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.ObjectStreamField;
29 import java.io.UnsupportedEncodingException;
30 import java.util.Comparator;
33 * The <code>String</code> class represents character strings. All
34 * string literals in Java programs, such as <code>"abc"</code>, are
35 * implemented as instances of this class.
37 * Strings are constant; their values cannot be changed after they
38 * are created. String buffers support mutable strings.
39 * Because String objects are immutable they can be shared. For example:
40 * <p><blockquote><pre>
42 * </pre></blockquote><p>
44 * <p><blockquote><pre>
45 * char data[] = {'a', 'b', 'c'};
46 * String str = new String(data);
47 * </pre></blockquote><p>
48 * Here are some more examples of how strings can be used:
49 * <p><blockquote><pre>
50 * System.out.println("abc");
52 * System.out.println("abc" + cde);
53 * String c = "abc".substring(2,3);
54 * String d = cde.substring(1, 2);
57 * The class <code>String</code> includes methods for examining
58 * individual characters of the sequence, for comparing strings, for
59 * searching strings, for extracting substrings, and for creating a
60 * copy of a string with all characters translated to uppercase or to
61 * lowercase. Case mapping is based on the Unicode Standard version
62 * specified by the {@link java.lang.Character Character} class.
64 * The Java language provides special support for the string
65 * concatenation operator ( + ), and for conversion of
66 * other objects to strings. String concatenation is implemented
67 * through the <code>StringBuilder</code>(or <code>StringBuffer</code>)
68 * class and its <code>append</code> method.
69 * String conversions are implemented through the method
70 * <code>toString</code>, defined by <code>Object</code> and
71 * inherited by all classes in Java. For additional information on
72 * string concatenation and conversion, see Gosling, Joy, and Steele,
73 * <i>The Java Language Specification</i>.
75 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
76 * or method in this class will cause a {@link NullPointerException} to be
79 * <p>A <code>String</code> represents a string in the UTF-16 format
80 * in which <em>supplementary characters</em> are represented by <em>surrogate
81 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
82 * Character Representations</a> in the <code>Character</code> class for
84 * Index values refer to <code>char</code> code units, so a supplementary
85 * character uses two positions in a <code>String</code>.
86 * <p>The <code>String</code> class provides methods for dealing with
87 * Unicode code points (i.e., characters), in addition to those for
88 * dealing with Unicode code units (i.e., <code>char</code> values).
91 * @author Arthur van Hoff
92 * @author Martin Buchholz
94 * @see java.lang.Object#toString()
95 * @see java.lang.StringBuffer
96 * @see java.lang.StringBuilder
97 * @see java.nio.charset.Charset
101 public final class String
102 implements java.io.Serializable, Comparable<String>, CharSequence
104 /** The value is used for character storage. */
105 private final char value[];
107 /** The offset is the first index of the storage that is used. */
108 private final int offset;
110 /** The count is the number of characters in the String. */
111 private final int count;
113 /** Cache the hash code for the string */
114 private int hash; // Default to 0
116 /** use serialVersionUID from JDK 1.0.2 for interoperability */
117 private static final long serialVersionUID = -6849794470754667710L;
120 * Class String is special cased within the Serialization Stream Protocol.
122 * A String instance is written initially into an ObjectOutputStream in the
125 * <code>TC_STRING</code> (utf String)
127 * The String is written by method <code>DataOutput.writeUTF</code>.
128 * A new handle is generated to refer to all future references to the
129 * string instance within the stream.
131 private static final ObjectStreamField[] serialPersistentFields =
132 new ObjectStreamField[0];
135 * Initializes a newly created {@code String} object so that it represents
136 * an empty character sequence. Note that use of this constructor is
137 * unnecessary since Strings are immutable.
142 this.value = new char[0];
146 * Initializes a newly created {@code String} object so that it represents
147 * the same sequence of characters as the argument; in other words, the
148 * newly created string is a copy of the argument string. Unless an
149 * explicit copy of {@code original} is needed, use of this constructor is
150 * unnecessary since Strings are immutable.
155 public String(String original) {
156 int size = original.count;
157 char[] originalValue = original.value;
159 if (originalValue.length > size) {
160 // The array representing the String is bigger than the new
161 // String itself. Perhaps this constructor is being called
162 // in order to trim the baggage, so make a copy of the array.
163 int off = original.offset;
164 v = copyOfRange(originalValue, off, off+size);
166 // The array representing the String is the same
167 // size as the String, so no point in making a copy.
176 * Allocates a new {@code String} so that it represents the sequence of
177 * characters currently contained in the character array argument. The
178 * contents of the character array are copied; subsequent modification of
179 * the character array does not affect the newly created string.
182 * The initial value of the string
184 public String(char value[]) {
185 int size = value.length;
188 this.value = copyOf(value, size);
192 * Allocates a new {@code String} that contains characters from a subarray
193 * of the character array argument. The {@code offset} argument is the
194 * index of the first character of the subarray and the {@code count}
195 * argument specifies the length of the subarray. The contents of the
196 * subarray are copied; subsequent modification of the character array does
197 * not affect the newly created string.
200 * Array that is the source of characters
208 * @throws IndexOutOfBoundsException
209 * If the {@code offset} and {@code count} arguments index
210 * characters outside the bounds of the {@code value} array
212 public String(char value[], int offset, int count) {
214 throw new StringIndexOutOfBoundsException(offset);
217 throw new StringIndexOutOfBoundsException(count);
219 // Note: offset or count might be near -1>>>1.
220 if (offset > value.length - count) {
221 throw new StringIndexOutOfBoundsException(offset + count);
225 this.value = copyOfRange(value, offset, offset+count);
229 * Allocates a new {@code String} that contains characters from a subarray
230 * of the <a href="Character.html#unicode">Unicode code point</a> array
231 * argument. The {@code offset} argument is the index of the first code
232 * point of the subarray and the {@code count} argument specifies the
233 * length of the subarray. The contents of the subarray are converted to
234 * {@code char}s; subsequent modification of the {@code int} array does not
235 * affect the newly created string.
238 * Array that is the source of Unicode code points
246 * @throws IllegalArgumentException
247 * If any invalid Unicode code point is found in {@code
250 * @throws IndexOutOfBoundsException
251 * If the {@code offset} and {@code count} arguments index
252 * characters outside the bounds of the {@code codePoints} array
256 public String(int[] codePoints, int offset, int count) {
258 throw new StringIndexOutOfBoundsException(offset);
261 throw new StringIndexOutOfBoundsException(count);
263 // Note: offset or count might be near -1>>>1.
264 if (offset > codePoints.length - count) {
265 throw new StringIndexOutOfBoundsException(offset + count);
268 final int end = offset + count;
270 // Pass 1: Compute precise size of char[]
272 for (int i = offset; i < end; i++) {
273 int c = codePoints[i];
274 if (Character.isBmpCodePoint(c))
276 else if (Character.isValidCodePoint(c))
278 else throw new IllegalArgumentException(Integer.toString(c));
281 // Pass 2: Allocate and fill in char[]
282 final char[] v = new char[n];
284 for (int i = offset, j = 0; i < end; i++, j++) {
285 int c = codePoints[i];
286 if (Character.isBmpCodePoint(c))
289 Character.toSurrogates(c, v, j++);
298 * Allocates a new {@code String} constructed from a subarray of an array
299 * of 8-bit integer values.
301 * <p> The {@code offset} argument is the index of the first byte of the
302 * subarray, and the {@code count} argument specifies the length of the
305 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
306 * specified in the method above.
308 * @deprecated This method does not properly convert bytes into characters.
309 * As of JDK 1.1, the preferred way to do this is via the
310 * {@code String} constructors that take a {@link
311 * java.nio.charset.Charset}, charset name, or that use the platform's
315 * The bytes to be converted to characters
318 * The top 8 bits of each 16-bit Unicode code unit
325 * @throws IndexOutOfBoundsException
326 * If the {@code offset} or {@code count} argument is invalid
328 * @see #String(byte[], int)
329 * @see #String(byte[], int, int, java.lang.String)
330 * @see #String(byte[], int, int, java.nio.charset.Charset)
331 * @see #String(byte[], int, int)
332 * @see #String(byte[], java.lang.String)
333 * @see #String(byte[], java.nio.charset.Charset)
334 * @see #String(byte[])
337 public String(byte ascii[], int hibyte, int offset, int count) {
338 checkBounds(ascii, offset, count);
339 char value[] = new char[count];
342 for (int i = count ; i-- > 0 ;) {
343 value[i] = (char) (ascii[i + offset] & 0xff);
347 for (int i = count ; i-- > 0 ;) {
348 value[i] = (char) (hibyte | (ascii[i + offset] & 0xff));
357 * Allocates a new {@code String} containing characters constructed from
358 * an array of 8-bit integer values. Each character <i>c</i>in the
359 * resulting string is constructed from the corresponding component
360 * <i>b</i> in the byte array such that:
363 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
364 * | (<b><i>b</i></b> & 0xff))
365 * </pre></blockquote>
367 * @deprecated This method does not properly convert bytes into
368 * characters. As of JDK 1.1, the preferred way to do this is via the
369 * {@code String} constructors that take a {@link
370 * java.nio.charset.Charset}, charset name, or that use the platform's
374 * The bytes to be converted to characters
377 * The top 8 bits of each 16-bit Unicode code unit
379 * @see #String(byte[], int, int, java.lang.String)
380 * @see #String(byte[], int, int, java.nio.charset.Charset)
381 * @see #String(byte[], int, int)
382 * @see #String(byte[], java.lang.String)
383 * @see #String(byte[], java.nio.charset.Charset)
384 * @see #String(byte[])
387 public String(byte ascii[], int hibyte) {
388 this(ascii, hibyte, 0, ascii.length);
391 /* Common private utility method used to bounds check the byte array
392 * and requested offset & length values used by the String(byte[],..)
395 private static void checkBounds(byte[] bytes, int offset, int length) {
397 throw new StringIndexOutOfBoundsException(length);
399 throw new StringIndexOutOfBoundsException(offset);
400 if (offset > bytes.length - length)
401 throw new StringIndexOutOfBoundsException(offset + length);
405 * Constructs a new {@code String} by decoding the specified subarray of
406 * bytes using the specified charset. The length of the new {@code String}
407 * is a function of the charset, and hence may not be equal to the length
410 * <p> The behavior of this constructor when the given bytes are not valid
411 * in the given charset is unspecified. The {@link
412 * java.nio.charset.CharsetDecoder} class should be used when more control
413 * over the decoding process is required.
416 * The bytes to be decoded into characters
419 * The index of the first byte to decode
422 * The number of bytes to decode
425 * The name of a supported {@linkplain java.nio.charset.Charset
428 * @throws UnsupportedEncodingException
429 * If the named charset is not supported
431 * @throws IndexOutOfBoundsException
432 * If the {@code offset} and {@code length} arguments index
433 * characters outside the bounds of the {@code bytes} array
437 public String(byte bytes[], int offset, int length, String charsetName)
438 throws UnsupportedEncodingException
440 if (charsetName == null)
441 throw new NullPointerException("charsetName");
442 checkBounds(bytes, offset, length);
443 char[] v = StringCoding.decode(charsetName, bytes, offset, length);
445 this.count = v.length;
450 * Constructs a new {@code String} by decoding the specified subarray of
451 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
452 * The length of the new {@code String} is a function of the charset, and
453 * hence may not be equal to the length of the subarray.
455 * <p> This method always replaces malformed-input and unmappable-character
456 * sequences with this charset's default replacement string. The {@link
457 * java.nio.charset.CharsetDecoder} class should be used when more control
458 * over the decoding process is required.
461 * The bytes to be decoded into characters
464 * The index of the first byte to decode
467 * The number of bytes to decode
470 * The {@linkplain java.nio.charset.Charset charset} to be used to
471 * decode the {@code bytes}
473 * @throws IndexOutOfBoundsException
474 * If the {@code offset} and {@code length} arguments index
475 * characters outside the bounds of the {@code bytes} array
479 /* don't want dependnecy on Charset
480 public String(byte bytes[], int offset, int length, Charset charset) {
482 throw new NullPointerException("charset");
483 checkBounds(bytes, offset, length);
484 char[] v = StringCoding.decode(charset, bytes, offset, length);
486 this.count = v.length;
492 * Constructs a new {@code String} by decoding the specified array of bytes
493 * using the specified {@linkplain java.nio.charset.Charset charset}. The
494 * length of the new {@code String} is a function of the charset, and hence
495 * may not be equal to the length of the byte array.
497 * <p> The behavior of this constructor when the given bytes are not valid
498 * in the given charset is unspecified. The {@link
499 * java.nio.charset.CharsetDecoder} class should be used when more control
500 * over the decoding process is required.
503 * The bytes to be decoded into characters
506 * The name of a supported {@linkplain java.nio.charset.Charset
509 * @throws UnsupportedEncodingException
510 * If the named charset is not supported
514 public String(byte bytes[], String charsetName)
515 throws UnsupportedEncodingException
517 this(bytes, 0, bytes.length, charsetName);
521 * Constructs a new {@code String} by decoding the specified array of
522 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
523 * The length of the new {@code String} is a function of the charset, and
524 * hence may not be equal to the length of the byte array.
526 * <p> This method always replaces malformed-input and unmappable-character
527 * sequences with this charset's default replacement string. The {@link
528 * java.nio.charset.CharsetDecoder} class should be used when more control
529 * over the decoding process is required.
532 * The bytes to be decoded into characters
535 * The {@linkplain java.nio.charset.Charset charset} to be used to
536 * decode the {@code bytes}
540 /* don't want dep on Charset
541 public String(byte bytes[], Charset charset) {
542 this(bytes, 0, bytes.length, charset);
547 * Constructs a new {@code String} by decoding the specified subarray of
548 * bytes using the platform's default charset. The length of the new
549 * {@code String} is a function of the charset, and hence may not be equal
550 * to the length of the subarray.
552 * <p> The behavior of this constructor when the given bytes are not valid
553 * in the default charset is unspecified. The {@link
554 * java.nio.charset.CharsetDecoder} class should be used when more control
555 * over the decoding process is required.
558 * The bytes to be decoded into characters
561 * The index of the first byte to decode
564 * The number of bytes to decode
566 * @throws IndexOutOfBoundsException
567 * If the {@code offset} and the {@code length} arguments index
568 * characters outside the bounds of the {@code bytes} array
572 public String(byte bytes[], int offset, int length) {
573 checkBounds(bytes, offset, length);
574 char[] v = StringCoding.decode(bytes, offset, length);
576 this.count = v.length;
581 * Constructs a new {@code String} by decoding the specified array of bytes
582 * using the platform's default charset. The length of the new {@code
583 * String} is a function of the charset, and hence may not be equal to the
584 * length of the byte array.
586 * <p> The behavior of this constructor when the given bytes are not valid
587 * in the default charset is unspecified. The {@link
588 * java.nio.charset.CharsetDecoder} class should be used when more control
589 * over the decoding process is required.
592 * The bytes to be decoded into characters
596 public String(byte bytes[]) {
597 this(bytes, 0, bytes.length);
601 * Allocates a new string that contains the sequence of characters
602 * currently contained in the string buffer argument. The contents of the
603 * string buffer are copied; subsequent modification of the string buffer
604 * does not affect the newly created string.
607 * A {@code StringBuffer}
609 public String(StringBuffer buffer) {
610 String result = buffer.toString();
611 this.value = result.value;
612 this.count = result.count;
613 this.offset = result.offset;
617 * Allocates a new string that contains the sequence of characters
618 * currently contained in the string builder argument. The contents of the
619 * string builder are copied; subsequent modification of the string builder
620 * does not affect the newly created string.
622 * <p> This constructor is provided to ease migration to {@code
623 * StringBuilder}. Obtaining a string from a string builder via the {@code
624 * toString} method is likely to run faster and is generally preferred.
627 * A {@code StringBuilder}
631 public String(StringBuilder builder) {
632 String result = builder.toString();
633 this.value = result.value;
634 this.count = result.count;
635 this.offset = result.offset;
639 // Package private constructor which shares value array for speed.
640 String(int offset, int count, char value[]) {
642 this.offset = offset;
647 * Returns the length of this string.
648 * The length is equal to the number of <a href="Character.html#unicode">Unicode
649 * code units</a> in the string.
651 * @return the length of the sequence of characters represented by this
654 public int length() {
659 * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>.
661 * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise
666 public boolean isEmpty() {
671 * Returns the <code>char</code> value at the
672 * specified index. An index ranges from <code>0</code> to
673 * <code>length() - 1</code>. The first <code>char</code> value of the sequence
674 * is at index <code>0</code>, the next at index <code>1</code>,
675 * and so on, as for array indexing.
677 * <p>If the <code>char</code> value specified by the index is a
678 * <a href="Character.html#unicode">surrogate</a>, the surrogate
681 * @param index the index of the <code>char</code> value.
682 * @return the <code>char</code> value at the specified index of this string.
683 * The first <code>char</code> value is at index <code>0</code>.
684 * @exception IndexOutOfBoundsException if the <code>index</code>
685 * argument is negative or not less than the length of this
688 public char charAt(int index) {
689 if ((index < 0) || (index >= count)) {
690 throw new StringIndexOutOfBoundsException(index);
692 return value[index + offset];
696 * Returns the character (Unicode code point) at the specified
697 * index. The index refers to <code>char</code> values
698 * (Unicode code units) and ranges from <code>0</code> to
699 * {@link #length()}<code> - 1</code>.
701 * <p> If the <code>char</code> value specified at the given index
702 * is in the high-surrogate range, the following index is less
703 * than the length of this <code>String</code>, and the
704 * <code>char</code> value at the following index is in the
705 * low-surrogate range, then the supplementary code point
706 * corresponding to this surrogate pair is returned. Otherwise,
707 * the <code>char</code> value at the given index is returned.
709 * @param index the index to the <code>char</code> values
710 * @return the code point value of the character at the
712 * @exception IndexOutOfBoundsException if the <code>index</code>
713 * argument is negative or not less than the length of this
717 public int codePointAt(int index) {
718 if ((index < 0) || (index >= count)) {
719 throw new StringIndexOutOfBoundsException(index);
721 return Character.codePointAtImpl(value, offset + index, offset + count);
725 * Returns the character (Unicode code point) before the specified
726 * index. The index refers to <code>char</code> values
727 * (Unicode code units) and ranges from <code>1</code> to {@link
728 * CharSequence#length() length}.
730 * <p> If the <code>char</code> value at <code>(index - 1)</code>
731 * is in the low-surrogate range, <code>(index - 2)</code> is not
732 * negative, and the <code>char</code> value at <code>(index -
733 * 2)</code> is in the high-surrogate range, then the
734 * supplementary code point value of the surrogate pair is
735 * returned. If the <code>char</code> value at <code>index -
736 * 1</code> is an unpaired low-surrogate or a high-surrogate, the
737 * surrogate value is returned.
739 * @param index the index following the code point that should be returned
740 * @return the Unicode code point value before the given index.
741 * @exception IndexOutOfBoundsException if the <code>index</code>
742 * argument is less than 1 or greater than the length
746 public int codePointBefore(int index) {
748 if ((i < 0) || (i >= count)) {
749 throw new StringIndexOutOfBoundsException(index);
751 return Character.codePointBeforeImpl(value, offset + index, offset);
755 * Returns the number of Unicode code points in the specified text
756 * range of this <code>String</code>. The text range begins at the
757 * specified <code>beginIndex</code> and extends to the
758 * <code>char</code> at index <code>endIndex - 1</code>. Thus the
759 * length (in <code>char</code>s) of the text range is
760 * <code>endIndex-beginIndex</code>. Unpaired surrogates within
761 * the text range count as one code point each.
763 * @param beginIndex the index to the first <code>char</code> of
765 * @param endIndex the index after the last <code>char</code> of
767 * @return the number of Unicode code points in the specified text
769 * @exception IndexOutOfBoundsException if the
770 * <code>beginIndex</code> is negative, or <code>endIndex</code>
771 * is larger than the length of this <code>String</code>, or
772 * <code>beginIndex</code> is larger than <code>endIndex</code>.
775 public int codePointCount(int beginIndex, int endIndex) {
776 if (beginIndex < 0 || endIndex > count || beginIndex > endIndex) {
777 throw new IndexOutOfBoundsException();
779 return Character.codePointCountImpl(value, offset+beginIndex, endIndex-beginIndex);
783 * Returns the index within this <code>String</code> that is
784 * offset from the given <code>index</code> by
785 * <code>codePointOffset</code> code points. Unpaired surrogates
786 * within the text range given by <code>index</code> and
787 * <code>codePointOffset</code> count as one code point each.
789 * @param index the index to be offset
790 * @param codePointOffset the offset in code points
791 * @return the index within this <code>String</code>
792 * @exception IndexOutOfBoundsException if <code>index</code>
793 * is negative or larger then the length of this
794 * <code>String</code>, or if <code>codePointOffset</code> is positive
795 * and the substring starting with <code>index</code> has fewer
796 * than <code>codePointOffset</code> code points,
797 * or if <code>codePointOffset</code> is negative and the substring
798 * before <code>index</code> has fewer than the absolute value
799 * of <code>codePointOffset</code> code points.
802 public int offsetByCodePoints(int index, int codePointOffset) {
803 if (index < 0 || index > count) {
804 throw new IndexOutOfBoundsException();
806 return Character.offsetByCodePointsImpl(value, offset, count,
807 offset+index, codePointOffset) - offset;
811 * Copy characters from this string into dst starting at dstBegin.
812 * This method doesn't perform any range checking.
814 void getChars(char dst[], int dstBegin) {
815 System.arraycopy(value, offset, dst, dstBegin, count);
819 * Copies characters from this string into the destination character
822 * The first character to be copied is at index <code>srcBegin</code>;
823 * the last character to be copied is at index <code>srcEnd-1</code>
824 * (thus the total number of characters to be copied is
825 * <code>srcEnd-srcBegin</code>). The characters are copied into the
826 * subarray of <code>dst</code> starting at index <code>dstBegin</code>
827 * and ending at index:
828 * <p><blockquote><pre>
829 * dstbegin + (srcEnd-srcBegin) - 1
830 * </pre></blockquote>
832 * @param srcBegin index of the first character in the string
834 * @param srcEnd index after the last character in the string
836 * @param dst the destination array.
837 * @param dstBegin the start offset in the destination array.
838 * @exception IndexOutOfBoundsException If any of the following
840 * <ul><li><code>srcBegin</code> is negative.
841 * <li><code>srcBegin</code> is greater than <code>srcEnd</code>
842 * <li><code>srcEnd</code> is greater than the length of this
844 * <li><code>dstBegin</code> is negative
845 * <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
846 * <code>dst.length</code></ul>
848 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
850 throw new StringIndexOutOfBoundsException(srcBegin);
852 if (srcEnd > count) {
853 throw new StringIndexOutOfBoundsException(srcEnd);
855 if (srcBegin > srcEnd) {
856 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
858 System.arraycopy(value, offset + srcBegin, dst, dstBegin,
863 * Copies characters from this string into the destination byte array. Each
864 * byte receives the 8 low-order bits of the corresponding character. The
865 * eight high-order bits of each character are not copied and do not
866 * participate in the transfer in any way.
868 * <p> The first character to be copied is at index {@code srcBegin}; the
869 * last character to be copied is at index {@code srcEnd-1}. The total
870 * number of characters to be copied is {@code srcEnd-srcBegin}. The
871 * characters, converted to bytes, are copied into the subarray of {@code
872 * dst} starting at index {@code dstBegin} and ending at index:
875 * dstbegin + (srcEnd-srcBegin) - 1
876 * </pre></blockquote>
878 * @deprecated This method does not properly convert characters into
879 * bytes. As of JDK 1.1, the preferred way to do this is via the
880 * {@link #getBytes()} method, which uses the platform's default charset.
883 * Index of the first character in the string to copy
886 * Index after the last character in the string to copy
889 * The destination array
892 * The start offset in the destination array
894 * @throws IndexOutOfBoundsException
895 * If any of the following is true:
897 * <li> {@code srcBegin} is negative
898 * <li> {@code srcBegin} is greater than {@code srcEnd}
899 * <li> {@code srcEnd} is greater than the length of this String
900 * <li> {@code dstBegin} is negative
901 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
906 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
908 throw new StringIndexOutOfBoundsException(srcBegin);
910 if (srcEnd > count) {
911 throw new StringIndexOutOfBoundsException(srcEnd);
913 if (srcBegin > srcEnd) {
914 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
917 int n = offset + srcEnd;
918 int i = offset + srcBegin;
919 char[] val = value; /* avoid getfield opcode */
922 dst[j++] = (byte)val[i++];
927 * Encodes this {@code String} into a sequence of bytes using the named
928 * charset, storing the result into a new byte array.
930 * <p> The behavior of this method when this string cannot be encoded in
931 * the given charset is unspecified. The {@link
932 * java.nio.charset.CharsetEncoder} class should be used when more control
933 * over the encoding process is required.
936 * The name of a supported {@linkplain java.nio.charset.Charset
939 * @return The resultant byte array
941 * @throws UnsupportedEncodingException
942 * If the named charset is not supported
946 public byte[] getBytes(String charsetName)
947 throws UnsupportedEncodingException
949 if (charsetName == null) throw new NullPointerException();
950 return StringCoding.encode(charsetName, value, offset, count);
954 * Encodes this {@code String} into a sequence of bytes using the given
955 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
958 * <p> This method always replaces malformed-input and unmappable-character
959 * sequences with this charset's default replacement byte array. The
960 * {@link java.nio.charset.CharsetEncoder} class should be used when more
961 * control over the encoding process is required.
964 * The {@linkplain java.nio.charset.Charset} to be used to encode
967 * @return The resultant byte array
971 /* don't want dep on Charset
972 public byte[] getBytes(Charset charset) {
973 if (charset == null) throw new NullPointerException();
974 return StringCoding.encode(charset, value, offset, count);
979 * Encodes this {@code String} into a sequence of bytes using the
980 * platform's default charset, storing the result into a new byte array.
982 * <p> The behavior of this method when this string cannot be encoded in
983 * the default charset is unspecified. The {@link
984 * java.nio.charset.CharsetEncoder} class should be used when more control
985 * over the encoding process is required.
987 * @return The resultant byte array
991 public byte[] getBytes() {
992 return StringCoding.encode(value, offset, count);
996 * Compares this string to the specified object. The result is {@code
997 * true} if and only if the argument is not {@code null} and is a {@code
998 * String} object that represents the same sequence of characters as this
1002 * The object to compare this {@code String} against
1004 * @return {@code true} if the given object represents a {@code String}
1005 * equivalent to this string, {@code false} otherwise
1007 * @see #compareTo(String)
1008 * @see #equalsIgnoreCase(String)
1010 public boolean equals(Object anObject) {
1011 if (this == anObject) {
1014 if (anObject instanceof String) {
1015 String anotherString = (String)anObject;
1017 if (n == anotherString.count) {
1019 char v2[] = anotherString.value;
1021 int j = anotherString.offset;
1023 if (v1[i++] != v2[j++])
1033 * Compares this string to the specified {@code StringBuffer}. The result
1034 * is {@code true} if and only if this {@code String} represents the same
1035 * sequence of characters as the specified {@code StringBuffer}.
1038 * The {@code StringBuffer} to compare this {@code String} against
1040 * @return {@code true} if this {@code String} represents the same
1041 * sequence of characters as the specified {@code StringBuffer},
1042 * {@code false} otherwise
1046 public boolean contentEquals(StringBuffer sb) {
1048 return contentEquals((CharSequence)sb);
1053 * Compares this string to the specified {@code CharSequence}. The result
1054 * is {@code true} if and only if this {@code String} represents the same
1055 * sequence of char values as the specified sequence.
1058 * The sequence to compare this {@code String} against
1060 * @return {@code true} if this {@code String} represents the same
1061 * sequence of char values as the specified sequence, {@code
1066 public boolean contentEquals(CharSequence cs) {
1067 if (count != cs.length())
1069 // Argument is a StringBuffer, StringBuilder
1070 if (cs instanceof AbstractStringBuilder) {
1072 char v2[] = ((AbstractStringBuilder)cs).getValue();
1077 if (v1[i++] != v2[j++])
1082 // Argument is a String
1083 if (cs.equals(this))
1085 // Argument is a generic CharSequence
1091 if (v1[i++] != cs.charAt(j++))
1098 * Compares this {@code String} to another {@code String}, ignoring case
1099 * considerations. Two strings are considered equal ignoring case if they
1100 * are of the same length and corresponding characters in the two strings
1101 * are equal ignoring case.
1103 * <p> Two characters {@code c1} and {@code c2} are considered the same
1104 * ignoring case if at least one of the following is true:
1106 * <li> The two characters are the same (as compared by the
1107 * {@code ==} operator)
1108 * <li> Applying the method {@link
1109 * java.lang.Character#toUpperCase(char)} to each character
1110 * produces the same result
1111 * <li> Applying the method {@link
1112 * java.lang.Character#toLowerCase(char)} to each character
1113 * produces the same result
1116 * @param anotherString
1117 * The {@code String} to compare this {@code String} against
1119 * @return {@code true} if the argument is not {@code null} and it
1120 * represents an equivalent {@code String} ignoring case; {@code
1123 * @see #equals(Object)
1125 public boolean equalsIgnoreCase(String anotherString) {
1126 return (this == anotherString) ? true :
1127 (anotherString != null) && (anotherString.count == count) &&
1128 regionMatches(true, 0, anotherString, 0, count);
1132 * Compares two strings lexicographically.
1133 * The comparison is based on the Unicode value of each character in
1134 * the strings. The character sequence represented by this
1135 * <code>String</code> object is compared lexicographically to the
1136 * character sequence represented by the argument string. The result is
1137 * a negative integer if this <code>String</code> object
1138 * lexicographically precedes the argument string. The result is a
1139 * positive integer if this <code>String</code> object lexicographically
1140 * follows the argument string. The result is zero if the strings
1141 * are equal; <code>compareTo</code> returns <code>0</code> exactly when
1142 * the {@link #equals(Object)} method would return <code>true</code>.
1144 * This is the definition of lexicographic ordering. If two strings are
1145 * different, then either they have different characters at some index
1146 * that is a valid index for both strings, or their lengths are different,
1147 * or both. If they have different characters at one or more index
1148 * positions, let <i>k</i> be the smallest such index; then the string
1149 * whose character at position <i>k</i> has the smaller value, as
1150 * determined by using the < operator, lexicographically precedes the
1151 * other string. In this case, <code>compareTo</code> returns the
1152 * difference of the two character values at position <code>k</code> in
1153 * the two string -- that is, the value:
1155 * this.charAt(k)-anotherString.charAt(k)
1156 * </pre></blockquote>
1157 * If there is no index position at which they differ, then the shorter
1158 * string lexicographically precedes the longer string. In this case,
1159 * <code>compareTo</code> returns the difference of the lengths of the
1160 * strings -- that is, the value:
1162 * this.length()-anotherString.length()
1163 * </pre></blockquote>
1165 * @param anotherString the <code>String</code> to be compared.
1166 * @return the value <code>0</code> if the argument string is equal to
1167 * this string; a value less than <code>0</code> if this string
1168 * is lexicographically less than the string argument; and a
1169 * value greater than <code>0</code> if this string is
1170 * lexicographically greater than the string argument.
1172 public int compareTo(String anotherString) {
1174 int len2 = anotherString.count;
1175 int n = Math.min(len1, len2);
1177 char v2[] = anotherString.value;
1179 int j = anotherString.offset;
1205 * A Comparator that orders <code>String</code> objects as by
1206 * <code>compareToIgnoreCase</code>. This comparator is serializable.
1208 * Note that this Comparator does <em>not</em> take locale into account,
1209 * and will result in an unsatisfactory ordering for certain locales.
1210 * The java.text package provides <em>Collators</em> to allow
1211 * locale-sensitive ordering.
1213 * @see java.text.Collator#compare(String, String)
1216 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1217 = new CaseInsensitiveComparator();
1218 private static class CaseInsensitiveComparator
1219 implements Comparator<String>, java.io.Serializable {
1220 // use serialVersionUID from JDK 1.2.2 for interoperability
1221 private static final long serialVersionUID = 8575799808933029326L;
1223 public int compare(String s1, String s2) {
1224 int n1 = s1.length();
1225 int n2 = s2.length();
1226 int min = Math.min(n1, n2);
1227 for (int i = 0; i < min; i++) {
1228 char c1 = s1.charAt(i);
1229 char c2 = s2.charAt(i);
1231 c1 = Character.toUpperCase(c1);
1232 c2 = Character.toUpperCase(c2);
1234 c1 = Character.toLowerCase(c1);
1235 c2 = Character.toLowerCase(c2);
1237 // No overflow because of numeric promotion
1248 * Compares two strings lexicographically, ignoring case
1249 * differences. This method returns an integer whose sign is that of
1250 * calling <code>compareTo</code> with normalized versions of the strings
1251 * where case differences have been eliminated by calling
1252 * <code>Character.toLowerCase(Character.toUpperCase(character))</code> on
1255 * Note that this method does <em>not</em> take locale into account,
1256 * and will result in an unsatisfactory ordering for certain locales.
1257 * The java.text package provides <em>collators</em> to allow
1258 * locale-sensitive ordering.
1260 * @param str the <code>String</code> to be compared.
1261 * @return a negative integer, zero, or a positive integer as the
1262 * specified String is greater than, equal to, or less
1263 * than this String, ignoring case considerations.
1264 * @see java.text.Collator#compare(String, String)
1267 public int compareToIgnoreCase(String str) {
1268 return CASE_INSENSITIVE_ORDER.compare(this, str);
1272 * Tests if two string regions are equal.
1274 * A substring of this <tt>String</tt> object is compared to a substring
1275 * of the argument other. The result is true if these substrings
1276 * represent identical character sequences. The substring of this
1277 * <tt>String</tt> object to be compared begins at index <tt>toffset</tt>
1278 * and has length <tt>len</tt>. The substring of other to be compared
1279 * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The
1280 * result is <tt>false</tt> if and only if at least one of the following
1282 * <ul><li><tt>toffset</tt> is negative.
1283 * <li><tt>ooffset</tt> is negative.
1284 * <li><tt>toffset+len</tt> is greater than the length of this
1285 * <tt>String</tt> object.
1286 * <li><tt>ooffset+len</tt> is greater than the length of the other
1288 * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt>
1290 * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt>
1293 * @param toffset the starting offset of the subregion in this string.
1294 * @param other the string argument.
1295 * @param ooffset the starting offset of the subregion in the string
1297 * @param len the number of characters to compare.
1298 * @return <code>true</code> if the specified subregion of this string
1299 * exactly matches the specified subregion of the string argument;
1300 * <code>false</code> otherwise.
1302 public boolean regionMatches(int toffset, String other, int ooffset,
1305 int to = offset + toffset;
1306 char pa[] = other.value;
1307 int po = other.offset + ooffset;
1308 // Note: toffset, ooffset, or len might be near -1>>>1.
1309 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len)
1310 || (ooffset > (long)other.count - len)) {
1314 if (ta[to++] != pa[po++]) {
1322 * Tests if two string regions are equal.
1324 * A substring of this <tt>String</tt> object is compared to a substring
1325 * of the argument <tt>other</tt>. The result is <tt>true</tt> if these
1326 * substrings represent character sequences that are the same, ignoring
1327 * case if and only if <tt>ignoreCase</tt> is true. The substring of
1328 * this <tt>String</tt> object to be compared begins at index
1329 * <tt>toffset</tt> and has length <tt>len</tt>. The substring of
1330 * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and
1331 * has length <tt>len</tt>. The result is <tt>false</tt> if and only if
1332 * at least one of the following is true:
1333 * <ul><li><tt>toffset</tt> is negative.
1334 * <li><tt>ooffset</tt> is negative.
1335 * <li><tt>toffset+len</tt> is greater than the length of this
1336 * <tt>String</tt> object.
1337 * <li><tt>ooffset+len</tt> is greater than the length of the other
1339 * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative
1340 * integer <i>k</i> less than <tt>len</tt> such that:
1342 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1343 * </pre></blockquote>
1344 * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative
1345 * integer <i>k</i> less than <tt>len</tt> such that:
1347 * Character.toLowerCase(this.charAt(toffset+k)) !=
1348 Character.toLowerCase(other.charAt(ooffset+k))
1349 * </pre></blockquote>
1352 * Character.toUpperCase(this.charAt(toffset+k)) !=
1353 * Character.toUpperCase(other.charAt(ooffset+k))
1354 * </pre></blockquote>
1357 * @param ignoreCase if <code>true</code>, ignore case when comparing
1359 * @param toffset the starting offset of the subregion in this
1361 * @param other the string argument.
1362 * @param ooffset the starting offset of the subregion in the string
1364 * @param len the number of characters to compare.
1365 * @return <code>true</code> if the specified subregion of this string
1366 * matches the specified subregion of the string argument;
1367 * <code>false</code> otherwise. Whether the matching is exact
1368 * or case insensitive depends on the <code>ignoreCase</code>
1371 public boolean regionMatches(boolean ignoreCase, int toffset,
1372 String other, int ooffset, int len) {
1374 int to = offset + toffset;
1375 char pa[] = other.value;
1376 int po = other.offset + ooffset;
1377 // Note: toffset, ooffset, or len might be near -1>>>1.
1378 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) ||
1379 (ooffset > (long)other.count - len)) {
1389 // If characters don't match but case may be ignored,
1390 // try converting both characters to uppercase.
1391 // If the results match, then the comparison scan should
1393 char u1 = Character.toUpperCase(c1);
1394 char u2 = Character.toUpperCase(c2);
1398 // Unfortunately, conversion to uppercase does not work properly
1399 // for the Georgian alphabet, which has strange rules about case
1400 // conversion. So we need to make one last check before
1402 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1412 * Tests if the substring of this string beginning at the
1413 * specified index starts with the specified prefix.
1415 * @param prefix the prefix.
1416 * @param toffset where to begin looking in this string.
1417 * @return <code>true</code> if the character sequence represented by the
1418 * argument is a prefix of the substring of this object starting
1419 * at index <code>toffset</code>; <code>false</code> otherwise.
1420 * The result is <code>false</code> if <code>toffset</code> is
1421 * negative or greater than the length of this
1422 * <code>String</code> object; otherwise the result is the same
1423 * as the result of the expression
1425 * this.substring(toffset).startsWith(prefix)
1428 public boolean startsWith(String prefix, int toffset) {
1430 int to = offset + toffset;
1431 char pa[] = prefix.value;
1432 int po = prefix.offset;
1433 int pc = prefix.count;
1434 // Note: toffset might be near -1>>>1.
1435 if ((toffset < 0) || (toffset > count - pc)) {
1439 if (ta[to++] != pa[po++]) {
1447 * Tests if this string starts with the specified prefix.
1449 * @param prefix the prefix.
1450 * @return <code>true</code> if the character sequence represented by the
1451 * argument is a prefix of the character sequence represented by
1452 * this string; <code>false</code> otherwise.
1453 * Note also that <code>true</code> will be returned if the
1454 * argument is an empty string or is equal to this
1455 * <code>String</code> object as determined by the
1456 * {@link #equals(Object)} method.
1459 public boolean startsWith(String prefix) {
1460 return startsWith(prefix, 0);
1464 * Tests if this string ends with the specified suffix.
1466 * @param suffix the suffix.
1467 * @return <code>true</code> if the character sequence represented by the
1468 * argument is a suffix of the character sequence represented by
1469 * this object; <code>false</code> otherwise. Note that the
1470 * result will be <code>true</code> if the argument is the
1471 * empty string or is equal to this <code>String</code> object
1472 * as determined by the {@link #equals(Object)} method.
1474 public boolean endsWith(String suffix) {
1475 return startsWith(suffix, count - suffix.count);
1479 * Returns a hash code for this string. The hash code for a
1480 * <code>String</code> object is computed as
1482 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1483 * </pre></blockquote>
1484 * using <code>int</code> arithmetic, where <code>s[i]</code> is the
1485 * <i>i</i>th character of the string, <code>n</code> is the length of
1486 * the string, and <code>^</code> indicates exponentiation.
1487 * (The hash value of the empty string is zero.)
1489 * @return a hash code value for this object.
1491 public int hashCode() {
1493 if (h == 0 && count > 0) {
1498 for (int i = 0; i < len; i++) {
1499 h = 31*h + val[off++];
1507 * Returns the index within this string of the first occurrence of
1508 * the specified character. If a character with value
1509 * <code>ch</code> occurs in the character sequence represented by
1510 * this <code>String</code> object, then the index (in Unicode
1511 * code units) of the first such occurrence is returned. For
1512 * values of <code>ch</code> in the range from 0 to 0xFFFF
1513 * (inclusive), this is the smallest value <i>k</i> such that:
1515 * this.charAt(<i>k</i>) == ch
1516 * </pre></blockquote>
1517 * is true. For other values of <code>ch</code>, it is the
1518 * smallest value <i>k</i> such that:
1520 * this.codePointAt(<i>k</i>) == ch
1521 * </pre></blockquote>
1522 * is true. In either case, if no such character occurs in this
1523 * string, then <code>-1</code> is returned.
1525 * @param ch a character (Unicode code point).
1526 * @return the index of the first occurrence of the character in the
1527 * character sequence represented by this object, or
1528 * <code>-1</code> if the character does not occur.
1530 public int indexOf(int ch) {
1531 return indexOf(ch, 0);
1535 * Returns the index within this string of the first occurrence of the
1536 * specified character, starting the search at the specified index.
1538 * If a character with value <code>ch</code> occurs in the
1539 * character sequence represented by this <code>String</code>
1540 * object at an index no smaller than <code>fromIndex</code>, then
1541 * the index of the first such occurrence is returned. For values
1542 * of <code>ch</code> in the range from 0 to 0xFFFF (inclusive),
1543 * this is the smallest value <i>k</i> such that:
1545 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1546 * </pre></blockquote>
1547 * is true. For other values of <code>ch</code>, it is the
1548 * smallest value <i>k</i> such that:
1550 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1551 * </pre></blockquote>
1552 * is true. In either case, if no such character occurs in this
1553 * string at or after position <code>fromIndex</code>, then
1554 * <code>-1</code> is returned.
1557 * There is no restriction on the value of <code>fromIndex</code>. If it
1558 * is negative, it has the same effect as if it were zero: this entire
1559 * string may be searched. If it is greater than the length of this
1560 * string, it has the same effect as if it were equal to the length of
1561 * this string: <code>-1</code> is returned.
1563 * <p>All indices are specified in <code>char</code> values
1564 * (Unicode code units).
1566 * @param ch a character (Unicode code point).
1567 * @param fromIndex the index to start the search from.
1568 * @return the index of the first occurrence of the character in the
1569 * character sequence represented by this object that is greater
1570 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1571 * if the character does not occur.
1573 public int indexOf(int ch, int fromIndex) {
1574 if (fromIndex < 0) {
1576 } else if (fromIndex >= count) {
1577 // Note: fromIndex might be near -1>>>1.
1581 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1582 // handle most cases here (ch is a BMP code point or a
1583 // negative value (invalid code point))
1584 final char[] value = this.value;
1585 final int offset = this.offset;
1586 final int max = offset + count;
1587 for (int i = offset + fromIndex; i < max ; i++) {
1588 if (value[i] == ch) {
1594 return indexOfSupplementary(ch, fromIndex);
1599 * Handles (rare) calls of indexOf with a supplementary character.
1601 private int indexOfSupplementary(int ch, int fromIndex) {
1602 if (Character.isValidCodePoint(ch)) {
1603 final char[] value = this.value;
1604 final int offset = this.offset;
1605 final char hi = Character.highSurrogate(ch);
1606 final char lo = Character.lowSurrogate(ch);
1607 final int max = offset + count - 1;
1608 for (int i = offset + fromIndex; i < max; i++) {
1609 if (value[i] == hi && value[i+1] == lo) {
1618 * Returns the index within this string of the last occurrence of
1619 * the specified character. For values of <code>ch</code> in the
1620 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1621 * units) returned is the largest value <i>k</i> such that:
1623 * this.charAt(<i>k</i>) == ch
1624 * </pre></blockquote>
1625 * is true. For other values of <code>ch</code>, it is the
1626 * largest value <i>k</i> such that:
1628 * this.codePointAt(<i>k</i>) == ch
1629 * </pre></blockquote>
1630 * is true. In either case, if no such character occurs in this
1631 * string, then <code>-1</code> is returned. The
1632 * <code>String</code> is searched backwards starting at the last
1635 * @param ch a character (Unicode code point).
1636 * @return the index of the last occurrence of the character in the
1637 * character sequence represented by this object, or
1638 * <code>-1</code> if the character does not occur.
1640 public int lastIndexOf(int ch) {
1641 return lastIndexOf(ch, count - 1);
1645 * Returns the index within this string of the last occurrence of
1646 * the specified character, searching backward starting at the
1647 * specified index. For values of <code>ch</code> in the range
1648 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1649 * value <i>k</i> such that:
1651 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1652 * </pre></blockquote>
1653 * is true. For other values of <code>ch</code>, it is the
1654 * largest value <i>k</i> such that:
1656 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1657 * </pre></blockquote>
1658 * is true. In either case, if no such character occurs in this
1659 * string at or before position <code>fromIndex</code>, then
1660 * <code>-1</code> is returned.
1662 * <p>All indices are specified in <code>char</code> values
1663 * (Unicode code units).
1665 * @param ch a character (Unicode code point).
1666 * @param fromIndex the index to start the search from. There is no
1667 * restriction on the value of <code>fromIndex</code>. If it is
1668 * greater than or equal to the length of this string, it has
1669 * the same effect as if it were equal to one less than the
1670 * length of this string: this entire string may be searched.
1671 * If it is negative, it has the same effect as if it were -1:
1673 * @return the index of the last occurrence of the character in the
1674 * character sequence represented by this object that is less
1675 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1676 * if the character does not occur before that point.
1678 public int lastIndexOf(int ch, int fromIndex) {
1679 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1680 // handle most cases here (ch is a BMP code point or a
1681 // negative value (invalid code point))
1682 final char[] value = this.value;
1683 final int offset = this.offset;
1684 int i = offset + Math.min(fromIndex, count - 1);
1685 for (; i >= offset ; i--) {
1686 if (value[i] == ch) {
1692 return lastIndexOfSupplementary(ch, fromIndex);
1697 * Handles (rare) calls of lastIndexOf with a supplementary character.
1699 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1700 if (Character.isValidCodePoint(ch)) {
1701 final char[] value = this.value;
1702 final int offset = this.offset;
1703 char hi = Character.highSurrogate(ch);
1704 char lo = Character.lowSurrogate(ch);
1705 int i = offset + Math.min(fromIndex, count - 2);
1706 for (; i >= offset; i--) {
1707 if (value[i] == hi && value[i+1] == lo) {
1716 * Returns the index within this string of the first occurrence of the
1717 * specified substring.
1719 * <p>The returned index is the smallest value <i>k</i> for which:
1721 * this.startsWith(str, <i>k</i>)
1722 * </pre></blockquote>
1723 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1725 * @param str the substring to search for.
1726 * @return the index of the first occurrence of the specified substring,
1727 * or {@code -1} if there is no such occurrence.
1729 public int indexOf(String str) {
1730 return indexOf(str, 0);
1734 * Returns the index within this string of the first occurrence of the
1735 * specified substring, starting at the specified index.
1737 * <p>The returned index is the smallest value <i>k</i> for which:
1739 * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>)
1740 * </pre></blockquote>
1741 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1743 * @param str the substring to search for.
1744 * @param fromIndex the index from which to start the search.
1745 * @return the index of the first occurrence of the specified substring,
1746 * starting at the specified index,
1747 * or {@code -1} if there is no such occurrence.
1749 public int indexOf(String str, int fromIndex) {
1750 return indexOf(value, offset, count,
1751 str.value, str.offset, str.count, fromIndex);
1755 * Code shared by String and StringBuffer to do searches. The
1756 * source is the character array being searched, and the target
1757 * is the string being searched for.
1759 * @param source the characters being searched.
1760 * @param sourceOffset offset of the source string.
1761 * @param sourceCount count of the source string.
1762 * @param target the characters being searched for.
1763 * @param targetOffset offset of the target string.
1764 * @param targetCount count of the target string.
1765 * @param fromIndex the index to begin searching from.
1767 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1768 char[] target, int targetOffset, int targetCount,
1770 if (fromIndex >= sourceCount) {
1771 return (targetCount == 0 ? sourceCount : -1);
1773 if (fromIndex < 0) {
1776 if (targetCount == 0) {
1780 char first = target[targetOffset];
1781 int max = sourceOffset + (sourceCount - targetCount);
1783 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1784 /* Look for first character. */
1785 if (source[i] != first) {
1786 while (++i <= max && source[i] != first);
1789 /* Found first character, now look at the rest of v2 */
1792 int end = j + targetCount - 1;
1793 for (int k = targetOffset + 1; j < end && source[j] ==
1794 target[k]; j++, k++);
1797 /* Found whole string. */
1798 return i - sourceOffset;
1806 * Returns the index within this string of the last occurrence of the
1807 * specified substring. The last occurrence of the empty string ""
1808 * is considered to occur at the index value {@code this.length()}.
1810 * <p>The returned index is the largest value <i>k</i> for which:
1812 * this.startsWith(str, <i>k</i>)
1813 * </pre></blockquote>
1814 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1816 * @param str the substring to search for.
1817 * @return the index of the last occurrence of the specified substring,
1818 * or {@code -1} if there is no such occurrence.
1820 public int lastIndexOf(String str) {
1821 return lastIndexOf(str, count);
1825 * Returns the index within this string of the last occurrence of the
1826 * specified substring, searching backward starting at the specified index.
1828 * <p>The returned index is the largest value <i>k</i> for which:
1830 * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>)
1831 * </pre></blockquote>
1832 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1834 * @param str the substring to search for.
1835 * @param fromIndex the index to start the search from.
1836 * @return the index of the last occurrence of the specified substring,
1837 * searching backward from the specified index,
1838 * or {@code -1} if there is no such occurrence.
1840 public int lastIndexOf(String str, int fromIndex) {
1841 return lastIndexOf(value, offset, count,
1842 str.value, str.offset, str.count, fromIndex);
1846 * Code shared by String and StringBuffer to do searches. The
1847 * source is the character array being searched, and the target
1848 * is the string being searched for.
1850 * @param source the characters being searched.
1851 * @param sourceOffset offset of the source string.
1852 * @param sourceCount count of the source string.
1853 * @param target the characters being searched for.
1854 * @param targetOffset offset of the target string.
1855 * @param targetCount count of the target string.
1856 * @param fromIndex the index to begin searching from.
1858 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1859 char[] target, int targetOffset, int targetCount,
1862 * Check arguments; return immediately where possible. For
1863 * consistency, don't check for null str.
1865 int rightIndex = sourceCount - targetCount;
1866 if (fromIndex < 0) {
1869 if (fromIndex > rightIndex) {
1870 fromIndex = rightIndex;
1872 /* Empty string always matches. */
1873 if (targetCount == 0) {
1877 int strLastIndex = targetOffset + targetCount - 1;
1878 char strLastChar = target[strLastIndex];
1879 int min = sourceOffset + targetCount - 1;
1880 int i = min + fromIndex;
1882 startSearchForLastChar:
1884 while (i >= min && source[i] != strLastChar) {
1891 int start = j - (targetCount - 1);
1892 int k = strLastIndex - 1;
1895 if (source[j--] != target[k--]) {
1897 continue startSearchForLastChar;
1900 return start - sourceOffset + 1;
1905 * Returns a new string that is a substring of this string. The
1906 * substring begins with the character at the specified index and
1907 * extends to the end of this string. <p>
1910 * "unhappy".substring(2) returns "happy"
1911 * "Harbison".substring(3) returns "bison"
1912 * "emptiness".substring(9) returns "" (an empty string)
1913 * </pre></blockquote>
1915 * @param beginIndex the beginning index, inclusive.
1916 * @return the specified substring.
1917 * @exception IndexOutOfBoundsException if
1918 * <code>beginIndex</code> is negative or larger than the
1919 * length of this <code>String</code> object.
1921 public String substring(int beginIndex) {
1922 return substring(beginIndex, count);
1926 * Returns a new string that is a substring of this string. The
1927 * substring begins at the specified <code>beginIndex</code> and
1928 * extends to the character at index <code>endIndex - 1</code>.
1929 * Thus the length of the substring is <code>endIndex-beginIndex</code>.
1933 * "hamburger".substring(4, 8) returns "urge"
1934 * "smiles".substring(1, 5) returns "mile"
1935 * </pre></blockquote>
1937 * @param beginIndex the beginning index, inclusive.
1938 * @param endIndex the ending index, exclusive.
1939 * @return the specified substring.
1940 * @exception IndexOutOfBoundsException if the
1941 * <code>beginIndex</code> is negative, or
1942 * <code>endIndex</code> is larger than the length of
1943 * this <code>String</code> object, or
1944 * <code>beginIndex</code> is larger than
1945 * <code>endIndex</code>.
1947 public String substring(int beginIndex, int endIndex) {
1948 if (beginIndex < 0) {
1949 throw new StringIndexOutOfBoundsException(beginIndex);
1951 if (endIndex > count) {
1952 throw new StringIndexOutOfBoundsException(endIndex);
1954 if (beginIndex > endIndex) {
1955 throw new StringIndexOutOfBoundsException(endIndex - beginIndex);
1957 return ((beginIndex == 0) && (endIndex == count)) ? this :
1958 new String(offset + beginIndex, endIndex - beginIndex, value);
1962 * Returns a new character sequence that is a subsequence of this sequence.
1964 * <p> An invocation of this method of the form
1967 * str.subSequence(begin, end)</pre></blockquote>
1969 * behaves in exactly the same way as the invocation
1972 * str.substring(begin, end)</pre></blockquote>
1974 * This method is defined so that the <tt>String</tt> class can implement
1975 * the {@link CharSequence} interface. </p>
1977 * @param beginIndex the begin index, inclusive.
1978 * @param endIndex the end index, exclusive.
1979 * @return the specified subsequence.
1981 * @throws IndexOutOfBoundsException
1982 * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative,
1983 * if <tt>endIndex</tt> is greater than <tt>length()</tt>,
1984 * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt>
1989 public CharSequence subSequence(int beginIndex, int endIndex) {
1990 return this.substring(beginIndex, endIndex);
1994 * Concatenates the specified string to the end of this string.
1996 * If the length of the argument string is <code>0</code>, then this
1997 * <code>String</code> object is returned. Otherwise, a new
1998 * <code>String</code> object is created, representing a character
1999 * sequence that is the concatenation of the character sequence
2000 * represented by this <code>String</code> object and the character
2001 * sequence represented by the argument string.<p>
2004 * "cares".concat("s") returns "caress"
2005 * "to".concat("get").concat("her") returns "together"
2006 * </pre></blockquote>
2008 * @param str the <code>String</code> that is concatenated to the end
2009 * of this <code>String</code>.
2010 * @return a string that represents the concatenation of this object's
2011 * characters followed by the string argument's characters.
2013 public String concat(String str) {
2014 int otherLen = str.length();
2015 if (otherLen == 0) {
2018 char buf[] = new char[count + otherLen];
2019 getChars(0, count, buf, 0);
2020 str.getChars(0, otherLen, buf, count);
2021 return new String(0, count + otherLen, buf);
2025 * Returns a new string resulting from replacing all occurrences of
2026 * <code>oldChar</code> in this string with <code>newChar</code>.
2028 * If the character <code>oldChar</code> does not occur in the
2029 * character sequence represented by this <code>String</code> object,
2030 * then a reference to this <code>String</code> object is returned.
2031 * Otherwise, a new <code>String</code> object is created that
2032 * represents a character sequence identical to the character sequence
2033 * represented by this <code>String</code> object, except that every
2034 * occurrence of <code>oldChar</code> is replaced by an occurrence
2035 * of <code>newChar</code>.
2039 * "mesquite in your cellar".replace('e', 'o')
2040 * returns "mosquito in your collar"
2041 * "the war of baronets".replace('r', 'y')
2042 * returns "the way of bayonets"
2043 * "sparring with a purple porpoise".replace('p', 't')
2044 * returns "starring with a turtle tortoise"
2045 * "JonL".replace('q', 'x') returns "JonL" (no change)
2046 * </pre></blockquote>
2048 * @param oldChar the old character.
2049 * @param newChar the new character.
2050 * @return a string derived from this string by replacing every
2051 * occurrence of <code>oldChar</code> with <code>newChar</code>.
2053 public String replace(char oldChar, char newChar) {
2054 if (oldChar != newChar) {
2057 char[] val = value; /* avoid getfield opcode */
2058 int off = offset; /* avoid getfield opcode */
2061 if (val[off + i] == oldChar) {
2066 char buf[] = new char[len];
2067 for (int j = 0 ; j < i ; j++) {
2068 buf[j] = val[off+j];
2071 char c = val[off + i];
2072 buf[i] = (c == oldChar) ? newChar : c;
2075 return new String(0, len, buf);
2082 * Tells whether or not this string matches the given <a
2083 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2085 * <p> An invocation of this method of the form
2086 * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the
2087 * same result as the expression
2089 * <blockquote><tt> {@link java.util.regex.Pattern}.{@link
2090 * java.util.regex.Pattern#matches(String,CharSequence)
2091 * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote>
2094 * the regular expression to which this string is to be matched
2096 * @return <tt>true</tt> if, and only if, this string matches the
2097 * given regular expression
2099 * @throws PatternSyntaxException
2100 * if the regular expression's syntax is invalid
2102 * @see java.util.regex.Pattern
2107 public boolean matches(String regex) {
2108 throw new UnsupportedOperationException();
2112 * Returns true if and only if this string contains the specified
2113 * sequence of char values.
2115 * @param s the sequence to search for
2116 * @return true if this string contains <code>s</code>, false otherwise
2117 * @throws NullPointerException if <code>s</code> is <code>null</code>
2120 public boolean contains(CharSequence s) {
2121 return indexOf(s.toString()) > -1;
2125 * Replaces the first substring of this string that matches the given <a
2126 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2127 * given replacement.
2129 * <p> An invocation of this method of the form
2130 * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2131 * yields exactly the same result as the expression
2134 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2135 * compile}(</tt><i>regex</i><tt>).{@link
2136 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2137 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst
2138 * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote>
2141 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2142 * replacement string may cause the results to be different than if it were
2143 * being treated as a literal replacement string; see
2144 * {@link java.util.regex.Matcher#replaceFirst}.
2145 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2146 * meaning of these characters, if desired.
2149 * the regular expression to which this string is to be matched
2150 * @param replacement
2151 * the string to be substituted for the first match
2153 * @return The resulting <tt>String</tt>
2155 * @throws PatternSyntaxException
2156 * if the regular expression's syntax is invalid
2158 * @see java.util.regex.Pattern
2163 public String replaceFirst(String regex, String replacement) {
2164 throw new UnsupportedOperationException();
2168 * Replaces each substring of this string that matches the given <a
2169 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2170 * given replacement.
2172 * <p> An invocation of this method of the form
2173 * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2174 * yields exactly the same result as the expression
2177 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2178 * compile}(</tt><i>regex</i><tt>).{@link
2179 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2180 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll
2181 * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote>
2184 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2185 * replacement string may cause the results to be different than if it were
2186 * being treated as a literal replacement string; see
2187 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2188 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2189 * meaning of these characters, if desired.
2192 * the regular expression to which this string is to be matched
2193 * @param replacement
2194 * the string to be substituted for each match
2196 * @return The resulting <tt>String</tt>
2198 * @throws PatternSyntaxException
2199 * if the regular expression's syntax is invalid
2201 * @see java.util.regex.Pattern
2206 public String replaceAll(String regex, String replacement) {
2207 throw new UnsupportedOperationException();
2211 * Replaces each substring of this string that matches the literal target
2212 * sequence with the specified literal replacement sequence. The
2213 * replacement proceeds from the beginning of the string to the end, for
2214 * example, replacing "aa" with "b" in the string "aaa" will result in
2215 * "ba" rather than "ab".
2217 * @param target The sequence of char values to be replaced
2218 * @param replacement The replacement sequence of char values
2219 * @return The resulting string
2220 * @throws NullPointerException if <code>target</code> or
2221 * <code>replacement</code> is <code>null</code>.
2224 public String replace(CharSequence target, CharSequence replacement) {
2225 throw new UnsupportedOperationException("This one should be supported, but without dep on rest of regexp");
2229 * Splits this string around matches of the given
2230 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2232 * <p> The array returned by this method contains each substring of this
2233 * string that is terminated by another substring that matches the given
2234 * expression or is terminated by the end of the string. The substrings in
2235 * the array are in the order in which they occur in this string. If the
2236 * expression does not match any part of the input then the resulting array
2237 * has just one element, namely this string.
2239 * <p> The <tt>limit</tt> parameter controls the number of times the
2240 * pattern is applied and therefore affects the length of the resulting
2241 * array. If the limit <i>n</i> is greater than zero then the pattern
2242 * will be applied at most <i>n</i> - 1 times, the array's
2243 * length will be no greater than <i>n</i>, and the array's last entry
2244 * will contain all input beyond the last matched delimiter. If <i>n</i>
2245 * is non-positive then the pattern will be applied as many times as
2246 * possible and the array can have any length. If <i>n</i> is zero then
2247 * the pattern will be applied as many times as possible, the array can
2248 * have any length, and trailing empty strings will be discarded.
2250 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the
2251 * following results with these parameters:
2253 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2259 * <tr><td align=center>:</td>
2260 * <td align=center>2</td>
2261 * <td><tt>{ "boo", "and:foo" }</tt></td></tr>
2262 * <tr><td align=center>:</td>
2263 * <td align=center>5</td>
2264 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2265 * <tr><td align=center>:</td>
2266 * <td align=center>-2</td>
2267 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2268 * <tr><td align=center>o</td>
2269 * <td align=center>5</td>
2270 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2271 * <tr><td align=center>o</td>
2272 * <td align=center>-2</td>
2273 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2274 * <tr><td align=center>o</td>
2275 * <td align=center>0</td>
2276 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2277 * </table></blockquote>
2279 * <p> An invocation of this method of the form
2280 * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt>
2281 * yields the same result as the expression
2284 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2285 * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link
2286 * java.util.regex.Pattern#split(java.lang.CharSequence,int)
2287 * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt>
2292 * the delimiting regular expression
2295 * the result threshold, as described above
2297 * @return the array of strings computed by splitting this string
2298 * around matches of the given regular expression
2300 * @throws PatternSyntaxException
2301 * if the regular expression's syntax is invalid
2303 * @see java.util.regex.Pattern
2308 public String[] split(String regex, int limit) {
2309 throw new UnsupportedOperationException("Needs regexp");
2313 * Splits this string around matches of the given <a
2314 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2316 * <p> This method works as if by invoking the two-argument {@link
2317 * #split(String, int) split} method with the given expression and a limit
2318 * argument of zero. Trailing empty strings are therefore not included in
2319 * the resulting array.
2321 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the following
2322 * results with these expressions:
2324 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2329 * <tr><td align=center>:</td>
2330 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2331 * <tr><td align=center>o</td>
2332 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2333 * </table></blockquote>
2337 * the delimiting regular expression
2339 * @return the array of strings computed by splitting this string
2340 * around matches of the given regular expression
2342 * @throws PatternSyntaxException
2343 * if the regular expression's syntax is invalid
2345 * @see java.util.regex.Pattern
2350 public String[] split(String regex) {
2351 return split(regex, 0);
2355 * Converts all of the characters in this <code>String</code> to lower
2356 * case using the rules of the given <code>Locale</code>. Case mapping is based
2357 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2358 * class. Since case mappings are not always 1:1 char mappings, the resulting
2359 * <code>String</code> may be a different length than the original <code>String</code>.
2361 * Examples of lowercase mappings are in the following table:
2362 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2364 * <th>Language Code of Locale</th>
2365 * <th>Upper Case</th>
2366 * <th>Lower Case</th>
2367 * <th>Description</th>
2370 * <td>tr (Turkish)</td>
2371 * <td>\u0130</td>
2372 * <td>\u0069</td>
2373 * <td>capital letter I with dot above -> small letter i</td>
2376 * <td>tr (Turkish)</td>
2377 * <td>\u0049</td>
2378 * <td>\u0131</td>
2379 * <td>capital letter I -> small letter dotless i </td>
2383 * <td>French Fries</td>
2384 * <td>french fries</td>
2385 * <td>lowercased all chars in String</td>
2389 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2390 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2391 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2392 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2393 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2394 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2395 * <td>lowercased all chars in String</td>
2399 * @param locale use the case transformation rules for this locale
2400 * @return the <code>String</code>, converted to lowercase.
2401 * @see java.lang.String#toLowerCase()
2402 * @see java.lang.String#toUpperCase()
2403 * @see java.lang.String#toUpperCase(Locale)
2406 // public String toLowerCase(Locale locale) {
2407 // if (locale == null) {
2408 // throw new NullPointerException();
2413 // /* Now check if there are any characters that need to be changed. */
2415 // for (firstUpper = 0 ; firstUpper < count; ) {
2416 // char c = value[offset+firstUpper];
2417 // if ((c >= Character.MIN_HIGH_SURROGATE) &&
2418 // (c <= Character.MAX_HIGH_SURROGATE)) {
2419 // int supplChar = codePointAt(firstUpper);
2420 // if (supplChar != Character.toLowerCase(supplChar)) {
2423 // firstUpper += Character.charCount(supplChar);
2425 // if (c != Character.toLowerCase(c)) {
2434 // char[] result = new char[count];
2435 // int resultOffset = 0; /* result may grow, so i+resultOffset
2436 // * is the write location in result */
2438 // /* Just copy the first few lowerCase characters. */
2439 // System.arraycopy(value, offset, result, 0, firstUpper);
2441 // String lang = locale.getLanguage();
2442 // boolean localeDependent =
2443 // (lang == "tr" || lang == "az" || lang == "lt");
2444 // char[] lowerCharArray;
2448 // for (int i = firstUpper; i < count; i += srcCount) {
2449 // srcChar = (int)value[offset+i];
2450 // if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2451 // (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2452 // srcChar = codePointAt(i);
2453 // srcCount = Character.charCount(srcChar);
2457 // if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2458 // lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2459 // } else if (srcChar == '\u0130') { // LATIN CAPITAL LETTER I DOT
2460 // lowerChar = Character.ERROR;
2462 // lowerChar = Character.toLowerCase(srcChar);
2464 // if ((lowerChar == Character.ERROR) ||
2465 // (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2466 // if (lowerChar == Character.ERROR) {
2467 // if (!localeDependent && srcChar == '\u0130') {
2469 // ConditionalSpecialCasing.toLowerCaseCharArray(this, i, Locale.ENGLISH);
2472 // ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2474 // } else if (srcCount == 2) {
2475 // resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount;
2478 // lowerCharArray = Character.toChars(lowerChar);
2481 // /* Grow result if needed */
2482 // int mapLen = lowerCharArray.length;
2483 // if (mapLen > srcCount) {
2484 // char[] result2 = new char[result.length + mapLen - srcCount];
2485 // System.arraycopy(result, 0, result2, 0,
2486 // i + resultOffset);
2487 // result = result2;
2489 // for (int x=0; x<mapLen; ++x) {
2490 // result[i+resultOffset+x] = lowerCharArray[x];
2492 // resultOffset += (mapLen - srcCount);
2494 // result[i+resultOffset] = (char)lowerChar;
2497 // return new String(0, count+resultOffset, result);
2501 * Converts all of the characters in this <code>String</code> to lower
2502 * case using the rules of the default locale. This is equivalent to calling
2503 * <code>toLowerCase(Locale.getDefault())</code>.
2505 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2506 * results if used for strings that are intended to be interpreted locale
2508 * Examples are programming language identifiers, protocol keys, and HTML
2510 * For instance, <code>"TITLE".toLowerCase()</code> in a Turkish locale
2511 * returns <code>"t\u005Cu0131tle"</code>, where '\u005Cu0131' is the
2512 * LATIN SMALL LETTER DOTLESS I character.
2513 * To obtain correct results for locale insensitive strings, use
2514 * <code>toLowerCase(Locale.ENGLISH)</code>.
2516 * @return the <code>String</code>, converted to lowercase.
2517 * @see java.lang.String#toLowerCase(Locale)
2519 public String toLowerCase() {
2520 throw new UnsupportedOperationException("Should be supported but without connection to locale");
2524 * Converts all of the characters in this <code>String</code> to upper
2525 * case using the rules of the given <code>Locale</code>. Case mapping is based
2526 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2527 * class. Since case mappings are not always 1:1 char mappings, the resulting
2528 * <code>String</code> may be a different length than the original <code>String</code>.
2530 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2532 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2534 * <th>Language Code of Locale</th>
2535 * <th>Lower Case</th>
2536 * <th>Upper Case</th>
2537 * <th>Description</th>
2540 * <td>tr (Turkish)</td>
2541 * <td>\u0069</td>
2542 * <td>\u0130</td>
2543 * <td>small letter i -> capital letter I with dot above</td>
2546 * <td>tr (Turkish)</td>
2547 * <td>\u0131</td>
2548 * <td>\u0049</td>
2549 * <td>small letter dotless i -> capital letter I</td>
2553 * <td>\u00df</td>
2554 * <td>\u0053 \u0053</td>
2555 * <td>small letter sharp s -> two letters: SS</td>
2559 * <td>Fahrvergnügen</td>
2560 * <td>FAHRVERGNÜGEN</td>
2564 * @param locale use the case transformation rules for this locale
2565 * @return the <code>String</code>, converted to uppercase.
2566 * @see java.lang.String#toUpperCase()
2567 * @see java.lang.String#toLowerCase()
2568 * @see java.lang.String#toLowerCase(Locale)
2571 /* not for javascript
2572 public String toUpperCase(Locale locale) {
2573 if (locale == null) {
2574 throw new NullPointerException();
2579 // Now check if there are any characters that need to be changed.
2581 for (firstLower = 0 ; firstLower < count; ) {
2582 int c = (int)value[offset+firstLower];
2584 if ((c >= Character.MIN_HIGH_SURROGATE) &&
2585 (c <= Character.MAX_HIGH_SURROGATE)) {
2586 c = codePointAt(firstLower);
2587 srcCount = Character.charCount(c);
2591 int upperCaseChar = Character.toUpperCaseEx(c);
2592 if ((upperCaseChar == Character.ERROR) ||
2593 (c != upperCaseChar)) {
2596 firstLower += srcCount;
2601 char[] result = new char[count]; /* may grow *
2602 int resultOffset = 0; /* result may grow, so i+resultOffset
2603 * is the write location in result *
2605 /* Just copy the first few upperCase characters. *
2606 System.arraycopy(value, offset, result, 0, firstLower);
2608 String lang = locale.getLanguage();
2609 boolean localeDependent =
2610 (lang == "tr" || lang == "az" || lang == "lt");
2611 char[] upperCharArray;
2615 for (int i = firstLower; i < count; i += srcCount) {
2616 srcChar = (int)value[offset+i];
2617 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2618 (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2619 srcChar = codePointAt(i);
2620 srcCount = Character.charCount(srcChar);
2624 if (localeDependent) {
2625 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2627 upperChar = Character.toUpperCaseEx(srcChar);
2629 if ((upperChar == Character.ERROR) ||
2630 (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2631 if (upperChar == Character.ERROR) {
2632 if (localeDependent) {
2634 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
2636 upperCharArray = Character.toUpperCaseCharArray(srcChar);
2638 } else if (srcCount == 2) {
2639 resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount;
2642 upperCharArray = Character.toChars(upperChar);
2645 /* Grow result if needed *
2646 int mapLen = upperCharArray.length;
2647 if (mapLen > srcCount) {
2648 char[] result2 = new char[result.length + mapLen - srcCount];
2649 System.arraycopy(result, 0, result2, 0,
2653 for (int x=0; x<mapLen; ++x) {
2654 result[i+resultOffset+x] = upperCharArray[x];
2656 resultOffset += (mapLen - srcCount);
2658 result[i+resultOffset] = (char)upperChar;
2661 return new String(0, count+resultOffset, result);
2666 * Converts all of the characters in this <code>String</code> to upper
2667 * case using the rules of the default locale. This method is equivalent to
2668 * <code>toUpperCase(Locale.getDefault())</code>.
2670 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2671 * results if used for strings that are intended to be interpreted locale
2673 * Examples are programming language identifiers, protocol keys, and HTML
2675 * For instance, <code>"title".toUpperCase()</code> in a Turkish locale
2676 * returns <code>"T\u005Cu0130TLE"</code>, where '\u005Cu0130' is the
2677 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2678 * To obtain correct results for locale insensitive strings, use
2679 * <code>toUpperCase(Locale.ENGLISH)</code>.
2681 * @return the <code>String</code>, converted to uppercase.
2682 * @see java.lang.String#toUpperCase(Locale)
2684 public String toUpperCase() {
2685 throw new UnsupportedOperationException();
2689 * Returns a copy of the string, with leading and trailing whitespace
2692 * If this <code>String</code> object represents an empty character
2693 * sequence, or the first and last characters of character sequence
2694 * represented by this <code>String</code> object both have codes
2695 * greater than <code>'\u0020'</code> (the space character), then a
2696 * reference to this <code>String</code> object is returned.
2698 * Otherwise, if there is no character with a code greater than
2699 * <code>'\u0020'</code> in the string, then a new
2700 * <code>String</code> object representing an empty string is created
2703 * Otherwise, let <i>k</i> be the index of the first character in the
2704 * string whose code is greater than <code>'\u0020'</code>, and let
2705 * <i>m</i> be the index of the last character in the string whose code
2706 * is greater than <code>'\u0020'</code>. A new <code>String</code>
2707 * object is created, representing the substring of this string that
2708 * begins with the character at index <i>k</i> and ends with the
2709 * character at index <i>m</i>-that is, the result of
2710 * <code>this.substring(<i>k</i>, <i>m</i>+1)</code>.
2712 * This method may be used to trim whitespace (as defined above) from
2713 * the beginning and end of a string.
2715 * @return A copy of this string with leading and trailing white
2716 * space removed, or this string if it has no leading or
2717 * trailing white space.
2719 public String trim() {
2722 int off = offset; /* avoid getfield opcode */
2723 char[] val = value; /* avoid getfield opcode */
2725 while ((st < len) && (val[off + st] <= ' ')) {
2728 while ((st < len) && (val[off + len - 1] <= ' ')) {
2731 return ((st > 0) || (len < count)) ? substring(st, len) : this;
2735 * This object (which is already a string!) is itself returned.
2737 * @return the string itself.
2739 public String toString() {
2744 * Converts this string to a new character array.
2746 * @return a newly allocated character array whose length is the length
2747 * of this string and whose contents are initialized to contain
2748 * the character sequence represented by this string.
2750 public char[] toCharArray() {
2751 char result[] = new char[count];
2752 getChars(0, count, result, 0);
2757 * Returns a formatted string using the specified format string and
2760 * <p> The locale always used is the one returned by {@link
2761 * java.util.Locale#getDefault() Locale.getDefault()}.
2764 * A <a href="../util/Formatter.html#syntax">format string</a>
2767 * Arguments referenced by the format specifiers in the format
2768 * string. If there are more arguments than format specifiers, the
2769 * extra arguments are ignored. The number of arguments is
2770 * variable and may be zero. The maximum number of arguments is
2771 * limited by the maximum dimension of a Java array as defined by
2772 * <cite>The Java™ Virtual Machine Specification</cite>.
2773 * The behaviour on a
2774 * <tt>null</tt> argument depends on the <a
2775 * href="../util/Formatter.html#syntax">conversion</a>.
2777 * @throws IllegalFormatException
2778 * If a format string contains an illegal syntax, a format
2779 * specifier that is incompatible with the given arguments,
2780 * insufficient arguments given the format string, or other
2781 * illegal conditions. For specification of all possible
2782 * formatting errors, see the <a
2783 * href="../util/Formatter.html#detail">Details</a> section of the
2784 * formatter class specification.
2786 * @throws NullPointerException
2787 * If the <tt>format</tt> is <tt>null</tt>
2789 * @return A formatted string
2791 * @see java.util.Formatter
2794 public static String format(String format, Object ... args) {
2795 throw new UnsupportedOperationException();
2799 * Returns a formatted string using the specified locale, format string,
2803 * The {@linkplain java.util.Locale locale} to apply during
2804 * formatting. If <tt>l</tt> is <tt>null</tt> then no localization
2808 * A <a href="../util/Formatter.html#syntax">format string</a>
2811 * Arguments referenced by the format specifiers in the format
2812 * string. If there are more arguments than format specifiers, the
2813 * extra arguments are ignored. The number of arguments is
2814 * variable and may be zero. The maximum number of arguments is
2815 * limited by the maximum dimension of a Java array as defined by
2816 * <cite>The Java™ Virtual Machine Specification</cite>.
2817 * The behaviour on a
2818 * <tt>null</tt> argument depends on the <a
2819 * href="../util/Formatter.html#syntax">conversion</a>.
2821 * @throws IllegalFormatException
2822 * If a format string contains an illegal syntax, a format
2823 * specifier that is incompatible with the given arguments,
2824 * insufficient arguments given the format string, or other
2825 * illegal conditions. For specification of all possible
2826 * formatting errors, see the <a
2827 * href="../util/Formatter.html#detail">Details</a> section of the
2828 * formatter class specification
2830 * @throws NullPointerException
2831 * If the <tt>format</tt> is <tt>null</tt>
2833 * @return A formatted string
2835 * @see java.util.Formatter
2838 // public static String format(Locale l, String format, Object ... args) {
2839 // return new Formatter(l).format(format, args).toString();
2843 * Returns the string representation of the <code>Object</code> argument.
2845 * @param obj an <code>Object</code>.
2846 * @return if the argument is <code>null</code>, then a string equal to
2847 * <code>"null"</code>; otherwise, the value of
2848 * <code>obj.toString()</code> is returned.
2849 * @see java.lang.Object#toString()
2851 public static String valueOf(Object obj) {
2852 return (obj == null) ? "null" : obj.toString();
2856 * Returns the string representation of the <code>char</code> array
2857 * argument. The contents of the character array are copied; subsequent
2858 * modification of the character array does not affect the newly
2861 * @param data a <code>char</code> array.
2862 * @return a newly allocated string representing the same sequence of
2863 * characters contained in the character array argument.
2865 public static String valueOf(char data[]) {
2866 return new String(data);
2870 * Returns the string representation of a specific subarray of the
2871 * <code>char</code> array argument.
2873 * The <code>offset</code> argument is the index of the first
2874 * character of the subarray. The <code>count</code> argument
2875 * specifies the length of the subarray. The contents of the subarray
2876 * are copied; subsequent modification of the character array does not
2877 * affect the newly created string.
2879 * @param data the character array.
2880 * @param offset the initial offset into the value of the
2881 * <code>String</code>.
2882 * @param count the length of the value of the <code>String</code>.
2883 * @return a string representing the sequence of characters contained
2884 * in the subarray of the character array argument.
2885 * @exception IndexOutOfBoundsException if <code>offset</code> is
2886 * negative, or <code>count</code> is negative, or
2887 * <code>offset+count</code> is larger than
2888 * <code>data.length</code>.
2890 public static String valueOf(char data[], int offset, int count) {
2891 return new String(data, offset, count);
2895 * Returns a String that represents the character sequence in the
2898 * @param data the character array.
2899 * @param offset initial offset of the subarray.
2900 * @param count length of the subarray.
2901 * @return a <code>String</code> that contains the characters of the
2902 * specified subarray of the character array.
2904 public static String copyValueOf(char data[], int offset, int count) {
2905 // All public String constructors now copy the data.
2906 return new String(data, offset, count);
2910 * Returns a String that represents the character sequence in the
2913 * @param data the character array.
2914 * @return a <code>String</code> that contains the characters of the
2917 public static String copyValueOf(char data[]) {
2918 return copyValueOf(data, 0, data.length);
2922 * Returns the string representation of the <code>boolean</code> argument.
2924 * @param b a <code>boolean</code>.
2925 * @return if the argument is <code>true</code>, a string equal to
2926 * <code>"true"</code> is returned; otherwise, a string equal to
2927 * <code>"false"</code> is returned.
2929 public static String valueOf(boolean b) {
2930 return b ? "true" : "false";
2934 * Returns the string representation of the <code>char</code>
2937 * @param c a <code>char</code>.
2938 * @return a string of length <code>1</code> containing
2939 * as its single character the argument <code>c</code>.
2941 public static String valueOf(char c) {
2943 return new String(0, 1, data);
2947 * Returns the string representation of the <code>int</code> argument.
2949 * The representation is exactly the one returned by the
2950 * <code>Integer.toString</code> method of one argument.
2952 * @param i an <code>int</code>.
2953 * @return a string representation of the <code>int</code> argument.
2954 * @see java.lang.Integer#toString(int, int)
2956 public static String valueOf(int i) {
2957 return Integer.toString(i);
2961 * Returns the string representation of the <code>long</code> argument.
2963 * The representation is exactly the one returned by the
2964 * <code>Long.toString</code> method of one argument.
2966 * @param l a <code>long</code>.
2967 * @return a string representation of the <code>long</code> argument.
2968 * @see java.lang.Long#toString(long)
2970 public static String valueOf(long l) {
2971 return Long.toString(l);
2975 * Returns the string representation of the <code>float</code> argument.
2977 * The representation is exactly the one returned by the
2978 * <code>Float.toString</code> method of one argument.
2980 * @param f a <code>float</code>.
2981 * @return a string representation of the <code>float</code> argument.
2982 * @see java.lang.Float#toString(float)
2984 public static String valueOf(float f) {
2985 return Float.toString(f);
2989 * Returns the string representation of the <code>double</code> argument.
2991 * The representation is exactly the one returned by the
2992 * <code>Double.toString</code> method of one argument.
2994 * @param d a <code>double</code>.
2995 * @return a string representation of the <code>double</code> argument.
2996 * @see java.lang.Double#toString(double)
2998 public static String valueOf(double d) {
2999 return Double.toString(d);
3003 * Returns a canonical representation for the string object.
3005 * A pool of strings, initially empty, is maintained privately by the
3006 * class <code>String</code>.
3008 * When the intern method is invoked, if the pool already contains a
3009 * string equal to this <code>String</code> object as determined by
3010 * the {@link #equals(Object)} method, then the string from the pool is
3011 * returned. Otherwise, this <code>String</code> object is added to the
3012 * pool and a reference to this <code>String</code> object is returned.
3014 * It follows that for any two strings <code>s</code> and <code>t</code>,
3015 * <code>s.intern() == t.intern()</code> is <code>true</code>
3016 * if and only if <code>s.equals(t)</code> is <code>true</code>.
3018 * All literal strings and string-valued constant expressions are
3019 * interned. String literals are defined in section 3.10.5 of the
3020 * <cite>The Java™ Language Specification</cite>.
3022 * @return a string that has the same contents as this string, but is
3023 * guaranteed to be from a pool of unique strings.
3025 public native String intern();
3027 static char[] copyOfRange(char[] original, int from, int to) {
3028 int newLength = to - from;
3029 if (newLength < 0) {
3030 throw new IllegalArgumentException(from + " > " + to);
3032 char[] copy = new char[newLength];
3033 System.arraycopy(original, from, copy, 0,
3034 Math.min(original.length - from, newLength));
3037 static char[] copyOf(char[] original, int newLength) {
3038 char[] copy = new char[newLength];
3039 System.arraycopy(original, 0, copy, 0,
3040 Math.min(original.length, newLength));