
2902 return (obj == null) ? "null" : obj.toString();
2906 * Returns the string representation of the <code>char</code> array
2907 * argument. The contents of the character array are copied; subsequent
2908 * modification of the character array does not affect the newly
2911 * @param data a <code>char</code> array.
2912 * @return a newly allocated string representing the same sequence of
2913 * characters contained in the character array argument.
2915 public static String valueOf(char data[]) {
2916 return new String(data);
2920 * Returns the string representation of a specific subarray of the
2921 * <code>char</code> array argument.
2923 * The <code>offset</code> argument is the index of the first
2924 * character of the subarray. The <code>count</code> argument
2925 * specifies the length of the subarray. The contents of the subarray
2926 * are copied; subsequent modification of the character array does not
2927 * affect the newly created string.
2929 * @param data the character array.
2930 * @param offset the initial offset into the value of the
2931 * <code>String</code>.
2932 * @param count the length of the value of the <code>String</code>.
2933 * @return a string representing the sequence of characters contained
2934 * in the subarray of the character array argument.
2935 * @exception IndexOutOfBoundsException if <code>offset</code> is
2936 * negative, or <code>count</code> is negative, or
2937 * <code>offset+count</code> is larger than
2938 * <code>data.length</code>.
2940 public static String valueOf(char data[], int offset, int count) {
2941 return new String(data, offset, count);
2945 * Returns a String that represents the character sequence in the
2948 * @param data the character array.
2949 * @param offset initial offset of the subarray.
2950 * @param count length of the subarray.
2951 * @return a <code>String</code> that contains the characters of the
2952 * specified subarray of the character array.
2954 public static String copyValueOf(char data[], int offset, int count) {
2955 // All public String constructors now copy the data.
2956 return new String(data, offset, count);
2960 * Returns a String that represents the character sequence in the
2963 * @param data the character array.
2964 * @return a <code>String</code> that contains the characters of the
2967 public static String copyValueOf(char data[]) {
2968 return copyValueOf(data, 0, data.length);
2972 * Returns the string representation of the <code>boolean</code> argument.
2974 * @param b a <code>boolean</code>.
2975 * @return if the argument is <code>true</code>, a string equal to
2976 * <code>"true"</code> is returned; otherwise, a string equal to
2977 * <code>"false"</code> is returned.
2979 public static String valueOf(boolean b) {
2980 return b ? "true" : "false";
2984 * Returns the string representation of the <code>char</code>
2987 * @param c a <code>char</code>.
2988 * @return a string of length <code>1</code> containing
2989 * as its single character the argument <code>c</code>.
2991 public static String valueOf(char c) {
2993 return new String(0, 1, data);
2997 * Returns the string representation of the <code>int</code> argument.
2999 * The representation is exactly the one returned by the
3000 * <code>Integer.toString</code> method of one argument.
3002 * @param i an <code>int</code>.
3003 * @return a string representation of the <code>int</code> argument.
3004 * @see java.lang.Integer#toString(int, int)
3006 public static String valueOf(int i) {
3007 return Integer.toString(i);
3011 * Returns the string representation of the <code>long</code> argument.
3013 * The representation is exactly the one returned by the
3014 * <code>Long.toString</code> method of one argument.
3016 * @param l a <code>long</code>.
3017 * @return a string representation of the <code>long</code> argument.
3018 * @see java.lang.Long#toString(long)
3020 public static String valueOf(long l) {
3021 return Long.toString(l);
3025 * Returns the string representation of the <code>float</code> argument.
3027 * The representation is exactly the one returned by the
3028 * <code>Float.toString</code> method of one argument.
3030 * @param f a <code>float</code>.
3031 * @return a string representation of the <code>float</code> argument.
3032 * @see java.lang.Float#toString(float)
3034 public static String valueOf(float f) {
3035 return Float.toString(f);
3039 * Returns the string representation of the <code>double</code> argument.
3041 * The representation is exactly the one returned by the
3042 * <code>Double.toString</code> method of one argument.
3044 * @param d a <code>double</code>.
3045 * @return a string representation of the <code>double</code> argument.
3046 * @see java.lang.Double#toString(double)
3048 public static String valueOf(double d) {
3049 return Double.toString(d);
3053 * Returns a canonical representation for the string object.
3055 * A pool of strings, initially empty, is maintained privately by the
3056 * class <code>String</code>.
3058 * When the intern method is invoked, if the pool already contains a
3059 * string equal to this <code>String</code> object as determined by
3060 * the {@link #equals(Object)} method, then the string from the pool is
3061 * returned. Otherwise, this <code>String</code> object is added to the
3062 * pool and a reference to this <code>String</code> object is returned.
3064 * It follows that for any two strings <code>s</code> and <code>t</code>,
3065 * <code>s.intern() == t.intern()</code> is <code>true</code>
3066 * if and only if <code>s.equals(t)</code> is <code>true</code>.
3068 * All literal strings and string-valued constant expressions are
3069 * interned. String literals are defined in section 3.10.5 of the
3070 * <cite>The Java™ Language Specification</cite>.
3072 * @return a string that has the same contents as this string, but is
3073 * guaranteed to be from a pool of unique strings.
3075 public native String intern();