2 * Copyright (c) 1994, 2010, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
28 import java.io.UnsupportedEncodingException;
29 import java.util.Comparator;
30 import org.apidesign.bck2brwsr.core.ExtraJavaScript;
31 import org.apidesign.bck2brwsr.core.JavaScriptBody;
32 import org.apidesign.bck2brwsr.core.JavaScriptOnly;
33 import org.apidesign.bck2brwsr.core.JavaScriptPrototype;
34 import org.apidesign.bck2brwsr.emul.lang.System;
37 * The <code>String</code> class represents character strings. All
38 * string literals in Java programs, such as <code>"abc"</code>, are
39 * implemented as instances of this class.
41 * Strings are constant; their values cannot be changed after they
42 * are created. String buffers support mutable strings.
43 * Because String objects are immutable they can be shared. For example:
44 * <p><blockquote><pre>
46 * </pre></blockquote><p>
48 * <p><blockquote><pre>
49 * char data[] = {'a', 'b', 'c'};
50 * String str = new String(data);
51 * </pre></blockquote><p>
52 * Here are some more examples of how strings can be used:
53 * <p><blockquote><pre>
54 * System.out.println("abc");
56 * System.out.println("abc" + cde);
57 * String c = "abc".substring(2,3);
58 * String d = cde.substring(1, 2);
61 * The class <code>String</code> includes methods for examining
62 * individual characters of the sequence, for comparing strings, for
63 * searching strings, for extracting substrings, and for creating a
64 * copy of a string with all characters translated to uppercase or to
65 * lowercase. Case mapping is based on the Unicode Standard version
66 * specified by the {@link java.lang.Character Character} class.
68 * The Java language provides special support for the string
69 * concatenation operator ( + ), and for conversion of
70 * other objects to strings. String concatenation is implemented
71 * through the <code>StringBuilder</code>(or <code>StringBuffer</code>)
72 * class and its <code>append</code> method.
73 * String conversions are implemented through the method
74 * <code>toString</code>, defined by <code>Object</code> and
75 * inherited by all classes in Java. For additional information on
76 * string concatenation and conversion, see Gosling, Joy, and Steele,
77 * <i>The Java Language Specification</i>.
79 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
80 * or method in this class will cause a {@link NullPointerException} to be
83 * <p>A <code>String</code> represents a string in the UTF-16 format
84 * in which <em>supplementary characters</em> are represented by <em>surrogate
85 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
86 * Character Representations</a> in the <code>Character</code> class for
88 * Index values refer to <code>char</code> code units, so a supplementary
89 * character uses two positions in a <code>String</code>.
90 * <p>The <code>String</code> class provides methods for dealing with
91 * Unicode code points (i.e., characters), in addition to those for
92 * dealing with Unicode code units (i.e., <code>char</code> values).
95 * @author Arthur van Hoff
96 * @author Martin Buchholz
98 * @see java.lang.Object#toString()
99 * @see java.lang.StringBuffer
100 * @see java.lang.StringBuilder
101 * @see java.nio.charset.Charset
106 resource="/org/apidesign/vm4brwsr/emul/lang/java_lang_String.js",
109 @JavaScriptPrototype(container = "String.prototype", prototype = "new String")
110 public final class String
111 implements java.io.Serializable, Comparable<String>, CharSequence
113 /** real string to delegate to */
116 /** use serialVersionUID from JDK 1.0.2 for interoperability */
117 private static final long serialVersionUID = -6849794470754667710L;
122 @JavaScriptBody(args = {}, body =
123 "var p = vm.java_lang_String(false);\n"
124 + "p.toString = function() {\nreturn this._r().toString();\n};\n"
125 + "p.valueOf = function() {\nreturn this._r().valueOf();\n}\n"
127 private static native void registerToString();
130 * Class String is special cased within the Serialization Stream Protocol.
132 * A String instance is written initially into an ObjectOutputStream in the
135 * <code>TC_STRING</code> (utf String)
137 * The String is written by method <code>DataOutput.writeUTF</code>.
138 * A new handle is generated to refer to all future references to the
139 * string instance within the stream.
141 // private static final ObjectStreamField[] serialPersistentFields =
142 // new ObjectStreamField[0];
145 * Initializes a newly created {@code String} object so that it represents
146 * an empty character sequence. Note that use of this constructor is
147 * unnecessary since Strings are immutable.
154 * Initializes a newly created {@code String} object so that it represents
155 * the same sequence of characters as the argument; in other words, the
156 * newly created string is a copy of the argument string. Unless an
157 * explicit copy of {@code original} is needed, use of this constructor is
158 * unnecessary since Strings are immutable.
163 public String(String original) {
164 this.r = original.toString();
168 * Allocates a new {@code String} so that it represents the sequence of
169 * characters currently contained in the character array argument. The
170 * contents of the character array are copied; subsequent modification of
171 * the character array does not affect the newly created string.
174 * The initial value of the string
176 @JavaScriptBody(args = { "charArr" }, body=
177 "for (var i = 0; i < charArr.length; i++) {\n"
178 + " if (typeof charArr[i] === 'number') charArr[i] = String.fromCharCode(charArr[i]);\n"
180 + "this._r(charArr.join(''));\n"
182 public String(char value[]) {
186 * Allocates a new {@code String} that contains characters from a subarray
187 * of the character array argument. The {@code offset} argument is the
188 * index of the first character of the subarray and the {@code count}
189 * argument specifies the length of the subarray. The contents of the
190 * subarray are copied; subsequent modification of the character array does
191 * not affect the newly created string.
194 * Array that is the source of characters
202 * @throws IndexOutOfBoundsException
203 * If the {@code offset} and {@code count} arguments index
204 * characters outside the bounds of the {@code value} array
206 public String(char value[], int offset, int count) {
207 initFromCharArray(value, offset, count);
210 @JavaScriptBody(args = { "charArr", "off", "cnt" }, body =
211 "var up = off + cnt;\n" +
212 "for (var i = off; i < up; i++) {\n" +
213 " if (typeof charArr[i] === 'number') charArr[i] = String.fromCharCode(charArr[i]);\n" +
215 "this._r(charArr.slice(off, up).join(\"\"));\n"
217 private native void initFromCharArray(char value[], int offset, int count);
220 * Allocates a new {@code String} that contains characters from a subarray
221 * of the <a href="Character.html#unicode">Unicode code point</a> array
222 * argument. The {@code offset} argument is the index of the first code
223 * point of the subarray and the {@code count} argument specifies the
224 * length of the subarray. The contents of the subarray are converted to
225 * {@code char}s; subsequent modification of the {@code int} array does not
226 * affect the newly created string.
229 * Array that is the source of Unicode code points
237 * @throws IllegalArgumentException
238 * If any invalid Unicode code point is found in {@code
241 * @throws IndexOutOfBoundsException
242 * If the {@code offset} and {@code count} arguments index
243 * characters outside the bounds of the {@code codePoints} array
247 public String(int[] codePoints, int offset, int count) {
249 throw new StringIndexOutOfBoundsException(offset);
252 throw new StringIndexOutOfBoundsException(count);
254 // Note: offset or count might be near -1>>>1.
255 if (offset > codePoints.length - count) {
256 throw new StringIndexOutOfBoundsException(offset + count);
259 final int end = offset + count;
261 // Pass 1: Compute precise size of char[]
263 for (int i = offset; i < end; i++) {
264 int c = codePoints[i];
265 if (Character.isBmpCodePoint(c))
267 else if (Character.isValidCodePoint(c))
269 else throw new IllegalArgumentException(Integer.toString(c));
272 // Pass 2: Allocate and fill in char[]
273 final char[] v = new char[n];
275 for (int i = offset, j = 0; i < end; i++, j++) {
276 int c = codePoints[i];
277 if (Character.isBmpCodePoint(c))
280 Character.toSurrogates(c, v, j++);
283 this.r = new String(v, 0, n);
287 * Allocates a new {@code String} constructed from a subarray of an array
288 * of 8-bit integer values.
290 * <p> The {@code offset} argument is the index of the first byte of the
291 * subarray, and the {@code count} argument specifies the length of the
294 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
295 * specified in the method above.
297 * @deprecated This method does not properly convert bytes into characters.
298 * As of JDK 1.1, the preferred way to do this is via the
299 * {@code String} constructors that take a {@link
300 * java.nio.charset.Charset}, charset name, or that use the platform's
304 * The bytes to be converted to characters
307 * The top 8 bits of each 16-bit Unicode code unit
314 * @throws IndexOutOfBoundsException
315 * If the {@code offset} or {@code count} argument is invalid
317 * @see #String(byte[], int)
318 * @see #String(byte[], int, int, java.lang.String)
319 * @see #String(byte[], int, int, java.nio.charset.Charset)
320 * @see #String(byte[], int, int)
321 * @see #String(byte[], java.lang.String)
322 * @see #String(byte[], java.nio.charset.Charset)
323 * @see #String(byte[])
326 public String(byte ascii[], int hibyte, int offset, int count) {
327 checkBounds(ascii, offset, count);
328 char value[] = new char[count];
331 for (int i = count ; i-- > 0 ;) {
332 value[i] = (char) (ascii[i + offset] & 0xff);
336 for (int i = count ; i-- > 0 ;) {
337 value[i] = (char) (hibyte | (ascii[i + offset] & 0xff));
340 initFromCharArray(value, offset, count);
344 * Allocates a new {@code String} containing characters constructed from
345 * an array of 8-bit integer values. Each character <i>c</i>in the
346 * resulting string is constructed from the corresponding component
347 * <i>b</i> in the byte array such that:
350 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
351 * | (<b><i>b</i></b> & 0xff))
352 * </pre></blockquote>
354 * @deprecated This method does not properly convert bytes into
355 * characters. As of JDK 1.1, the preferred way to do this is via the
356 * {@code String} constructors that take a {@link
357 * java.nio.charset.Charset}, charset name, or that use the platform's
361 * The bytes to be converted to characters
364 * The top 8 bits of each 16-bit Unicode code unit
366 * @see #String(byte[], int, int, java.lang.String)
367 * @see #String(byte[], int, int, java.nio.charset.Charset)
368 * @see #String(byte[], int, int)
369 * @see #String(byte[], java.lang.String)
370 * @see #String(byte[], java.nio.charset.Charset)
371 * @see #String(byte[])
374 public String(byte ascii[], int hibyte) {
375 this(ascii, hibyte, 0, ascii.length);
378 /* Common private utility method used to bounds check the byte array
379 * and requested offset & length values used by the String(byte[],..)
382 private static void checkBounds(byte[] bytes, int offset, int length) {
384 throw new StringIndexOutOfBoundsException(length);
386 throw new StringIndexOutOfBoundsException(offset);
387 if (offset > bytes.length - length)
388 throw new StringIndexOutOfBoundsException(offset + length);
392 * Constructs a new {@code String} by decoding the specified subarray of
393 * bytes using the specified charset. The length of the new {@code String}
394 * is a function of the charset, and hence may not be equal to the length
397 * <p> The behavior of this constructor when the given bytes are not valid
398 * in the given charset is unspecified. The {@link
399 * java.nio.charset.CharsetDecoder} class should be used when more control
400 * over the decoding process is required.
403 * The bytes to be decoded into characters
406 * The index of the first byte to decode
409 * The number of bytes to decode
412 * The name of a supported {@linkplain java.nio.charset.Charset
415 * @throws UnsupportedEncodingException
416 * If the named charset is not supported
418 * @throws IndexOutOfBoundsException
419 * If the {@code offset} and {@code length} arguments index
420 * characters outside the bounds of the {@code bytes} array
424 public String(byte bytes[], int offset, int length, String charsetName)
425 throws UnsupportedEncodingException
427 this(checkUTF8(bytes, charsetName), offset, length);
431 * Constructs a new {@code String} by decoding the specified subarray of
432 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
433 * The length of the new {@code String} is a function of the charset, and
434 * hence may not be equal to the length of the subarray.
436 * <p> This method always replaces malformed-input and unmappable-character
437 * sequences with this charset's default replacement string. The {@link
438 * java.nio.charset.CharsetDecoder} class should be used when more control
439 * over the decoding process is required.
442 * The bytes to be decoded into characters
445 * The index of the first byte to decode
448 * The number of bytes to decode
451 * The {@linkplain java.nio.charset.Charset charset} to be used to
452 * decode the {@code bytes}
454 * @throws IndexOutOfBoundsException
455 * If the {@code offset} and {@code length} arguments index
456 * characters outside the bounds of the {@code bytes} array
460 /* don't want dependnecy on Charset
461 public String(byte bytes[], int offset, int length, Charset charset) {
463 throw new NullPointerException("charset");
464 checkBounds(bytes, offset, length);
465 char[] v = StringCoding.decode(charset, bytes, offset, length);
467 this.count = v.length;
473 * Constructs a new {@code String} by decoding the specified array of bytes
474 * using the specified {@linkplain java.nio.charset.Charset charset}. The
475 * length of the new {@code String} is a function of the charset, and hence
476 * may not be equal to the length of the byte array.
478 * <p> The behavior of this constructor when the given bytes are not valid
479 * in the given charset is unspecified. The {@link
480 * java.nio.charset.CharsetDecoder} class should be used when more control
481 * over the decoding process is required.
484 * The bytes to be decoded into characters
487 * The name of a supported {@linkplain java.nio.charset.Charset
490 * @throws UnsupportedEncodingException
491 * If the named charset is not supported
495 public String(byte bytes[], String charsetName)
496 throws UnsupportedEncodingException
498 this(bytes, 0, bytes.length, charsetName);
502 * Constructs a new {@code String} by decoding the specified array of
503 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
504 * The length of the new {@code String} is a function of the charset, and
505 * hence may not be equal to the length of the byte array.
507 * <p> This method always replaces malformed-input and unmappable-character
508 * sequences with this charset's default replacement string. The {@link
509 * java.nio.charset.CharsetDecoder} class should be used when more control
510 * over the decoding process is required.
513 * The bytes to be decoded into characters
516 * The {@linkplain java.nio.charset.Charset charset} to be used to
517 * decode the {@code bytes}
521 /* don't want dep on Charset
522 public String(byte bytes[], Charset charset) {
523 this(bytes, 0, bytes.length, charset);
528 * Constructs a new {@code String} by decoding the specified subarray of
529 * bytes using the platform's default charset. The length of the new
530 * {@code String} is a function of the charset, and hence may not be equal
531 * to the length of the subarray.
533 * <p> The behavior of this constructor when the given bytes are not valid
534 * in the default charset is unspecified. The {@link
535 * java.nio.charset.CharsetDecoder} class should be used when more control
536 * over the decoding process is required.
539 * The bytes to be decoded into characters
542 * The index of the first byte to decode
545 * The number of bytes to decode
547 * @throws IndexOutOfBoundsException
548 * If the {@code offset} and the {@code length} arguments index
549 * characters outside the bounds of the {@code bytes} array
553 public String(byte bytes[], int offset, int length) {
554 checkBounds(bytes, offset, length);
555 char[] v = new char[length];
556 int[] at = { offset };
557 int end = offset + length;
559 while (at[0] < end) {
560 int ch = nextChar(bytes, at);
561 v[chlen++] = (char)ch;
563 initFromCharArray(v, 0, chlen);
567 * Constructs a new {@code String} by decoding the specified array of bytes
568 * using the platform's default charset. The length of the new {@code
569 * String} is a function of the charset, and hence may not be equal to the
570 * length of the byte array.
572 * <p> The behavior of this constructor when the given bytes are not valid
573 * in the default charset is unspecified. The {@link
574 * java.nio.charset.CharsetDecoder} class should be used when more control
575 * over the decoding process is required.
578 * The bytes to be decoded into characters
582 public String(byte bytes[]) {
583 this(bytes, 0, bytes.length);
587 * Allocates a new string that contains the sequence of characters
588 * currently contained in the string buffer argument. The contents of the
589 * string buffer are copied; subsequent modification of the string buffer
590 * does not affect the newly created string.
593 * A {@code StringBuffer}
595 public String(StringBuffer buffer) {
596 this.r = buffer.toString();
600 * Allocates a new string that contains the sequence of characters
601 * currently contained in the string builder argument. The contents of the
602 * string builder are copied; subsequent modification of the string builder
603 * does not affect the newly created string.
605 * <p> This constructor is provided to ease migration to {@code
606 * StringBuilder}. Obtaining a string from a string builder via the {@code
607 * toString} method is likely to run faster and is generally preferred.
610 * A {@code StringBuilder}
614 public String(StringBuilder builder) {
615 this.r = builder.toString();
619 * Returns the length of this string.
620 * The length is equal to the number of <a href="Character.html#unicode">Unicode
621 * code units</a> in the string.
623 * @return the length of the sequence of characters represented by this
626 @JavaScriptBody(args = {}, body = "return this.toString().length;")
627 public int length() {
628 throw new UnsupportedOperationException();
632 * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>.
634 * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise
639 @JavaScriptBody(args = {}, body="return this.toString().length === 0;")
640 public boolean isEmpty() {
641 return length() == 0;
645 * Returns the <code>char</code> value at the
646 * specified index. An index ranges from <code>0</code> to
647 * <code>length() - 1</code>. The first <code>char</code> value of the sequence
648 * is at index <code>0</code>, the next at index <code>1</code>,
649 * and so on, as for array indexing.
651 * <p>If the <code>char</code> value specified by the index is a
652 * <a href="Character.html#unicode">surrogate</a>, the surrogate
655 * @param index the index of the <code>char</code> value.
656 * @return the <code>char</code> value at the specified index of this string.
657 * The first <code>char</code> value is at index <code>0</code>.
658 * @exception IndexOutOfBoundsException if the <code>index</code>
659 * argument is negative or not less than the length of this
662 @JavaScriptBody(args = { "index" },
663 body = "return this.toString().charCodeAt(index);"
665 public char charAt(int index) {
666 throw new UnsupportedOperationException();
670 * Returns the character (Unicode code point) at the specified
671 * index. The index refers to <code>char</code> values
672 * (Unicode code units) and ranges from <code>0</code> to
673 * {@link #length()}<code> - 1</code>.
675 * <p> If the <code>char</code> value specified at the given index
676 * is in the high-surrogate range, the following index is less
677 * than the length of this <code>String</code>, and the
678 * <code>char</code> value at the following index is in the
679 * low-surrogate range, then the supplementary code point
680 * corresponding to this surrogate pair is returned. Otherwise,
681 * the <code>char</code> value at the given index is returned.
683 * @param index the index to the <code>char</code> values
684 * @return the code point value of the character at the
686 * @exception IndexOutOfBoundsException if the <code>index</code>
687 * argument is negative or not less than the length of this
691 public int codePointAt(int index) {
692 if ((index < 0) || (index >= length())) {
693 throw new StringIndexOutOfBoundsException(index);
695 return Character.codePointAtImpl(toCharArray(), offset() + index, offset() + length());
699 * Returns the character (Unicode code point) before the specified
700 * index. The index refers to <code>char</code> values
701 * (Unicode code units) and ranges from <code>1</code> to {@link
702 * CharSequence#length() length}.
704 * <p> If the <code>char</code> value at <code>(index - 1)</code>
705 * is in the low-surrogate range, <code>(index - 2)</code> is not
706 * negative, and the <code>char</code> value at <code>(index -
707 * 2)</code> is in the high-surrogate range, then the
708 * supplementary code point value of the surrogate pair is
709 * returned. If the <code>char</code> value at <code>index -
710 * 1</code> is an unpaired low-surrogate or a high-surrogate, the
711 * surrogate value is returned.
713 * @param index the index following the code point that should be returned
714 * @return the Unicode code point value before the given index.
715 * @exception IndexOutOfBoundsException if the <code>index</code>
716 * argument is less than 1 or greater than the length
720 public int codePointBefore(int index) {
722 if ((i < 0) || (i >= length())) {
723 throw new StringIndexOutOfBoundsException(index);
725 return Character.codePointBeforeImpl(toCharArray(), offset() + index, offset());
729 * Returns the number of Unicode code points in the specified text
730 * range of this <code>String</code>. The text range begins at the
731 * specified <code>beginIndex</code> and extends to the
732 * <code>char</code> at index <code>endIndex - 1</code>. Thus the
733 * length (in <code>char</code>s) of the text range is
734 * <code>endIndex-beginIndex</code>. Unpaired surrogates within
735 * the text range count as one code point each.
737 * @param beginIndex the index to the first <code>char</code> of
739 * @param endIndex the index after the last <code>char</code> of
741 * @return the number of Unicode code points in the specified text
743 * @exception IndexOutOfBoundsException if the
744 * <code>beginIndex</code> is negative, or <code>endIndex</code>
745 * is larger than the length of this <code>String</code>, or
746 * <code>beginIndex</code> is larger than <code>endIndex</code>.
749 public int codePointCount(int beginIndex, int endIndex) {
750 if (beginIndex < 0 || endIndex > length() || beginIndex > endIndex) {
751 throw new IndexOutOfBoundsException();
753 return Character.codePointCountImpl(toCharArray(), offset()+beginIndex, endIndex-beginIndex);
757 * Returns the index within this <code>String</code> that is
758 * offset from the given <code>index</code> by
759 * <code>codePointOffset</code> code points. Unpaired surrogates
760 * within the text range given by <code>index</code> and
761 * <code>codePointOffset</code> count as one code point each.
763 * @param index the index to be offset
764 * @param codePointOffset the offset in code points
765 * @return the index within this <code>String</code>
766 * @exception IndexOutOfBoundsException if <code>index</code>
767 * is negative or larger then the length of this
768 * <code>String</code>, or if <code>codePointOffset</code> is positive
769 * and the substring starting with <code>index</code> has fewer
770 * than <code>codePointOffset</code> code points,
771 * or if <code>codePointOffset</code> is negative and the substring
772 * before <code>index</code> has fewer than the absolute value
773 * of <code>codePointOffset</code> code points.
776 public int offsetByCodePoints(int index, int codePointOffset) {
777 if (index < 0 || index > length()) {
778 throw new IndexOutOfBoundsException();
780 return Character.offsetByCodePointsImpl(toCharArray(), offset(), length(),
781 offset()+index, codePointOffset) - offset();
785 * Copy characters from this string into dst starting at dstBegin.
786 * This method doesn't perform any range checking.
788 @JavaScriptBody(args = { "arr", "to" }, body =
789 "var s = this.toString();\n" +
790 "for (var i = 0; i < s.length; i++) {\n" +
791 " arr[to++] = s[i];\n" +
794 void getChars(char dst[], int dstBegin) {
795 System.arraycopy(toCharArray(), offset(), dst, dstBegin, length());
799 * Copies characters from this string into the destination character
802 * The first character to be copied is at index <code>srcBegin</code>;
803 * the last character to be copied is at index <code>srcEnd-1</code>
804 * (thus the total number of characters to be copied is
805 * <code>srcEnd-srcBegin</code>). The characters are copied into the
806 * subarray of <code>dst</code> starting at index <code>dstBegin</code>
807 * and ending at index:
808 * <p><blockquote><pre>
809 * dstbegin + (srcEnd-srcBegin) - 1
810 * </pre></blockquote>
812 * @param srcBegin index of the first character in the string
814 * @param srcEnd index after the last character in the string
816 * @param dst the destination array.
817 * @param dstBegin the start offset in the destination array.
818 * @exception IndexOutOfBoundsException If any of the following
820 * <ul><li><code>srcBegin</code> is negative.
821 * <li><code>srcBegin</code> is greater than <code>srcEnd</code>
822 * <li><code>srcEnd</code> is greater than the length of this
824 * <li><code>dstBegin</code> is negative
825 * <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
826 * <code>dst.length</code></ul>
828 @JavaScriptBody(args = { "beg", "end", "arr", "dst" }, body=
829 "var s = this.toString();\n" +
830 "while (beg < end) {\n" +
831 " arr[dst++] = s.charCodeAt(beg++);\n" +
834 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
836 throw new StringIndexOutOfBoundsException(srcBegin);
838 if (srcEnd > length()) {
839 throw new StringIndexOutOfBoundsException(srcEnd);
841 if (srcBegin > srcEnd) {
842 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
844 System.arraycopy(toCharArray(), offset() + srcBegin, dst, dstBegin,
849 * Copies characters from this string into the destination byte array. Each
850 * byte receives the 8 low-order bits of the corresponding character. The
851 * eight high-order bits of each character are not copied and do not
852 * participate in the transfer in any way.
854 * <p> The first character to be copied is at index {@code srcBegin}; the
855 * last character to be copied is at index {@code srcEnd-1}. The total
856 * number of characters to be copied is {@code srcEnd-srcBegin}. The
857 * characters, converted to bytes, are copied into the subarray of {@code
858 * dst} starting at index {@code dstBegin} and ending at index:
861 * dstbegin + (srcEnd-srcBegin) - 1
862 * </pre></blockquote>
864 * @deprecated This method does not properly convert characters into
865 * bytes. As of JDK 1.1, the preferred way to do this is via the
866 * {@link #getBytes()} method, which uses the platform's default charset.
869 * Index of the first character in the string to copy
872 * Index after the last character in the string to copy
875 * The destination array
878 * The start offset in the destination array
880 * @throws IndexOutOfBoundsException
881 * If any of the following is true:
883 * <li> {@code srcBegin} is negative
884 * <li> {@code srcBegin} is greater than {@code srcEnd}
885 * <li> {@code srcEnd} is greater than the length of this String
886 * <li> {@code dstBegin} is negative
887 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
892 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
894 throw new StringIndexOutOfBoundsException(srcBegin);
896 if (srcEnd > length()) {
897 throw new StringIndexOutOfBoundsException(srcEnd);
899 if (srcBegin > srcEnd) {
900 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
903 int n = offset() + srcEnd;
904 int i = offset() + srcBegin;
905 char[] val = toCharArray(); /* avoid getfield opcode */
908 dst[j++] = (byte)val[i++];
913 * Encodes this {@code String} into a sequence of bytes using the named
914 * charset, storing the result into a new byte array.
916 * <p> The behavior of this method when this string cannot be encoded in
917 * the given charset is unspecified. The {@link
918 * java.nio.charset.CharsetEncoder} class should be used when more control
919 * over the encoding process is required.
922 * The name of a supported {@linkplain java.nio.charset.Charset
925 * @return The resultant byte array
927 * @throws UnsupportedEncodingException
928 * If the named charset is not supported
932 public byte[] getBytes(String charsetName)
933 throws UnsupportedEncodingException
935 checkUTF8(null, charsetName);
940 * Encodes this {@code String} into a sequence of bytes using the given
941 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
944 * <p> This method always replaces malformed-input and unmappable-character
945 * sequences with this charset's default replacement byte array. The
946 * {@link java.nio.charset.CharsetEncoder} class should be used when more
947 * control over the encoding process is required.
950 * The {@linkplain java.nio.charset.Charset} to be used to encode
953 * @return The resultant byte array
957 /* don't want dep on Charset
958 public byte[] getBytes(Charset charset) {
959 if (charset == null) throw new NullPointerException();
960 return StringCoding.encode(charset, value, offset, count);
965 * Encodes this {@code String} into a sequence of bytes using the
966 * platform's default charset, storing the result into a new byte array.
968 * <p> The behavior of this method when this string cannot be encoded in
969 * the default charset is unspecified. The {@link
970 * java.nio.charset.CharsetEncoder} class should be used when more control
971 * over the encoding process is required.
973 * @return The resultant byte array
977 public byte[] getBytes() {
979 byte[] arr = new byte[len];
980 for (int i = 0, j = 0; j < len; j++) {
981 final int v = charAt(j);
987 arr = System.expandArray(arr, i + 1);
988 arr[i++] = (byte) (0xC0 | (v >> 6));
989 arr[i++] = (byte) (0x80 | (0x3F & v));
992 arr = System.expandArray(arr, i + 2);
993 arr[i++] = (byte) (0xE0 | (v >> 12));
994 arr[i++] = (byte) (0x80 | ((v >> 6) & 0x7F));
995 arr[i++] = (byte) (0x80 | (0x3F & v));
1001 * Compares this string to the specified object. The result is {@code
1002 * true} if and only if the argument is not {@code null} and is a {@code
1003 * String} object that represents the same sequence of characters as this
1007 * The object to compare this {@code String} against
1009 * @return {@code true} if the given object represents a {@code String}
1010 * equivalent to this string, {@code false} otherwise
1012 * @see #compareTo(String)
1013 * @see #equalsIgnoreCase(String)
1015 @JavaScriptBody(args = { "obj" }, body =
1016 "return obj != null && obj.$instOf_java_lang_String && "
1017 + "this.toString() === obj.toString();"
1019 public boolean equals(Object anObject) {
1020 if (this == anObject) {
1023 if (anObject instanceof String) {
1024 String anotherString = (String)anObject;
1026 if (n == anotherString.length()) {
1027 char v1[] = toCharArray();
1028 char v2[] = anotherString.toCharArray();
1030 int j = anotherString.offset();
1032 if (v1[i++] != v2[j++])
1042 * Compares this string to the specified {@code StringBuffer}. The result
1043 * is {@code true} if and only if this {@code String} represents the same
1044 * sequence of characters as the specified {@code StringBuffer}.
1047 * The {@code StringBuffer} to compare this {@code String} against
1049 * @return {@code true} if this {@code String} represents the same
1050 * sequence of characters as the specified {@code StringBuffer},
1051 * {@code false} otherwise
1055 public boolean contentEquals(StringBuffer sb) {
1057 return contentEquals((CharSequence)sb);
1062 * Compares this string to the specified {@code CharSequence}. The result
1063 * is {@code true} if and only if this {@code String} represents the same
1064 * sequence of char values as the specified sequence.
1067 * The sequence to compare this {@code String} against
1069 * @return {@code true} if this {@code String} represents the same
1070 * sequence of char values as the specified sequence, {@code
1075 public boolean contentEquals(CharSequence cs) {
1076 if (length() != cs.length())
1078 // Argument is a StringBuffer, StringBuilder
1079 if (cs instanceof AbstractStringBuilder) {
1080 char v1[] = toCharArray();
1081 char v2[] = ((AbstractStringBuilder)cs).getValue();
1086 if (v1[i++] != v2[j++])
1091 // Argument is a String
1092 if (cs.equals(this))
1094 // Argument is a generic CharSequence
1095 char v1[] = toCharArray();
1100 if (v1[i++] != cs.charAt(j++))
1107 * Compares this {@code String} to another {@code String}, ignoring case
1108 * considerations. Two strings are considered equal ignoring case if they
1109 * are of the same length and corresponding characters in the two strings
1110 * are equal ignoring case.
1112 * <p> Two characters {@code c1} and {@code c2} are considered the same
1113 * ignoring case if at least one of the following is true:
1115 * <li> The two characters are the same (as compared by the
1116 * {@code ==} operator)
1117 * <li> Applying the method {@link
1118 * java.lang.Character#toUpperCase(char)} to each character
1119 * produces the same result
1120 * <li> Applying the method {@link
1121 * java.lang.Character#toLowerCase(char)} to each character
1122 * produces the same result
1125 * @param anotherString
1126 * The {@code String} to compare this {@code String} against
1128 * @return {@code true} if the argument is not {@code null} and it
1129 * represents an equivalent {@code String} ignoring case; {@code
1132 * @see #equals(Object)
1134 public boolean equalsIgnoreCase(String anotherString) {
1135 return (this == anotherString) ? true :
1136 (anotherString != null) && (anotherString.length() == length()) &&
1137 regionMatches(true, 0, anotherString, 0, length());
1141 * Compares two strings lexicographically.
1142 * The comparison is based on the Unicode value of each character in
1143 * the strings. The character sequence represented by this
1144 * <code>String</code> object is compared lexicographically to the
1145 * character sequence represented by the argument string. The result is
1146 * a negative integer if this <code>String</code> object
1147 * lexicographically precedes the argument string. The result is a
1148 * positive integer if this <code>String</code> object lexicographically
1149 * follows the argument string. The result is zero if the strings
1150 * are equal; <code>compareTo</code> returns <code>0</code> exactly when
1151 * the {@link #equals(Object)} method would return <code>true</code>.
1153 * This is the definition of lexicographic ordering. If two strings are
1154 * different, then either they have different characters at some index
1155 * that is a valid index for both strings, or their lengths are different,
1156 * or both. If they have different characters at one or more index
1157 * positions, let <i>k</i> be the smallest such index; then the string
1158 * whose character at position <i>k</i> has the smaller value, as
1159 * determined by using the < operator, lexicographically precedes the
1160 * other string. In this case, <code>compareTo</code> returns the
1161 * difference of the two character values at position <code>k</code> in
1162 * the two string -- that is, the value:
1164 * this.charAt(k)-anotherString.charAt(k)
1165 * </pre></blockquote>
1166 * If there is no index position at which they differ, then the shorter
1167 * string lexicographically precedes the longer string. In this case,
1168 * <code>compareTo</code> returns the difference of the lengths of the
1169 * strings -- that is, the value:
1171 * this.length()-anotherString.length()
1172 * </pre></blockquote>
1174 * @param anotherString the <code>String</code> to be compared.
1175 * @return the value <code>0</code> if the argument string is equal to
1176 * this string; a value less than <code>0</code> if this string
1177 * is lexicographically less than the string argument; and a
1178 * value greater than <code>0</code> if this string is
1179 * lexicographically greater than the string argument.
1181 public int compareTo(String anotherString) {
1182 int len1 = length();
1183 int len2 = anotherString.length();
1184 int n = Math.min(len1, len2);
1185 char v1[] = toCharArray();
1186 char v2[] = anotherString.toCharArray();
1188 int j = anotherString.offset();
1214 * A Comparator that orders <code>String</code> objects as by
1215 * <code>compareToIgnoreCase</code>. This comparator is serializable.
1217 * Note that this Comparator does <em>not</em> take locale into account,
1218 * and will result in an unsatisfactory ordering for certain locales.
1219 * The java.text package provides <em>Collators</em> to allow
1220 * locale-sensitive ordering.
1222 * @see java.text.Collator#compare(String, String)
1225 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1226 = new CaseInsensitiveComparator();
1228 private static int offset() {
1232 private static class CaseInsensitiveComparator
1233 implements Comparator<String>, java.io.Serializable {
1234 // use serialVersionUID from JDK 1.2.2 for interoperability
1235 private static final long serialVersionUID = 8575799808933029326L;
1237 public int compare(String s1, String s2) {
1238 int n1 = s1.length();
1239 int n2 = s2.length();
1240 int min = Math.min(n1, n2);
1241 for (int i = 0; i < min; i++) {
1242 char c1 = s1.charAt(i);
1243 char c2 = s2.charAt(i);
1245 c1 = Character.toUpperCase(c1);
1246 c2 = Character.toUpperCase(c2);
1248 c1 = Character.toLowerCase(c1);
1249 c2 = Character.toLowerCase(c2);
1251 // No overflow because of numeric promotion
1262 * Compares two strings lexicographically, ignoring case
1263 * differences. This method returns an integer whose sign is that of
1264 * calling <code>compareTo</code> with normalized versions of the strings
1265 * where case differences have been eliminated by calling
1266 * <code>Character.toLowerCase(Character.toUpperCase(character))</code> on
1269 * Note that this method does <em>not</em> take locale into account,
1270 * and will result in an unsatisfactory ordering for certain locales.
1271 * The java.text package provides <em>collators</em> to allow
1272 * locale-sensitive ordering.
1274 * @param str the <code>String</code> to be compared.
1275 * @return a negative integer, zero, or a positive integer as the
1276 * specified String is greater than, equal to, or less
1277 * than this String, ignoring case considerations.
1278 * @see java.text.Collator#compare(String, String)
1281 public int compareToIgnoreCase(String str) {
1282 return CASE_INSENSITIVE_ORDER.compare(this, str);
1286 * Tests if two string regions are equal.
1288 * A substring of this <tt>String</tt> object is compared to a substring
1289 * of the argument other. The result is true if these substrings
1290 * represent identical character sequences. The substring of this
1291 * <tt>String</tt> object to be compared begins at index <tt>toffset</tt>
1292 * and has length <tt>len</tt>. The substring of other to be compared
1293 * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The
1294 * result is <tt>false</tt> if and only if at least one of the following
1296 * <ul><li><tt>toffset</tt> is negative.
1297 * <li><tt>ooffset</tt> is negative.
1298 * <li><tt>toffset+len</tt> is greater than the length of this
1299 * <tt>String</tt> object.
1300 * <li><tt>ooffset+len</tt> is greater than the length of the other
1302 * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt>
1304 * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt>
1307 * @param toffset the starting offset of the subregion in this string.
1308 * @param other the string argument.
1309 * @param ooffset the starting offset of the subregion in the string
1311 * @param len the number of characters to compare.
1312 * @return <code>true</code> if the specified subregion of this string
1313 * exactly matches the specified subregion of the string argument;
1314 * <code>false</code> otherwise.
1316 public boolean regionMatches(int toffset, String other, int ooffset,
1318 char ta[] = toCharArray();
1319 int to = offset() + toffset;
1320 char pa[] = other.toCharArray();
1321 int po = other.offset() + ooffset;
1322 // Note: toffset, ooffset, or len might be near -1>>>1.
1323 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)length() - len)
1324 || (ooffset > (long)other.length() - len)) {
1328 if (ta[to++] != pa[po++]) {
1336 * Tests if two string regions are equal.
1338 * A substring of this <tt>String</tt> object is compared to a substring
1339 * of the argument <tt>other</tt>. The result is <tt>true</tt> if these
1340 * substrings represent character sequences that are the same, ignoring
1341 * case if and only if <tt>ignoreCase</tt> is true. The substring of
1342 * this <tt>String</tt> object to be compared begins at index
1343 * <tt>toffset</tt> and has length <tt>len</tt>. The substring of
1344 * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and
1345 * has length <tt>len</tt>. The result is <tt>false</tt> if and only if
1346 * at least one of the following is true:
1347 * <ul><li><tt>toffset</tt> is negative.
1348 * <li><tt>ooffset</tt> is negative.
1349 * <li><tt>toffset+len</tt> is greater than the length of this
1350 * <tt>String</tt> object.
1351 * <li><tt>ooffset+len</tt> is greater than the length of the other
1353 * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative
1354 * integer <i>k</i> less than <tt>len</tt> such that:
1356 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1357 * </pre></blockquote>
1358 * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative
1359 * integer <i>k</i> less than <tt>len</tt> such that:
1361 * Character.toLowerCase(this.charAt(toffset+k)) !=
1362 Character.toLowerCase(other.charAt(ooffset+k))
1363 * </pre></blockquote>
1366 * Character.toUpperCase(this.charAt(toffset+k)) !=
1367 * Character.toUpperCase(other.charAt(ooffset+k))
1368 * </pre></blockquote>
1371 * @param ignoreCase if <code>true</code>, ignore case when comparing
1373 * @param toffset the starting offset of the subregion in this
1375 * @param other the string argument.
1376 * @param ooffset the starting offset of the subregion in the string
1378 * @param len the number of characters to compare.
1379 * @return <code>true</code> if the specified subregion of this string
1380 * matches the specified subregion of the string argument;
1381 * <code>false</code> otherwise. Whether the matching is exact
1382 * or case insensitive depends on the <code>ignoreCase</code>
1385 public boolean regionMatches(boolean ignoreCase, int toffset,
1386 String other, int ooffset, int len) {
1387 char ta[] = toCharArray();
1388 int to = offset() + toffset;
1389 char pa[] = other.toCharArray();
1390 int po = other.offset() + ooffset;
1391 // Note: toffset, ooffset, or len might be near -1>>>1.
1392 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)length() - len) ||
1393 (ooffset > (long)other.length() - len)) {
1403 // If characters don't match but case may be ignored,
1404 // try converting both characters to uppercase.
1405 // If the results match, then the comparison scan should
1407 char u1 = Character.toUpperCase(c1);
1408 char u2 = Character.toUpperCase(c2);
1412 // Unfortunately, conversion to uppercase does not work properly
1413 // for the Georgian alphabet, which has strange rules about case
1414 // conversion. So we need to make one last check before
1416 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1426 * Tests if the substring of this string beginning at the
1427 * specified index starts with the specified prefix.
1429 * @param prefix the prefix.
1430 * @param toffset where to begin looking in this string.
1431 * @return <code>true</code> if the character sequence represented by the
1432 * argument is a prefix of the substring of this object starting
1433 * at index <code>toffset</code>; <code>false</code> otherwise.
1434 * The result is <code>false</code> if <code>toffset</code> is
1435 * negative or greater than the length of this
1436 * <code>String</code> object; otherwise the result is the same
1437 * as the result of the expression
1439 * this.substring(toffset).startsWith(prefix)
1442 @JavaScriptBody(args = { "find", "from" }, body=
1443 "find = find.toString();\n" +
1444 "return this.toString().substring(from, from + find.length) === find;\n"
1446 public boolean startsWith(String prefix, int toffset) {
1447 char ta[] = toCharArray();
1448 int to = offset() + toffset;
1449 char pa[] = prefix.toCharArray();
1450 int po = prefix.offset();
1451 int pc = prefix.length();
1452 // Note: toffset might be near -1>>>1.
1453 if ((toffset < 0) || (toffset > length() - pc)) {
1457 if (ta[to++] != pa[po++]) {
1465 * Tests if this string starts with the specified prefix.
1467 * @param prefix the prefix.
1468 * @return <code>true</code> if the character sequence represented by the
1469 * argument is a prefix of the character sequence represented by
1470 * this string; <code>false</code> otherwise.
1471 * Note also that <code>true</code> will be returned if the
1472 * argument is an empty string or is equal to this
1473 * <code>String</code> object as determined by the
1474 * {@link #equals(Object)} method.
1477 public boolean startsWith(String prefix) {
1478 return startsWith(prefix, 0);
1482 * Tests if this string ends with the specified suffix.
1484 * @param suffix the suffix.
1485 * @return <code>true</code> if the character sequence represented by the
1486 * argument is a suffix of the character sequence represented by
1487 * this object; <code>false</code> otherwise. Note that the
1488 * result will be <code>true</code> if the argument is the
1489 * empty string or is equal to this <code>String</code> object
1490 * as determined by the {@link #equals(Object)} method.
1492 public boolean endsWith(String suffix) {
1493 return startsWith(suffix, length() - suffix.length());
1497 * Returns a hash code for this string. The hash code for a
1498 * <code>String</code> object is computed as
1500 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1501 * </pre></blockquote>
1502 * using <code>int</code> arithmetic, where <code>s[i]</code> is the
1503 * <i>i</i>th character of the string, <code>n</code> is the length of
1504 * the string, and <code>^</code> indicates exponentiation.
1505 * (The hash value of the empty string is zero.)
1507 * @return a hash code value for this object.
1509 public int hashCode() {
1510 return super.hashCode();
1512 int computeHashCode() {
1514 if (h == 0 && length() > 0) {
1518 for (int i = 0; i < len; i++) {
1519 h = 31*h + charAt(off++);
1526 * Returns the index within this string of the first occurrence of
1527 * the specified character. If a character with value
1528 * <code>ch</code> occurs in the character sequence represented by
1529 * this <code>String</code> object, then the index (in Unicode
1530 * code units) of the first such occurrence is returned. For
1531 * values of <code>ch</code> in the range from 0 to 0xFFFF
1532 * (inclusive), this is the smallest value <i>k</i> such that:
1534 * this.charAt(<i>k</i>) == ch
1535 * </pre></blockquote>
1536 * is true. For other values of <code>ch</code>, it is the
1537 * smallest value <i>k</i> such that:
1539 * this.codePointAt(<i>k</i>) == ch
1540 * </pre></blockquote>
1541 * is true. In either case, if no such character occurs in this
1542 * string, then <code>-1</code> is returned.
1544 * @param ch a character (Unicode code point).
1545 * @return the index of the first occurrence of the character in the
1546 * character sequence represented by this object, or
1547 * <code>-1</code> if the character does not occur.
1549 public int indexOf(int ch) {
1550 return indexOf(ch, 0);
1554 * Returns the index within this string of the first occurrence of the
1555 * specified character, starting the search at the specified index.
1557 * If a character with value <code>ch</code> occurs in the
1558 * character sequence represented by this <code>String</code>
1559 * object at an index no smaller than <code>fromIndex</code>, then
1560 * the index of the first such occurrence is returned. For values
1561 * of <code>ch</code> in the range from 0 to 0xFFFF (inclusive),
1562 * this is the smallest value <i>k</i> such that:
1564 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1565 * </pre></blockquote>
1566 * is true. For other values of <code>ch</code>, it is the
1567 * smallest value <i>k</i> such that:
1569 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1570 * </pre></blockquote>
1571 * is true. In either case, if no such character occurs in this
1572 * string at or after position <code>fromIndex</code>, then
1573 * <code>-1</code> is returned.
1576 * There is no restriction on the value of <code>fromIndex</code>. If it
1577 * is negative, it has the same effect as if it were zero: this entire
1578 * string may be searched. If it is greater than the length of this
1579 * string, it has the same effect as if it were equal to the length of
1580 * this string: <code>-1</code> is returned.
1582 * <p>All indices are specified in <code>char</code> values
1583 * (Unicode code units).
1585 * @param ch a character (Unicode code point).
1586 * @param fromIndex the index to start the search from.
1587 * @return the index of the first occurrence of the character in the
1588 * character sequence represented by this object that is greater
1589 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1590 * if the character does not occur.
1592 @JavaScriptBody(args = { "ch", "from" }, body =
1593 "if (typeof ch === 'number') ch = String.fromCharCode(ch);\n" +
1594 "return this.toString().indexOf(ch, from);\n"
1596 public int indexOf(int ch, int fromIndex) {
1597 if (fromIndex < 0) {
1599 } else if (fromIndex >= length()) {
1600 // Note: fromIndex might be near -1>>>1.
1604 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1605 // handle most cases here (ch is a BMP code point or a
1606 // negative value (invalid code point))
1607 final char[] value = this.toCharArray();
1608 final int offset = this.offset();
1609 final int max = offset + length();
1610 for (int i = offset + fromIndex; i < max ; i++) {
1611 if (value[i] == ch) {
1617 return indexOfSupplementary(ch, fromIndex);
1622 * Handles (rare) calls of indexOf with a supplementary character.
1624 private int indexOfSupplementary(int ch, int fromIndex) {
1625 if (Character.isValidCodePoint(ch)) {
1626 final char[] value = this.toCharArray();
1627 final int offset = this.offset();
1628 final char hi = Character.highSurrogate(ch);
1629 final char lo = Character.lowSurrogate(ch);
1630 final int max = offset + length() - 1;
1631 for (int i = offset + fromIndex; i < max; i++) {
1632 if (value[i] == hi && value[i+1] == lo) {
1641 * Returns the index within this string of the last occurrence of
1642 * the specified character. For values of <code>ch</code> in the
1643 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1644 * units) returned is the largest value <i>k</i> such that:
1646 * this.charAt(<i>k</i>) == ch
1647 * </pre></blockquote>
1648 * is true. For other values of <code>ch</code>, it is the
1649 * largest value <i>k</i> such that:
1651 * this.codePointAt(<i>k</i>) == ch
1652 * </pre></blockquote>
1653 * is true. In either case, if no such character occurs in this
1654 * string, then <code>-1</code> is returned. The
1655 * <code>String</code> is searched backwards starting at the last
1658 * @param ch a character (Unicode code point).
1659 * @return the index of the last occurrence of the character in the
1660 * character sequence represented by this object, or
1661 * <code>-1</code> if the character does not occur.
1663 public int lastIndexOf(int ch) {
1664 return lastIndexOf(ch, length() - 1);
1668 * Returns the index within this string of the last occurrence of
1669 * the specified character, searching backward starting at the
1670 * specified index. For values of <code>ch</code> in the range
1671 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1672 * value <i>k</i> such that:
1674 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1675 * </pre></blockquote>
1676 * is true. For other values of <code>ch</code>, it is the
1677 * largest value <i>k</i> such that:
1679 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1680 * </pre></blockquote>
1681 * is true. In either case, if no such character occurs in this
1682 * string at or before position <code>fromIndex</code>, then
1683 * <code>-1</code> is returned.
1685 * <p>All indices are specified in <code>char</code> values
1686 * (Unicode code units).
1688 * @param ch a character (Unicode code point).
1689 * @param fromIndex the index to start the search from. There is no
1690 * restriction on the value of <code>fromIndex</code>. If it is
1691 * greater than or equal to the length of this string, it has
1692 * the same effect as if it were equal to one less than the
1693 * length of this string: this entire string may be searched.
1694 * If it is negative, it has the same effect as if it were -1:
1696 * @return the index of the last occurrence of the character in the
1697 * character sequence represented by this object that is less
1698 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1699 * if the character does not occur before that point.
1701 @JavaScriptBody(args = { "ch", "from" }, body =
1702 "if (typeof ch === 'number') ch = String.fromCharCode(ch);\n" +
1703 "return this.toString().lastIndexOf(ch, from);"
1705 public int lastIndexOf(int ch, int fromIndex) {
1706 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1707 // handle most cases here (ch is a BMP code point or a
1708 // negative value (invalid code point))
1709 final char[] value = this.toCharArray();
1710 final int offset = this.offset();
1711 int i = offset + Math.min(fromIndex, length() - 1);
1712 for (; i >= offset ; i--) {
1713 if (value[i] == ch) {
1719 return lastIndexOfSupplementary(ch, fromIndex);
1724 * Handles (rare) calls of lastIndexOf with a supplementary character.
1726 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1727 if (Character.isValidCodePoint(ch)) {
1728 final char[] value = this.toCharArray();
1729 final int offset = this.offset();
1730 char hi = Character.highSurrogate(ch);
1731 char lo = Character.lowSurrogate(ch);
1732 int i = offset + Math.min(fromIndex, length() - 2);
1733 for (; i >= offset; i--) {
1734 if (value[i] == hi && value[i+1] == lo) {
1743 * Returns the index within this string of the first occurrence of the
1744 * specified substring.
1746 * <p>The returned index is the smallest value <i>k</i> for which:
1748 * this.startsWith(str, <i>k</i>)
1749 * </pre></blockquote>
1750 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1752 * @param str the substring to search for.
1753 * @return the index of the first occurrence of the specified substring,
1754 * or {@code -1} if there is no such occurrence.
1756 public int indexOf(String str) {
1757 return indexOf(str, 0);
1761 * Returns the index within this string of the first occurrence of the
1762 * specified substring, starting at the specified index.
1764 * <p>The returned index is the smallest value <i>k</i> for which:
1766 * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>)
1767 * </pre></blockquote>
1768 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1770 * @param str the substring to search for.
1771 * @param fromIndex the index from which to start the search.
1772 * @return the index of the first occurrence of the specified substring,
1773 * starting at the specified index,
1774 * or {@code -1} if there is no such occurrence.
1776 @JavaScriptBody(args = { "str", "fromIndex" }, body =
1777 "return this.toString().indexOf(str.toString(), fromIndex);"
1779 public native int indexOf(String str, int fromIndex);
1782 * Returns the index within this string of the last occurrence of the
1783 * specified substring. The last occurrence of the empty string ""
1784 * is considered to occur at the index value {@code this.length()}.
1786 * <p>The returned index is the largest value <i>k</i> for which:
1788 * this.startsWith(str, <i>k</i>)
1789 * </pre></blockquote>
1790 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1792 * @param str the substring to search for.
1793 * @return the index of the last occurrence of the specified substring,
1794 * or {@code -1} if there is no such occurrence.
1796 public int lastIndexOf(String str) {
1797 return lastIndexOf(str, length());
1801 * Returns the index within this string of the last occurrence of the
1802 * specified substring, searching backward starting at the specified index.
1804 * <p>The returned index is the largest value <i>k</i> for which:
1806 * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>)
1807 * </pre></blockquote>
1808 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1810 * @param str the substring to search for.
1811 * @param fromIndex the index to start the search from.
1812 * @return the index of the last occurrence of the specified substring,
1813 * searching backward from the specified index,
1814 * or {@code -1} if there is no such occurrence.
1816 @JavaScriptBody(args = { "s", "from" }, body =
1817 "return this.toString().lastIndexOf(s.toString(), from);"
1819 public int lastIndexOf(String str, int fromIndex) {
1820 return lastIndexOf(toCharArray(), offset(), length(), str.toCharArray(), str.offset(), str.length(), fromIndex);
1824 * Code shared by String and StringBuffer to do searches. The
1825 * source is the character array being searched, and the target
1826 * is the string being searched for.
1828 * @param source the characters being searched.
1829 * @param sourceOffset offset of the source string.
1830 * @param sourceCount count of the source string.
1831 * @param target the characters being searched for.
1832 * @param targetOffset offset of the target string.
1833 * @param targetCount count of the target string.
1834 * @param fromIndex the index to begin searching from.
1836 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1837 char[] target, int targetOffset, int targetCount,
1840 * Check arguments; return immediately where possible. For
1841 * consistency, don't check for null str.
1843 int rightIndex = sourceCount - targetCount;
1844 if (fromIndex < 0) {
1847 if (fromIndex > rightIndex) {
1848 fromIndex = rightIndex;
1850 /* Empty string always matches. */
1851 if (targetCount == 0) {
1855 int strLastIndex = targetOffset + targetCount - 1;
1856 char strLastChar = target[strLastIndex];
1857 int min = sourceOffset + targetCount - 1;
1858 int i = min + fromIndex;
1860 startSearchForLastChar:
1862 while (i >= min && source[i] != strLastChar) {
1869 int start = j - (targetCount - 1);
1870 int k = strLastIndex - 1;
1873 if (source[j--] != target[k--]) {
1875 continue startSearchForLastChar;
1878 return start - sourceOffset + 1;
1883 * Returns a new string that is a substring of this string. The
1884 * substring begins with the character at the specified index and
1885 * extends to the end of this string. <p>
1888 * "unhappy".substring(2) returns "happy"
1889 * "Harbison".substring(3) returns "bison"
1890 * "emptiness".substring(9) returns "" (an empty string)
1891 * </pre></blockquote>
1893 * @param beginIndex the beginning index, inclusive.
1894 * @return the specified substring.
1895 * @exception IndexOutOfBoundsException if
1896 * <code>beginIndex</code> is negative or larger than the
1897 * length of this <code>String</code> object.
1899 public String substring(int beginIndex) {
1900 return substring(beginIndex, length());
1904 * Returns a new string that is a substring of this string. The
1905 * substring begins at the specified <code>beginIndex</code> and
1906 * extends to the character at index <code>endIndex - 1</code>.
1907 * Thus the length of the substring is <code>endIndex-beginIndex</code>.
1911 * "hamburger".substring(4, 8) returns "urge"
1912 * "smiles".substring(1, 5) returns "mile"
1913 * </pre></blockquote>
1915 * @param beginIndex the beginning index, inclusive.
1916 * @param endIndex the ending index, exclusive.
1917 * @return the specified substring.
1918 * @exception IndexOutOfBoundsException if the
1919 * <code>beginIndex</code> is negative, or
1920 * <code>endIndex</code> is larger than the length of
1921 * this <code>String</code> object, or
1922 * <code>beginIndex</code> is larger than
1923 * <code>endIndex</code>.
1925 @JavaScriptBody(args = { "beginIndex", "endIndex" }, body =
1926 "return this.toString().substring(beginIndex, endIndex);"
1928 public String substring(int beginIndex, int endIndex) {
1929 if (beginIndex < 0) {
1930 throw new StringIndexOutOfBoundsException(beginIndex);
1932 if (endIndex > length()) {
1933 throw new StringIndexOutOfBoundsException(endIndex);
1935 if (beginIndex > endIndex) {
1936 throw new StringIndexOutOfBoundsException(endIndex - beginIndex);
1938 return ((beginIndex == 0) && (endIndex == length())) ? this :
1939 new String(toCharArray(), offset() + beginIndex, endIndex - beginIndex);
1943 * Returns a new character sequence that is a subsequence of this sequence.
1945 * <p> An invocation of this method of the form
1948 * str.subSequence(begin, end)</pre></blockquote>
1950 * behaves in exactly the same way as the invocation
1953 * str.substring(begin, end)</pre></blockquote>
1955 * This method is defined so that the <tt>String</tt> class can implement
1956 * the {@link CharSequence} interface. </p>
1958 * @param beginIndex the begin index, inclusive.
1959 * @param endIndex the end index, exclusive.
1960 * @return the specified subsequence.
1962 * @throws IndexOutOfBoundsException
1963 * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative,
1964 * if <tt>endIndex</tt> is greater than <tt>length()</tt>,
1965 * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt>
1970 public CharSequence subSequence(int beginIndex, int endIndex) {
1971 return this.substring(beginIndex, endIndex);
1975 * Concatenates the specified string to the end of this string.
1977 * If the length of the argument string is <code>0</code>, then this
1978 * <code>String</code> object is returned. Otherwise, a new
1979 * <code>String</code> object is created, representing a character
1980 * sequence that is the concatenation of the character sequence
1981 * represented by this <code>String</code> object and the character
1982 * sequence represented by the argument string.<p>
1985 * "cares".concat("s") returns "caress"
1986 * "to".concat("get").concat("her") returns "together"
1987 * </pre></blockquote>
1989 * @param str the <code>String</code> that is concatenated to the end
1990 * of this <code>String</code>.
1991 * @return a string that represents the concatenation of this object's
1992 * characters followed by the string argument's characters.
1994 public String concat(String str) {
1995 int otherLen = str.length();
1996 if (otherLen == 0) {
1999 char buf[] = new char[length() + otherLen];
2000 getChars(0, length(), buf, 0);
2001 str.getChars(0, otherLen, buf, length());
2002 return new String(buf, 0, length() + otherLen);
2006 * Returns a new string resulting from replacing all occurrences of
2007 * <code>oldChar</code> in this string with <code>newChar</code>.
2009 * If the character <code>oldChar</code> does not occur in the
2010 * character sequence represented by this <code>String</code> object,
2011 * then a reference to this <code>String</code> object is returned.
2012 * Otherwise, a new <code>String</code> object is created that
2013 * represents a character sequence identical to the character sequence
2014 * represented by this <code>String</code> object, except that every
2015 * occurrence of <code>oldChar</code> is replaced by an occurrence
2016 * of <code>newChar</code>.
2020 * "mesquite in your cellar".replace('e', 'o')
2021 * returns "mosquito in your collar"
2022 * "the war of baronets".replace('r', 'y')
2023 * returns "the way of bayonets"
2024 * "sparring with a purple porpoise".replace('p', 't')
2025 * returns "starring with a turtle tortoise"
2026 * "JonL".replace('q', 'x') returns "JonL" (no change)
2027 * </pre></blockquote>
2029 * @param oldChar the old character.
2030 * @param newChar the new character.
2031 * @return a string derived from this string by replacing every
2032 * occurrence of <code>oldChar</code> with <code>newChar</code>.
2034 @JavaScriptBody(args = { "arg1", "arg2" }, body =
2035 "if (typeof arg1 === 'number') arg1 = String.fromCharCode(arg1);\n" +
2036 "if (typeof arg2 === 'number') arg2 = String.fromCharCode(arg2);\n" +
2037 "var s = this.toString();\n" +
2039 " var ret = s.replace(arg1, arg2);\n" +
2040 " if (ret === s) {\n" +
2046 public String replace(char oldChar, char newChar) {
2047 if (oldChar != newChar) {
2050 char[] val = toCharArray(); /* avoid getfield opcode */
2051 int off = offset(); /* avoid getfield opcode */
2054 if (val[off + i] == oldChar) {
2059 char buf[] = new char[len];
2060 for (int j = 0 ; j < i ; j++) {
2061 buf[j] = val[off+j];
2064 char c = val[off + i];
2065 buf[i] = (c == oldChar) ? newChar : c;
2068 return new String(buf, 0, len);
2075 * Tells whether or not this string matches the given <a
2076 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2078 * <p> An invocation of this method of the form
2079 * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the
2080 * same result as the expression
2082 * <blockquote><tt> {@link java.util.regex.Pattern}.{@link
2083 * java.util.regex.Pattern#matches(String,CharSequence)
2084 * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote>
2087 * the regular expression to which this string is to be matched
2089 * @return <tt>true</tt> if, and only if, this string matches the
2090 * given regular expression
2092 * @throws PatternSyntaxException
2093 * if the regular expression's syntax is invalid
2095 * @see java.util.regex.Pattern
2100 @JavaScriptBody(args = { "regex" }, body =
2101 "var self = this.toString();\n"
2102 + "var re = new RegExp(regex.toString());\n"
2103 + "var r = re.exec(self);\n"
2104 + "return r != null && r.length > 0 && self.length == r[0].length;"
2106 public boolean matches(String regex) {
2107 throw new UnsupportedOperationException();
2111 * Returns true if and only if this string contains the specified
2112 * sequence of char values.
2114 * @param s the sequence to search for
2115 * @return true if this string contains <code>s</code>, false otherwise
2116 * @throws NullPointerException if <code>s</code> is <code>null</code>
2119 public boolean contains(CharSequence s) {
2120 return indexOf(s.toString()) > -1;
2124 * Replaces the first substring of this string that matches the given <a
2125 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2126 * given replacement.
2128 * <p> An invocation of this method of the form
2129 * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2130 * yields exactly the same result as the expression
2133 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2134 * compile}(</tt><i>regex</i><tt>).{@link
2135 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2136 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst
2137 * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote>
2140 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2141 * replacement string may cause the results to be different than if it were
2142 * being treated as a literal replacement string; see
2143 * {@link java.util.regex.Matcher#replaceFirst}.
2144 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2145 * meaning of these characters, if desired.
2148 * the regular expression to which this string is to be matched
2149 * @param replacement
2150 * the string to be substituted for the first match
2152 * @return The resulting <tt>String</tt>
2154 * @throws PatternSyntaxException
2155 * if the regular expression's syntax is invalid
2157 * @see java.util.regex.Pattern
2162 public String replaceFirst(String regex, String replacement) {
2163 throw new UnsupportedOperationException();
2167 * Replaces each substring of this string that matches the given <a
2168 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2169 * given replacement.
2171 * <p> An invocation of this method of the form
2172 * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2173 * yields exactly the same result as the expression
2176 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2177 * compile}(</tt><i>regex</i><tt>).{@link
2178 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2179 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll
2180 * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote>
2183 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2184 * replacement string may cause the results to be different than if it were
2185 * being treated as a literal replacement string; see
2186 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2187 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2188 * meaning of these characters, if desired.
2191 * the regular expression to which this string is to be matched
2192 * @param replacement
2193 * the string to be substituted for each match
2195 * @return The resulting <tt>String</tt>
2197 * @throws PatternSyntaxException
2198 * if the regular expression's syntax is invalid
2200 * @see java.util.regex.Pattern
2205 public String replaceAll(String regex, String replacement) {
2206 throw new UnsupportedOperationException();
2210 * Replaces each substring of this string that matches the literal target
2211 * sequence with the specified literal replacement sequence. The
2212 * replacement proceeds from the beginning of the string to the end, for
2213 * example, replacing "aa" with "b" in the string "aaa" will result in
2214 * "ba" rather than "ab".
2216 * @param target The sequence of char values to be replaced
2217 * @param replacement The replacement sequence of char values
2218 * @return The resulting string
2219 * @throws NullPointerException if <code>target</code> or
2220 * <code>replacement</code> is <code>null</code>.
2223 @JavaScriptBody(args = { "target", "replacement" }, body =
2224 "var s = this.toString();\n"
2225 + "target = target.toString();\n"
2226 + "replacement = replacement.toString();\n"
2228 + " var ret = s.replace(target, replacement);\n"
2229 + " if (ret === s) {\n"
2235 public native String replace(CharSequence target, CharSequence replacement);
2238 * Splits this string around matches of the given
2239 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2241 * <p> The array returned by this method contains each substring of this
2242 * string that is terminated by another substring that matches the given
2243 * expression or is terminated by the end of the string. The substrings in
2244 * the array are in the order in which they occur in this string. If the
2245 * expression does not match any part of the input then the resulting array
2246 * has just one element, namely this string.
2248 * <p> The <tt>limit</tt> parameter controls the number of times the
2249 * pattern is applied and therefore affects the length of the resulting
2250 * array. If the limit <i>n</i> is greater than zero then the pattern
2251 * will be applied at most <i>n</i> - 1 times, the array's
2252 * length will be no greater than <i>n</i>, and the array's last entry
2253 * will contain all input beyond the last matched delimiter. If <i>n</i>
2254 * is non-positive then the pattern will be applied as many times as
2255 * possible and the array can have any length. If <i>n</i> is zero then
2256 * the pattern will be applied as many times as possible, the array can
2257 * have any length, and trailing empty strings will be discarded.
2259 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the
2260 * following results with these parameters:
2262 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2268 * <tr><td align=center>:</td>
2269 * <td align=center>2</td>
2270 * <td><tt>{ "boo", "and:foo" }</tt></td></tr>
2271 * <tr><td align=center>:</td>
2272 * <td align=center>5</td>
2273 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2274 * <tr><td align=center>:</td>
2275 * <td align=center>-2</td>
2276 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2277 * <tr><td align=center>o</td>
2278 * <td align=center>5</td>
2279 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2280 * <tr><td align=center>o</td>
2281 * <td align=center>-2</td>
2282 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2283 * <tr><td align=center>o</td>
2284 * <td align=center>0</td>
2285 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2286 * </table></blockquote>
2288 * <p> An invocation of this method of the form
2289 * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt>
2290 * yields the same result as the expression
2293 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2294 * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link
2295 * java.util.regex.Pattern#split(java.lang.CharSequence,int)
2296 * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt>
2301 * the delimiting regular expression
2304 * the result threshold, as described above
2306 * @return the array of strings computed by splitting this string
2307 * around matches of the given regular expression
2309 * @throws PatternSyntaxException
2310 * if the regular expression's syntax is invalid
2312 * @see java.util.regex.Pattern
2317 public String[] split(String regex, int limit) {
2319 Object[] arr = splitImpl(this, regex, Integer.MAX_VALUE);
2320 int to = arr.length;
2322 while (to > 1 && ((String)arr[--to]).isEmpty()) {
2326 String[] ret = new String[to];
2327 System.arraycopy(arr, 0, ret, 0, to);
2330 Object[] arr = splitImpl(this, regex, limit);
2331 String[] ret = new String[arr.length];
2333 for (int i = 0; i < arr.length; i++) {
2334 final String s = (String)arr[i];
2336 pos = indexOf(s, pos) + s.length();
2338 ret[arr.length - 1] += substring(pos);
2343 @JavaScriptBody(args = { "str", "regex", "limit"}, body =
2344 "return str.split(new RegExp(regex), limit);"
2346 private static native Object[] splitImpl(String str, String regex, int limit);
2349 * Splits this string around matches of the given <a
2350 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2352 * <p> This method works as if by invoking the two-argument {@link
2353 * #split(String, int) split} method with the given expression and a limit
2354 * argument of zero. Trailing empty strings are therefore not included in
2355 * the resulting array.
2357 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the following
2358 * results with these expressions:
2360 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2365 * <tr><td align=center>:</td>
2366 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2367 * <tr><td align=center>o</td>
2368 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2369 * </table></blockquote>
2373 * the delimiting regular expression
2375 * @return the array of strings computed by splitting this string
2376 * around matches of the given regular expression
2378 * @throws PatternSyntaxException
2379 * if the regular expression's syntax is invalid
2381 * @see java.util.regex.Pattern
2386 public String[] split(String regex) {
2387 return split(regex, 0);
2391 * Converts all of the characters in this <code>String</code> to lower
2392 * case using the rules of the given <code>Locale</code>. Case mapping is based
2393 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2394 * class. Since case mappings are not always 1:1 char mappings, the resulting
2395 * <code>String</code> may be a different length than the original <code>String</code>.
2397 * Examples of lowercase mappings are in the following table:
2398 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2400 * <th>Language Code of Locale</th>
2401 * <th>Upper Case</th>
2402 * <th>Lower Case</th>
2403 * <th>Description</th>
2406 * <td>tr (Turkish)</td>
2407 * <td>\u0130</td>
2408 * <td>\u0069</td>
2409 * <td>capital letter I with dot above -> small letter i</td>
2412 * <td>tr (Turkish)</td>
2413 * <td>\u0049</td>
2414 * <td>\u0131</td>
2415 * <td>capital letter I -> small letter dotless i </td>
2419 * <td>French Fries</td>
2420 * <td>french fries</td>
2421 * <td>lowercased all chars in String</td>
2425 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2426 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2427 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2428 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2429 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2430 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2431 * <td>lowercased all chars in String</td>
2435 * @param locale use the case transformation rules for this locale
2436 * @return the <code>String</code>, converted to lowercase.
2437 * @see java.lang.String#toLowerCase()
2438 * @see java.lang.String#toUpperCase()
2439 * @see java.lang.String#toUpperCase(Locale)
2442 // public String toLowerCase(Locale locale) {
2443 // if (locale == null) {
2444 // throw new NullPointerException();
2449 // /* Now check if there are any characters that need to be changed. */
2451 // for (firstUpper = 0 ; firstUpper < count; ) {
2452 // char c = value[offset+firstUpper];
2453 // if ((c >= Character.MIN_HIGH_SURROGATE) &&
2454 // (c <= Character.MAX_HIGH_SURROGATE)) {
2455 // int supplChar = codePointAt(firstUpper);
2456 // if (supplChar != Character.toLowerCase(supplChar)) {
2459 // firstUpper += Character.charCount(supplChar);
2461 // if (c != Character.toLowerCase(c)) {
2470 // char[] result = new char[count];
2471 // int resultOffset = 0; /* result may grow, so i+resultOffset
2472 // * is the write location in result */
2474 // /* Just copy the first few lowerCase characters. */
2475 // System.arraycopy(value, offset, result, 0, firstUpper);
2477 // String lang = locale.getLanguage();
2478 // boolean localeDependent =
2479 // (lang == "tr" || lang == "az" || lang == "lt");
2480 // char[] lowerCharArray;
2484 // for (int i = firstUpper; i < count; i += srcCount) {
2485 // srcChar = (int)value[offset+i];
2486 // if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2487 // (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2488 // srcChar = codePointAt(i);
2489 // srcCount = Character.charCount(srcChar);
2493 // if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2494 // lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2495 // } else if (srcChar == '\u0130') { // LATIN CAPITAL LETTER I DOT
2496 // lowerChar = Character.ERROR;
2498 // lowerChar = Character.toLowerCase(srcChar);
2500 // if ((lowerChar == Character.ERROR) ||
2501 // (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2502 // if (lowerChar == Character.ERROR) {
2503 // if (!localeDependent && srcChar == '\u0130') {
2505 // ConditionalSpecialCasing.toLowerCaseCharArray(this, i, Locale.ENGLISH);
2508 // ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2510 // } else if (srcCount == 2) {
2511 // resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount;
2514 // lowerCharArray = Character.toChars(lowerChar);
2517 // /* Grow result if needed */
2518 // int mapLen = lowerCharArray.length;
2519 // if (mapLen > srcCount) {
2520 // char[] result2 = new char[result.length + mapLen - srcCount];
2521 // System.arraycopy(result, 0, result2, 0,
2522 // i + resultOffset);
2523 // result = result2;
2525 // for (int x=0; x<mapLen; ++x) {
2526 // result[i+resultOffset+x] = lowerCharArray[x];
2528 // resultOffset += (mapLen - srcCount);
2530 // result[i+resultOffset] = (char)lowerChar;
2533 // return new String(0, count+resultOffset, result);
2537 * Converts all of the characters in this <code>String</code> to lower
2538 * case using the rules of the default locale. This is equivalent to calling
2539 * <code>toLowerCase(Locale.getDefault())</code>.
2541 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2542 * results if used for strings that are intended to be interpreted locale
2544 * Examples are programming language identifiers, protocol keys, and HTML
2546 * For instance, <code>"TITLE".toLowerCase()</code> in a Turkish locale
2547 * returns <code>"t\u005Cu0131tle"</code>, where '\u005Cu0131' is the
2548 * LATIN SMALL LETTER DOTLESS I character.
2549 * To obtain correct results for locale insensitive strings, use
2550 * <code>toLowerCase(Locale.ENGLISH)</code>.
2552 * @return the <code>String</code>, converted to lowercase.
2553 * @see java.lang.String#toLowerCase(Locale)
2555 @JavaScriptBody(args = {}, body = "return this.toLowerCase();")
2556 public String toLowerCase() {
2557 throw new UnsupportedOperationException("Should be supported but without connection to locale");
2561 * Converts all of the characters in this <code>String</code> to upper
2562 * case using the rules of the given <code>Locale</code>. Case mapping is based
2563 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2564 * class. Since case mappings are not always 1:1 char mappings, the resulting
2565 * <code>String</code> may be a different length than the original <code>String</code>.
2567 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2569 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2571 * <th>Language Code of Locale</th>
2572 * <th>Lower Case</th>
2573 * <th>Upper Case</th>
2574 * <th>Description</th>
2577 * <td>tr (Turkish)</td>
2578 * <td>\u0069</td>
2579 * <td>\u0130</td>
2580 * <td>small letter i -> capital letter I with dot above</td>
2583 * <td>tr (Turkish)</td>
2584 * <td>\u0131</td>
2585 * <td>\u0049</td>
2586 * <td>small letter dotless i -> capital letter I</td>
2590 * <td>\u00df</td>
2591 * <td>\u0053 \u0053</td>
2592 * <td>small letter sharp s -> two letters: SS</td>
2596 * <td>Fahrvergnügen</td>
2597 * <td>FAHRVERGNÜGEN</td>
2601 * @param locale use the case transformation rules for this locale
2602 * @return the <code>String</code>, converted to uppercase.
2603 * @see java.lang.String#toUpperCase()
2604 * @see java.lang.String#toLowerCase()
2605 * @see java.lang.String#toLowerCase(Locale)
2608 /* not for javascript
2609 public String toUpperCase(Locale locale) {
2610 if (locale == null) {
2611 throw new NullPointerException();
2616 // Now check if there are any characters that need to be changed.
2618 for (firstLower = 0 ; firstLower < count; ) {
2619 int c = (int)value[offset+firstLower];
2621 if ((c >= Character.MIN_HIGH_SURROGATE) &&
2622 (c <= Character.MAX_HIGH_SURROGATE)) {
2623 c = codePointAt(firstLower);
2624 srcCount = Character.charCount(c);
2628 int upperCaseChar = Character.toUpperCaseEx(c);
2629 if ((upperCaseChar == Character.ERROR) ||
2630 (c != upperCaseChar)) {
2633 firstLower += srcCount;
2638 char[] result = new char[count]; /* may grow *
2639 int resultOffset = 0; /* result may grow, so i+resultOffset
2640 * is the write location in result *
2642 /* Just copy the first few upperCase characters. *
2643 System.arraycopy(value, offset, result, 0, firstLower);
2645 String lang = locale.getLanguage();
2646 boolean localeDependent =
2647 (lang == "tr" || lang == "az" || lang == "lt");
2648 char[] upperCharArray;
2652 for (int i = firstLower; i < count; i += srcCount) {
2653 srcChar = (int)value[offset+i];
2654 if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
2655 (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
2656 srcChar = codePointAt(i);
2657 srcCount = Character.charCount(srcChar);
2661 if (localeDependent) {
2662 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2664 upperChar = Character.toUpperCaseEx(srcChar);
2666 if ((upperChar == Character.ERROR) ||
2667 (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
2668 if (upperChar == Character.ERROR) {
2669 if (localeDependent) {
2671 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
2673 upperCharArray = Character.toUpperCaseCharArray(srcChar);
2675 } else if (srcCount == 2) {
2676 resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount;
2679 upperCharArray = Character.toChars(upperChar);
2682 /* Grow result if needed *
2683 int mapLen = upperCharArray.length;
2684 if (mapLen > srcCount) {
2685 char[] result2 = new char[result.length + mapLen - srcCount];
2686 System.arraycopy(result, 0, result2, 0,
2690 for (int x=0; x<mapLen; ++x) {
2691 result[i+resultOffset+x] = upperCharArray[x];
2693 resultOffset += (mapLen - srcCount);
2695 result[i+resultOffset] = (char)upperChar;
2698 return new String(0, count+resultOffset, result);
2703 * Converts all of the characters in this <code>String</code> to upper
2704 * case using the rules of the default locale. This method is equivalent to
2705 * <code>toUpperCase(Locale.getDefault())</code>.
2707 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2708 * results if used for strings that are intended to be interpreted locale
2710 * Examples are programming language identifiers, protocol keys, and HTML
2712 * For instance, <code>"title".toUpperCase()</code> in a Turkish locale
2713 * returns <code>"T\u005Cu0130TLE"</code>, where '\u005Cu0130' is the
2714 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2715 * To obtain correct results for locale insensitive strings, use
2716 * <code>toUpperCase(Locale.ENGLISH)</code>.
2718 * @return the <code>String</code>, converted to uppercase.
2719 * @see java.lang.String#toUpperCase(Locale)
2721 @JavaScriptBody(args = {}, body = "return this.toUpperCase();")
2722 public String toUpperCase() {
2723 throw new UnsupportedOperationException();
2727 * Returns a copy of the string, with leading and trailing whitespace
2730 * If this <code>String</code> object represents an empty character
2731 * sequence, or the first and last characters of character sequence
2732 * represented by this <code>String</code> object both have codes
2733 * greater than <code>'\u0020'</code> (the space character), then a
2734 * reference to this <code>String</code> object is returned.
2736 * Otherwise, if there is no character with a code greater than
2737 * <code>'\u0020'</code> in the string, then a new
2738 * <code>String</code> object representing an empty string is created
2741 * Otherwise, let <i>k</i> be the index of the first character in the
2742 * string whose code is greater than <code>'\u0020'</code>, and let
2743 * <i>m</i> be the index of the last character in the string whose code
2744 * is greater than <code>'\u0020'</code>. A new <code>String</code>
2745 * object is created, representing the substring of this string that
2746 * begins with the character at index <i>k</i> and ends with the
2747 * character at index <i>m</i>-that is, the result of
2748 * <code>this.substring(<i>k</i>, <i>m</i>+1)</code>.
2750 * This method may be used to trim whitespace (as defined above) from
2751 * the beginning and end of a string.
2753 * @return A copy of this string with leading and trailing white
2754 * space removed, or this string if it has no leading or
2755 * trailing white space.
2757 public String trim() {
2760 int off = offset(); /* avoid getfield opcode */
2761 char[] val = toCharArray(); /* avoid getfield opcode */
2763 while ((st < len) && (val[off + st] <= ' ')) {
2766 while ((st < len) && (val[off + len - 1] <= ' ')) {
2769 return ((st > 0) || (len < length())) ? substring(st, len) : this;
2773 * This object (which is already a string!) is itself returned.
2775 * @return the string itself.
2777 @JavaScriptBody(args = {}, body = "return this.toString();")
2778 public String toString() {
2783 * Converts this string to a new character array.
2785 * @return a newly allocated character array whose length is the length
2786 * of this string and whose contents are initialized to contain
2787 * the character sequence represented by this string.
2789 public char[] toCharArray() {
2790 char result[] = new char[length()];
2791 getChars(0, length(), result, 0);
2796 * Returns a formatted string using the specified format string and
2799 * <p> The locale always used is the one returned by {@link
2800 * java.util.Locale#getDefault() Locale.getDefault()}.
2803 * A <a href="../util/Formatter.html#syntax">format string</a>
2806 * Arguments referenced by the format specifiers in the format
2807 * string. If there are more arguments than format specifiers, the
2808 * extra arguments are ignored. The number of arguments is
2809 * variable and may be zero. The maximum number of arguments is
2810 * limited by the maximum dimension of a Java array as defined by
2811 * <cite>The Java™ Virtual Machine Specification</cite>.
2812 * The behaviour on a
2813 * <tt>null</tt> argument depends on the <a
2814 * href="../util/Formatter.html#syntax">conversion</a>.
2816 * @throws IllegalFormatException
2817 * If a format string contains an illegal syntax, a format
2818 * specifier that is incompatible with the given arguments,
2819 * insufficient arguments given the format string, or other
2820 * illegal conditions. For specification of all possible
2821 * formatting errors, see the <a
2822 * href="../util/Formatter.html#detail">Details</a> section of the
2823 * formatter class specification.
2825 * @throws NullPointerException
2826 * If the <tt>format</tt> is <tt>null</tt>
2828 * @return A formatted string
2830 * @see java.util.Formatter
2833 public static String format(String format, Object ... args) {
2834 throw new UnsupportedOperationException();
2838 * Returns a formatted string using the specified locale, format string,
2842 * The {@linkplain java.util.Locale locale} to apply during
2843 * formatting. If <tt>l</tt> is <tt>null</tt> then no localization
2847 * A <a href="../util/Formatter.html#syntax">format string</a>
2850 * Arguments referenced by the format specifiers in the format
2851 * string. If there are more arguments than format specifiers, the
2852 * extra arguments are ignored. The number of arguments is
2853 * variable and may be zero. The maximum number of arguments is
2854 * limited by the maximum dimension of a Java array as defined by
2855 * <cite>The Java™ Virtual Machine Specification</cite>.
2856 * The behaviour on a
2857 * <tt>null</tt> argument depends on the <a
2858 * href="../util/Formatter.html#syntax">conversion</a>.
2860 * @throws IllegalFormatException
2861 * If a format string contains an illegal syntax, a format
2862 * specifier that is incompatible with the given arguments,
2863 * insufficient arguments given the format string, or other
2864 * illegal conditions. For specification of all possible
2865 * formatting errors, see the <a
2866 * href="../util/Formatter.html#detail">Details</a> section of the
2867 * formatter class specification
2869 * @throws NullPointerException
2870 * If the <tt>format</tt> is <tt>null</tt>
2872 * @return A formatted string
2874 * @see java.util.Formatter
2877 // public static String format(Locale l, String format, Object ... args) {
2878 // return new Formatter(l).format(format, args).toString();
2882 * Returns the string representation of the <code>Object</code> argument.
2884 * @param obj an <code>Object</code>.
2885 * @return if the argument is <code>null</code>, then a string equal to
2886 * <code>"null"</code>; otherwise, the value of
2887 * <code>obj.toString()</code> is returned.
2888 * @see java.lang.Object#toString()
2890 public static String valueOf(Object obj) {
2891 return (obj == null) ? "null" : obj.toString();
2895 * Returns the string representation of the <code>char</code> array
2896 * argument. The contents of the character array are copied; subsequent
2897 * modification of the character array does not affect the newly
2900 * @param data a <code>char</code> array.
2901 * @return a newly allocated string representing the same sequence of
2902 * characters contained in the character array argument.
2904 public static String valueOf(char data[]) {
2905 return new String(data);
2909 * Returns the string representation of a specific subarray of the
2910 * <code>char</code> array argument.
2912 * The <code>offset</code> argument is the index of the first
2913 * character of the subarray. The <code>count</code> argument
2914 * specifies the length of the subarray. The contents of the subarray
2915 * are copied; subsequent modification of the character array does not
2916 * affect the newly created string.
2918 * @param data the character array.
2919 * @param offset the initial offset into the value of the
2920 * <code>String</code>.
2921 * @param count the length of the value of the <code>String</code>.
2922 * @return a string representing the sequence of characters contained
2923 * in the subarray of the character array argument.
2924 * @exception IndexOutOfBoundsException if <code>offset</code> is
2925 * negative, or <code>count</code> is negative, or
2926 * <code>offset+count</code> is larger than
2927 * <code>data.length</code>.
2929 public static String valueOf(char data[], int offset, int count) {
2930 return new String(data, offset, count);
2934 * Returns a String that represents the character sequence in the
2937 * @param data the character array.
2938 * @param offset initial offset of the subarray.
2939 * @param count length of the subarray.
2940 * @return a <code>String</code> that contains the characters of the
2941 * specified subarray of the character array.
2943 public static String copyValueOf(char data[], int offset, int count) {
2944 // All public String constructors now copy the data.
2945 return new String(data, offset, count);
2949 * Returns a String that represents the character sequence in the
2952 * @param data the character array.
2953 * @return a <code>String</code> that contains the characters of the
2956 public static String copyValueOf(char data[]) {
2957 return copyValueOf(data, 0, data.length);
2961 * Returns the string representation of the <code>boolean</code> argument.
2963 * @param b a <code>boolean</code>.
2964 * @return if the argument is <code>true</code>, a string equal to
2965 * <code>"true"</code> is returned; otherwise, a string equal to
2966 * <code>"false"</code> is returned.
2968 public static String valueOf(boolean b) {
2969 return b ? "true" : "false";
2973 * Returns the string representation of the <code>char</code>
2976 * @param c a <code>char</code>.
2977 * @return a string of length <code>1</code> containing
2978 * as its single character the argument <code>c</code>.
2980 public static String valueOf(char c) {
2982 return new String(data, 0, 1);
2986 * Returns the string representation of the <code>int</code> argument.
2988 * The representation is exactly the one returned by the
2989 * <code>Integer.toString</code> method of one argument.
2991 * @param i an <code>int</code>.
2992 * @return a string representation of the <code>int</code> argument.
2993 * @see java.lang.Integer#toString(int, int)
2995 public static String valueOf(int i) {
2996 return Integer.toString(i);
3000 * Returns the string representation of the <code>long</code> argument.
3002 * The representation is exactly the one returned by the
3003 * <code>Long.toString</code> method of one argument.
3005 * @param l a <code>long</code>.
3006 * @return a string representation of the <code>long</code> argument.
3007 * @see java.lang.Long#toString(long)
3009 public static String valueOf(long l) {
3010 return Long.toString(l);
3014 * Returns the string representation of the <code>float</code> argument.
3016 * The representation is exactly the one returned by the
3017 * <code>Float.toString</code> method of one argument.
3019 * @param f a <code>float</code>.
3020 * @return a string representation of the <code>float</code> argument.
3021 * @see java.lang.Float#toString(float)
3023 public static String valueOf(float f) {
3024 return Float.toString(f);
3028 * Returns the string representation of the <code>double</code> argument.
3030 * The representation is exactly the one returned by the
3031 * <code>Double.toString</code> method of one argument.
3033 * @param d a <code>double</code>.
3034 * @return a string representation of the <code>double</code> argument.
3035 * @see java.lang.Double#toString(double)
3037 public static String valueOf(double d) {
3038 return Double.toString(d);
3042 * Returns a canonical representation for the string object.
3044 * A pool of strings, initially empty, is maintained privately by the
3045 * class <code>String</code>.
3047 * When the intern method is invoked, if the pool already contains a
3048 * string equal to this <code>String</code> object as determined by
3049 * the {@link #equals(Object)} method, then the string from the pool is
3050 * returned. Otherwise, this <code>String</code> object is added to the
3051 * pool and a reference to this <code>String</code> object is returned.
3053 * It follows that for any two strings <code>s</code> and <code>t</code>,
3054 * <code>s.intern() == t.intern()</code> is <code>true</code>
3055 * if and only if <code>s.equals(t)</code> is <code>true</code>.
3057 * All literal strings and string-valued constant expressions are
3058 * interned. String literals are defined in section 3.10.5 of the
3059 * <cite>The Java™ Language Specification</cite>.
3061 * @return a string that has the same contents as this string, but is
3062 * guaranteed to be from a pool of unique strings.
3064 public native String intern();
3067 private static <T> T checkUTF8(T data, String charsetName)
3068 throws UnsupportedEncodingException {
3069 if (charsetName == null) {
3070 throw new NullPointerException("charsetName");
3072 if (!charsetName.equalsIgnoreCase("UTF-8")
3073 && !charsetName.equalsIgnoreCase("UTF8")) {
3074 throw new UnsupportedEncodingException(charsetName);
3079 private static int nextChar(byte[] arr, int[] index) throws IndexOutOfBoundsException {
3080 int c = arr[index[0]++] & 0xff;
3094 /* 110x xxxx 10xx xxxx*/
3095 int char2 = (int) arr[index[0]++];
3096 if ((char2 & 0xC0) != 0x80) {
3097 throw new IndexOutOfBoundsException("malformed input");
3099 return (((c & 0x1F) << 6) | (char2 & 0x3F));
3102 /* 1110 xxxx 10xx xxxx 10xx xxxx */
3103 int char2 = arr[index[0]++];
3104 int char3 = arr[index[0]++];
3105 if (((char2 & 0xC0) != 0x80) || ((char3 & 0xC0) != 0x80)) {
3106 throw new IndexOutOfBoundsException("malformed input");
3108 return (((c & 0x0F) << 12)
3109 | ((char2 & 0x3F) << 6)
3110 | ((char3 & 0x3F) << 0));
3113 /* 10xx xxxx, 1111 xxxx */
3114 throw new IndexOutOfBoundsException("malformed input");