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.UnsupportedEncodingException;
29 import java.util.Comparator;
32 * The <code>String</code> class represents character strings. All
33 * string literals in Java programs, such as <code>"abc"</code>, are
34 * implemented as instances of this class.
36 * Strings are constant; their values cannot be changed after they
37 * are created. String buffers support mutable strings.
38 * Because String objects are immutable they can be shared. For example:
39 * <p><blockquote><pre>
41 * </pre></blockquote><p>
43 * <p><blockquote><pre>
44 * char data[] = {'a', 'b', 'c'};
45 * String str = new String(data);
46 * </pre></blockquote><p>
47 * Here are some more examples of how strings can be used:
48 * <p><blockquote><pre>
49 * System.out.println("abc");
51 * System.out.println("abc" + cde);
52 * String c = "abc".substring(2,3);
53 * String d = cde.substring(1, 2);
56 * The class <code>String</code> includes methods for examining
57 * individual characters of the sequence, for comparing strings, for
58 * searching strings, for extracting substrings, and for creating a
59 * copy of a string with all characters translated to uppercase or to
60 * lowercase. Case mapping is based on the Unicode Standard version
61 * specified by the {@link java.lang.Character Character} class.
63 * The Java language provides special support for the string
64 * concatenation operator ( + ), and for conversion of
65 * other objects to strings. String concatenation is implemented
66 * through the <code>StringBuilder</code>(or <code>StringBuffer</code>)
67 * class and its <code>append</code> method.
68 * String conversions are implemented through the method
69 * <code>toString</code>, defined by <code>Object</code> and
70 * inherited by all classes in Java. For additional information on
71 * string concatenation and conversion, see Gosling, Joy, and Steele,
72 * <i>The Java Language Specification</i>.
74 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
75 * or method in this class will cause a {@link NullPointerException} to be
78 * <p>A <code>String</code> represents a string in the UTF-16 format
79 * in which <em>supplementary characters</em> are represented by <em>surrogate
80 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
81 * Character Representations</a> in the <code>Character</code> class for
83 * Index values refer to <code>char</code> code units, so a supplementary
84 * character uses two positions in a <code>String</code>.
85 * <p>The <code>String</code> class provides methods for dealing with
86 * Unicode code points (i.e., characters), in addition to those for
87 * dealing with Unicode code units (i.e., <code>char</code> values).
90 * @author Arthur van Hoff
91 * @author Martin Buchholz
93 * @see java.lang.Object#toString()
94 * @see java.lang.StringBuffer
95 * @see java.lang.StringBuilder
96 * @see java.nio.charset.Charset
100 public final class String
101 implements java.io.Serializable, Comparable<String>, CharSequence
103 /** The value is used for character storage. */
104 private final char value[];
106 /** The offset is the first index of the storage that is used. */
107 private final int offset;
109 /** The count is the number of characters in the String. */
110 private final int count;
112 /** Cache the hash code for the string */
113 private int hash; // Default to 0
115 /** use serialVersionUID from JDK 1.0.2 for interoperability */
116 private static final long serialVersionUID = -6849794470754667710L;
119 * Class String is special cased within the Serialization Stream Protocol.
121 * A String instance is written initially into an ObjectOutputStream in the
124 * <code>TC_STRING</code> (utf String)
126 * The String is written by method <code>DataOutput.writeUTF</code>.
127 * A new handle is generated to refer to all future references to the
128 * string instance within the stream.
130 // private static final ObjectStreamField[] serialPersistentFields =
131 // new ObjectStreamField[0];
134 * Initializes a newly created {@code String} object so that it represents
135 * an empty character sequence. Note that use of this constructor is
136 * unnecessary since Strings are immutable.
141 this.value = new char[0];
145 * Initializes a newly created {@code String} object so that it represents
146 * the same sequence of characters as the argument; in other words, the
147 * newly created string is a copy of the argument string. Unless an
148 * explicit copy of {@code original} is needed, use of this constructor is
149 * unnecessary since Strings are immutable.
154 public String(String original) {
155 int size = original.count;
156 char[] originalValue = original.value;
158 if (originalValue.length > size) {
159 // The array representing the String is bigger than the new
160 // String itself. Perhaps this constructor is being called
161 // in order to trim the baggage, so make a copy of the array.
162 int off = original.offset;
163 v = copyOfRange(originalValue, off, off+size);
165 // The array representing the String is the same
166 // size as the String, so no point in making a copy.
175 * Allocates a new {@code String} so that it represents the sequence of
176 * characters currently contained in the character array argument. The
177 * contents of the character array are copied; subsequent modification of
178 * the character array does not affect the newly created string.
181 * The initial value of the string
183 public String(char value[]) {
184 int size = value.length;
187 this.value = copyOf(value, size);
191 * Allocates a new {@code String} that contains characters from a subarray
192 * of the character array argument. The {@code offset} argument is the
193 * index of the first character of the subarray and the {@code count}
194 * argument specifies the length of the subarray. The contents of the
195 * subarray are copied; subsequent modification of the character array does
196 * not affect the newly created string.
199 * Array that is the source of characters
207 * @throws IndexOutOfBoundsException
208 * If the {@code offset} and {@code count} arguments index
209 * characters outside the bounds of the {@code value} array
211 public String(char value[], int offset, int count) {
213 throw new StringIndexOutOfBoundsException(offset);
216 throw new StringIndexOutOfBoundsException(count);
218 // Note: offset or count might be near -1>>>1.
219 if (offset > value.length - count) {
220 throw new StringIndexOutOfBoundsException(offset + count);
224 this.value = copyOfRange(value, offset, offset+count);
228 * Allocates a new {@code String} that contains characters from a subarray
229 * of the <a href="Character.html#unicode">Unicode code point</a> array
230 * argument. The {@code offset} argument is the index of the first code
231 * point of the subarray and the {@code count} argument specifies the
232 * length of the subarray. The contents of the subarray are converted to
233 * {@code char}s; subsequent modification of the {@code int} array does not
234 * affect the newly created string.
237 * Array that is the source of Unicode code points
245 * @throws IllegalArgumentException
246 * If any invalid Unicode code point is found in {@code
249 * @throws IndexOutOfBoundsException
250 * If the {@code offset} and {@code count} arguments index
251 * characters outside the bounds of the {@code codePoints} array
255 public String(int[] codePoints, int offset, int count) {
257 throw new StringIndexOutOfBoundsException(offset);
260 throw new StringIndexOutOfBoundsException(count);
262 // Note: offset or count might be near -1>>>1.
263 if (offset > codePoints.length - count) {
264 throw new StringIndexOutOfBoundsException(offset + count);
267 final int end = offset + count;
269 // Pass 1: Compute precise size of char[]
271 for (int i = offset; i < end; i++) {
272 int c = codePoints[i];
273 if (Character.isBmpCodePoint(c))
275 else if (Character.isValidCodePoint(c))
277 else throw new IllegalArgumentException(Integer.toString(c));
280 // Pass 2: Allocate and fill in char[]
281 final char[] v = new char[n];
283 for (int i = offset, j = 0; i < end; i++, j++) {
284 int c = codePoints[i];
285 if (Character.isBmpCodePoint(c))
288 Character.toSurrogates(c, v, j++);
297 * Allocates a new {@code String} constructed from a subarray of an array
298 * of 8-bit integer values.
300 * <p> The {@code offset} argument is the index of the first byte of the
301 * subarray, and the {@code count} argument specifies the length of the
304 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
305 * specified in the method above.
307 * @deprecated This method does not properly convert bytes into characters.
308 * As of JDK 1.1, the preferred way to do this is via the
309 * {@code String} constructors that take a {@link
310 * java.nio.charset.Charset}, charset name, or that use the platform's
314 * The bytes to be converted to characters
317 * The top 8 bits of each 16-bit Unicode code unit
324 * @throws IndexOutOfBoundsException
325 * If the {@code offset} or {@code count} argument is invalid
327 * @see #String(byte[], int)
328 * @see #String(byte[], int, int, java.lang.String)
329 * @see #String(byte[], int, int, java.nio.charset.Charset)
330 * @see #String(byte[], int, int)
331 * @see #String(byte[], java.lang.String)
332 * @see #String(byte[], java.nio.charset.Charset)
333 * @see #String(byte[])
336 public String(byte ascii[], int hibyte, int offset, int count) {
337 checkBounds(ascii, offset, count);
338 char value[] = new char[count];
341 for (int i = count ; i-- > 0 ;) {
342 value[i] = (char) (ascii[i + offset] & 0xff);
346 for (int i = count ; i-- > 0 ;) {
347 value[i] = (char) (hibyte | (ascii[i + offset] & 0xff));
356 * Allocates a new {@code String} containing characters constructed from
357 * an array of 8-bit integer values. Each character <i>c</i>in the
358 * resulting string is constructed from the corresponding component
359 * <i>b</i> in the byte array such that:
362 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
363 * | (<b><i>b</i></b> & 0xff))
364 * </pre></blockquote>
366 * @deprecated This method does not properly convert bytes into
367 * characters. As of JDK 1.1, the preferred way to do this is via the
368 * {@code String} constructors that take a {@link
369 * java.nio.charset.Charset}, charset name, or that use the platform's
373 * The bytes to be converted to characters
376 * The top 8 bits of each 16-bit Unicode code unit
378 * @see #String(byte[], int, int, java.lang.String)
379 * @see #String(byte[], int, int, java.nio.charset.Charset)
380 * @see #String(byte[], int, int)
381 * @see #String(byte[], java.lang.String)
382 * @see #String(byte[], java.nio.charset.Charset)
383 * @see #String(byte[])
386 public String(byte ascii[], int hibyte) {
387 this(ascii, hibyte, 0, ascii.length);
390 /* Common private utility method used to bounds check the byte array
391 * and requested offset & length values used by the String(byte[],..)
394 private static void checkBounds(byte[] bytes, int offset, int length) {
396 throw new StringIndexOutOfBoundsException(length);
398 throw new StringIndexOutOfBoundsException(offset);
399 if (offset > bytes.length - length)
400 throw new StringIndexOutOfBoundsException(offset + length);
404 * Constructs a new {@code String} by decoding the specified subarray of
405 * bytes using the specified charset. The length of the new {@code String}
406 * is a function of the charset, and hence may not be equal to the length
409 * <p> The behavior of this constructor when the given bytes are not valid
410 * in the given charset is unspecified. The {@link
411 * java.nio.charset.CharsetDecoder} class should be used when more control
412 * over the decoding process is required.
415 * The bytes to be decoded into characters
418 * The index of the first byte to decode
421 * The number of bytes to decode
424 * The name of a supported {@linkplain java.nio.charset.Charset
427 * @throws UnsupportedEncodingException
428 * If the named charset is not supported
430 * @throws IndexOutOfBoundsException
431 * If the {@code offset} and {@code length} arguments index
432 * characters outside the bounds of the {@code bytes} array
436 // public String(byte bytes[], int offset, int length, String charsetName)
437 // throws UnsupportedEncodingException
439 // if (charsetName == null)
440 // throw new NullPointerException("charsetName");
441 // checkBounds(bytes, offset, length);
442 // char[] v = StringCoding.decode(charsetName, bytes, offset, length);
444 // this.count = v.length;
449 * Constructs a new {@code String} by decoding the specified subarray of
450 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
451 * The length of the new {@code String} is a function of the charset, and
452 * hence may not be equal to the length of the subarray.
454 * <p> This method always replaces malformed-input and unmappable-character
455 * sequences with this charset's default replacement string. The {@link
456 * java.nio.charset.CharsetDecoder} class should be used when more control
457 * over the decoding process is required.
460 * The bytes to be decoded into characters
463 * The index of the first byte to decode
466 * The number of bytes to decode
469 * The {@linkplain java.nio.charset.Charset charset} to be used to
470 * decode the {@code bytes}
472 * @throws IndexOutOfBoundsException
473 * If the {@code offset} and {@code length} arguments index
474 * characters outside the bounds of the {@code bytes} array
478 /* don't want dependnecy on Charset
479 public String(byte bytes[], int offset, int length, Charset charset) {
481 throw new NullPointerException("charset");
482 checkBounds(bytes, offset, length);
483 char[] v = StringCoding.decode(charset, bytes, offset, length);
485 this.count = v.length;
491 * Constructs a new {@code String} by decoding the specified array of bytes
492 * using the specified {@linkplain java.nio.charset.Charset charset}. The
493 * length of the new {@code String} is a function of the charset, and hence
494 * may not be equal to the length of the byte array.
496 * <p> The behavior of this constructor when the given bytes are not valid
497 * in the given charset is unspecified. The {@link
498 * java.nio.charset.CharsetDecoder} class should be used when more control
499 * over the decoding process is required.
502 * The bytes to be decoded into characters
505 * The name of a supported {@linkplain java.nio.charset.Charset
508 * @throws UnsupportedEncodingException
509 * If the named charset is not supported
513 // public String(byte bytes[], String charsetName)
514 // throws UnsupportedEncodingException
516 // this(bytes, 0, bytes.length, charsetName);
520 * Constructs a new {@code String} by decoding the specified array of
521 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
522 * The length of the new {@code String} is a function of the charset, and
523 * hence may not be equal to the length of the byte array.
525 * <p> This method always replaces malformed-input and unmappable-character
526 * sequences with this charset's default replacement string. The {@link
527 * java.nio.charset.CharsetDecoder} class should be used when more control
528 * over the decoding process is required.
531 * The bytes to be decoded into characters
534 * The {@linkplain java.nio.charset.Charset charset} to be used to
535 * decode the {@code bytes}
539 /* don't want dep on Charset
540 public String(byte bytes[], Charset charset) {
541 this(bytes, 0, bytes.length, charset);
546 * Constructs a new {@code String} by decoding the specified subarray of
547 * bytes using the platform's default charset. The length of the new
548 * {@code String} is a function of the charset, and hence may not be equal
549 * to the length of the subarray.
551 * <p> The behavior of this constructor when the given bytes are not valid
552 * in the default charset is unspecified. The {@link
553 * java.nio.charset.CharsetDecoder} class should be used when more control
554 * over the decoding process is required.
557 * The bytes to be decoded into characters
560 * The index of the first byte to decode
563 * The number of bytes to decode
565 * @throws IndexOutOfBoundsException
566 * If the {@code offset} and the {@code length} arguments index
567 * characters outside the bounds of the {@code bytes} array
571 public String(byte bytes[], int offset, int length) {
572 checkBounds(bytes, offset, length);
573 char[] v = new char[length];
574 for (int i = 0; i < length; i++) {
575 v[i] = (char)bytes[offset++];
578 this.count = v.length;
583 * Constructs a new {@code String} by decoding the specified array of bytes
584 * using the platform's default charset. The length of the new {@code
585 * String} is a function of the charset, and hence may not be equal to the
586 * length of the byte array.
588 * <p> The behavior of this constructor when the given bytes are not valid
589 * in the default charset is unspecified. The {@link
590 * java.nio.charset.CharsetDecoder} class should be used when more control
591 * over the decoding process is required.
594 * The bytes to be decoded into characters
598 public String(byte bytes[]) {
599 this(bytes, 0, bytes.length);
603 * Allocates a new string that contains the sequence of characters
604 * currently contained in the string buffer argument. The contents of the
605 * string buffer are copied; subsequent modification of the string buffer
606 * does not affect the newly created string.
609 * A {@code StringBuffer}
611 public String(StringBuffer buffer) {
612 String result = buffer.toString();
613 this.value = result.value;
614 this.count = result.count;
615 this.offset = result.offset;
619 * Allocates a new string that contains the sequence of characters
620 * currently contained in the string builder argument. The contents of the
621 * string builder are copied; subsequent modification of the string builder
622 * does not affect the newly created string.
624 * <p> This constructor is provided to ease migration to {@code
625 * StringBuilder}. Obtaining a string from a string builder via the {@code
626 * toString} method is likely to run faster and is generally preferred.
629 * A {@code StringBuilder}
633 public String(StringBuilder builder) {
634 String result = builder.toString();
635 this.value = result.value;
636 this.count = result.count;
637 this.offset = result.offset;
641 // Package private constructor which shares value array for speed.
642 String(int offset, int count, char value[]) {
644 this.offset = offset;
649 * Returns the length of this string.
650 * The length is equal to the number of <a href="Character.html#unicode">Unicode
651 * code units</a> in the string.
653 * @return the length of the sequence of characters represented by this
656 public int length() {
661 * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>.
663 * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise
668 public boolean isEmpty() {
673 * Returns the <code>char</code> value at the
674 * specified index. An index ranges from <code>0</code> to
675 * <code>length() - 1</code>. The first <code>char</code> value of the sequence
676 * is at index <code>0</code>, the next at index <code>1</code>,
677 * and so on, as for array indexing.
679 * <p>If the <code>char</code> value specified by the index is a
680 * <a href="Character.html#unicode">surrogate</a>, the surrogate
683 * @param index the index of the <code>char</code> value.
684 * @return the <code>char</code> value at the specified index of this string.
685 * The first <code>char</code> value is at index <code>0</code>.
686 * @exception IndexOutOfBoundsException if the <code>index</code>
687 * argument is negative or not less than the length of this
690 public char charAt(int index) {
691 if ((index < 0) || (index >= count)) {
692 throw new StringIndexOutOfBoundsException(index);
694 return value[index + offset];
698 * Returns the character (Unicode code point) at the specified
699 * index. The index refers to <code>char</code> values
700 * (Unicode code units) and ranges from <code>0</code> to
701 * {@link #length()}<code> - 1</code>.
703 * <p> If the <code>char</code> value specified at the given index
704 * is in the high-surrogate range, the following index is less
705 * than the length of this <code>String</code>, and the
706 * <code>char</code> value at the following index is in the
707 * low-surrogate range, then the supplementary code point
708 * corresponding to this surrogate pair is returned. Otherwise,
709 * the <code>char</code> value at the given index is returned.
711 * @param index the index to the <code>char</code> values
712 * @return the code point value of the character at the
714 * @exception IndexOutOfBoundsException if the <code>index</code>
715 * argument is negative or not less than the length of this
719 public int codePointAt(int index) {
720 if ((index < 0) || (index >= count)) {
721 throw new StringIndexOutOfBoundsException(index);
723 return Character.codePointAtImpl(value, offset + index, offset + count);
727 * Returns the character (Unicode code point) before the specified
728 * index. The index refers to <code>char</code> values
729 * (Unicode code units) and ranges from <code>1</code> to {@link
730 * CharSequence#length() length}.
732 * <p> If the <code>char</code> value at <code>(index - 1)</code>
733 * is in the low-surrogate range, <code>(index - 2)</code> is not
734 * negative, and the <code>char</code> value at <code>(index -
735 * 2)</code> is in the high-surrogate range, then the
736 * supplementary code point value of the surrogate pair is
737 * returned. If the <code>char</code> value at <code>index -
738 * 1</code> is an unpaired low-surrogate or a high-surrogate, the
739 * surrogate value is returned.
741 * @param index the index following the code point that should be returned
742 * @return the Unicode code point value before the given index.
743 * @exception IndexOutOfBoundsException if the <code>index</code>
744 * argument is less than 1 or greater than the length
748 public int codePointBefore(int index) {
750 if ((i < 0) || (i >= count)) {
751 throw new StringIndexOutOfBoundsException(index);
753 return Character.codePointBeforeImpl(value, offset + index, offset);
757 * Returns the number of Unicode code points in the specified text
758 * range of this <code>String</code>. The text range begins at the
759 * specified <code>beginIndex</code> and extends to the
760 * <code>char</code> at index <code>endIndex - 1</code>. Thus the
761 * length (in <code>char</code>s) of the text range is
762 * <code>endIndex-beginIndex</code>. Unpaired surrogates within
763 * the text range count as one code point each.
765 * @param beginIndex the index to the first <code>char</code> of
767 * @param endIndex the index after the last <code>char</code> of
769 * @return the number of Unicode code points in the specified text
771 * @exception IndexOutOfBoundsException if the
772 * <code>beginIndex</code> is negative, or <code>endIndex</code>
773 * is larger than the length of this <code>String</code>, or
774 * <code>beginIndex</code> is larger than <code>endIndex</code>.
777 public int codePointCount(int beginIndex, int endIndex) {
778 if (beginIndex < 0 || endIndex > count || beginIndex > endIndex) {
779 throw new IndexOutOfBoundsException();
781 return Character.codePointCountImpl(value, offset+beginIndex, endIndex-beginIndex);
785 * Returns the index within this <code>String</code> that is
786 * offset from the given <code>index</code> by
787 * <code>codePointOffset</code> code points. Unpaired surrogates
788 * within the text range given by <code>index</code> and
789 * <code>codePointOffset</code> count as one code point each.
791 * @param index the index to be offset
792 * @param codePointOffset the offset in code points
793 * @return the index within this <code>String</code>
794 * @exception IndexOutOfBoundsException if <code>index</code>
795 * is negative or larger then the length of this
796 * <code>String</code>, or if <code>codePointOffset</code> is positive
797 * and the substring starting with <code>index</code> has fewer
798 * than <code>codePointOffset</code> code points,
799 * or if <code>codePointOffset</code> is negative and the substring
800 * before <code>index</code> has fewer than the absolute value
801 * of <code>codePointOffset</code> code points.
804 public int offsetByCodePoints(int index, int codePointOffset) {
805 if (index < 0 || index > count) {
806 throw new IndexOutOfBoundsException();
808 return Character.offsetByCodePointsImpl(value, offset, count,
809 offset+index, codePointOffset) - offset;
813 * Copy characters from this string into dst starting at dstBegin.
814 * This method doesn't perform any range checking.
816 void getChars(char dst[], int dstBegin) {
817 arraycopy(value, offset, dst, dstBegin, count);
821 * Copies characters from this string into the destination character
824 * The first character to be copied is at index <code>srcBegin</code>;
825 * the last character to be copied is at index <code>srcEnd-1</code>
826 * (thus the total number of characters to be copied is
827 * <code>srcEnd-srcBegin</code>). The characters are copied into the
828 * subarray of <code>dst</code> starting at index <code>dstBegin</code>
829 * and ending at index:
830 * <p><blockquote><pre>
831 * dstbegin + (srcEnd-srcBegin) - 1
832 * </pre></blockquote>
834 * @param srcBegin index of the first character in the string
836 * @param srcEnd index after the last character in the string
838 * @param dst the destination array.
839 * @param dstBegin the start offset in the destination array.
840 * @exception IndexOutOfBoundsException If any of the following
842 * <ul><li><code>srcBegin</code> is negative.
843 * <li><code>srcBegin</code> is greater than <code>srcEnd</code>
844 * <li><code>srcEnd</code> is greater than the length of this
846 * <li><code>dstBegin</code> is negative
847 * <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
848 * <code>dst.length</code></ul>
850 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
852 throw new StringIndexOutOfBoundsException(srcBegin);
854 if (srcEnd > count) {
855 throw new StringIndexOutOfBoundsException(srcEnd);
857 if (srcBegin > srcEnd) {
858 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
860 arraycopy(value, offset + srcBegin, dst, dstBegin,
865 * Copies characters from this string into the destination byte array. Each
866 * byte receives the 8 low-order bits of the corresponding character. The
867 * eight high-order bits of each character are not copied and do not
868 * participate in the transfer in any way.
870 * <p> The first character to be copied is at index {@code srcBegin}; the
871 * last character to be copied is at index {@code srcEnd-1}. The total
872 * number of characters to be copied is {@code srcEnd-srcBegin}. The
873 * characters, converted to bytes, are copied into the subarray of {@code
874 * dst} starting at index {@code dstBegin} and ending at index:
877 * dstbegin + (srcEnd-srcBegin) - 1
878 * </pre></blockquote>
880 * @deprecated This method does not properly convert characters into
881 * bytes. As of JDK 1.1, the preferred way to do this is via the
882 * {@link #getBytes()} method, which uses the platform's default charset.
885 * Index of the first character in the string to copy
888 * Index after the last character in the string to copy
891 * The destination array
894 * The start offset in the destination array
896 * @throws IndexOutOfBoundsException
897 * If any of the following is true:
899 * <li> {@code srcBegin} is negative
900 * <li> {@code srcBegin} is greater than {@code srcEnd}
901 * <li> {@code srcEnd} is greater than the length of this String
902 * <li> {@code dstBegin} is negative
903 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
908 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
910 throw new StringIndexOutOfBoundsException(srcBegin);
912 if (srcEnd > count) {
913 throw new StringIndexOutOfBoundsException(srcEnd);
915 if (srcBegin > srcEnd) {
916 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
919 int n = offset + srcEnd;
920 int i = offset + srcBegin;
921 char[] val = value; /* avoid getfield opcode */
924 dst[j++] = (byte)val[i++];
929 * Encodes this {@code String} into a sequence of bytes using the named
930 * charset, storing the result into a new byte array.
932 * <p> The behavior of this method when this string cannot be encoded in
933 * the given charset is unspecified. The {@link
934 * java.nio.charset.CharsetEncoder} class should be used when more control
935 * over the encoding process is required.
938 * The name of a supported {@linkplain java.nio.charset.Charset
941 * @return The resultant byte array
943 * @throws UnsupportedEncodingException
944 * If the named charset is not supported
948 // public byte[] getBytes(String charsetName)
949 // throws UnsupportedEncodingException
951 // if (charsetName == null) throw new NullPointerException();
952 // return StringCoding.encode(charsetName, value, offset, count);
956 * Encodes this {@code String} into a sequence of bytes using the given
957 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
960 * <p> This method always replaces malformed-input and unmappable-character
961 * sequences with this charset's default replacement byte array. The
962 * {@link java.nio.charset.CharsetEncoder} class should be used when more
963 * control over the encoding process is required.
966 * The {@linkplain java.nio.charset.Charset} to be used to encode
969 * @return The resultant byte array
973 /* don't want dep on Charset
974 public byte[] getBytes(Charset charset) {
975 if (charset == null) throw new NullPointerException();
976 return StringCoding.encode(charset, value, offset, count);
981 * Encodes this {@code String} into a sequence of bytes using the
982 * platform's default charset, storing the result into a new byte array.
984 * <p> The behavior of this method when this string cannot be encoded in
985 * the default charset is unspecified. The {@link
986 * java.nio.charset.CharsetEncoder} class should be used when more control
987 * over the encoding process is required.
989 * @return The resultant byte array
993 public byte[] getBytes() {
994 byte[] arr = new byte[length()];
995 for (int i = 0; i < arr.length; i++) {
996 final char v = charAt(i);
1003 * Compares this string to the specified object. The result is {@code
1004 * true} if and only if the argument is not {@code null} and is a {@code
1005 * String} object that represents the same sequence of characters as this
1009 * The object to compare this {@code String} against
1011 * @return {@code true} if the given object represents a {@code String}
1012 * equivalent to this string, {@code false} otherwise
1014 * @see #compareTo(String)
1015 * @see #equalsIgnoreCase(String)
1017 public boolean equals(Object anObject) {
1018 if (this == anObject) {
1021 if (anObject instanceof String) {
1022 String anotherString = (String)anObject;
1024 if (n == anotherString.count) {
1026 char v2[] = anotherString.value;
1028 int j = anotherString.offset;
1030 if (v1[i++] != v2[j++])
1040 * Compares this string to the specified {@code StringBuffer}. The result
1041 * is {@code true} if and only if this {@code String} represents the same
1042 * sequence of characters as the specified {@code StringBuffer}.
1045 * The {@code StringBuffer} to compare this {@code String} against
1047 * @return {@code true} if this {@code String} represents the same
1048 * sequence of characters as the specified {@code StringBuffer},
1049 * {@code false} otherwise
1053 public boolean contentEquals(StringBuffer sb) {
1055 return contentEquals((CharSequence)sb);
1060 * Compares this string to the specified {@code CharSequence}. The result
1061 * is {@code true} if and only if this {@code String} represents the same
1062 * sequence of char values as the specified sequence.
1065 * The sequence to compare this {@code String} against
1067 * @return {@code true} if this {@code String} represents the same
1068 * sequence of char values as the specified sequence, {@code
1073 public boolean contentEquals(CharSequence cs) {
1074 if (count != cs.length())
1076 // Argument is a StringBuffer, StringBuilder
1077 if (cs instanceof AbstractStringBuilder) {
1079 char v2[] = ((AbstractStringBuilder)cs).getValue();
1084 if (v1[i++] != v2[j++])
1089 // Argument is a String
1090 if (cs.equals(this))
1092 // Argument is a generic CharSequence
1098 if (v1[i++] != cs.charAt(j++))
1105 * Compares this {@code String} to another {@code String}, ignoring case
1106 * considerations. Two strings are considered equal ignoring case if they
1107 * are of the same length and corresponding characters in the two strings
1108 * are equal ignoring case.
1110 * <p> Two characters {@code c1} and {@code c2} are considered the same
1111 * ignoring case if at least one of the following is true:
1113 * <li> The two characters are the same (as compared by the
1114 * {@code ==} operator)
1115 * <li> Applying the method {@link
1116 * java.lang.Character#toUpperCase(char)} to each character
1117 * produces the same result
1118 * <li> Applying the method {@link
1119 * java.lang.Character#toLowerCase(char)} to each character
1120 * produces the same result
1123 * @param anotherString
1124 * The {@code String} to compare this {@code String} against
1126 * @return {@code true} if the argument is not {@code null} and it
1127 * represents an equivalent {@code String} ignoring case; {@code
1130 * @see #equals(Object)
1132 public boolean equalsIgnoreCase(String anotherString) {
1133 return (this == anotherString) ? true :
1134 (anotherString != null) && (anotherString.count == count) &&
1135 regionMatches(true, 0, anotherString, 0, count);
1139 * Compares two strings lexicographically.
1140 * The comparison is based on the Unicode value of each character in
1141 * the strings. The character sequence represented by this
1142 * <code>String</code> object is compared lexicographically to the
1143 * character sequence represented by the argument string. The result is
1144 * a negative integer if this <code>String</code> object
1145 * lexicographically precedes the argument string. The result is a
1146 * positive integer if this <code>String</code> object lexicographically
1147 * follows the argument string. The result is zero if the strings
1148 * are equal; <code>compareTo</code> returns <code>0</code> exactly when
1149 * the {@link #equals(Object)} method would return <code>true</code>.
1151 * This is the definition of lexicographic ordering. If two strings are
1152 * different, then either they have different characters at some index
1153 * that is a valid index for both strings, or their lengths are different,
1154 * or both. If they have different characters at one or more index
1155 * positions, let <i>k</i> be the smallest such index; then the string
1156 * whose character at position <i>k</i> has the smaller value, as
1157 * determined by using the < operator, lexicographically precedes the
1158 * other string. In this case, <code>compareTo</code> returns the
1159 * difference of the two character values at position <code>k</code> in
1160 * the two string -- that is, the value:
1162 * this.charAt(k)-anotherString.charAt(k)
1163 * </pre></blockquote>
1164 * If there is no index position at which they differ, then the shorter
1165 * string lexicographically precedes the longer string. In this case,
1166 * <code>compareTo</code> returns the difference of the lengths of the
1167 * strings -- that is, the value:
1169 * this.length()-anotherString.length()
1170 * </pre></blockquote>
1172 * @param anotherString the <code>String</code> to be compared.
1173 * @return the value <code>0</code> if the argument string is equal to
1174 * this string; a value less than <code>0</code> if this string
1175 * is lexicographically less than the string argument; and a
1176 * value greater than <code>0</code> if this string is
1177 * lexicographically greater than the string argument.
1179 public int compareTo(String anotherString) {
1181 int len2 = anotherString.count;
1182 int n = Math.min(len1, len2);
1184 char v2[] = anotherString.value;
1186 int j = anotherString.offset;
1212 * A Comparator that orders <code>String</code> objects as by
1213 * <code>compareToIgnoreCase</code>. This comparator is serializable.
1215 * Note that this Comparator does <em>not</em> take locale into account,
1216 * and will result in an unsatisfactory ordering for certain locales.
1217 * The java.text package provides <em>Collators</em> to allow
1218 * locale-sensitive ordering.
1220 * @see java.text.Collator#compare(String, String)
1223 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1224 = new CaseInsensitiveComparator();
1225 private static class CaseInsensitiveComparator
1226 implements Comparator<String>, java.io.Serializable {
1227 // use serialVersionUID from JDK 1.2.2 for interoperability
1228 private static final long serialVersionUID = 8575799808933029326L;
1230 public int compare(String s1, String s2) {
1231 int n1 = s1.length();
1232 int n2 = s2.length();
1233 int min = Math.min(n1, n2);
1234 for (int i = 0; i < min; i++) {
1235 char c1 = s1.charAt(i);
1236 char c2 = s2.charAt(i);
1238 c1 = Character.toUpperCase(c1);
1239 c2 = Character.toUpperCase(c2);
1241 c1 = Character.toLowerCase(c1);
1242 c2 = Character.toLowerCase(c2);
1244 // No overflow because of numeric promotion
1255 * Compares two strings lexicographically, ignoring case
1256 * differences. This method returns an integer whose sign is that of
1257 * calling <code>compareTo</code> with normalized versions of the strings
1258 * where case differences have been eliminated by calling
1259 * <code>Character.toLowerCase(Character.toUpperCase(character))</code> on
1262 * Note that this method does <em>not</em> take locale into account,
1263 * and will result in an unsatisfactory ordering for certain locales.
1264 * The java.text package provides <em>collators</em> to allow
1265 * locale-sensitive ordering.
1267 * @param str the <code>String</code> to be compared.
1268 * @return a negative integer, zero, or a positive integer as the
1269 * specified String is greater than, equal to, or less
1270 * than this String, ignoring case considerations.
1271 * @see java.text.Collator#compare(String, String)
1274 public int compareToIgnoreCase(String str) {
1275 return CASE_INSENSITIVE_ORDER.compare(this, str);
1279 * Tests if two string regions are equal.
1281 * A substring of this <tt>String</tt> object is compared to a substring
1282 * of the argument other. The result is true if these substrings
1283 * represent identical character sequences. The substring of this
1284 * <tt>String</tt> object to be compared begins at index <tt>toffset</tt>
1285 * and has length <tt>len</tt>. The substring of other to be compared
1286 * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The
1287 * result is <tt>false</tt> if and only if at least one of the following
1289 * <ul><li><tt>toffset</tt> is negative.
1290 * <li><tt>ooffset</tt> is negative.
1291 * <li><tt>toffset+len</tt> is greater than the length of this
1292 * <tt>String</tt> object.
1293 * <li><tt>ooffset+len</tt> is greater than the length of the other
1295 * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt>
1297 * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt>
1300 * @param toffset the starting offset of the subregion in this string.
1301 * @param other the string argument.
1302 * @param ooffset the starting offset of the subregion in the string
1304 * @param len the number of characters to compare.
1305 * @return <code>true</code> if the specified subregion of this string
1306 * exactly matches the specified subregion of the string argument;
1307 * <code>false</code> otherwise.
1309 public boolean regionMatches(int toffset, String other, int ooffset,
1312 int to = offset + toffset;
1313 char pa[] = other.value;
1314 int po = other.offset + ooffset;
1315 // Note: toffset, ooffset, or len might be near -1>>>1.
1316 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len)
1317 || (ooffset > (long)other.count - len)) {
1321 if (ta[to++] != pa[po++]) {
1329 * Tests if two string regions are equal.
1331 * A substring of this <tt>String</tt> object is compared to a substring
1332 * of the argument <tt>other</tt>. The result is <tt>true</tt> if these
1333 * substrings represent character sequences that are the same, ignoring
1334 * case if and only if <tt>ignoreCase</tt> is true. The substring of
1335 * this <tt>String</tt> object to be compared begins at index
1336 * <tt>toffset</tt> and has length <tt>len</tt>. The substring of
1337 * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and
1338 * has length <tt>len</tt>. The result is <tt>false</tt> if and only if
1339 * at least one of the following is true:
1340 * <ul><li><tt>toffset</tt> is negative.
1341 * <li><tt>ooffset</tt> is negative.
1342 * <li><tt>toffset+len</tt> is greater than the length of this
1343 * <tt>String</tt> object.
1344 * <li><tt>ooffset+len</tt> is greater than the length of the other
1346 * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative
1347 * integer <i>k</i> less than <tt>len</tt> such that:
1349 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1350 * </pre></blockquote>
1351 * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative
1352 * integer <i>k</i> less than <tt>len</tt> such that:
1354 * Character.toLowerCase(this.charAt(toffset+k)) !=
1355 Character.toLowerCase(other.charAt(ooffset+k))
1356 * </pre></blockquote>
1359 * Character.toUpperCase(this.charAt(toffset+k)) !=
1360 * Character.toUpperCase(other.charAt(ooffset+k))
1361 * </pre></blockquote>
1364 * @param ignoreCase if <code>true</code>, ignore case when comparing
1366 * @param toffset the starting offset of the subregion in this
1368 * @param other the string argument.
1369 * @param ooffset the starting offset of the subregion in the string
1371 * @param len the number of characters to compare.
1372 * @return <code>true</code> if the specified subregion of this string
1373 * matches the specified subregion of the string argument;
1374 * <code>false</code> otherwise. Whether the matching is exact
1375 * or case insensitive depends on the <code>ignoreCase</code>
1378 public boolean regionMatches(boolean ignoreCase, int toffset,
1379 String other, int ooffset, int len) {
1381 int to = offset + toffset;
1382 char pa[] = other.value;
1383 int po = other.offset + ooffset;
1384 // Note: toffset, ooffset, or len might be near -1>>>1.
1385 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) ||
1386 (ooffset > (long)other.count - len)) {
1396 // If characters don't match but case may be ignored,
1397 // try converting both characters to uppercase.
1398 // If the results match, then the comparison scan should
1400 char u1 = Character.toUpperCase(c1);
1401 char u2 = Character.toUpperCase(c2);
1405 // Unfortunately, conversion to uppercase does not work properly
1406 // for the Georgian alphabet, which has strange rules about case
1407 // conversion. So we need to make one last check before
1409 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1419 * Tests if the substring of this string beginning at the
1420 * specified index starts with the specified prefix.
1422 * @param prefix the prefix.
1423 * @param toffset where to begin looking in this string.
1424 * @return <code>true</code> if the character sequence represented by the
1425 * argument is a prefix of the substring of this object starting
1426 * at index <code>toffset</code>; <code>false</code> otherwise.
1427 * The result is <code>false</code> if <code>toffset</code> is
1428 * negative or greater than the length of this
1429 * <code>String</code> object; otherwise the result is the same
1430 * as the result of the expression
1432 * this.substring(toffset).startsWith(prefix)
1435 public boolean startsWith(String prefix, int toffset) {
1437 int to = offset + toffset;
1438 char pa[] = prefix.value;
1439 int po = prefix.offset;
1440 int pc = prefix.count;
1441 // Note: toffset might be near -1>>>1.
1442 if ((toffset < 0) || (toffset > count - pc)) {
1446 if (ta[to++] != pa[po++]) {
1454 * Tests if this string starts with the specified prefix.
1456 * @param prefix the prefix.
1457 * @return <code>true</code> if the character sequence represented by the
1458 * argument is a prefix of the character sequence represented by
1459 * this string; <code>false</code> otherwise.
1460 * Note also that <code>true</code> will be returned if the
1461 * argument is an empty string or is equal to this
1462 * <code>String</code> object as determined by the
1463 * {@link #equals(Object)} method.
1466 public boolean startsWith(String prefix) {
1467 return startsWith(prefix, 0);
1471 * Tests if this string ends with the specified suffix.
1473 * @param suffix the suffix.
1474 * @return <code>true</code> if the character sequence represented by the
1475 * argument is a suffix of the character sequence represented by
1476 * this object; <code>false</code> otherwise. Note that the
1477 * result will be <code>true</code> if the argument is the
1478 * empty string or is equal to this <code>String</code> object
1479 * as determined by the {@link #equals(Object)} method.
1481 public boolean endsWith(String suffix) {
1482 return startsWith(suffix, count - suffix.count);
1486 * Returns a hash code for this string. The hash code for a
1487 * <code>String</code> object is computed as
1489 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1490 * </pre></blockquote>
1491 * using <code>int</code> arithmetic, where <code>s[i]</code> is the
1492 * <i>i</i>th character of the string, <code>n</code> is the length of
1493 * the string, and <code>^</code> indicates exponentiation.
1494 * (The hash value of the empty string is zero.)
1496 * @return a hash code value for this object.
1498 public int hashCode() {
1500 if (h == 0 && count > 0) {
1505 for (int i = 0; i < len; i++) {
1506 h = 31*h + val[off++];
1514 * Returns the index within this string of the first occurrence of
1515 * the specified character. If a character with value
1516 * <code>ch</code> occurs in the character sequence represented by
1517 * this <code>String</code> object, then the index (in Unicode
1518 * code units) of the first such occurrence is returned. For
1519 * values of <code>ch</code> in the range from 0 to 0xFFFF
1520 * (inclusive), this is the smallest value <i>k</i> such that:
1522 * this.charAt(<i>k</i>) == ch
1523 * </pre></blockquote>
1524 * is true. For other values of <code>ch</code>, it is the
1525 * smallest value <i>k</i> such that:
1527 * this.codePointAt(<i>k</i>) == ch
1528 * </pre></blockquote>
1529 * is true. In either case, if no such character occurs in this
1530 * string, then <code>-1</code> is returned.
1532 * @param ch a character (Unicode code point).
1533 * @return the index of the first occurrence of the character in the
1534 * character sequence represented by this object, or
1535 * <code>-1</code> if the character does not occur.
1537 public int indexOf(int ch) {
1538 return indexOf(ch, 0);
1542 * Returns the index within this string of the first occurrence of the
1543 * specified character, starting the search at the specified index.
1545 * If a character with value <code>ch</code> occurs in the
1546 * character sequence represented by this <code>String</code>
1547 * object at an index no smaller than <code>fromIndex</code>, then
1548 * the index of the first such occurrence is returned. For values
1549 * of <code>ch</code> in the range from 0 to 0xFFFF (inclusive),
1550 * this is the smallest value <i>k</i> such that:
1552 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1553 * </pre></blockquote>
1554 * is true. For other values of <code>ch</code>, it is the
1555 * smallest value <i>k</i> such that:
1557 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1558 * </pre></blockquote>
1559 * is true. In either case, if no such character occurs in this
1560 * string at or after position <code>fromIndex</code>, then
1561 * <code>-1</code> is returned.
1564 * There is no restriction on the value of <code>fromIndex</code>. If it
1565 * is negative, it has the same effect as if it were zero: this entire
1566 * string may be searched. If it is greater than the length of this
1567 * string, it has the same effect as if it were equal to the length of
1568 * this string: <code>-1</code> is returned.
1570 * <p>All indices are specified in <code>char</code> values
1571 * (Unicode code units).
1573 * @param ch a character (Unicode code point).
1574 * @param fromIndex the index to start the search from.
1575 * @return the index of the first occurrence of the character in the
1576 * character sequence represented by this object that is greater
1577 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1578 * if the character does not occur.
1580 public int indexOf(int ch, int fromIndex) {
1581 if (fromIndex < 0) {
1583 } else if (fromIndex >= count) {
1584 // Note: fromIndex might be near -1>>>1.
1588 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1589 // handle most cases here (ch is a BMP code point or a
1590 // negative value (invalid code point))
1591 final char[] value = this.value;
1592 final int offset = this.offset;
1593 final int max = offset + count;
1594 for (int i = offset + fromIndex; i < max ; i++) {
1595 if (value[i] == ch) {
1601 return indexOfSupplementary(ch, fromIndex);
1606 * Handles (rare) calls of indexOf with a supplementary character.
1608 private int indexOfSupplementary(int ch, int fromIndex) {
1609 if (Character.isValidCodePoint(ch)) {
1610 final char[] value = this.value;
1611 final int offset = this.offset;
1612 final char hi = Character.highSurrogate(ch);
1613 final char lo = Character.lowSurrogate(ch);
1614 final int max = offset + count - 1;
1615 for (int i = offset + fromIndex; i < max; i++) {
1616 if (value[i] == hi && value[i+1] == lo) {
1625 * Returns the index within this string of the last occurrence of
1626 * the specified character. For values of <code>ch</code> in the
1627 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1628 * units) returned is the largest value <i>k</i> such that:
1630 * this.charAt(<i>k</i>) == ch
1631 * </pre></blockquote>
1632 * is true. For other values of <code>ch</code>, it is the
1633 * largest value <i>k</i> such that:
1635 * this.codePointAt(<i>k</i>) == ch
1636 * </pre></blockquote>
1637 * is true. In either case, if no such character occurs in this
1638 * string, then <code>-1</code> is returned. The
1639 * <code>String</code> is searched backwards starting at the last
1642 * @param ch a character (Unicode code point).
1643 * @return the index of the last occurrence of the character in the
1644 * character sequence represented by this object, or
1645 * <code>-1</code> if the character does not occur.
1647 public int lastIndexOf(int ch) {
1648 return lastIndexOf(ch, count - 1);
1652 * Returns the index within this string of the last occurrence of
1653 * the specified character, searching backward starting at the
1654 * specified index. For values of <code>ch</code> in the range
1655 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1656 * value <i>k</i> such that:
1658 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1659 * </pre></blockquote>
1660 * is true. For other values of <code>ch</code>, it is the
1661 * largest value <i>k</i> such that:
1663 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1664 * </pre></blockquote>
1665 * is true. In either case, if no such character occurs in this
1666 * string at or before position <code>fromIndex</code>, then
1667 * <code>-1</code> is returned.
1669 * <p>All indices are specified in <code>char</code> values
1670 * (Unicode code units).
1672 * @param ch a character (Unicode code point).
1673 * @param fromIndex the index to start the search from. There is no
1674 * restriction on the value of <code>fromIndex</code>. If it is
1675 * greater than or equal to the length of this string, it has
1676 * the same effect as if it were equal to one less than the
1677 * length of this string: this entire string may be searched.
1678 * If it is negative, it has the same effect as if it were -1:
1680 * @return the index of the last occurrence of the character in the
1681 * character sequence represented by this object that is less
1682 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1683 * if the character does not occur before that point.
1685 public int lastIndexOf(int ch, int fromIndex) {
1686 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1687 // handle most cases here (ch is a BMP code point or a
1688 // negative value (invalid code point))
1689 final char[] value = this.value;
1690 final int offset = this.offset;
1691 int i = offset + Math.min(fromIndex, count - 1);
1692 for (; i >= offset ; i--) {
1693 if (value[i] == ch) {
1699 return lastIndexOfSupplementary(ch, fromIndex);
1704 * Handles (rare) calls of lastIndexOf with a supplementary character.
1706 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1707 if (Character.isValidCodePoint(ch)) {
1708 final char[] value = this.value;
1709 final int offset = this.offset;
1710 char hi = Character.highSurrogate(ch);
1711 char lo = Character.lowSurrogate(ch);
1712 int i = offset + Math.min(fromIndex, count - 2);
1713 for (; i >= offset; i--) {
1714 if (value[i] == hi && value[i+1] == lo) {
1723 * Returns the index within this string of the first occurrence of the
1724 * specified substring.
1726 * <p>The returned index is the smallest value <i>k</i> for which:
1728 * this.startsWith(str, <i>k</i>)
1729 * </pre></blockquote>
1730 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1732 * @param str the substring to search for.
1733 * @return the index of the first occurrence of the specified substring,
1734 * or {@code -1} if there is no such occurrence.
1736 public int indexOf(String str) {
1737 return indexOf(str, 0);
1741 * Returns the index within this string of the first occurrence of the
1742 * specified substring, starting at the specified index.
1744 * <p>The returned index is the smallest value <i>k</i> for which:
1746 * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>)
1747 * </pre></blockquote>
1748 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1750 * @param str the substring to search for.
1751 * @param fromIndex the index from which to start the search.
1752 * @return the index of the first occurrence of the specified substring,
1753 * starting at the specified index,
1754 * or {@code -1} if there is no such occurrence.
1756 public int indexOf(String str, int fromIndex) {
1757 return indexOf(value, offset, count,
1758 str.value, str.offset, str.count, fromIndex);
1762 * Code shared by String and StringBuffer to do searches. The
1763 * source is the character array being searched, and the target
1764 * is the string being searched for.
1766 * @param source the characters being searched.
1767 * @param sourceOffset offset of the source string.
1768 * @param sourceCount count of the source string.
1769 * @param target the characters being searched for.
1770 * @param targetOffset offset of the target string.
1771 * @param targetCount count of the target string.
1772 * @param fromIndex the index to begin searching from.
1774 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1775 char[] target, int targetOffset, int targetCount,
1777 if (fromIndex >= sourceCount) {
1778 return (targetCount == 0 ? sourceCount : -1);
1780 if (fromIndex < 0) {
1783 if (targetCount == 0) {
1787 char first = target[targetOffset];
1788 int max = sourceOffset + (sourceCount - targetCount);
1790 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1791 /* Look for first character. */
1792 if (source[i] != first) {
1793 while (++i <= max && source[i] != first);
1796 /* Found first character, now look at the rest of v2 */
1799 int end = j + targetCount - 1;
1800 for (int k = targetOffset + 1; j < end && source[j] ==
1801 target[k]; j++, k++);
1804 /* Found whole string. */
1805 return i - sourceOffset;
1813 * Returns the index within this string of the last occurrence of the
1814 * specified substring. The last occurrence of the empty string ""
1815 * is considered to occur at the index value {@code this.length()}.
1817 * <p>The returned index is the largest value <i>k</i> for which:
1819 * this.startsWith(str, <i>k</i>)
1820 * </pre></blockquote>
1821 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1823 * @param str the substring to search for.
1824 * @return the index of the last occurrence of the specified substring,
1825 * or {@code -1} if there is no such occurrence.
1827 public int lastIndexOf(String str) {
1828 return lastIndexOf(str, count);
1832 * Returns the index within this string of the last occurrence of the
1833 * specified substring, searching backward starting at the specified index.
1835 * <p>The returned index is the largest value <i>k</i> for which:
1837 * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>)
1838 * </pre></blockquote>
1839 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1841 * @param str the substring to search for.
1842 * @param fromIndex the index to start the search from.
1843 * @return the index of the last occurrence of the specified substring,
1844 * searching backward from the specified index,
1845 * or {@code -1} if there is no such occurrence.
1847 public int lastIndexOf(String str, int fromIndex) {
1848 return lastIndexOf(value, offset, count,
1849 str.value, str.offset, str.count, fromIndex);
1853 * Code shared by String and StringBuffer to do searches. The
1854 * source is the character array being searched, and the target
1855 * is the string being searched for.
1857 * @param source the characters being searched.
1858 * @param sourceOffset offset of the source string.
1859 * @param sourceCount count of the source string.
1860 * @param target the characters being searched for.
1861 * @param targetOffset offset of the target string.
1862 * @param targetCount count of the target string.
1863 * @param fromIndex the index to begin searching from.
1865 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1866 char[] target, int targetOffset, int targetCount,
1869 * Check arguments; return immediately where possible. For
1870 * consistency, don't check for null str.
1872 int rightIndex = sourceCount - targetCount;
1873 if (fromIndex < 0) {
1876 if (fromIndex > rightIndex) {
1877 fromIndex = rightIndex;
1879 /* Empty string always matches. */
1880 if (targetCount == 0) {
1884 int strLastIndex = targetOffset + targetCount - 1;
1885 char strLastChar = target[strLastIndex];
1886 int min = sourceOffset + targetCount - 1;
1887 int i = min + fromIndex;
1889 startSearchForLastChar:
1891 while (i >= min && source[i] != strLastChar) {
1898 int start = j - (targetCount - 1);
1899 int k = strLastIndex - 1;
1902 if (source[j--] != target[k--]) {
1904 continue startSearchForLastChar;
1907 return start - sourceOffset + 1;
1912 * Returns a new string that is a substring of this string. The
1913 * substring begins with the character at the specified index and
1914 * extends to the end of this string. <p>
1917 * "unhappy".substring(2) returns "happy"
1918 * "Harbison".substring(3) returns "bison"
1919 * "emptiness".substring(9) returns "" (an empty string)
1920 * </pre></blockquote>
1922 * @param beginIndex the beginning index, inclusive.
1923 * @return the specified substring.
1924 * @exception IndexOutOfBoundsException if
1925 * <code>beginIndex</code> is negative or larger than the
1926 * length of this <code>String</code> object.
1928 public String substring(int beginIndex) {
1929 return substring(beginIndex, count);
1933 * Returns a new string that is a substring of this string. The
1934 * substring begins at the specified <code>beginIndex</code> and
1935 * extends to the character at index <code>endIndex - 1</code>.
1936 * Thus the length of the substring is <code>endIndex-beginIndex</code>.
1940 * "hamburger".substring(4, 8) returns "urge"
1941 * "smiles".substring(1, 5) returns "mile"
1942 * </pre></blockquote>
1944 * @param beginIndex the beginning index, inclusive.
1945 * @param endIndex the ending index, exclusive.
1946 * @return the specified substring.
1947 * @exception IndexOutOfBoundsException if the
1948 * <code>beginIndex</code> is negative, or
1949 * <code>endIndex</code> is larger than the length of
1950 * this <code>String</code> object, or
1951 * <code>beginIndex</code> is larger than
1952 * <code>endIndex</code>.
1954 public String substring(int beginIndex, int endIndex) {
1955 if (beginIndex < 0) {
1956 throw new StringIndexOutOfBoundsException(beginIndex);
1958 if (endIndex > count) {
1959 throw new StringIndexOutOfBoundsException(endIndex);
1961 if (beginIndex > endIndex) {
1962 throw new StringIndexOutOfBoundsException(endIndex - beginIndex);
1964 return ((beginIndex == 0) && (endIndex == count)) ? this :
1965 new String(offset + beginIndex, endIndex - beginIndex, value);
1969 * Returns a new character sequence that is a subsequence of this sequence.
1971 * <p> An invocation of this method of the form
1974 * str.subSequence(begin, end)</pre></blockquote>
1976 * behaves in exactly the same way as the invocation
1979 * str.substring(begin, end)</pre></blockquote>
1981 * This method is defined so that the <tt>String</tt> class can implement
1982 * the {@link CharSequence} interface. </p>
1984 * @param beginIndex the begin index, inclusive.
1985 * @param endIndex the end index, exclusive.
1986 * @return the specified subsequence.
1988 * @throws IndexOutOfBoundsException
1989 * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative,
1990 * if <tt>endIndex</tt> is greater than <tt>length()</tt>,
1991 * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt>
1996 public CharSequence subSequence(int beginIndex, int endIndex) {
1997 return this.substring(beginIndex, endIndex);
2001 * Concatenates the specified string to the end of this string.
2003 * If the length of the argument string is <code>0</code>, then this
2004 * <code>String</code> object is returned. Otherwise, a new
2005 * <code>String</code> object is created, representing a character
2006 * sequence that is the concatenation of the character sequence
2007 * represented by this <code>String</code> object and the character
2008 * sequence represented by the argument string.<p>
2011 * "cares".concat("s") returns "caress"
2012 * "to".concat("get").concat("her") returns "together"
2013 * </pre></blockquote>
2015 * @param str the <code>String</code> that is concatenated to the end
2016 * of this <code>String</code>.
2017 * @return a string that represents the concatenation of this object's
2018 * characters followed by the string argument's characters.
2020 public String concat(String str) {
2021 int otherLen = str.length();
2022 if (otherLen == 0) {
2025 char buf[] = new char[count + otherLen];
2026 getChars(0, count, buf, 0);
2027 str.getChars(0, otherLen, buf, count);
2028 return new String(0, count + otherLen, buf);
2032 * Returns a new string resulting from replacing all occurrences of
2033 * <code>oldChar</code> in this string with <code>newChar</code>.
2035 * If the character <code>oldChar</code> does not occur in the
2036 * character sequence represented by this <code>String</code> object,
2037 * then a reference to this <code>String</code> object is returned.
2038 * Otherwise, a new <code>String</code> object is created that
2039 * represents a character sequence identical to the character sequence
2040 * represented by this <code>String</code> object, except that every
2041 * occurrence of <code>oldChar</code> is replaced by an occurrence
2042 * of <code>newChar</code>.
2046 * "mesquite in your cellar".replace('e', 'o')
2047 * returns "mosquito in your collar"
2048 * "the war of baronets".replace('r', 'y')
2049 * returns "the way of bayonets"
2050 * "sparring with a purple porpoise".replace('p', 't')
2051 * returns "starring with a turtle tortoise"
2052 * "JonL".replace('q', 'x') returns "JonL" (no change)
2053 * </pre></blockquote>
2055 * @param oldChar the old character.
2056 * @param newChar the new character.
2057 * @return a string derived from this string by replacing every
2058 * occurrence of <code>oldChar</code> with <code>newChar</code>.
2060 public String replace(char oldChar, char newChar) {
2061 if (oldChar != newChar) {
2064 char[] val = value; /* avoid getfield opcode */
2065 int off = offset; /* avoid getfield opcode */
2068 if (val[off + i] == oldChar) {
2073 char buf[] = new char[len];
2074 for (int j = 0 ; j < i ; j++) {
2075 buf[j] = val[off+j];
2078 char c = val[off + i];
2079 buf[i] = (c == oldChar) ? newChar : c;
2082 return new String(0, len, buf);
2089 * Tells whether or not this string matches the given <a
2090 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2092 * <p> An invocation of this method of the form
2093 * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the
2094 * same result as the expression
2096 * <blockquote><tt> {@link java.util.regex.Pattern}.{@link
2097 * java.util.regex.Pattern#matches(String,CharSequence)
2098 * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote>
2101 * the regular expression to which this string is to be matched
2103 * @return <tt>true</tt> if, and only if, this string matches the
2104 * given regular expression
2106 * @throws PatternSyntaxException
2107 * if the regular expression's syntax is invalid
2109 * @see java.util.regex.Pattern
2114 public boolean matches(String regex) {
2115 throw new UnsupportedOperationException();
2119 * Returns true if and only if this string contains the specified
2120 * sequence of char values.
2122 * @param s the sequence to search for
2123 * @return true if this string contains <code>s</code>, false otherwise
2124 * @throws NullPointerException if <code>s</code> is <code>null</code>
2127 public boolean contains(CharSequence s) {
2128 return indexOf(s.toString()) > -1;
2132 * Replaces the first substring of this string that matches the given <a
2133 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2134 * given replacement.
2136 * <p> An invocation of this method of the form
2137 * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2138 * yields exactly the same result as the expression
2141 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2142 * compile}(</tt><i>regex</i><tt>).{@link
2143 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2144 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst
2145 * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote>
2148 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2149 * replacement string may cause the results to be different than if it were
2150 * being treated as a literal replacement string; see
2151 * {@link java.util.regex.Matcher#replaceFirst}.
2152 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2153 * meaning of these characters, if desired.
2156 * the regular expression to which this string is to be matched
2157 * @param replacement
2158 * the string to be substituted for the first match
2160 * @return The resulting <tt>String</tt>
2162 * @throws PatternSyntaxException
2163 * if the regular expression's syntax is invalid
2165 * @see java.util.regex.Pattern
2170 public String replaceFirst(String regex, String replacement) {
2171 throw new UnsupportedOperationException();
2175 * Replaces each substring of this string that matches the given <a
2176 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2177 * given replacement.
2179 * <p> An invocation of this method of the form
2180 * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2181 * yields exactly the same result as the expression
2184 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2185 * compile}(</tt><i>regex</i><tt>).{@link
2186 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2187 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll
2188 * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote>
2191 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2192 * replacement string may cause the results to be different than if it were
2193 * being treated as a literal replacement string; see
2194 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2195 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2196 * meaning of these characters, if desired.
2199 * the regular expression to which this string is to be matched
2200 * @param replacement
2201 * the string to be substituted for each match
2203 * @return The resulting <tt>String</tt>
2205 * @throws PatternSyntaxException
2206 * if the regular expression's syntax is invalid
2208 * @see java.util.regex.Pattern
2213 public String replaceAll(String regex, String replacement) {
2214 throw new UnsupportedOperationException();
2218 * Replaces each substring of this string that matches the literal target
2219 * sequence with the specified literal replacement sequence. The
2220 * replacement proceeds from the beginning of the string to the end, for
2221 * example, replacing "aa" with "b" in the string "aaa" will result in
2222 * "ba" rather than "ab".
2224 * @param target The sequence of char values to be replaced
2225 * @param replacement The replacement sequence of char values
2226 * @return The resulting string
2227 * @throws NullPointerException if <code>target</code> or
2228 * <code>replacement</code> is <code>null</code>.
2231 public String replace(CharSequence target, CharSequence replacement) {
2232 throw new UnsupportedOperationException("This one should be supported, but without dep on rest of regexp");
2236 * Splits this string around matches of the given
2237 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2239 * <p> The array returned by this method contains each substring of this
2240 * string that is terminated by another substring that matches the given
2241 * expression or is terminated by the end of the string. The substrings in
2242 * the array are in the order in which they occur in this string. If the
2243 * expression does not match any part of the input then the resulting array
2244 * has just one element, namely this string.
2246 * <p> The <tt>limit</tt> parameter controls the number of times the
2247 * pattern is applied and therefore affects the length of the resulting
2248 * array. If the limit <i>n</i> is greater than zero then the pattern
2249 * will be applied at most <i>n</i> - 1 times, the array's
2250 * length will be no greater than <i>n</i>, and the array's last entry
2251 * will contain all input beyond the last matched delimiter. If <i>n</i>
2252 * is non-positive then the pattern will be applied as many times as
2253 * possible and the array can have any length. If <i>n</i> is zero then
2254 * the pattern will be applied as many times as possible, the array can
2255 * have any length, and trailing empty strings will be discarded.
2257 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the
2258 * following results with these parameters:
2260 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2266 * <tr><td align=center>:</td>
2267 * <td align=center>2</td>
2268 * <td><tt>{ "boo", "and:foo" }</tt></td></tr>
2269 * <tr><td align=center>:</td>
2270 * <td align=center>5</td>
2271 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2272 * <tr><td align=center>:</td>
2273 * <td align=center>-2</td>
2274 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2275 * <tr><td align=center>o</td>
2276 * <td align=center>5</td>
2277 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2278 * <tr><td align=center>o</td>
2279 * <td align=center>-2</td>
2280 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2281 * <tr><td align=center>o</td>
2282 * <td align=center>0</td>
2283 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2284 * </table></blockquote>
2286 * <p> An invocation of this method of the form
2287 * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt>
2288 * yields the same result as the expression
2291 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2292 * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link
2293 * java.util.regex.Pattern#split(java.lang.CharSequence,int)
2294 * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt>
2299 * the delimiting regular expression
2302 * the result threshold, as described above
2304 * @return the array of strings computed by splitting this string
2305 * around matches of the given regular expression
2307 * @throws PatternSyntaxException
2308 * if the regular expression's syntax is invalid
2310 * @see java.util.regex.Pattern
2315 public String[] split(String regex, int limit) {
2316 throw new UnsupportedOperationException("Needs regexp");
2320 * Splits this string around matches of the given <a
2321 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2323 * <p> This method works as if by invoking the two-argument {@link
2324 * #split(String, int) split} method with the given expression and a limit
2325 * argument of zero. Trailing empty strings are therefore not included in
2326 * the resulting array.
2328 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the following
2329 * results with these expressions:
2331 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2336 * <tr><td align=center>:</td>
2337 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2338 * <tr><td align=center>o</td>
2339 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2340 * </table></blockquote>
2344 * the delimiting regular expression
2346 * @return the array of strings computed by splitting this string
2347 * around matches of the given regular expression
2349 * @throws PatternSyntaxException
2350 * if the regular expression's syntax is invalid
2352 * @see java.util.regex.Pattern
2357 public String[] split(String regex) {
2358 return split(regex, 0);
2362 * Converts all of the characters in this <code>String</code> to lower
2363 * case using the rules of the given <code>Locale</code>. Case mapping is based
2364 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2365 * class. Since case mappings are not always 1:1 char mappings, the resulting
2366 * <code>String</code> may be a different length than the original <code>String</code>.
2368 * Examples of lowercase mappings are in the following table:
2369 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2371 * <th>Language Code of Locale</th>
2372 * <th>Upper Case</th>
2373 * <th>Lower Case</th>
2374 * <th>Description</th>
2377 * <td>tr (Turkish)</td>
2378 * <td>\u0130</td>
2379 * <td>\u0069</td>
2380 * <td>capital letter I with dot above -> small letter i</td>
2383 * <td>tr (Turkish)</td>
2384 * <td>\u0049</td>
2385 * <td>\u0131</td>
2386 * <td>capital letter I -> small letter dotless i </td>
2390 * <td>French Fries</td>
2391 * <td>french fries</td>
2392 * <td>lowercased all chars in String</td>
2396 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2397 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2398 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2399 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2400 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2401 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2402 * <td>lowercased all chars in String</td>
2406 * @param locale use the case transformation rules for this locale
2407 * @return the <code>String</code>, converted to lowercase.
2408 * @see java.lang.String#toLowerCase()
2409 * @see java.lang.String#toUpperCase()
2410 * @see java.lang.String#toUpperCase(Locale)
2413 // public String toLowerCase(Locale locale) {
2414 // if (locale == null) {
2415 // throw new NullPointerException();
2420 // /* Now check if there are any characters that need to be changed. */
2422 // for (firstUpper = 0 ; firstUpper < count; ) {
2423 // char c = value[offset+firstUpper];
2424 // if ((c >= Character.MIN_HIGH_SURROGATE) &&
2425 // (c <= Character.MAX_HIGH_SURROGATE)) {
2426 // int supplChar = codePointAt(firstUpper);
2427 // if (supplChar != Character.toLowerCase(supplChar)) {
2430 // firstUpper += Character.charCount(supplChar);
2432 // if (c != Character.toLowerCase(c)) {
2441 // char[] result = new char[count];
2442 // int resultOffset = 0; /* result may grow, so i+resultOffset
2443 // * is the write location in result */
2445 // /* Just copy the first few lowerCase characters. */
2446 // arraycopy(value, offset, result, 0, firstUpper);
2448 // String lang = locale.getLanguage();
2449 // boolean localeDependent =
2450 // (lang == "tr" || lang == "az" || lang == "lt");
2451 // char[] lowerCharArray;
2455 // for (int i = firstUpper; i < count; i += srcCount) {
2456 // srcChar = (int)value[offset+i];
2457 // if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2458 // (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2459 // srcChar = codePointAt(i);
2460 // srcCount = Character.charCount(srcChar);
2464 // if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2465 // lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2466 // } else if (srcChar == '\u0130') { // LATIN CAPITAL LETTER I DOT
2467 // lowerChar = Character.ERROR;
2469 // lowerChar = Character.toLowerCase(srcChar);
2471 // if ((lowerChar == Character.ERROR) ||
2472 // (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2473 // if (lowerChar == Character.ERROR) {
2474 // if (!localeDependent && srcChar == '\u0130') {
2476 // ConditionalSpecialCasing.toLowerCaseCharArray(this, i, Locale.ENGLISH);
2479 // ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2481 // } else if (srcCount == 2) {
2482 // resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount;
2485 // lowerCharArray = Character.toChars(lowerChar);
2488 // /* Grow result if needed */
2489 // int mapLen = lowerCharArray.length;
2490 // if (mapLen > srcCount) {
2491 // char[] result2 = new char[result.length + mapLen - srcCount];
2492 // arraycopy(result, 0, result2, 0,
2493 // i + resultOffset);
2494 // result = result2;
2496 // for (int x=0; x<mapLen; ++x) {
2497 // result[i+resultOffset+x] = lowerCharArray[x];
2499 // resultOffset += (mapLen - srcCount);
2501 // result[i+resultOffset] = (char)lowerChar;
2504 // return new String(0, count+resultOffset, result);
2508 * Converts all of the characters in this <code>String</code> to lower
2509 * case using the rules of the default locale. This is equivalent to calling
2510 * <code>toLowerCase(Locale.getDefault())</code>.
2512 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2513 * results if used for strings that are intended to be interpreted locale
2515 * Examples are programming language identifiers, protocol keys, and HTML
2517 * For instance, <code>"TITLE".toLowerCase()</code> in a Turkish locale
2518 * returns <code>"t\u005Cu0131tle"</code>, where '\u005Cu0131' is the
2519 * LATIN SMALL LETTER DOTLESS I character.
2520 * To obtain correct results for locale insensitive strings, use
2521 * <code>toLowerCase(Locale.ENGLISH)</code>.
2523 * @return the <code>String</code>, converted to lowercase.
2524 * @see java.lang.String#toLowerCase(Locale)
2526 public String toLowerCase() {
2527 throw new UnsupportedOperationException("Should be supported but without connection to locale");
2531 * Converts all of the characters in this <code>String</code> to upper
2532 * case using the rules of the given <code>Locale</code>. Case mapping is based
2533 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2534 * class. Since case mappings are not always 1:1 char mappings, the resulting
2535 * <code>String</code> may be a different length than the original <code>String</code>.
2537 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2539 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2541 * <th>Language Code of Locale</th>
2542 * <th>Lower Case</th>
2543 * <th>Upper Case</th>
2544 * <th>Description</th>
2547 * <td>tr (Turkish)</td>
2548 * <td>\u0069</td>
2549 * <td>\u0130</td>
2550 * <td>small letter i -> capital letter I with dot above</td>
2553 * <td>tr (Turkish)</td>
2554 * <td>\u0131</td>
2555 * <td>\u0049</td>
2556 * <td>small letter dotless i -> capital letter I</td>
2560 * <td>\u00df</td>
2561 * <td>\u0053 \u0053</td>
2562 * <td>small letter sharp s -> two letters: SS</td>
2566 * <td>Fahrvergnügen</td>
2567 * <td>FAHRVERGNÜGEN</td>
2571 * @param locale use the case transformation rules for this locale
2572 * @return the <code>String</code>, converted to uppercase.
2573 * @see java.lang.String#toUpperCase()
2574 * @see java.lang.String#toLowerCase()
2575 * @see java.lang.String#toLowerCase(Locale)
2578 /* not for javascript
2579 public String toUpperCase(Locale locale) {
2580 if (locale == null) {
2581 throw new NullPointerException();
2586 // Now check if there are any characters that need to be changed.
2588 for (firstLower = 0 ; firstLower < count; ) {
2589 int c = (int)value[offset+firstLower];
2591 if ((c >= Character.MIN_HIGH_SURROGATE) &&
2592 (c <= Character.MAX_HIGH_SURROGATE)) {
2593 c = codePointAt(firstLower);
2594 srcCount = Character.charCount(c);
2598 int upperCaseChar = Character.toUpperCaseEx(c);
2599 if ((upperCaseChar == Character.ERROR) ||
2600 (c != upperCaseChar)) {
2603 firstLower += srcCount;
2608 char[] result = new char[count]; /* may grow *
2609 int resultOffset = 0; /* result may grow, so i+resultOffset
2610 * is the write location in result *
2612 /* Just copy the first few upperCase characters. *
2613 arraycopy(value, offset, result, 0, firstLower);
2615 String lang = locale.getLanguage();
2616 boolean localeDependent =
2617 (lang == "tr" || lang == "az" || lang == "lt");
2618 char[] upperCharArray;
2622 for (int i = firstLower; i < count; i += srcCount) {
2623 srcChar = (int)value[offset+i];
2624 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2625 (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2626 srcChar = codePointAt(i);
2627 srcCount = Character.charCount(srcChar);
2631 if (localeDependent) {
2632 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2634 upperChar = Character.toUpperCaseEx(srcChar);
2636 if ((upperChar == Character.ERROR) ||
2637 (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2638 if (upperChar == Character.ERROR) {
2639 if (localeDependent) {
2641 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
2643 upperCharArray = Character.toUpperCaseCharArray(srcChar);
2645 } else if (srcCount == 2) {
2646 resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount;
2649 upperCharArray = Character.toChars(upperChar);
2652 /* Grow result if needed *
2653 int mapLen = upperCharArray.length;
2654 if (mapLen > srcCount) {
2655 char[] result2 = new char[result.length + mapLen - srcCount];
2656 arraycopy(result, 0, result2, 0,
2660 for (int x=0; x<mapLen; ++x) {
2661 result[i+resultOffset+x] = upperCharArray[x];
2663 resultOffset += (mapLen - srcCount);
2665 result[i+resultOffset] = (char)upperChar;
2668 return new String(0, count+resultOffset, result);
2673 * Converts all of the characters in this <code>String</code> to upper
2674 * case using the rules of the default locale. This method is equivalent to
2675 * <code>toUpperCase(Locale.getDefault())</code>.
2677 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2678 * results if used for strings that are intended to be interpreted locale
2680 * Examples are programming language identifiers, protocol keys, and HTML
2682 * For instance, <code>"title".toUpperCase()</code> in a Turkish locale
2683 * returns <code>"T\u005Cu0130TLE"</code>, where '\u005Cu0130' is the
2684 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2685 * To obtain correct results for locale insensitive strings, use
2686 * <code>toUpperCase(Locale.ENGLISH)</code>.
2688 * @return the <code>String</code>, converted to uppercase.
2689 * @see java.lang.String#toUpperCase(Locale)
2691 public String toUpperCase() {
2692 throw new UnsupportedOperationException();
2696 * Returns a copy of the string, with leading and trailing whitespace
2699 * If this <code>String</code> object represents an empty character
2700 * sequence, or the first and last characters of character sequence
2701 * represented by this <code>String</code> object both have codes
2702 * greater than <code>'\u0020'</code> (the space character), then a
2703 * reference to this <code>String</code> object is returned.
2705 * Otherwise, if there is no character with a code greater than
2706 * <code>'\u0020'</code> in the string, then a new
2707 * <code>String</code> object representing an empty string is created
2710 * Otherwise, let <i>k</i> be the index of the first character in the
2711 * string whose code is greater than <code>'\u0020'</code>, and let
2712 * <i>m</i> be the index of the last character in the string whose code
2713 * is greater than <code>'\u0020'</code>. A new <code>String</code>
2714 * object is created, representing the substring of this string that
2715 * begins with the character at index <i>k</i> and ends with the
2716 * character at index <i>m</i>-that is, the result of
2717 * <code>this.substring(<i>k</i>, <i>m</i>+1)</code>.
2719 * This method may be used to trim whitespace (as defined above) from
2720 * the beginning and end of a string.
2722 * @return A copy of this string with leading and trailing white
2723 * space removed, or this string if it has no leading or
2724 * trailing white space.
2726 public String trim() {
2729 int off = offset; /* avoid getfield opcode */
2730 char[] val = value; /* avoid getfield opcode */
2732 while ((st < len) && (val[off + st] <= ' ')) {
2735 while ((st < len) && (val[off + len - 1] <= ' ')) {
2738 return ((st > 0) || (len < count)) ? substring(st, len) : this;
2742 * This object (which is already a string!) is itself returned.
2744 * @return the string itself.
2746 public String toString() {
2751 * Converts this string to a new character array.
2753 * @return a newly allocated character array whose length is the length
2754 * of this string and whose contents are initialized to contain
2755 * the character sequence represented by this string.
2757 public char[] toCharArray() {
2758 char result[] = new char[count];
2759 getChars(0, count, result, 0);
2764 * Returns a formatted string using the specified format string and
2767 * <p> The locale always used is the one returned by {@link
2768 * java.util.Locale#getDefault() Locale.getDefault()}.
2771 * A <a href="../util/Formatter.html#syntax">format string</a>
2774 * Arguments referenced by the format specifiers in the format
2775 * string. If there are more arguments than format specifiers, the
2776 * extra arguments are ignored. The number of arguments is
2777 * variable and may be zero. The maximum number of arguments is
2778 * limited by the maximum dimension of a Java array as defined by
2779 * <cite>The Java™ Virtual Machine Specification</cite>.
2780 * The behaviour on a
2781 * <tt>null</tt> argument depends on the <a
2782 * href="../util/Formatter.html#syntax">conversion</a>.
2784 * @throws IllegalFormatException
2785 * If a format string contains an illegal syntax, a format
2786 * specifier that is incompatible with the given arguments,
2787 * insufficient arguments given the format string, or other
2788 * illegal conditions. For specification of all possible
2789 * formatting errors, see the <a
2790 * href="../util/Formatter.html#detail">Details</a> section of the
2791 * formatter class specification.
2793 * @throws NullPointerException
2794 * If the <tt>format</tt> is <tt>null</tt>
2796 * @return A formatted string
2798 * @see java.util.Formatter
2801 public static String format(String format, Object ... args) {
2802 throw new UnsupportedOperationException();
2806 * Returns a formatted string using the specified locale, format string,
2810 * The {@linkplain java.util.Locale locale} to apply during
2811 * formatting. If <tt>l</tt> is <tt>null</tt> then no localization
2815 * A <a href="../util/Formatter.html#syntax">format string</a>
2818 * Arguments referenced by the format specifiers in the format
2819 * string. If there are more arguments than format specifiers, the
2820 * extra arguments are ignored. The number of arguments is
2821 * variable and may be zero. The maximum number of arguments is
2822 * limited by the maximum dimension of a Java array as defined by
2823 * <cite>The Java™ Virtual Machine Specification</cite>.
2824 * The behaviour on a
2825 * <tt>null</tt> argument depends on the <a
2826 * href="../util/Formatter.html#syntax">conversion</a>.
2828 * @throws IllegalFormatException
2829 * If a format string contains an illegal syntax, a format
2830 * specifier that is incompatible with the given arguments,
2831 * insufficient arguments given the format string, or other
2832 * illegal conditions. For specification of all possible
2833 * formatting errors, see the <a
2834 * href="../util/Formatter.html#detail">Details</a> section of the
2835 * formatter class specification
2837 * @throws NullPointerException
2838 * If the <tt>format</tt> is <tt>null</tt>
2840 * @return A formatted string
2842 * @see java.util.Formatter
2845 // public static String format(Locale l, String format, Object ... args) {
2846 // return new Formatter(l).format(format, args).toString();
2850 * Returns the string representation of the <code>Object</code> argument.
2852 * @param obj an <code>Object</code>.
2853 * @return if the argument is <code>null</code>, then a string equal to
2854 * <code>"null"</code>; otherwise, the value of
2855 * <code>obj.toString()</code> is returned.
2856 * @see java.lang.Object#toString()
2858 public static String valueOf(Object obj) {
2859 return (obj == null) ? "null" : obj.toString();
2863 * Returns the string representation of the <code>char</code> array
2864 * argument. The contents of the character array are copied; subsequent
2865 * modification of the character array does not affect the newly
2868 * @param data a <code>char</code> array.
2869 * @return a newly allocated string representing the same sequence of
2870 * characters contained in the character array argument.
2872 public static String valueOf(char data[]) {
2873 return new String(data);
2877 * Returns the string representation of a specific subarray of the
2878 * <code>char</code> array argument.
2880 * The <code>offset</code> argument is the index of the first
2881 * character of the subarray. The <code>count</code> argument
2882 * specifies the length of the subarray. The contents of the subarray
2883 * are copied; subsequent modification of the character array does not
2884 * affect the newly created string.
2886 * @param data the character array.
2887 * @param offset the initial offset into the value of the
2888 * <code>String</code>.
2889 * @param count the length of the value of the <code>String</code>.
2890 * @return a string representing the sequence of characters contained
2891 * in the subarray of the character array argument.
2892 * @exception IndexOutOfBoundsException if <code>offset</code> is
2893 * negative, or <code>count</code> is negative, or
2894 * <code>offset+count</code> is larger than
2895 * <code>data.length</code>.
2897 public static String valueOf(char data[], int offset, int count) {
2898 return new String(data, offset, count);
2902 * Returns a String that represents the character sequence in the
2905 * @param data the character array.
2906 * @param offset initial offset of the subarray.
2907 * @param count length of the subarray.
2908 * @return a <code>String</code> that contains the characters of the
2909 * specified subarray of the character array.
2911 public static String copyValueOf(char data[], int offset, int count) {
2912 // All public String constructors now copy the data.
2913 return new String(data, offset, count);
2917 * Returns a String that represents the character sequence in the
2920 * @param data the character array.
2921 * @return a <code>String</code> that contains the characters of the
2924 public static String copyValueOf(char data[]) {
2925 return copyValueOf(data, 0, data.length);
2929 * Returns the string representation of the <code>boolean</code> argument.
2931 * @param b a <code>boolean</code>.
2932 * @return if the argument is <code>true</code>, a string equal to
2933 * <code>"true"</code> is returned; otherwise, a string equal to
2934 * <code>"false"</code> is returned.
2936 public static String valueOf(boolean b) {
2937 return b ? "true" : "false";
2941 * Returns the string representation of the <code>char</code>
2944 * @param c a <code>char</code>.
2945 * @return a string of length <code>1</code> containing
2946 * as its single character the argument <code>c</code>.
2948 public static String valueOf(char c) {
2950 return new String(0, 1, data);
2954 * Returns the string representation of the <code>int</code> argument.
2956 * The representation is exactly the one returned by the
2957 * <code>Integer.toString</code> method of one argument.
2959 * @param i an <code>int</code>.
2960 * @return a string representation of the <code>int</code> argument.
2961 * @see java.lang.Integer#toString(int, int)
2963 public static String valueOf(int i) {
2964 return Integer.toString(i);
2968 * Returns the string representation of the <code>long</code> argument.
2970 * The representation is exactly the one returned by the
2971 * <code>Long.toString</code> method of one argument.
2973 * @param l a <code>long</code>.
2974 * @return a string representation of the <code>long</code> argument.
2975 * @see java.lang.Long#toString(long)
2977 public static String valueOf(long l) {
2978 return Long.toString(l);
2982 * Returns the string representation of the <code>float</code> argument.
2984 * The representation is exactly the one returned by the
2985 * <code>Float.toString</code> method of one argument.
2987 * @param f a <code>float</code>.
2988 * @return a string representation of the <code>float</code> argument.
2989 * @see java.lang.Float#toString(float)
2991 public static String valueOf(float f) {
2992 return Float.toString(f);
2996 * Returns the string representation of the <code>double</code> argument.
2998 * The representation is exactly the one returned by the
2999 * <code>Double.toString</code> method of one argument.
3001 * @param d a <code>double</code>.
3002 * @return a string representation of the <code>double</code> argument.
3003 * @see java.lang.Double#toString(double)
3005 public static String valueOf(double d) {
3006 return Double.toString(d);
3010 * Returns a canonical representation for the string object.
3012 * A pool of strings, initially empty, is maintained privately by the
3013 * class <code>String</code>.
3015 * When the intern method is invoked, if the pool already contains a
3016 * string equal to this <code>String</code> object as determined by
3017 * the {@link #equals(Object)} method, then the string from the pool is
3018 * returned. Otherwise, this <code>String</code> object is added to the
3019 * pool and a reference to this <code>String</code> object is returned.
3021 * It follows that for any two strings <code>s</code> and <code>t</code>,
3022 * <code>s.intern() == t.intern()</code> is <code>true</code>
3023 * if and only if <code>s.equals(t)</code> is <code>true</code>.
3025 * All literal strings and string-valued constant expressions are
3026 * interned. String literals are defined in section 3.10.5 of the
3027 * <cite>The Java™ Language Specification</cite>.
3029 * @return a string that has the same contents as this string, but is
3030 * guaranteed to be from a pool of unique strings.
3032 public native String intern();
3034 static char[] copyOfRange(char[] original, int from, int to) {
3035 int newLength = to - from;
3036 if (newLength < 0) {
3037 throw new IllegalArgumentException(from + " > " + to);
3039 char[] copy = new char[newLength];
3040 arraycopy(original, from, copy, 0,
3041 Math.min(original.length - from, newLength));
3044 static char[] copyOf(char[] original, int newLength) {
3045 char[] copy = new char[newLength];
3046 arraycopy(original, 0, copy, 0,
3047 Math.min(original.length, newLength));
3050 static void arraycopy(
3051 char[] value, int srcBegin, char[] dst, int dstBegin, int count
3053 while (count-- > 0) {
3054 dst[dstBegin++] = value[srcBegin++];
3057 // access system property
3058 static String getProperty(String nm) {