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 org.apidesign.bck2brwsr.core.ExtraJavaScript;
29 import java.util.Comparator;
32 * The <code>String</code> class represents character strings. All
33 * string literals in Java programs, such as <code>"abc"</code>, are
34 * implemented as instances of this class.
36 * Strings are constant; their values cannot be changed after they
37 * are created. String buffers support mutable strings.
38 * Because String objects are immutable they can be shared. For example:
39 * <p><blockquote><pre>
41 * </pre></blockquote><p>
43 * <p><blockquote><pre>
44 * char data[] = {'a', 'b', 'c'};
45 * String str = new String(data);
46 * </pre></blockquote><p>
47 * Here are some more examples of how strings can be used:
48 * <p><blockquote><pre>
49 * System.out.println("abc");
51 * System.out.println("abc" + cde);
52 * String c = "abc".substring(2,3);
53 * String d = cde.substring(1, 2);
56 * The class <code>String</code> includes methods for examining
57 * individual characters of the sequence, for comparing strings, for
58 * searching strings, for extracting substrings, and for creating a
59 * copy of a string with all characters translated to uppercase or to
60 * lowercase. Case mapping is based on the Unicode Standard version
61 * specified by the {@link java.lang.Character Character} class.
63 * The Java language provides special support for the string
64 * concatenation operator ( + ), and for conversion of
65 * other objects to strings. String concatenation is implemented
66 * through the <code>StringBuilder</code>(or <code>StringBuffer</code>)
67 * class and its <code>append</code> method.
68 * String conversions are implemented through the method
69 * <code>toString</code>, defined by <code>Object</code> and
70 * inherited by all classes in Java. For additional information on
71 * string concatenation and conversion, see Gosling, Joy, and Steele,
72 * <i>The Java Language Specification</i>.
74 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
75 * or method in this class will cause a {@link NullPointerException} to be
78 * <p>A <code>String</code> represents a string in the UTF-16 format
79 * in which <em>supplementary characters</em> are represented by <em>surrogate
80 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
81 * Character Representations</a> in the <code>Character</code> class for
83 * Index values refer to <code>char</code> code units, so a supplementary
84 * character uses two positions in a <code>String</code>.
85 * <p>The <code>String</code> class provides methods for dealing with
86 * Unicode code points (i.e., characters), in addition to those for
87 * dealing with Unicode code units (i.e., <code>char</code> values).
90 * @author Arthur van Hoff
91 * @author Martin Buchholz
93 * @see java.lang.Object#toString()
94 * @see java.lang.StringBuffer
95 * @see java.lang.StringBuilder
96 * @see java.nio.charset.Charset
101 resource="/org/apidesign/vm4brwsr/emul/java_lang_String.js",
102 processByteCode=false
104 public final class String
105 implements java.io.Serializable, Comparable<String>, CharSequence
107 /** The value is used for character storage. */
108 private final char value[];
110 /** The offset is the first index of the storage that is used. */
111 private final int offset;
113 /** The count is the number of characters in the String. */
114 private final int count;
116 /** Cache the hash code for the string */
117 private int hash; // Default to 0
119 /** use serialVersionUID from JDK 1.0.2 for interoperability */
120 private static final long serialVersionUID = -6849794470754667710L;
123 * Class String is special cased within the Serialization Stream Protocol.
125 * A String instance is written initially into an ObjectOutputStream in the
128 * <code>TC_STRING</code> (utf String)
130 * The String is written by method <code>DataOutput.writeUTF</code>.
131 * A new handle is generated to refer to all future references to the
132 * string instance within the stream.
134 // private static final ObjectStreamField[] serialPersistentFields =
135 // new ObjectStreamField[0];
138 * Initializes a newly created {@code String} object so that it represents
139 * an empty character sequence. Note that use of this constructor is
140 * unnecessary since Strings are immutable.
145 this.value = new char[0];
149 * Initializes a newly created {@code String} object so that it represents
150 * the same sequence of characters as the argument; in other words, the
151 * newly created string is a copy of the argument string. Unless an
152 * explicit copy of {@code original} is needed, use of this constructor is
153 * unnecessary since Strings are immutable.
158 public String(String original) {
159 int size = original.count;
160 char[] originalValue = original.value;
162 if (originalValue.length > size) {
163 // The array representing the String is bigger than the new
164 // String itself. Perhaps this constructor is being called
165 // in order to trim the baggage, so make a copy of the array.
166 int off = original.offset;
167 v = AbstractStringBuilder.copyOfRange(originalValue, off, off+size);
169 // The array representing the String is the same
170 // size as the String, so no point in making a copy.
179 * Allocates a new {@code String} so that it represents the sequence of
180 * characters currently contained in the character array argument. The
181 * contents of the character array are copied; subsequent modification of
182 * the character array does not affect the newly created string.
185 * The initial value of the string
187 public String(char value[]) {
188 int size = value.length;
191 this.value = AbstractStringBuilder.copyOf(value, size);
195 * Allocates a new {@code String} that contains characters from a subarray
196 * of the character array argument. The {@code offset} argument is the
197 * index of the first character of the subarray and the {@code count}
198 * argument specifies the length of the subarray. The contents of the
199 * subarray are copied; subsequent modification of the character array does
200 * not affect the newly created string.
203 * Array that is the source of characters
211 * @throws IndexOutOfBoundsException
212 * If the {@code offset} and {@code count} arguments index
213 * characters outside the bounds of the {@code value} array
215 public String(char value[], int offset, int count) {
217 throw new StringIndexOutOfBoundsException(offset);
220 throw new StringIndexOutOfBoundsException(count);
222 // Note: offset or count might be near -1>>>1.
223 if (offset > value.length - count) {
224 throw new StringIndexOutOfBoundsException(offset + count);
228 this.value = AbstractStringBuilder.copyOfRange(value, offset, offset+count);
232 * Allocates a new {@code String} that contains characters from a subarray
233 * of the <a href="Character.html#unicode">Unicode code point</a> array
234 * argument. The {@code offset} argument is the index of the first code
235 * point of the subarray and the {@code count} argument specifies the
236 * length of the subarray. The contents of the subarray are converted to
237 * {@code char}s; subsequent modification of the {@code int} array does not
238 * affect the newly created string.
241 * Array that is the source of Unicode code points
249 * @throws IllegalArgumentException
250 * If any invalid Unicode code point is found in {@code
253 * @throws IndexOutOfBoundsException
254 * If the {@code offset} and {@code count} arguments index
255 * characters outside the bounds of the {@code codePoints} array
259 public String(int[] codePoints, int offset, int count) {
261 throw new StringIndexOutOfBoundsException(offset);
264 throw new StringIndexOutOfBoundsException(count);
266 // Note: offset or count might be near -1>>>1.
267 if (offset > codePoints.length - count) {
268 throw new StringIndexOutOfBoundsException(offset + count);
271 final int end = offset + count;
273 // Pass 1: Compute precise size of char[]
275 for (int i = offset; i < end; i++) {
276 int c = codePoints[i];
277 if (Character.isBmpCodePoint(c))
279 else if (Character.isValidCodePoint(c))
281 else throw new IllegalArgumentException(Integer.toString(c));
284 // Pass 2: Allocate and fill in char[]
285 final char[] v = new char[n];
287 for (int i = offset, j = 0; i < end; i++, j++) {
288 int c = codePoints[i];
289 if (Character.isBmpCodePoint(c))
292 Character.toSurrogates(c, v, j++);
301 * Allocates a new {@code String} constructed from a subarray of an array
302 * of 8-bit integer values.
304 * <p> The {@code offset} argument is the index of the first byte of the
305 * subarray, and the {@code count} argument specifies the length of the
308 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
309 * specified in the method above.
311 * @deprecated This method does not properly convert bytes into characters.
312 * As of JDK 1.1, the preferred way to do this is via the
313 * {@code String} constructors that take a {@link
314 * java.nio.charset.Charset}, charset name, or that use the platform's
318 * The bytes to be converted to characters
321 * The top 8 bits of each 16-bit Unicode code unit
328 * @throws IndexOutOfBoundsException
329 * If the {@code offset} or {@code count} argument is invalid
331 * @see #String(byte[], int)
332 * @see #String(byte[], int, int, java.lang.String)
333 * @see #String(byte[], int, int, java.nio.charset.Charset)
334 * @see #String(byte[], int, int)
335 * @see #String(byte[], java.lang.String)
336 * @see #String(byte[], java.nio.charset.Charset)
337 * @see #String(byte[])
340 public String(byte ascii[], int hibyte, int offset, int count) {
341 checkBounds(ascii, offset, count);
342 char value[] = new char[count];
345 for (int i = count ; i-- > 0 ;) {
346 value[i] = (char) (ascii[i + offset] & 0xff);
350 for (int i = count ; i-- > 0 ;) {
351 value[i] = (char) (hibyte | (ascii[i + offset] & 0xff));
360 * Allocates a new {@code String} containing characters constructed from
361 * an array of 8-bit integer values. Each character <i>c</i>in the
362 * resulting string is constructed from the corresponding component
363 * <i>b</i> in the byte array such that:
366 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
367 * | (<b><i>b</i></b> & 0xff))
368 * </pre></blockquote>
370 * @deprecated This method does not properly convert bytes into
371 * characters. As of JDK 1.1, the preferred way to do this is via the
372 * {@code String} constructors that take a {@link
373 * java.nio.charset.Charset}, charset name, or that use the platform's
377 * The bytes to be converted to characters
380 * The top 8 bits of each 16-bit Unicode code unit
382 * @see #String(byte[], int, int, java.lang.String)
383 * @see #String(byte[], int, int, java.nio.charset.Charset)
384 * @see #String(byte[], int, int)
385 * @see #String(byte[], java.lang.String)
386 * @see #String(byte[], java.nio.charset.Charset)
387 * @see #String(byte[])
390 public String(byte ascii[], int hibyte) {
391 this(ascii, hibyte, 0, ascii.length);
394 /* Common private utility method used to bounds check the byte array
395 * and requested offset & length values used by the String(byte[],..)
398 private static void checkBounds(byte[] bytes, int offset, int length) {
400 throw new StringIndexOutOfBoundsException(length);
402 throw new StringIndexOutOfBoundsException(offset);
403 if (offset > bytes.length - length)
404 throw new StringIndexOutOfBoundsException(offset + length);
408 * Constructs a new {@code String} by decoding the specified subarray of
409 * bytes using the specified charset. The length of the new {@code String}
410 * is a function of the charset, and hence may not be equal to the length
413 * <p> The behavior of this constructor when the given bytes are not valid
414 * in the given charset is unspecified. The {@link
415 * java.nio.charset.CharsetDecoder} class should be used when more control
416 * over the decoding process is required.
419 * The bytes to be decoded into characters
422 * The index of the first byte to decode
425 * The number of bytes to decode
428 * The name of a supported {@linkplain java.nio.charset.Charset
431 * @throws UnsupportedEncodingException
432 * If the named charset is not supported
434 * @throws IndexOutOfBoundsException
435 * If the {@code offset} and {@code length} arguments index
436 * characters outside the bounds of the {@code bytes} array
440 // public String(byte bytes[], int offset, int length, String charsetName)
441 // throws UnsupportedEncodingException
443 // if (charsetName == null)
444 // throw new NullPointerException("charsetName");
445 // checkBounds(bytes, offset, length);
446 // char[] v = StringCoding.decode(charsetName, bytes, offset, length);
448 // this.count = v.length;
453 * Constructs a new {@code String} by decoding the specified subarray of
454 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
455 * The length of the new {@code String} is a function of the charset, and
456 * hence may not be equal to the length of the subarray.
458 * <p> This method always replaces malformed-input and unmappable-character
459 * sequences with this charset's default replacement string. The {@link
460 * java.nio.charset.CharsetDecoder} class should be used when more control
461 * over the decoding process is required.
464 * The bytes to be decoded into characters
467 * The index of the first byte to decode
470 * The number of bytes to decode
473 * The {@linkplain java.nio.charset.Charset charset} to be used to
474 * decode the {@code bytes}
476 * @throws IndexOutOfBoundsException
477 * If the {@code offset} and {@code length} arguments index
478 * characters outside the bounds of the {@code bytes} array
482 /* don't want dependnecy on Charset
483 public String(byte bytes[], int offset, int length, Charset charset) {
485 throw new NullPointerException("charset");
486 checkBounds(bytes, offset, length);
487 char[] v = StringCoding.decode(charset, bytes, offset, length);
489 this.count = v.length;
495 * Constructs a new {@code String} by decoding the specified array of bytes
496 * using the specified {@linkplain java.nio.charset.Charset charset}. The
497 * length of the new {@code String} is a function of the charset, and hence
498 * may not be equal to the length of the byte array.
500 * <p> The behavior of this constructor when the given bytes are not valid
501 * in the given charset is unspecified. The {@link
502 * java.nio.charset.CharsetDecoder} class should be used when more control
503 * over the decoding process is required.
506 * The bytes to be decoded into characters
509 * The name of a supported {@linkplain java.nio.charset.Charset
512 * @throws UnsupportedEncodingException
513 * If the named charset is not supported
517 // public String(byte bytes[], String charsetName)
518 // throws UnsupportedEncodingException
520 // this(bytes, 0, bytes.length, charsetName);
524 * Constructs a new {@code String} by decoding the specified array of
525 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
526 * The length of the new {@code String} is a function of the charset, and
527 * hence may not be equal to the length of the byte array.
529 * <p> This method always replaces malformed-input and unmappable-character
530 * sequences with this charset's default replacement string. The {@link
531 * java.nio.charset.CharsetDecoder} class should be used when more control
532 * over the decoding process is required.
535 * The bytes to be decoded into characters
538 * The {@linkplain java.nio.charset.Charset charset} to be used to
539 * decode the {@code bytes}
543 /* don't want dep on Charset
544 public String(byte bytes[], Charset charset) {
545 this(bytes, 0, bytes.length, charset);
550 * Constructs a new {@code String} by decoding the specified subarray of
551 * bytes using the platform's default charset. The length of the new
552 * {@code String} is a function of the charset, and hence may not be equal
553 * to the length of the subarray.
555 * <p> The behavior of this constructor when the given bytes are not valid
556 * in the default charset is unspecified. The {@link
557 * java.nio.charset.CharsetDecoder} class should be used when more control
558 * over the decoding process is required.
561 * The bytes to be decoded into characters
564 * The index of the first byte to decode
567 * The number of bytes to decode
569 * @throws IndexOutOfBoundsException
570 * If the {@code offset} and the {@code length} arguments index
571 * characters outside the bounds of the {@code bytes} array
575 public String(byte bytes[], int offset, int length) {
576 checkBounds(bytes, offset, length);
577 char[] v = new char[length];
578 for (int i = 0; i < length; i++) {
579 v[i] = (char)bytes[offset++];
582 this.count = v.length;
587 * Constructs a new {@code String} by decoding the specified array of bytes
588 * using the platform's default charset. The length of the new {@code
589 * String} is a function of the charset, and hence may not be equal to the
590 * length of the byte array.
592 * <p> The behavior of this constructor when the given bytes are not valid
593 * in the default charset is unspecified. The {@link
594 * java.nio.charset.CharsetDecoder} class should be used when more control
595 * over the decoding process is required.
598 * The bytes to be decoded into characters
602 public String(byte bytes[]) {
603 this(bytes, 0, bytes.length);
607 * Allocates a new string that contains the sequence of characters
608 * currently contained in the string buffer argument. The contents of the
609 * string buffer are copied; subsequent modification of the string buffer
610 * does not affect the newly created string.
613 * A {@code StringBuffer}
615 public String(StringBuffer buffer) {
616 String result = buffer.toString();
617 this.value = result.value;
618 this.count = result.count;
619 this.offset = result.offset;
623 * Allocates a new string that contains the sequence of characters
624 * currently contained in the string builder argument. The contents of the
625 * string builder are copied; subsequent modification of the string builder
626 * does not affect the newly created string.
628 * <p> This constructor is provided to ease migration to {@code
629 * StringBuilder}. Obtaining a string from a string builder via the {@code
630 * toString} method is likely to run faster and is generally preferred.
633 * A {@code StringBuilder}
637 public String(StringBuilder builder) {
638 String result = builder.toString();
639 this.value = result.value;
640 this.count = result.count;
641 this.offset = result.offset;
645 // Package private constructor which shares value array for speed.
646 String(int offset, int count, char value[]) {
648 this.offset = offset;
653 * Returns the length of this string.
654 * The length is equal to the number of <a href="Character.html#unicode">Unicode
655 * code units</a> in the string.
657 * @return the length of the sequence of characters represented by this
660 public int length() {
665 * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>.
667 * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise
672 public boolean isEmpty() {
677 * Returns the <code>char</code> value at the
678 * specified index. An index ranges from <code>0</code> to
679 * <code>length() - 1</code>. The first <code>char</code> value of the sequence
680 * is at index <code>0</code>, the next at index <code>1</code>,
681 * and so on, as for array indexing.
683 * <p>If the <code>char</code> value specified by the index is a
684 * <a href="Character.html#unicode">surrogate</a>, the surrogate
687 * @param index the index of the <code>char</code> value.
688 * @return the <code>char</code> value at the specified index of this string.
689 * The first <code>char</code> value is at index <code>0</code>.
690 * @exception IndexOutOfBoundsException if the <code>index</code>
691 * argument is negative or not less than the length of this
694 public char charAt(int index) {
695 if ((index < 0) || (index >= count)) {
696 throw new StringIndexOutOfBoundsException(index);
698 return value[index + offset];
702 * Returns the character (Unicode code point) at the specified
703 * index. The index refers to <code>char</code> values
704 * (Unicode code units) and ranges from <code>0</code> to
705 * {@link #length()}<code> - 1</code>.
707 * <p> If the <code>char</code> value specified at the given index
708 * is in the high-surrogate range, the following index is less
709 * than the length of this <code>String</code>, and the
710 * <code>char</code> value at the following index is in the
711 * low-surrogate range, then the supplementary code point
712 * corresponding to this surrogate pair is returned. Otherwise,
713 * the <code>char</code> value at the given index is returned.
715 * @param index the index to the <code>char</code> values
716 * @return the code point value of the character at the
718 * @exception IndexOutOfBoundsException if the <code>index</code>
719 * argument is negative or not less than the length of this
723 public int codePointAt(int index) {
724 if ((index < 0) || (index >= count)) {
725 throw new StringIndexOutOfBoundsException(index);
727 return Character.codePointAtImpl(value, offset + index, offset + count);
731 * Returns the character (Unicode code point) before the specified
732 * index. The index refers to <code>char</code> values
733 * (Unicode code units) and ranges from <code>1</code> to {@link
734 * CharSequence#length() length}.
736 * <p> If the <code>char</code> value at <code>(index - 1)</code>
737 * is in the low-surrogate range, <code>(index - 2)</code> is not
738 * negative, and the <code>char</code> value at <code>(index -
739 * 2)</code> is in the high-surrogate range, then the
740 * supplementary code point value of the surrogate pair is
741 * returned. If the <code>char</code> value at <code>index -
742 * 1</code> is an unpaired low-surrogate or a high-surrogate, the
743 * surrogate value is returned.
745 * @param index the index following the code point that should be returned
746 * @return the Unicode code point value before the given index.
747 * @exception IndexOutOfBoundsException if the <code>index</code>
748 * argument is less than 1 or greater than the length
752 public int codePointBefore(int index) {
754 if ((i < 0) || (i >= count)) {
755 throw new StringIndexOutOfBoundsException(index);
757 return Character.codePointBeforeImpl(value, offset + index, offset);
761 * Returns the number of Unicode code points in the specified text
762 * range of this <code>String</code>. The text range begins at the
763 * specified <code>beginIndex</code> and extends to the
764 * <code>char</code> at index <code>endIndex - 1</code>. Thus the
765 * length (in <code>char</code>s) of the text range is
766 * <code>endIndex-beginIndex</code>. Unpaired surrogates within
767 * the text range count as one code point each.
769 * @param beginIndex the index to the first <code>char</code> of
771 * @param endIndex the index after the last <code>char</code> of
773 * @return the number of Unicode code points in the specified text
775 * @exception IndexOutOfBoundsException if the
776 * <code>beginIndex</code> is negative, or <code>endIndex</code>
777 * is larger than the length of this <code>String</code>, or
778 * <code>beginIndex</code> is larger than <code>endIndex</code>.
781 public int codePointCount(int beginIndex, int endIndex) {
782 if (beginIndex < 0 || endIndex > count || beginIndex > endIndex) {
783 throw new IndexOutOfBoundsException();
785 return Character.codePointCountImpl(value, offset+beginIndex, endIndex-beginIndex);
789 * Returns the index within this <code>String</code> that is
790 * offset from the given <code>index</code> by
791 * <code>codePointOffset</code> code points. Unpaired surrogates
792 * within the text range given by <code>index</code> and
793 * <code>codePointOffset</code> count as one code point each.
795 * @param index the index to be offset
796 * @param codePointOffset the offset in code points
797 * @return the index within this <code>String</code>
798 * @exception IndexOutOfBoundsException if <code>index</code>
799 * is negative or larger then the length of this
800 * <code>String</code>, or if <code>codePointOffset</code> is positive
801 * and the substring starting with <code>index</code> has fewer
802 * than <code>codePointOffset</code> code points,
803 * or if <code>codePointOffset</code> is negative and the substring
804 * before <code>index</code> has fewer than the absolute value
805 * of <code>codePointOffset</code> code points.
808 public int offsetByCodePoints(int index, int codePointOffset) {
809 if (index < 0 || index > count) {
810 throw new IndexOutOfBoundsException();
812 return Character.offsetByCodePointsImpl(value, offset, count,
813 offset+index, codePointOffset) - offset;
817 * Copy characters from this string into dst starting at dstBegin.
818 * This method doesn't perform any range checking.
820 void getChars(char dst[], int dstBegin) {
821 AbstractStringBuilder.arraycopy(value, offset, dst, dstBegin, count);
825 * Copies characters from this string into the destination character
828 * The first character to be copied is at index <code>srcBegin</code>;
829 * the last character to be copied is at index <code>srcEnd-1</code>
830 * (thus the total number of characters to be copied is
831 * <code>srcEnd-srcBegin</code>). The characters are copied into the
832 * subarray of <code>dst</code> starting at index <code>dstBegin</code>
833 * and ending at index:
834 * <p><blockquote><pre>
835 * dstbegin + (srcEnd-srcBegin) - 1
836 * </pre></blockquote>
838 * @param srcBegin index of the first character in the string
840 * @param srcEnd index after the last character in the string
842 * @param dst the destination array.
843 * @param dstBegin the start offset in the destination array.
844 * @exception IndexOutOfBoundsException If any of the following
846 * <ul><li><code>srcBegin</code> is negative.
847 * <li><code>srcBegin</code> is greater than <code>srcEnd</code>
848 * <li><code>srcEnd</code> is greater than the length of this
850 * <li><code>dstBegin</code> is negative
851 * <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
852 * <code>dst.length</code></ul>
854 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
856 throw new StringIndexOutOfBoundsException(srcBegin);
858 if (srcEnd > count) {
859 throw new StringIndexOutOfBoundsException(srcEnd);
861 if (srcBegin > srcEnd) {
862 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
864 AbstractStringBuilder.arraycopy(value, offset + srcBegin, dst, dstBegin,
869 * Copies characters from this string into the destination byte array. Each
870 * byte receives the 8 low-order bits of the corresponding character. The
871 * eight high-order bits of each character are not copied and do not
872 * participate in the transfer in any way.
874 * <p> The first character to be copied is at index {@code srcBegin}; the
875 * last character to be copied is at index {@code srcEnd-1}. The total
876 * number of characters to be copied is {@code srcEnd-srcBegin}. The
877 * characters, converted to bytes, are copied into the subarray of {@code
878 * dst} starting at index {@code dstBegin} and ending at index:
881 * dstbegin + (srcEnd-srcBegin) - 1
882 * </pre></blockquote>
884 * @deprecated This method does not properly convert characters into
885 * bytes. As of JDK 1.1, the preferred way to do this is via the
886 * {@link #getBytes()} method, which uses the platform's default charset.
889 * Index of the first character in the string to copy
892 * Index after the last character in the string to copy
895 * The destination array
898 * The start offset in the destination array
900 * @throws IndexOutOfBoundsException
901 * If any of the following is true:
903 * <li> {@code srcBegin} is negative
904 * <li> {@code srcBegin} is greater than {@code srcEnd}
905 * <li> {@code srcEnd} is greater than the length of this String
906 * <li> {@code dstBegin} is negative
907 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
912 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
914 throw new StringIndexOutOfBoundsException(srcBegin);
916 if (srcEnd > count) {
917 throw new StringIndexOutOfBoundsException(srcEnd);
919 if (srcBegin > srcEnd) {
920 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
923 int n = offset + srcEnd;
924 int i = offset + srcBegin;
925 char[] val = value; /* avoid getfield opcode */
928 dst[j++] = (byte)val[i++];
933 * Encodes this {@code String} into a sequence of bytes using the named
934 * charset, storing the result into a new byte array.
936 * <p> The behavior of this method when this string cannot be encoded in
937 * the given charset is unspecified. The {@link
938 * java.nio.charset.CharsetEncoder} class should be used when more control
939 * over the encoding process is required.
942 * The name of a supported {@linkplain java.nio.charset.Charset
945 * @return The resultant byte array
947 * @throws UnsupportedEncodingException
948 * If the named charset is not supported
952 // public byte[] getBytes(String charsetName)
953 // throws UnsupportedEncodingException
955 // if (charsetName == null) throw new NullPointerException();
956 // return StringCoding.encode(charsetName, value, offset, count);
960 * Encodes this {@code String} into a sequence of bytes using the given
961 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
964 * <p> This method always replaces malformed-input and unmappable-character
965 * sequences with this charset's default replacement byte array. The
966 * {@link java.nio.charset.CharsetEncoder} class should be used when more
967 * control over the encoding process is required.
970 * The {@linkplain java.nio.charset.Charset} to be used to encode
973 * @return The resultant byte array
977 /* don't want dep on Charset
978 public byte[] getBytes(Charset charset) {
979 if (charset == null) throw new NullPointerException();
980 return StringCoding.encode(charset, value, offset, count);
985 * Encodes this {@code String} into a sequence of bytes using the
986 * platform's default charset, storing the result into a new byte array.
988 * <p> The behavior of this method when this string cannot be encoded in
989 * the default charset is unspecified. The {@link
990 * java.nio.charset.CharsetEncoder} class should be used when more control
991 * over the encoding process is required.
993 * @return The resultant byte array
997 public byte[] getBytes() {
998 byte[] arr = new byte[length()];
999 for (int i = 0; i < arr.length; i++) {
1000 final char v = charAt(i);
1007 * Compares this string to the specified object. The result is {@code
1008 * true} if and only if the argument is not {@code null} and is a {@code
1009 * String} object that represents the same sequence of characters as this
1013 * The object to compare this {@code String} against
1015 * @return {@code true} if the given object represents a {@code String}
1016 * equivalent to this string, {@code false} otherwise
1018 * @see #compareTo(String)
1019 * @see #equalsIgnoreCase(String)
1021 public boolean equals(Object anObject) {
1022 if (this == anObject) {
1025 if (anObject instanceof String) {
1026 String anotherString = (String)anObject;
1028 if (n == anotherString.count) {
1030 char v2[] = anotherString.value;
1032 int j = anotherString.offset;
1034 if (v1[i++] != v2[j++])
1044 * Compares this string to the specified {@code StringBuffer}. The result
1045 * is {@code true} if and only if this {@code String} represents the same
1046 * sequence of characters as the specified {@code StringBuffer}.
1049 * The {@code StringBuffer} to compare this {@code String} against
1051 * @return {@code true} if this {@code String} represents the same
1052 * sequence of characters as the specified {@code StringBuffer},
1053 * {@code false} otherwise
1057 public boolean contentEquals(StringBuffer sb) {
1059 return contentEquals((CharSequence)sb);
1064 * Compares this string to the specified {@code CharSequence}. The result
1065 * is {@code true} if and only if this {@code String} represents the same
1066 * sequence of char values as the specified sequence.
1069 * The sequence to compare this {@code String} against
1071 * @return {@code true} if this {@code String} represents the same
1072 * sequence of char values as the specified sequence, {@code
1077 public boolean contentEquals(CharSequence cs) {
1078 if (count != cs.length())
1080 // Argument is a StringBuffer, StringBuilder
1081 if (cs instanceof AbstractStringBuilder) {
1083 char v2[] = ((AbstractStringBuilder)cs).getValue();
1088 if (v1[i++] != v2[j++])
1093 // Argument is a String
1094 if (cs.equals(this))
1096 // Argument is a generic CharSequence
1102 if (v1[i++] != cs.charAt(j++))
1109 * Compares this {@code String} to another {@code String}, ignoring case
1110 * considerations. Two strings are considered equal ignoring case if they
1111 * are of the same length and corresponding characters in the two strings
1112 * are equal ignoring case.
1114 * <p> Two characters {@code c1} and {@code c2} are considered the same
1115 * ignoring case if at least one of the following is true:
1117 * <li> The two characters are the same (as compared by the
1118 * {@code ==} operator)
1119 * <li> Applying the method {@link
1120 * java.lang.Character#toUpperCase(char)} to each character
1121 * produces the same result
1122 * <li> Applying the method {@link
1123 * java.lang.Character#toLowerCase(char)} to each character
1124 * produces the same result
1127 * @param anotherString
1128 * The {@code String} to compare this {@code String} against
1130 * @return {@code true} if the argument is not {@code null} and it
1131 * represents an equivalent {@code String} ignoring case; {@code
1134 * @see #equals(Object)
1136 public boolean equalsIgnoreCase(String anotherString) {
1137 return (this == anotherString) ? true :
1138 (anotherString != null) && (anotherString.count == count) &&
1139 regionMatches(true, 0, anotherString, 0, count);
1143 * Compares two strings lexicographically.
1144 * The comparison is based on the Unicode value of each character in
1145 * the strings. The character sequence represented by this
1146 * <code>String</code> object is compared lexicographically to the
1147 * character sequence represented by the argument string. The result is
1148 * a negative integer if this <code>String</code> object
1149 * lexicographically precedes the argument string. The result is a
1150 * positive integer if this <code>String</code> object lexicographically
1151 * follows the argument string. The result is zero if the strings
1152 * are equal; <code>compareTo</code> returns <code>0</code> exactly when
1153 * the {@link #equals(Object)} method would return <code>true</code>.
1155 * This is the definition of lexicographic ordering. If two strings are
1156 * different, then either they have different characters at some index
1157 * that is a valid index for both strings, or their lengths are different,
1158 * or both. If they have different characters at one or more index
1159 * positions, let <i>k</i> be the smallest such index; then the string
1160 * whose character at position <i>k</i> has the smaller value, as
1161 * determined by using the < operator, lexicographically precedes the
1162 * other string. In this case, <code>compareTo</code> returns the
1163 * difference of the two character values at position <code>k</code> in
1164 * the two string -- that is, the value:
1166 * this.charAt(k)-anotherString.charAt(k)
1167 * </pre></blockquote>
1168 * If there is no index position at which they differ, then the shorter
1169 * string lexicographically precedes the longer string. In this case,
1170 * <code>compareTo</code> returns the difference of the lengths of the
1171 * strings -- that is, the value:
1173 * this.length()-anotherString.length()
1174 * </pre></blockquote>
1176 * @param anotherString the <code>String</code> to be compared.
1177 * @return the value <code>0</code> if the argument string is equal to
1178 * this string; a value less than <code>0</code> if this string
1179 * is lexicographically less than the string argument; and a
1180 * value greater than <code>0</code> if this string is
1181 * lexicographically greater than the string argument.
1183 public int compareTo(String anotherString) {
1185 int len2 = anotherString.count;
1186 int n = Math.min(len1, len2);
1188 char v2[] = anotherString.value;
1190 int j = anotherString.offset;
1216 * A Comparator that orders <code>String</code> objects as by
1217 * <code>compareToIgnoreCase</code>. This comparator is serializable.
1219 * Note that this Comparator does <em>not</em> take locale into account,
1220 * and will result in an unsatisfactory ordering for certain locales.
1221 * The java.text package provides <em>Collators</em> to allow
1222 * locale-sensitive ordering.
1224 * @see java.text.Collator#compare(String, String)
1227 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1228 = new CaseInsensitiveComparator();
1229 private static class CaseInsensitiveComparator
1230 implements Comparator<String>, java.io.Serializable {
1231 // use serialVersionUID from JDK 1.2.2 for interoperability
1232 private static final long serialVersionUID = 8575799808933029326L;
1234 public int compare(String s1, String s2) {
1235 int n1 = s1.length();
1236 int n2 = s2.length();
1237 int min = Math.min(n1, n2);
1238 for (int i = 0; i < min; i++) {
1239 char c1 = s1.charAt(i);
1240 char c2 = s2.charAt(i);
1242 c1 = Character.toUpperCase(c1);
1243 c2 = Character.toUpperCase(c2);
1245 c1 = Character.toLowerCase(c1);
1246 c2 = Character.toLowerCase(c2);
1248 // No overflow because of numeric promotion
1259 * Compares two strings lexicographically, ignoring case
1260 * differences. This method returns an integer whose sign is that of
1261 * calling <code>compareTo</code> with normalized versions of the strings
1262 * where case differences have been eliminated by calling
1263 * <code>Character.toLowerCase(Character.toUpperCase(character))</code> on
1266 * Note that this method does <em>not</em> take locale into account,
1267 * and will result in an unsatisfactory ordering for certain locales.
1268 * The java.text package provides <em>collators</em> to allow
1269 * locale-sensitive ordering.
1271 * @param str the <code>String</code> to be compared.
1272 * @return a negative integer, zero, or a positive integer as the
1273 * specified String is greater than, equal to, or less
1274 * than this String, ignoring case considerations.
1275 * @see java.text.Collator#compare(String, String)
1278 public int compareToIgnoreCase(String str) {
1279 return CASE_INSENSITIVE_ORDER.compare(this, str);
1283 * Tests if two string regions are equal.
1285 * A substring of this <tt>String</tt> object is compared to a substring
1286 * of the argument other. The result is true if these substrings
1287 * represent identical character sequences. The substring of this
1288 * <tt>String</tt> object to be compared begins at index <tt>toffset</tt>
1289 * and has length <tt>len</tt>. The substring of other to be compared
1290 * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The
1291 * result is <tt>false</tt> if and only if at least one of the following
1293 * <ul><li><tt>toffset</tt> is negative.
1294 * <li><tt>ooffset</tt> is negative.
1295 * <li><tt>toffset+len</tt> is greater than the length of this
1296 * <tt>String</tt> object.
1297 * <li><tt>ooffset+len</tt> is greater than the length of the other
1299 * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt>
1301 * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt>
1304 * @param toffset the starting offset of the subregion in this string.
1305 * @param other the string argument.
1306 * @param ooffset the starting offset of the subregion in the string
1308 * @param len the number of characters to compare.
1309 * @return <code>true</code> if the specified subregion of this string
1310 * exactly matches the specified subregion of the string argument;
1311 * <code>false</code> otherwise.
1313 public boolean regionMatches(int toffset, String other, int ooffset,
1316 int to = offset + toffset;
1317 char pa[] = other.value;
1318 int po = other.offset + ooffset;
1319 // Note: toffset, ooffset, or len might be near -1>>>1.
1320 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len)
1321 || (ooffset > (long)other.count - len)) {
1325 if (ta[to++] != pa[po++]) {
1333 * Tests if two string regions are equal.
1335 * A substring of this <tt>String</tt> object is compared to a substring
1336 * of the argument <tt>other</tt>. The result is <tt>true</tt> if these
1337 * substrings represent character sequences that are the same, ignoring
1338 * case if and only if <tt>ignoreCase</tt> is true. The substring of
1339 * this <tt>String</tt> object to be compared begins at index
1340 * <tt>toffset</tt> and has length <tt>len</tt>. The substring of
1341 * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and
1342 * has length <tt>len</tt>. The result is <tt>false</tt> if and only if
1343 * at least one of the following is true:
1344 * <ul><li><tt>toffset</tt> is negative.
1345 * <li><tt>ooffset</tt> is negative.
1346 * <li><tt>toffset+len</tt> is greater than the length of this
1347 * <tt>String</tt> object.
1348 * <li><tt>ooffset+len</tt> is greater than the length of the other
1350 * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative
1351 * integer <i>k</i> less than <tt>len</tt> such that:
1353 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1354 * </pre></blockquote>
1355 * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative
1356 * integer <i>k</i> less than <tt>len</tt> such that:
1358 * Character.toLowerCase(this.charAt(toffset+k)) !=
1359 Character.toLowerCase(other.charAt(ooffset+k))
1360 * </pre></blockquote>
1363 * Character.toUpperCase(this.charAt(toffset+k)) !=
1364 * Character.toUpperCase(other.charAt(ooffset+k))
1365 * </pre></blockquote>
1368 * @param ignoreCase if <code>true</code>, ignore case when comparing
1370 * @param toffset the starting offset of the subregion in this
1372 * @param other the string argument.
1373 * @param ooffset the starting offset of the subregion in the string
1375 * @param len the number of characters to compare.
1376 * @return <code>true</code> if the specified subregion of this string
1377 * matches the specified subregion of the string argument;
1378 * <code>false</code> otherwise. Whether the matching is exact
1379 * or case insensitive depends on the <code>ignoreCase</code>
1382 public boolean regionMatches(boolean ignoreCase, int toffset,
1383 String other, int ooffset, int len) {
1385 int to = offset + toffset;
1386 char pa[] = other.value;
1387 int po = other.offset + ooffset;
1388 // Note: toffset, ooffset, or len might be near -1>>>1.
1389 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) ||
1390 (ooffset > (long)other.count - len)) {
1400 // If characters don't match but case may be ignored,
1401 // try converting both characters to uppercase.
1402 // If the results match, then the comparison scan should
1404 char u1 = Character.toUpperCase(c1);
1405 char u2 = Character.toUpperCase(c2);
1409 // Unfortunately, conversion to uppercase does not work properly
1410 // for the Georgian alphabet, which has strange rules about case
1411 // conversion. So we need to make one last check before
1413 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1423 * Tests if the substring of this string beginning at the
1424 * specified index starts with the specified prefix.
1426 * @param prefix the prefix.
1427 * @param toffset where to begin looking in this string.
1428 * @return <code>true</code> if the character sequence represented by the
1429 * argument is a prefix of the substring of this object starting
1430 * at index <code>toffset</code>; <code>false</code> otherwise.
1431 * The result is <code>false</code> if <code>toffset</code> is
1432 * negative or greater than the length of this
1433 * <code>String</code> object; otherwise the result is the same
1434 * as the result of the expression
1436 * this.substring(toffset).startsWith(prefix)
1439 public boolean startsWith(String prefix, int toffset) {
1441 int to = offset + toffset;
1442 char pa[] = prefix.value;
1443 int po = prefix.offset;
1444 int pc = prefix.count;
1445 // Note: toffset might be near -1>>>1.
1446 if ((toffset < 0) || (toffset > count - pc)) {
1450 if (ta[to++] != pa[po++]) {
1458 * Tests if this string starts with the specified prefix.
1460 * @param prefix the prefix.
1461 * @return <code>true</code> if the character sequence represented by the
1462 * argument is a prefix of the character sequence represented by
1463 * this string; <code>false</code> otherwise.
1464 * Note also that <code>true</code> will be returned if the
1465 * argument is an empty string or is equal to this
1466 * <code>String</code> object as determined by the
1467 * {@link #equals(Object)} method.
1470 public boolean startsWith(String prefix) {
1471 return startsWith(prefix, 0);
1475 * Tests if this string ends with the specified suffix.
1477 * @param suffix the suffix.
1478 * @return <code>true</code> if the character sequence represented by the
1479 * argument is a suffix of the character sequence represented by
1480 * this object; <code>false</code> otherwise. Note that the
1481 * result will be <code>true</code> if the argument is the
1482 * empty string or is equal to this <code>String</code> object
1483 * as determined by the {@link #equals(Object)} method.
1485 public boolean endsWith(String suffix) {
1486 return startsWith(suffix, count - suffix.count);
1490 * Returns a hash code for this string. The hash code for a
1491 * <code>String</code> object is computed as
1493 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1494 * </pre></blockquote>
1495 * using <code>int</code> arithmetic, where <code>s[i]</code> is the
1496 * <i>i</i>th character of the string, <code>n</code> is the length of
1497 * the string, and <code>^</code> indicates exponentiation.
1498 * (The hash value of the empty string is zero.)
1500 * @return a hash code value for this object.
1502 public int hashCode() {
1504 if (h == 0 && count > 0) {
1509 for (int i = 0; i < len; i++) {
1510 h = 31*h + val[off++];
1518 * Returns the index within this string of the first occurrence of
1519 * the specified character. If a character with value
1520 * <code>ch</code> occurs in the character sequence represented by
1521 * this <code>String</code> object, then the index (in Unicode
1522 * code units) of the first such occurrence is returned. For
1523 * values of <code>ch</code> in the range from 0 to 0xFFFF
1524 * (inclusive), this is the smallest value <i>k</i> such that:
1526 * this.charAt(<i>k</i>) == ch
1527 * </pre></blockquote>
1528 * is true. For other values of <code>ch</code>, it is the
1529 * smallest value <i>k</i> such that:
1531 * this.codePointAt(<i>k</i>) == ch
1532 * </pre></blockquote>
1533 * is true. In either case, if no such character occurs in this
1534 * string, then <code>-1</code> is returned.
1536 * @param ch a character (Unicode code point).
1537 * @return the index of the first occurrence of the character in the
1538 * character sequence represented by this object, or
1539 * <code>-1</code> if the character does not occur.
1541 public int indexOf(int ch) {
1542 return indexOf(ch, 0);
1546 * Returns the index within this string of the first occurrence of the
1547 * specified character, starting the search at the specified index.
1549 * If a character with value <code>ch</code> occurs in the
1550 * character sequence represented by this <code>String</code>
1551 * object at an index no smaller than <code>fromIndex</code>, then
1552 * the index of the first such occurrence is returned. For values
1553 * of <code>ch</code> in the range from 0 to 0xFFFF (inclusive),
1554 * this is the smallest value <i>k</i> such that:
1556 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1557 * </pre></blockquote>
1558 * is true. For other values of <code>ch</code>, it is the
1559 * smallest value <i>k</i> such that:
1561 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1562 * </pre></blockquote>
1563 * is true. In either case, if no such character occurs in this
1564 * string at or after position <code>fromIndex</code>, then
1565 * <code>-1</code> is returned.
1568 * There is no restriction on the value of <code>fromIndex</code>. If it
1569 * is negative, it has the same effect as if it were zero: this entire
1570 * string may be searched. If it is greater than the length of this
1571 * string, it has the same effect as if it were equal to the length of
1572 * this string: <code>-1</code> is returned.
1574 * <p>All indices are specified in <code>char</code> values
1575 * (Unicode code units).
1577 * @param ch a character (Unicode code point).
1578 * @param fromIndex the index to start the search from.
1579 * @return the index of the first occurrence of the character in the
1580 * character sequence represented by this object that is greater
1581 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1582 * if the character does not occur.
1584 public int indexOf(int ch, int fromIndex) {
1585 if (fromIndex < 0) {
1587 } else if (fromIndex >= count) {
1588 // Note: fromIndex might be near -1>>>1.
1592 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1593 // handle most cases here (ch is a BMP code point or a
1594 // negative value (invalid code point))
1595 final char[] value = this.value;
1596 final int offset = this.offset;
1597 final int max = offset + count;
1598 for (int i = offset + fromIndex; i < max ; i++) {
1599 if (value[i] == ch) {
1605 return indexOfSupplementary(ch, fromIndex);
1610 * Handles (rare) calls of indexOf with a supplementary character.
1612 private int indexOfSupplementary(int ch, int fromIndex) {
1613 if (Character.isValidCodePoint(ch)) {
1614 final char[] value = this.value;
1615 final int offset = this.offset;
1616 final char hi = Character.highSurrogate(ch);
1617 final char lo = Character.lowSurrogate(ch);
1618 final int max = offset + count - 1;
1619 for (int i = offset + fromIndex; i < max; i++) {
1620 if (value[i] == hi && value[i+1] == lo) {
1629 * Returns the index within this string of the last occurrence of
1630 * the specified character. For values of <code>ch</code> in the
1631 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1632 * units) returned is the largest value <i>k</i> such that:
1634 * this.charAt(<i>k</i>) == ch
1635 * </pre></blockquote>
1636 * is true. For other values of <code>ch</code>, it is the
1637 * largest value <i>k</i> such that:
1639 * this.codePointAt(<i>k</i>) == ch
1640 * </pre></blockquote>
1641 * is true. In either case, if no such character occurs in this
1642 * string, then <code>-1</code> is returned. The
1643 * <code>String</code> is searched backwards starting at the last
1646 * @param ch a character (Unicode code point).
1647 * @return the index of the last occurrence of the character in the
1648 * character sequence represented by this object, or
1649 * <code>-1</code> if the character does not occur.
1651 public int lastIndexOf(int ch) {
1652 return lastIndexOf(ch, count - 1);
1656 * Returns the index within this string of the last occurrence of
1657 * the specified character, searching backward starting at the
1658 * specified index. For values of <code>ch</code> in the range
1659 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1660 * value <i>k</i> such that:
1662 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1663 * </pre></blockquote>
1664 * is true. For other values of <code>ch</code>, it is the
1665 * largest value <i>k</i> such that:
1667 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1668 * </pre></blockquote>
1669 * is true. In either case, if no such character occurs in this
1670 * string at or before position <code>fromIndex</code>, then
1671 * <code>-1</code> is returned.
1673 * <p>All indices are specified in <code>char</code> values
1674 * (Unicode code units).
1676 * @param ch a character (Unicode code point).
1677 * @param fromIndex the index to start the search from. There is no
1678 * restriction on the value of <code>fromIndex</code>. If it is
1679 * greater than or equal to the length of this string, it has
1680 * the same effect as if it were equal to one less than the
1681 * length of this string: this entire string may be searched.
1682 * If it is negative, it has the same effect as if it were -1:
1684 * @return the index of the last occurrence of the character in the
1685 * character sequence represented by this object that is less
1686 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1687 * if the character does not occur before that point.
1689 public int lastIndexOf(int ch, int fromIndex) {
1690 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1691 // handle most cases here (ch is a BMP code point or a
1692 // negative value (invalid code point))
1693 final char[] value = this.value;
1694 final int offset = this.offset;
1695 int i = offset + Math.min(fromIndex, count - 1);
1696 for (; i >= offset ; i--) {
1697 if (value[i] == ch) {
1703 return lastIndexOfSupplementary(ch, fromIndex);
1708 * Handles (rare) calls of lastIndexOf with a supplementary character.
1710 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1711 if (Character.isValidCodePoint(ch)) {
1712 final char[] value = this.value;
1713 final int offset = this.offset;
1714 char hi = Character.highSurrogate(ch);
1715 char lo = Character.lowSurrogate(ch);
1716 int i = offset + Math.min(fromIndex, count - 2);
1717 for (; i >= offset; i--) {
1718 if (value[i] == hi && value[i+1] == lo) {
1727 * Returns the index within this string of the first occurrence of the
1728 * specified substring.
1730 * <p>The returned index is the smallest value <i>k</i> for which:
1732 * this.startsWith(str, <i>k</i>)
1733 * </pre></blockquote>
1734 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1736 * @param str the substring to search for.
1737 * @return the index of the first occurrence of the specified substring,
1738 * or {@code -1} if there is no such occurrence.
1740 public int indexOf(String str) {
1741 return indexOf(str, 0);
1745 * Returns the index within this string of the first occurrence of the
1746 * specified substring, starting at the specified index.
1748 * <p>The returned index is the smallest value <i>k</i> for which:
1750 * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>)
1751 * </pre></blockquote>
1752 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1754 * @param str the substring to search for.
1755 * @param fromIndex the index from which to start the search.
1756 * @return the index of the first occurrence of the specified substring,
1757 * starting at the specified index,
1758 * or {@code -1} if there is no such occurrence.
1760 public int indexOf(String str, int fromIndex) {
1761 return indexOf(value, offset, count,
1762 str.value, str.offset, str.count, fromIndex);
1766 * Code shared by String and StringBuffer to do searches. The
1767 * source is the character array being searched, and the target
1768 * is the string being searched for.
1770 * @param source the characters being searched.
1771 * @param sourceOffset offset of the source string.
1772 * @param sourceCount count of the source string.
1773 * @param target the characters being searched for.
1774 * @param targetOffset offset of the target string.
1775 * @param targetCount count of the target string.
1776 * @param fromIndex the index to begin searching from.
1778 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1779 char[] target, int targetOffset, int targetCount,
1781 if (fromIndex >= sourceCount) {
1782 return (targetCount == 0 ? sourceCount : -1);
1784 if (fromIndex < 0) {
1787 if (targetCount == 0) {
1791 char first = target[targetOffset];
1792 int max = sourceOffset + (sourceCount - targetCount);
1794 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1795 /* Look for first character. */
1796 if (source[i] != first) {
1797 while (++i <= max && source[i] != first);
1800 /* Found first character, now look at the rest of v2 */
1803 int end = j + targetCount - 1;
1804 for (int k = targetOffset + 1; j < end && source[j] ==
1805 target[k]; j++, k++);
1808 /* Found whole string. */
1809 return i - sourceOffset;
1817 * Returns the index within this string of the last occurrence of the
1818 * specified substring. The last occurrence of the empty string ""
1819 * is considered to occur at the index value {@code this.length()}.
1821 * <p>The returned index is the largest value <i>k</i> for which:
1823 * this.startsWith(str, <i>k</i>)
1824 * </pre></blockquote>
1825 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1827 * @param str the substring to search for.
1828 * @return the index of the last occurrence of the specified substring,
1829 * or {@code -1} if there is no such occurrence.
1831 public int lastIndexOf(String str) {
1832 return lastIndexOf(str, count);
1836 * Returns the index within this string of the last occurrence of the
1837 * specified substring, searching backward starting at the specified index.
1839 * <p>The returned index is the largest value <i>k</i> for which:
1841 * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>)
1842 * </pre></blockquote>
1843 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1845 * @param str the substring to search for.
1846 * @param fromIndex the index to start the search from.
1847 * @return the index of the last occurrence of the specified substring,
1848 * searching backward from the specified index,
1849 * or {@code -1} if there is no such occurrence.
1851 public int lastIndexOf(String str, int fromIndex) {
1852 return lastIndexOf(value, offset, count,
1853 str.value, str.offset, str.count, fromIndex);
1857 * Code shared by String and StringBuffer to do searches. The
1858 * source is the character array being searched, and the target
1859 * is the string being searched for.
1861 * @param source the characters being searched.
1862 * @param sourceOffset offset of the source string.
1863 * @param sourceCount count of the source string.
1864 * @param target the characters being searched for.
1865 * @param targetOffset offset of the target string.
1866 * @param targetCount count of the target string.
1867 * @param fromIndex the index to begin searching from.
1869 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1870 char[] target, int targetOffset, int targetCount,
1873 * Check arguments; return immediately where possible. For
1874 * consistency, don't check for null str.
1876 int rightIndex = sourceCount - targetCount;
1877 if (fromIndex < 0) {
1880 if (fromIndex > rightIndex) {
1881 fromIndex = rightIndex;
1883 /* Empty string always matches. */
1884 if (targetCount == 0) {
1888 int strLastIndex = targetOffset + targetCount - 1;
1889 char strLastChar = target[strLastIndex];
1890 int min = sourceOffset + targetCount - 1;
1891 int i = min + fromIndex;
1893 startSearchForLastChar:
1895 while (i >= min && source[i] != strLastChar) {
1902 int start = j - (targetCount - 1);
1903 int k = strLastIndex - 1;
1906 if (source[j--] != target[k--]) {
1908 continue startSearchForLastChar;
1911 return start - sourceOffset + 1;
1916 * Returns a new string that is a substring of this string. The
1917 * substring begins with the character at the specified index and
1918 * extends to the end of this string. <p>
1921 * "unhappy".substring(2) returns "happy"
1922 * "Harbison".substring(3) returns "bison"
1923 * "emptiness".substring(9) returns "" (an empty string)
1924 * </pre></blockquote>
1926 * @param beginIndex the beginning index, inclusive.
1927 * @return the specified substring.
1928 * @exception IndexOutOfBoundsException if
1929 * <code>beginIndex</code> is negative or larger than the
1930 * length of this <code>String</code> object.
1932 public String substring(int beginIndex) {
1933 return substring(beginIndex, count);
1937 * Returns a new string that is a substring of this string. The
1938 * substring begins at the specified <code>beginIndex</code> and
1939 * extends to the character at index <code>endIndex - 1</code>.
1940 * Thus the length of the substring is <code>endIndex-beginIndex</code>.
1944 * "hamburger".substring(4, 8) returns "urge"
1945 * "smiles".substring(1, 5) returns "mile"
1946 * </pre></blockquote>
1948 * @param beginIndex the beginning index, inclusive.
1949 * @param endIndex the ending index, exclusive.
1950 * @return the specified substring.
1951 * @exception IndexOutOfBoundsException if the
1952 * <code>beginIndex</code> is negative, or
1953 * <code>endIndex</code> is larger than the length of
1954 * this <code>String</code> object, or
1955 * <code>beginIndex</code> is larger than
1956 * <code>endIndex</code>.
1958 public String substring(int beginIndex, int endIndex) {
1959 if (beginIndex < 0) {
1960 throw new StringIndexOutOfBoundsException(beginIndex);
1962 if (endIndex > count) {
1963 throw new StringIndexOutOfBoundsException(endIndex);
1965 if (beginIndex > endIndex) {
1966 throw new StringIndexOutOfBoundsException(endIndex - beginIndex);
1968 return ((beginIndex == 0) && (endIndex == count)) ? this :
1969 new String(offset + beginIndex, endIndex - beginIndex, value);
1973 * Returns a new character sequence that is a subsequence of this sequence.
1975 * <p> An invocation of this method of the form
1978 * str.subSequence(begin, end)</pre></blockquote>
1980 * behaves in exactly the same way as the invocation
1983 * str.substring(begin, end)</pre></blockquote>
1985 * This method is defined so that the <tt>String</tt> class can implement
1986 * the {@link CharSequence} interface. </p>
1988 * @param beginIndex the begin index, inclusive.
1989 * @param endIndex the end index, exclusive.
1990 * @return the specified subsequence.
1992 * @throws IndexOutOfBoundsException
1993 * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative,
1994 * if <tt>endIndex</tt> is greater than <tt>length()</tt>,
1995 * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt>
2000 public CharSequence subSequence(int beginIndex, int endIndex) {
2001 return this.substring(beginIndex, endIndex);
2005 * Concatenates the specified string to the end of this string.
2007 * If the length of the argument string is <code>0</code>, then this
2008 * <code>String</code> object is returned. Otherwise, a new
2009 * <code>String</code> object is created, representing a character
2010 * sequence that is the concatenation of the character sequence
2011 * represented by this <code>String</code> object and the character
2012 * sequence represented by the argument string.<p>
2015 * "cares".concat("s") returns "caress"
2016 * "to".concat("get").concat("her") returns "together"
2017 * </pre></blockquote>
2019 * @param str the <code>String</code> that is concatenated to the end
2020 * of this <code>String</code>.
2021 * @return a string that represents the concatenation of this object's
2022 * characters followed by the string argument's characters.
2024 public String concat(String str) {
2025 int otherLen = str.length();
2026 if (otherLen == 0) {
2029 char buf[] = new char[count + otherLen];
2030 getChars(0, count, buf, 0);
2031 str.getChars(0, otherLen, buf, count);
2032 return new String(0, count + otherLen, buf);
2036 * Returns a new string resulting from replacing all occurrences of
2037 * <code>oldChar</code> in this string with <code>newChar</code>.
2039 * If the character <code>oldChar</code> does not occur in the
2040 * character sequence represented by this <code>String</code> object,
2041 * then a reference to this <code>String</code> object is returned.
2042 * Otherwise, a new <code>String</code> object is created that
2043 * represents a character sequence identical to the character sequence
2044 * represented by this <code>String</code> object, except that every
2045 * occurrence of <code>oldChar</code> is replaced by an occurrence
2046 * of <code>newChar</code>.
2050 * "mesquite in your cellar".replace('e', 'o')
2051 * returns "mosquito in your collar"
2052 * "the war of baronets".replace('r', 'y')
2053 * returns "the way of bayonets"
2054 * "sparring with a purple porpoise".replace('p', 't')
2055 * returns "starring with a turtle tortoise"
2056 * "JonL".replace('q', 'x') returns "JonL" (no change)
2057 * </pre></blockquote>
2059 * @param oldChar the old character.
2060 * @param newChar the new character.
2061 * @return a string derived from this string by replacing every
2062 * occurrence of <code>oldChar</code> with <code>newChar</code>.
2064 public String replace(char oldChar, char newChar) {
2065 if (oldChar != newChar) {
2068 char[] val = value; /* avoid getfield opcode */
2069 int off = offset; /* avoid getfield opcode */
2072 if (val[off + i] == oldChar) {
2077 char buf[] = new char[len];
2078 for (int j = 0 ; j < i ; j++) {
2079 buf[j] = val[off+j];
2082 char c = val[off + i];
2083 buf[i] = (c == oldChar) ? newChar : c;
2086 return new String(0, len, buf);
2093 * Tells whether or not this string matches the given <a
2094 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2096 * <p> An invocation of this method of the form
2097 * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the
2098 * same result as the expression
2100 * <blockquote><tt> {@link java.util.regex.Pattern}.{@link
2101 * java.util.regex.Pattern#matches(String,CharSequence)
2102 * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote>
2105 * the regular expression to which this string is to be matched
2107 * @return <tt>true</tt> if, and only if, this string matches the
2108 * given regular expression
2110 * @throws PatternSyntaxException
2111 * if the regular expression's syntax is invalid
2113 * @see java.util.regex.Pattern
2118 public boolean matches(String regex) {
2119 throw new UnsupportedOperationException();
2123 * Returns true if and only if this string contains the specified
2124 * sequence of char values.
2126 * @param s the sequence to search for
2127 * @return true if this string contains <code>s</code>, false otherwise
2128 * @throws NullPointerException if <code>s</code> is <code>null</code>
2131 public boolean contains(CharSequence s) {
2132 return indexOf(s.toString()) > -1;
2136 * Replaces the first substring of this string that matches the given <a
2137 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2138 * given replacement.
2140 * <p> An invocation of this method of the form
2141 * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2142 * yields exactly the same result as the expression
2145 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2146 * compile}(</tt><i>regex</i><tt>).{@link
2147 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2148 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst
2149 * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote>
2152 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2153 * replacement string may cause the results to be different than if it were
2154 * being treated as a literal replacement string; see
2155 * {@link java.util.regex.Matcher#replaceFirst}.
2156 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2157 * meaning of these characters, if desired.
2160 * the regular expression to which this string is to be matched
2161 * @param replacement
2162 * the string to be substituted for the first match
2164 * @return The resulting <tt>String</tt>
2166 * @throws PatternSyntaxException
2167 * if the regular expression's syntax is invalid
2169 * @see java.util.regex.Pattern
2174 public String replaceFirst(String regex, String replacement) {
2175 throw new UnsupportedOperationException();
2179 * Replaces each substring of this string that matches the given <a
2180 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2181 * given replacement.
2183 * <p> An invocation of this method of the form
2184 * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2185 * yields exactly the same result as the expression
2188 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2189 * compile}(</tt><i>regex</i><tt>).{@link
2190 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2191 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll
2192 * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote>
2195 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2196 * replacement string may cause the results to be different than if it were
2197 * being treated as a literal replacement string; see
2198 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2199 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2200 * meaning of these characters, if desired.
2203 * the regular expression to which this string is to be matched
2204 * @param replacement
2205 * the string to be substituted for each match
2207 * @return The resulting <tt>String</tt>
2209 * @throws PatternSyntaxException
2210 * if the regular expression's syntax is invalid
2212 * @see java.util.regex.Pattern
2217 public String replaceAll(String regex, String replacement) {
2218 throw new UnsupportedOperationException();
2222 * Replaces each substring of this string that matches the literal target
2223 * sequence with the specified literal replacement sequence. The
2224 * replacement proceeds from the beginning of the string to the end, for
2225 * example, replacing "aa" with "b" in the string "aaa" will result in
2226 * "ba" rather than "ab".
2228 * @param target The sequence of char values to be replaced
2229 * @param replacement The replacement sequence of char values
2230 * @return The resulting string
2231 * @throws NullPointerException if <code>target</code> or
2232 * <code>replacement</code> is <code>null</code>.
2235 public String replace(CharSequence target, CharSequence replacement) {
2236 throw new UnsupportedOperationException("This one should be supported, but without dep on rest of regexp");
2240 * Splits this string around matches of the given
2241 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2243 * <p> The array returned by this method contains each substring of this
2244 * string that is terminated by another substring that matches the given
2245 * expression or is terminated by the end of the string. The substrings in
2246 * the array are in the order in which they occur in this string. If the
2247 * expression does not match any part of the input then the resulting array
2248 * has just one element, namely this string.
2250 * <p> The <tt>limit</tt> parameter controls the number of times the
2251 * pattern is applied and therefore affects the length of the resulting
2252 * array. If the limit <i>n</i> is greater than zero then the pattern
2253 * will be applied at most <i>n</i> - 1 times, the array's
2254 * length will be no greater than <i>n</i>, and the array's last entry
2255 * will contain all input beyond the last matched delimiter. If <i>n</i>
2256 * is non-positive then the pattern will be applied as many times as
2257 * possible and the array can have any length. If <i>n</i> is zero then
2258 * the pattern will be applied as many times as possible, the array can
2259 * have any length, and trailing empty strings will be discarded.
2261 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the
2262 * following results with these parameters:
2264 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2270 * <tr><td align=center>:</td>
2271 * <td align=center>2</td>
2272 * <td><tt>{ "boo", "and:foo" }</tt></td></tr>
2273 * <tr><td align=center>:</td>
2274 * <td align=center>5</td>
2275 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2276 * <tr><td align=center>:</td>
2277 * <td align=center>-2</td>
2278 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2279 * <tr><td align=center>o</td>
2280 * <td align=center>5</td>
2281 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2282 * <tr><td align=center>o</td>
2283 * <td align=center>-2</td>
2284 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2285 * <tr><td align=center>o</td>
2286 * <td align=center>0</td>
2287 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2288 * </table></blockquote>
2290 * <p> An invocation of this method of the form
2291 * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt>
2292 * yields the same result as the expression
2295 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2296 * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link
2297 * java.util.regex.Pattern#split(java.lang.CharSequence,int)
2298 * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt>
2303 * the delimiting regular expression
2306 * the result threshold, as described above
2308 * @return the array of strings computed by splitting this string
2309 * around matches of the given regular expression
2311 * @throws PatternSyntaxException
2312 * if the regular expression's syntax is invalid
2314 * @see java.util.regex.Pattern
2319 public String[] split(String regex, int limit) {
2320 throw new UnsupportedOperationException("Needs regexp");
2324 * Splits this string around matches of the given <a
2325 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2327 * <p> This method works as if by invoking the two-argument {@link
2328 * #split(String, int) split} method with the given expression and a limit
2329 * argument of zero. Trailing empty strings are therefore not included in
2330 * the resulting array.
2332 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the following
2333 * results with these expressions:
2335 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2340 * <tr><td align=center>:</td>
2341 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2342 * <tr><td align=center>o</td>
2343 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2344 * </table></blockquote>
2348 * the delimiting regular expression
2350 * @return the array of strings computed by splitting this string
2351 * around matches of the given regular expression
2353 * @throws PatternSyntaxException
2354 * if the regular expression's syntax is invalid
2356 * @see java.util.regex.Pattern
2361 public String[] split(String regex) {
2362 return split(regex, 0);
2366 * Converts all of the characters in this <code>String</code> to lower
2367 * case using the rules of the given <code>Locale</code>. Case mapping is based
2368 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2369 * class. Since case mappings are not always 1:1 char mappings, the resulting
2370 * <code>String</code> may be a different length than the original <code>String</code>.
2372 * Examples of lowercase mappings are in the following table:
2373 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2375 * <th>Language Code of Locale</th>
2376 * <th>Upper Case</th>
2377 * <th>Lower Case</th>
2378 * <th>Description</th>
2381 * <td>tr (Turkish)</td>
2382 * <td>\u0130</td>
2383 * <td>\u0069</td>
2384 * <td>capital letter I with dot above -> small letter i</td>
2387 * <td>tr (Turkish)</td>
2388 * <td>\u0049</td>
2389 * <td>\u0131</td>
2390 * <td>capital letter I -> small letter dotless i </td>
2394 * <td>French Fries</td>
2395 * <td>french fries</td>
2396 * <td>lowercased all chars in String</td>
2400 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2401 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2402 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2403 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2404 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2405 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2406 * <td>lowercased all chars in String</td>
2410 * @param locale use the case transformation rules for this locale
2411 * @return the <code>String</code>, converted to lowercase.
2412 * @see java.lang.String#toLowerCase()
2413 * @see java.lang.String#toUpperCase()
2414 * @see java.lang.String#toUpperCase(Locale)
2417 // public String toLowerCase(Locale locale) {
2418 // if (locale == null) {
2419 // throw new NullPointerException();
2424 // /* Now check if there are any characters that need to be changed. */
2426 // for (firstUpper = 0 ; firstUpper < count; ) {
2427 // char c = value[offset+firstUpper];
2428 // if ((c >= Character.MIN_HIGH_SURROGATE) &&
2429 // (c <= Character.MAX_HIGH_SURROGATE)) {
2430 // int supplChar = codePointAt(firstUpper);
2431 // if (supplChar != Character.toLowerCase(supplChar)) {
2434 // firstUpper += Character.charCount(supplChar);
2436 // if (c != Character.toLowerCase(c)) {
2445 // char[] result = new char[count];
2446 // int resultOffset = 0; /* result may grow, so i+resultOffset
2447 // * is the write location in result */
2449 // /* Just copy the first few lowerCase characters. */
2450 // arraycopy(value, offset, result, 0, firstUpper);
2452 // String lang = locale.getLanguage();
2453 // boolean localeDependent =
2454 // (lang == "tr" || lang == "az" || lang == "lt");
2455 // char[] lowerCharArray;
2459 // for (int i = firstUpper; i < count; i += srcCount) {
2460 // srcChar = (int)value[offset+i];
2461 // if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2462 // (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2463 // srcChar = codePointAt(i);
2464 // srcCount = Character.charCount(srcChar);
2468 // if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2469 // lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2470 // } else if (srcChar == '\u0130') { // LATIN CAPITAL LETTER I DOT
2471 // lowerChar = Character.ERROR;
2473 // lowerChar = Character.toLowerCase(srcChar);
2475 // if ((lowerChar == Character.ERROR) ||
2476 // (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2477 // if (lowerChar == Character.ERROR) {
2478 // if (!localeDependent && srcChar == '\u0130') {
2480 // ConditionalSpecialCasing.toLowerCaseCharArray(this, i, Locale.ENGLISH);
2483 // ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2485 // } else if (srcCount == 2) {
2486 // resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount;
2489 // lowerCharArray = Character.toChars(lowerChar);
2492 // /* Grow result if needed */
2493 // int mapLen = lowerCharArray.length;
2494 // if (mapLen > srcCount) {
2495 // char[] result2 = new char[result.length + mapLen - srcCount];
2496 // arraycopy(result, 0, result2, 0,
2497 // i + resultOffset);
2498 // result = result2;
2500 // for (int x=0; x<mapLen; ++x) {
2501 // result[i+resultOffset+x] = lowerCharArray[x];
2503 // resultOffset += (mapLen - srcCount);
2505 // result[i+resultOffset] = (char)lowerChar;
2508 // return new String(0, count+resultOffset, result);
2512 * Converts all of the characters in this <code>String</code> to lower
2513 * case using the rules of the default locale. This is equivalent to calling
2514 * <code>toLowerCase(Locale.getDefault())</code>.
2516 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2517 * results if used for strings that are intended to be interpreted locale
2519 * Examples are programming language identifiers, protocol keys, and HTML
2521 * For instance, <code>"TITLE".toLowerCase()</code> in a Turkish locale
2522 * returns <code>"t\u005Cu0131tle"</code>, where '\u005Cu0131' is the
2523 * LATIN SMALL LETTER DOTLESS I character.
2524 * To obtain correct results for locale insensitive strings, use
2525 * <code>toLowerCase(Locale.ENGLISH)</code>.
2527 * @return the <code>String</code>, converted to lowercase.
2528 * @see java.lang.String#toLowerCase(Locale)
2530 public String toLowerCase() {
2531 throw new UnsupportedOperationException("Should be supported but without connection to locale");
2535 * Converts all of the characters in this <code>String</code> to upper
2536 * case using the rules of the given <code>Locale</code>. Case mapping is based
2537 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2538 * class. Since case mappings are not always 1:1 char mappings, the resulting
2539 * <code>String</code> may be a different length than the original <code>String</code>.
2541 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2543 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2545 * <th>Language Code of Locale</th>
2546 * <th>Lower Case</th>
2547 * <th>Upper Case</th>
2548 * <th>Description</th>
2551 * <td>tr (Turkish)</td>
2552 * <td>\u0069</td>
2553 * <td>\u0130</td>
2554 * <td>small letter i -> capital letter I with dot above</td>
2557 * <td>tr (Turkish)</td>
2558 * <td>\u0131</td>
2559 * <td>\u0049</td>
2560 * <td>small letter dotless i -> capital letter I</td>
2564 * <td>\u00df</td>
2565 * <td>\u0053 \u0053</td>
2566 * <td>small letter sharp s -> two letters: SS</td>
2570 * <td>Fahrvergnügen</td>
2571 * <td>FAHRVERGNÜGEN</td>
2575 * @param locale use the case transformation rules for this locale
2576 * @return the <code>String</code>, converted to uppercase.
2577 * @see java.lang.String#toUpperCase()
2578 * @see java.lang.String#toLowerCase()
2579 * @see java.lang.String#toLowerCase(Locale)
2582 /* not for javascript
2583 public String toUpperCase(Locale locale) {
2584 if (locale == null) {
2585 throw new NullPointerException();
2590 // Now check if there are any characters that need to be changed.
2592 for (firstLower = 0 ; firstLower < count; ) {
2593 int c = (int)value[offset+firstLower];
2595 if ((c >= Character.MIN_HIGH_SURROGATE) &&
2596 (c <= Character.MAX_HIGH_SURROGATE)) {
2597 c = codePointAt(firstLower);
2598 srcCount = Character.charCount(c);
2602 int upperCaseChar = Character.toUpperCaseEx(c);
2603 if ((upperCaseChar == Character.ERROR) ||
2604 (c != upperCaseChar)) {
2607 firstLower += srcCount;
2612 char[] result = new char[count]; /* may grow *
2613 int resultOffset = 0; /* result may grow, so i+resultOffset
2614 * is the write location in result *
2616 /* Just copy the first few upperCase characters. *
2617 arraycopy(value, offset, result, 0, firstLower);
2619 String lang = locale.getLanguage();
2620 boolean localeDependent =
2621 (lang == "tr" || lang == "az" || lang == "lt");
2622 char[] upperCharArray;
2626 for (int i = firstLower; i < count; i += srcCount) {
2627 srcChar = (int)value[offset+i];
2628 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2629 (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2630 srcChar = codePointAt(i);
2631 srcCount = Character.charCount(srcChar);
2635 if (localeDependent) {
2636 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2638 upperChar = Character.toUpperCaseEx(srcChar);
2640 if ((upperChar == Character.ERROR) ||
2641 (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2642 if (upperChar == Character.ERROR) {
2643 if (localeDependent) {
2645 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
2647 upperCharArray = Character.toUpperCaseCharArray(srcChar);
2649 } else if (srcCount == 2) {
2650 resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount;
2653 upperCharArray = Character.toChars(upperChar);
2656 /* Grow result if needed *
2657 int mapLen = upperCharArray.length;
2658 if (mapLen > srcCount) {
2659 char[] result2 = new char[result.length + mapLen - srcCount];
2660 arraycopy(result, 0, result2, 0,
2664 for (int x=0; x<mapLen; ++x) {
2665 result[i+resultOffset+x] = upperCharArray[x];
2667 resultOffset += (mapLen - srcCount);
2669 result[i+resultOffset] = (char)upperChar;
2672 return new String(0, count+resultOffset, result);
2677 * Converts all of the characters in this <code>String</code> to upper
2678 * case using the rules of the default locale. This method is equivalent to
2679 * <code>toUpperCase(Locale.getDefault())</code>.
2681 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2682 * results if used for strings that are intended to be interpreted locale
2684 * Examples are programming language identifiers, protocol keys, and HTML
2686 * For instance, <code>"title".toUpperCase()</code> in a Turkish locale
2687 * returns <code>"T\u005Cu0130TLE"</code>, where '\u005Cu0130' is the
2688 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2689 * To obtain correct results for locale insensitive strings, use
2690 * <code>toUpperCase(Locale.ENGLISH)</code>.
2692 * @return the <code>String</code>, converted to uppercase.
2693 * @see java.lang.String#toUpperCase(Locale)
2695 public String toUpperCase() {
2696 throw new UnsupportedOperationException();
2700 * Returns a copy of the string, with leading and trailing whitespace
2703 * If this <code>String</code> object represents an empty character
2704 * sequence, or the first and last characters of character sequence
2705 * represented by this <code>String</code> object both have codes
2706 * greater than <code>'\u0020'</code> (the space character), then a
2707 * reference to this <code>String</code> object is returned.
2709 * Otherwise, if there is no character with a code greater than
2710 * <code>'\u0020'</code> in the string, then a new
2711 * <code>String</code> object representing an empty string is created
2714 * Otherwise, let <i>k</i> be the index of the first character in the
2715 * string whose code is greater than <code>'\u0020'</code>, and let
2716 * <i>m</i> be the index of the last character in the string whose code
2717 * is greater than <code>'\u0020'</code>. A new <code>String</code>
2718 * object is created, representing the substring of this string that
2719 * begins with the character at index <i>k</i> and ends with the
2720 * character at index <i>m</i>-that is, the result of
2721 * <code>this.substring(<i>k</i>, <i>m</i>+1)</code>.
2723 * This method may be used to trim whitespace (as defined above) from
2724 * the beginning and end of a string.
2726 * @return A copy of this string with leading and trailing white
2727 * space removed, or this string if it has no leading or
2728 * trailing white space.
2730 public String trim() {
2733 int off = offset; /* avoid getfield opcode */
2734 char[] val = value; /* avoid getfield opcode */
2736 while ((st < len) && (val[off + st] <= ' ')) {
2739 while ((st < len) && (val[off + len - 1] <= ' ')) {
2742 return ((st > 0) || (len < count)) ? substring(st, len) : this;
2746 * This object (which is already a string!) is itself returned.
2748 * @return the string itself.
2750 public String toString() {
2755 * Converts this string to a new character array.
2757 * @return a newly allocated character array whose length is the length
2758 * of this string and whose contents are initialized to contain
2759 * the character sequence represented by this string.
2761 public char[] toCharArray() {
2762 char result[] = new char[count];
2763 getChars(0, count, result, 0);
2768 * Returns a formatted string using the specified format string and
2771 * <p> The locale always used is the one returned by {@link
2772 * java.util.Locale#getDefault() Locale.getDefault()}.
2775 * A <a href="../util/Formatter.html#syntax">format string</a>
2778 * Arguments referenced by the format specifiers in the format
2779 * string. If there are more arguments than format specifiers, the
2780 * extra arguments are ignored. The number of arguments is
2781 * variable and may be zero. The maximum number of arguments is
2782 * limited by the maximum dimension of a Java array as defined by
2783 * <cite>The Java™ Virtual Machine Specification</cite>.
2784 * The behaviour on a
2785 * <tt>null</tt> argument depends on the <a
2786 * href="../util/Formatter.html#syntax">conversion</a>.
2788 * @throws IllegalFormatException
2789 * If a format string contains an illegal syntax, a format
2790 * specifier that is incompatible with the given arguments,
2791 * insufficient arguments given the format string, or other
2792 * illegal conditions. For specification of all possible
2793 * formatting errors, see the <a
2794 * href="../util/Formatter.html#detail">Details</a> section of the
2795 * formatter class specification.
2797 * @throws NullPointerException
2798 * If the <tt>format</tt> is <tt>null</tt>
2800 * @return A formatted string
2802 * @see java.util.Formatter
2805 public static String format(String format, Object ... args) {
2806 throw new UnsupportedOperationException();
2810 * Returns a formatted string using the specified locale, format string,
2814 * The {@linkplain java.util.Locale locale} to apply during
2815 * formatting. If <tt>l</tt> is <tt>null</tt> then no localization
2819 * A <a href="../util/Formatter.html#syntax">format string</a>
2822 * Arguments referenced by the format specifiers in the format
2823 * string. If there are more arguments than format specifiers, the
2824 * extra arguments are ignored. The number of arguments is
2825 * variable and may be zero. The maximum number of arguments is
2826 * limited by the maximum dimension of a Java array as defined by
2827 * <cite>The Java™ Virtual Machine Specification</cite>.
2828 * The behaviour on a
2829 * <tt>null</tt> argument depends on the <a
2830 * href="../util/Formatter.html#syntax">conversion</a>.
2832 * @throws IllegalFormatException
2833 * If a format string contains an illegal syntax, a format
2834 * specifier that is incompatible with the given arguments,
2835 * insufficient arguments given the format string, or other
2836 * illegal conditions. For specification of all possible
2837 * formatting errors, see the <a
2838 * href="../util/Formatter.html#detail">Details</a> section of the
2839 * formatter class specification
2841 * @throws NullPointerException
2842 * If the <tt>format</tt> is <tt>null</tt>
2844 * @return A formatted string
2846 * @see java.util.Formatter
2849 // public static String format(Locale l, String format, Object ... args) {
2850 // return new Formatter(l).format(format, args).toString();
2854 * Returns the string representation of the <code>Object</code> argument.
2856 * @param obj an <code>Object</code>.
2857 * @return if the argument is <code>null</code>, then a string equal to
2858 * <code>"null"</code>; otherwise, the value of
2859 * <code>obj.toString()</code> is returned.
2860 * @see java.lang.Object#toString()
2862 public static String valueOf(Object obj) {
2863 return (obj == null) ? "null" : obj.toString();
2867 * Returns the string representation of the <code>char</code> array
2868 * argument. The contents of the character array are copied; subsequent
2869 * modification of the character array does not affect the newly
2872 * @param data a <code>char</code> array.
2873 * @return a newly allocated string representing the same sequence of
2874 * characters contained in the character array argument.
2876 public static String valueOf(char data[]) {
2877 return new String(data);
2881 * Returns the string representation of a specific subarray of the
2882 * <code>char</code> array argument.
2884 * The <code>offset</code> argument is the index of the first
2885 * character of the subarray. The <code>count</code> argument
2886 * specifies the length of the subarray. The contents of the subarray
2887 * are copied; subsequent modification of the character array does not
2888 * affect the newly created string.
2890 * @param data the character array.
2891 * @param offset the initial offset into the value of the
2892 * <code>String</code>.
2893 * @param count the length of the value of the <code>String</code>.
2894 * @return a string representing the sequence of characters contained
2895 * in the subarray of the character array argument.
2896 * @exception IndexOutOfBoundsException if <code>offset</code> is
2897 * negative, or <code>count</code> is negative, or
2898 * <code>offset+count</code> is larger than
2899 * <code>data.length</code>.
2901 public static String valueOf(char data[], int offset, int count) {
2902 return new String(data, offset, count);
2906 * Returns a String that represents the character sequence in the
2909 * @param data the character array.
2910 * @param offset initial offset of the subarray.
2911 * @param count length of the subarray.
2912 * @return a <code>String</code> that contains the characters of the
2913 * specified subarray of the character array.
2915 public static String copyValueOf(char data[], int offset, int count) {
2916 // All public String constructors now copy the data.
2917 return new String(data, offset, count);
2921 * Returns a String that represents the character sequence in the
2924 * @param data the character array.
2925 * @return a <code>String</code> that contains the characters of the
2928 public static String copyValueOf(char data[]) {
2929 return copyValueOf(data, 0, data.length);
2933 * Returns the string representation of the <code>boolean</code> argument.
2935 * @param b a <code>boolean</code>.
2936 * @return if the argument is <code>true</code>, a string equal to
2937 * <code>"true"</code> is returned; otherwise, a string equal to
2938 * <code>"false"</code> is returned.
2940 public static String valueOf(boolean b) {
2941 return b ? "true" : "false";
2945 * Returns the string representation of the <code>char</code>
2948 * @param c a <code>char</code>.
2949 * @return a string of length <code>1</code> containing
2950 * as its single character the argument <code>c</code>.
2952 public static String valueOf(char c) {
2954 return new String(0, 1, data);
2958 * Returns the string representation of the <code>int</code> argument.
2960 * The representation is exactly the one returned by the
2961 * <code>Integer.toString</code> method of one argument.
2963 * @param i an <code>int</code>.
2964 * @return a string representation of the <code>int</code> argument.
2965 * @see java.lang.Integer#toString(int, int)
2967 public static String valueOf(int i) {
2968 return Integer.toString(i);
2972 * Returns the string representation of the <code>long</code> argument.
2974 * The representation is exactly the one returned by the
2975 * <code>Long.toString</code> method of one argument.
2977 * @param l a <code>long</code>.
2978 * @return a string representation of the <code>long</code> argument.
2979 * @see java.lang.Long#toString(long)
2981 public static String valueOf(long l) {
2982 return Long.toString(l);
2986 * Returns the string representation of the <code>float</code> argument.
2988 * The representation is exactly the one returned by the
2989 * <code>Float.toString</code> method of one argument.
2991 * @param f a <code>float</code>.
2992 * @return a string representation of the <code>float</code> argument.
2993 * @see java.lang.Float#toString(float)
2995 public static String valueOf(float f) {
2996 return Float.toString(f);
3000 * Returns the string representation of the <code>double</code> argument.
3002 * The representation is exactly the one returned by the
3003 * <code>Double.toString</code> method of one argument.
3005 * @param d a <code>double</code>.
3006 * @return a string representation of the <code>double</code> argument.
3007 * @see java.lang.Double#toString(double)
3009 public static String valueOf(double d) {
3010 return Double.toString(d);
3014 * Returns a canonical representation for the string object.
3016 * A pool of strings, initially empty, is maintained privately by the
3017 * class <code>String</code>.
3019 * When the intern method is invoked, if the pool already contains a
3020 * string equal to this <code>String</code> object as determined by
3021 * the {@link #equals(Object)} method, then the string from the pool is
3022 * returned. Otherwise, this <code>String</code> object is added to the
3023 * pool and a reference to this <code>String</code> object is returned.
3025 * It follows that for any two strings <code>s</code> and <code>t</code>,
3026 * <code>s.intern() == t.intern()</code> is <code>true</code>
3027 * if and only if <code>s.equals(t)</code> is <code>true</code>.
3029 * All literal strings and string-valued constant expressions are
3030 * interned. String literals are defined in section 3.10.5 of the
3031 * <cite>The Java™ Language Specification</cite>.
3033 * @return a string that has the same contents as this string, but is
3034 * guaranteed to be from a pool of unique strings.
3036 public native String intern();