Added tests for integer division and reminder after division. Removed JS version of String.hashCode since standard version is already correct.
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.util.Comparator;
29 import org.apidesign.bck2brwsr.core.ExtraJavaScript;
30 import org.apidesign.bck2brwsr.core.JavaScriptBody;
31 import org.apidesign.bck2brwsr.core.JavaScriptOnly;
32 import org.apidesign.bck2brwsr.core.JavaScriptPrototype;
35 * The <code>String</code> class represents character strings. All
36 * string literals in Java programs, such as <code>"abc"</code>, are
37 * implemented as instances of this class.
39 * Strings are constant; their values cannot be changed after they
40 * are created. String buffers support mutable strings.
41 * Because String objects are immutable they can be shared. For example:
42 * <p><blockquote><pre>
44 * </pre></blockquote><p>
46 * <p><blockquote><pre>
47 * char data[] = {'a', 'b', 'c'};
48 * String str = new String(data);
49 * </pre></blockquote><p>
50 * Here are some more examples of how strings can be used:
51 * <p><blockquote><pre>
52 * System.out.println("abc");
54 * System.out.println("abc" + cde);
55 * String c = "abc".substring(2,3);
56 * String d = cde.substring(1, 2);
59 * The class <code>String</code> includes methods for examining
60 * individual characters of the sequence, for comparing strings, for
61 * searching strings, for extracting substrings, and for creating a
62 * copy of a string with all characters translated to uppercase or to
63 * lowercase. Case mapping is based on the Unicode Standard version
64 * specified by the {@link java.lang.Character Character} class.
66 * The Java language provides special support for the string
67 * concatenation operator ( + ), and for conversion of
68 * other objects to strings. String concatenation is implemented
69 * through the <code>StringBuilder</code>(or <code>StringBuffer</code>)
70 * class and its <code>append</code> method.
71 * String conversions are implemented through the method
72 * <code>toString</code>, defined by <code>Object</code> and
73 * inherited by all classes in Java. For additional information on
74 * string concatenation and conversion, see Gosling, Joy, and Steele,
75 * <i>The Java Language Specification</i>.
77 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
78 * or method in this class will cause a {@link NullPointerException} to be
81 * <p>A <code>String</code> represents a string in the UTF-16 format
82 * in which <em>supplementary characters</em> are represented by <em>surrogate
83 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
84 * Character Representations</a> in the <code>Character</code> class for
86 * Index values refer to <code>char</code> code units, so a supplementary
87 * character uses two positions in a <code>String</code>.
88 * <p>The <code>String</code> class provides methods for dealing with
89 * Unicode code points (i.e., characters), in addition to those for
90 * dealing with Unicode code units (i.e., <code>char</code> values).
93 * @author Arthur van Hoff
94 * @author Martin Buchholz
96 * @see java.lang.Object#toString()
97 * @see java.lang.StringBuffer
98 * @see java.lang.StringBuilder
99 * @see java.nio.charset.Charset
104 resource="/org/apidesign/vm4brwsr/emul/java_lang_String.js",
107 @JavaScriptPrototype(container = "String.prototype", prototype = "new String")
108 public final class String
109 implements java.io.Serializable, Comparable<String>, CharSequence
112 /** Cache the hash code for the string */
113 private int hash; // Default to 0
115 /** real string to delegate to */
118 /** use serialVersionUID from JDK 1.0.2 for interoperability */
119 private static final long serialVersionUID = -6849794470754667710L;
121 @JavaScriptOnly(name="toString", value="function() { return this.fld_r; }")
122 private static void jsToString() {
125 @JavaScriptOnly(name="valueOf", value="function() { return this.toString().valueOf(); }")
126 private static void jsValudOf() {
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 = { "self", "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 + "self.fld_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 @JavaScriptBody(args = { "self", "charArr", "off", "cnt" }, body =
207 "var up = off + cnt;\n" +
208 "for (var i = off; i < up; i++) {\n" +
209 " if (typeof charArr[i] === 'number') charArr[i] = String.fromCharCode(charArr[i]);\n" +
211 "self.fld_r = charArr.slice(off, up).join(\"\");\n"
213 public String(char value[], int offset, int count) {
217 * Allocates a new {@code String} that contains characters from a subarray
218 * of the <a href="Character.html#unicode">Unicode code point</a> array
219 * argument. The {@code offset} argument is the index of the first code
220 * point of the subarray and the {@code count} argument specifies the
221 * length of the subarray. The contents of the subarray are converted to
222 * {@code char}s; subsequent modification of the {@code int} array does not
223 * affect the newly created string.
226 * Array that is the source of Unicode code points
234 * @throws IllegalArgumentException
235 * If any invalid Unicode code point is found in {@code
238 * @throws IndexOutOfBoundsException
239 * If the {@code offset} and {@code count} arguments index
240 * characters outside the bounds of the {@code codePoints} array
244 public String(int[] codePoints, int offset, int count) {
246 throw new StringIndexOutOfBoundsException(offset);
249 throw new StringIndexOutOfBoundsException(count);
251 // Note: offset or count might be near -1>>>1.
252 if (offset > codePoints.length - count) {
253 throw new StringIndexOutOfBoundsException(offset + count);
256 final int end = offset + count;
258 // Pass 1: Compute precise size of char[]
260 for (int i = offset; i < end; i++) {
261 int c = codePoints[i];
262 if (Character.isBmpCodePoint(c))
264 else if (Character.isValidCodePoint(c))
266 else throw new IllegalArgumentException(Integer.toString(c));
269 // Pass 2: Allocate and fill in char[]
270 final char[] v = new char[n];
272 for (int i = offset, j = 0; i < end; i++, j++) {
273 int c = codePoints[i];
274 if (Character.isBmpCodePoint(c))
277 Character.toSurrogates(c, v, j++);
280 this.r = new String(v, 0, n);
284 * Allocates a new {@code String} constructed from a subarray of an array
285 * of 8-bit integer values.
287 * <p> The {@code offset} argument is the index of the first byte of the
288 * subarray, and the {@code count} argument specifies the length of the
291 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
292 * specified in the method above.
294 * @deprecated This method does not properly convert bytes into characters.
295 * As of JDK 1.1, the preferred way to do this is via the
296 * {@code String} constructors that take a {@link
297 * java.nio.charset.Charset}, charset name, or that use the platform's
301 * The bytes to be converted to characters
304 * The top 8 bits of each 16-bit Unicode code unit
311 * @throws IndexOutOfBoundsException
312 * If the {@code offset} or {@code count} argument is invalid
314 * @see #String(byte[], int)
315 * @see #String(byte[], int, int, java.lang.String)
316 * @see #String(byte[], int, int, java.nio.charset.Charset)
317 * @see #String(byte[], int, int)
318 * @see #String(byte[], java.lang.String)
319 * @see #String(byte[], java.nio.charset.Charset)
320 * @see #String(byte[])
323 public String(byte ascii[], int hibyte, int offset, int count) {
324 checkBounds(ascii, offset, count);
325 char value[] = new char[count];
328 for (int i = count ; i-- > 0 ;) {
329 value[i] = (char) (ascii[i + offset] & 0xff);
333 for (int i = count ; i-- > 0 ;) {
334 value[i] = (char) (hibyte | (ascii[i + offset] & 0xff));
337 this.r = new String(value, 0, count);
341 * Allocates a new {@code String} containing characters constructed from
342 * an array of 8-bit integer values. Each character <i>c</i>in the
343 * resulting string is constructed from the corresponding component
344 * <i>b</i> in the byte array such that:
347 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
348 * | (<b><i>b</i></b> & 0xff))
349 * </pre></blockquote>
351 * @deprecated This method does not properly convert bytes into
352 * characters. As of JDK 1.1, the preferred way to do this is via the
353 * {@code String} constructors that take a {@link
354 * java.nio.charset.Charset}, charset name, or that use the platform's
358 * The bytes to be converted to characters
361 * The top 8 bits of each 16-bit Unicode code unit
363 * @see #String(byte[], int, int, java.lang.String)
364 * @see #String(byte[], int, int, java.nio.charset.Charset)
365 * @see #String(byte[], int, int)
366 * @see #String(byte[], java.lang.String)
367 * @see #String(byte[], java.nio.charset.Charset)
368 * @see #String(byte[])
371 public String(byte ascii[], int hibyte) {
372 this(ascii, hibyte, 0, ascii.length);
375 /* Common private utility method used to bounds check the byte array
376 * and requested offset & length values used by the String(byte[],..)
379 private static void checkBounds(byte[] bytes, int offset, int length) {
381 throw new StringIndexOutOfBoundsException(length);
383 throw new StringIndexOutOfBoundsException(offset);
384 if (offset > bytes.length - length)
385 throw new StringIndexOutOfBoundsException(offset + length);
389 * Constructs a new {@code String} by decoding the specified subarray of
390 * bytes using the specified charset. The length of the new {@code String}
391 * is a function of the charset, and hence may not be equal to the length
394 * <p> The behavior of this constructor when the given bytes are not valid
395 * in the given charset is unspecified. The {@link
396 * java.nio.charset.CharsetDecoder} class should be used when more control
397 * over the decoding process is required.
400 * The bytes to be decoded into characters
403 * The index of the first byte to decode
406 * The number of bytes to decode
409 * The name of a supported {@linkplain java.nio.charset.Charset
412 * @throws UnsupportedEncodingException
413 * If the named charset is not supported
415 * @throws IndexOutOfBoundsException
416 * If the {@code offset} and {@code length} arguments index
417 * characters outside the bounds of the {@code bytes} array
421 // public String(byte bytes[], int offset, int length, String charsetName)
422 // throws UnsupportedEncodingException
424 // if (charsetName == null)
425 // throw new NullPointerException("charsetName");
426 // checkBounds(bytes, offset, length);
427 // char[] v = StringCoding.decode(charsetName, bytes, offset, length);
429 // this.count = v.length;
434 * Constructs a new {@code String} by decoding the specified subarray of
435 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
436 * The length of the new {@code String} is a function of the charset, and
437 * hence may not be equal to the length of the subarray.
439 * <p> This method always replaces malformed-input and unmappable-character
440 * sequences with this charset's default replacement string. The {@link
441 * java.nio.charset.CharsetDecoder} class should be used when more control
442 * over the decoding process is required.
445 * The bytes to be decoded into characters
448 * The index of the first byte to decode
451 * The number of bytes to decode
454 * The {@linkplain java.nio.charset.Charset charset} to be used to
455 * decode the {@code bytes}
457 * @throws IndexOutOfBoundsException
458 * If the {@code offset} and {@code length} arguments index
459 * characters outside the bounds of the {@code bytes} array
463 /* don't want dependnecy on Charset
464 public String(byte bytes[], int offset, int length, Charset charset) {
466 throw new NullPointerException("charset");
467 checkBounds(bytes, offset, length);
468 char[] v = StringCoding.decode(charset, bytes, offset, length);
470 this.count = v.length;
476 * Constructs a new {@code String} by decoding the specified array of bytes
477 * using the specified {@linkplain java.nio.charset.Charset charset}. The
478 * length of the new {@code String} is a function of the charset, and hence
479 * may not be equal to the length of the byte array.
481 * <p> The behavior of this constructor when the given bytes are not valid
482 * in the given charset is unspecified. The {@link
483 * java.nio.charset.CharsetDecoder} class should be used when more control
484 * over the decoding process is required.
487 * The bytes to be decoded into characters
490 * The name of a supported {@linkplain java.nio.charset.Charset
493 * @throws UnsupportedEncodingException
494 * If the named charset is not supported
498 // public String(byte bytes[], String charsetName)
499 // throws UnsupportedEncodingException
501 // this(bytes, 0, bytes.length, charsetName);
505 * Constructs a new {@code String} by decoding the specified array of
506 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
507 * The length of the new {@code String} is a function of the charset, and
508 * hence may not be equal to the length of the byte array.
510 * <p> This method always replaces malformed-input and unmappable-character
511 * sequences with this charset's default replacement string. The {@link
512 * java.nio.charset.CharsetDecoder} class should be used when more control
513 * over the decoding process is required.
516 * The bytes to be decoded into characters
519 * The {@linkplain java.nio.charset.Charset charset} to be used to
520 * decode the {@code bytes}
524 /* don't want dep on Charset
525 public String(byte bytes[], Charset charset) {
526 this(bytes, 0, bytes.length, charset);
531 * Constructs a new {@code String} by decoding the specified subarray of
532 * bytes using the platform's default charset. The length of the new
533 * {@code String} is a function of the charset, and hence may not be equal
534 * to the length of the subarray.
536 * <p> The behavior of this constructor when the given bytes are not valid
537 * in the default charset is unspecified. The {@link
538 * java.nio.charset.CharsetDecoder} class should be used when more control
539 * over the decoding process is required.
542 * The bytes to be decoded into characters
545 * The index of the first byte to decode
548 * The number of bytes to decode
550 * @throws IndexOutOfBoundsException
551 * If the {@code offset} and the {@code length} arguments index
552 * characters outside the bounds of the {@code bytes} array
556 public String(byte bytes[], int offset, int length) {
557 checkBounds(bytes, offset, length);
558 char[] v = new char[length];
559 for (int i = 0; i < length; i++) {
560 v[i] = (char)bytes[offset++];
562 this.r = new String(v, 0, v.length);
566 * Constructs a new {@code String} by decoding the specified array of bytes
567 * using the platform's default charset. The length of the new {@code
568 * String} is a function of the charset, and hence may not be equal to the
569 * length of the byte array.
571 * <p> The behavior of this constructor when the given bytes are not valid
572 * in the default charset is unspecified. The {@link
573 * java.nio.charset.CharsetDecoder} class should be used when more control
574 * over the decoding process is required.
577 * The bytes to be decoded into characters
581 public String(byte bytes[]) {
582 this(bytes, 0, bytes.length);
586 * Allocates a new string that contains the sequence of characters
587 * currently contained in the string buffer argument. The contents of the
588 * string buffer are copied; subsequent modification of the string buffer
589 * does not affect the newly created string.
592 * A {@code StringBuffer}
594 public String(StringBuffer buffer) {
595 this.r = buffer.toString();
599 * Allocates a new string that contains the sequence of characters
600 * currently contained in the string builder argument. The contents of the
601 * string builder are copied; subsequent modification of the string builder
602 * does not affect the newly created string.
604 * <p> This constructor is provided to ease migration to {@code
605 * StringBuilder}. Obtaining a string from a string builder via the {@code
606 * toString} method is likely to run faster and is generally preferred.
609 * A {@code StringBuilder}
613 public String(StringBuilder builder) {
614 this.r = builder.toString();
618 * Returns the length of this string.
619 * The length is equal to the number of <a href="Character.html#unicode">Unicode
620 * code units</a> in the string.
622 * @return the length of the sequence of characters represented by this
625 @JavaScriptBody(args = "self", body = "return self.toString().length;")
626 public int length() {
627 throw new UnsupportedOperationException();
631 * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>.
633 * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise
638 @JavaScriptBody(args = "self", body="return self.toString().length === 0;")
639 public boolean isEmpty() {
640 return length() == 0;
644 * Returns the <code>char</code> value at the
645 * specified index. An index ranges from <code>0</code> to
646 * <code>length() - 1</code>. The first <code>char</code> value of the sequence
647 * is at index <code>0</code>, the next at index <code>1</code>,
648 * and so on, as for array indexing.
650 * <p>If the <code>char</code> value specified by the index is a
651 * <a href="Character.html#unicode">surrogate</a>, the surrogate
654 * @param index the index of the <code>char</code> value.
655 * @return the <code>char</code> value at the specified index of this string.
656 * The first <code>char</code> value is at index <code>0</code>.
657 * @exception IndexOutOfBoundsException if the <code>index</code>
658 * argument is negative or not less than the length of this
661 @JavaScriptBody(args = { "self", "index" },
662 body = "return self.toString().charCodeAt(index);"
664 public char charAt(int index) {
665 throw new UnsupportedOperationException();
669 * Returns the character (Unicode code point) at the specified
670 * index. The index refers to <code>char</code> values
671 * (Unicode code units) and ranges from <code>0</code> to
672 * {@link #length()}<code> - 1</code>.
674 * <p> If the <code>char</code> value specified at the given index
675 * is in the high-surrogate range, the following index is less
676 * than the length of this <code>String</code>, and the
677 * <code>char</code> value at the following index is in the
678 * low-surrogate range, then the supplementary code point
679 * corresponding to this surrogate pair is returned. Otherwise,
680 * the <code>char</code> value at the given index is returned.
682 * @param index the index to the <code>char</code> values
683 * @return the code point value of the character at the
685 * @exception IndexOutOfBoundsException if the <code>index</code>
686 * argument is negative or not less than the length of this
690 public int codePointAt(int index) {
691 if ((index < 0) || (index >= length())) {
692 throw new StringIndexOutOfBoundsException(index);
694 return Character.codePointAtImpl(toCharArray(), offset() + index, offset() + length());
698 * Returns the character (Unicode code point) before the specified
699 * index. The index refers to <code>char</code> values
700 * (Unicode code units) and ranges from <code>1</code> to {@link
701 * CharSequence#length() length}.
703 * <p> If the <code>char</code> value at <code>(index - 1)</code>
704 * is in the low-surrogate range, <code>(index - 2)</code> is not
705 * negative, and the <code>char</code> value at <code>(index -
706 * 2)</code> is in the high-surrogate range, then the
707 * supplementary code point value of the surrogate pair is
708 * returned. If the <code>char</code> value at <code>index -
709 * 1</code> is an unpaired low-surrogate or a high-surrogate, the
710 * surrogate value is returned.
712 * @param index the index following the code point that should be returned
713 * @return the Unicode code point value before the given index.
714 * @exception IndexOutOfBoundsException if the <code>index</code>
715 * argument is less than 1 or greater than the length
719 public int codePointBefore(int index) {
721 if ((i < 0) || (i >= length())) {
722 throw new StringIndexOutOfBoundsException(index);
724 return Character.codePointBeforeImpl(toCharArray(), offset() + index, offset());
728 * Returns the number of Unicode code points in the specified text
729 * range of this <code>String</code>. The text range begins at the
730 * specified <code>beginIndex</code> and extends to the
731 * <code>char</code> at index <code>endIndex - 1</code>. Thus the
732 * length (in <code>char</code>s) of the text range is
733 * <code>endIndex-beginIndex</code>. Unpaired surrogates within
734 * the text range count as one code point each.
736 * @param beginIndex the index to the first <code>char</code> of
738 * @param endIndex the index after the last <code>char</code> of
740 * @return the number of Unicode code points in the specified text
742 * @exception IndexOutOfBoundsException if the
743 * <code>beginIndex</code> is negative, or <code>endIndex</code>
744 * is larger than the length of this <code>String</code>, or
745 * <code>beginIndex</code> is larger than <code>endIndex</code>.
748 public int codePointCount(int beginIndex, int endIndex) {
749 if (beginIndex < 0 || endIndex > length() || beginIndex > endIndex) {
750 throw new IndexOutOfBoundsException();
752 return Character.codePointCountImpl(toCharArray(), offset()+beginIndex, endIndex-beginIndex);
756 * Returns the index within this <code>String</code> that is
757 * offset from the given <code>index</code> by
758 * <code>codePointOffset</code> code points. Unpaired surrogates
759 * within the text range given by <code>index</code> and
760 * <code>codePointOffset</code> count as one code point each.
762 * @param index the index to be offset
763 * @param codePointOffset the offset in code points
764 * @return the index within this <code>String</code>
765 * @exception IndexOutOfBoundsException if <code>index</code>
766 * is negative or larger then the length of this
767 * <code>String</code>, or if <code>codePointOffset</code> is positive
768 * and the substring starting with <code>index</code> has fewer
769 * than <code>codePointOffset</code> code points,
770 * or if <code>codePointOffset</code> is negative and the substring
771 * before <code>index</code> has fewer than the absolute value
772 * of <code>codePointOffset</code> code points.
775 public int offsetByCodePoints(int index, int codePointOffset) {
776 if (index < 0 || index > length()) {
777 throw new IndexOutOfBoundsException();
779 return Character.offsetByCodePointsImpl(toCharArray(), offset(), length(),
780 offset()+index, codePointOffset) - offset();
784 * Copy characters from this string into dst starting at dstBegin.
785 * This method doesn't perform any range checking.
787 @JavaScriptBody(args = { "self", "arr", "to" }, body =
788 "var s = self.toString();\n" +
789 "for (var i = 0; i < s.length; i++) {\n" +
790 " arr[to++] = s[i];\n" +
793 void getChars(char dst[], int dstBegin) {
794 AbstractStringBuilder.arraycopy(toCharArray(), offset(), dst, dstBegin, length());
798 * Copies characters from this string into the destination character
801 * The first character to be copied is at index <code>srcBegin</code>;
802 * the last character to be copied is at index <code>srcEnd-1</code>
803 * (thus the total number of characters to be copied is
804 * <code>srcEnd-srcBegin</code>). The characters are copied into the
805 * subarray of <code>dst</code> starting at index <code>dstBegin</code>
806 * and ending at index:
807 * <p><blockquote><pre>
808 * dstbegin + (srcEnd-srcBegin) - 1
809 * </pre></blockquote>
811 * @param srcBegin index of the first character in the string
813 * @param srcEnd index after the last character in the string
815 * @param dst the destination array.
816 * @param dstBegin the start offset in the destination array.
817 * @exception IndexOutOfBoundsException If any of the following
819 * <ul><li><code>srcBegin</code> is negative.
820 * <li><code>srcBegin</code> is greater than <code>srcEnd</code>
821 * <li><code>srcEnd</code> is greater than the length of this
823 * <li><code>dstBegin</code> is negative
824 * <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
825 * <code>dst.length</code></ul>
827 @JavaScriptBody(args = { "self", "beg", "end", "arr", "dst" }, body=
828 "var s = self.toString();\n" +
829 "while (beg < end) {\n" +
830 " arr[dst++] = s[beg++];\n" +
833 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
835 throw new StringIndexOutOfBoundsException(srcBegin);
837 if (srcEnd > length()) {
838 throw new StringIndexOutOfBoundsException(srcEnd);
840 if (srcBegin > srcEnd) {
841 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
843 AbstractStringBuilder.arraycopy(toCharArray(), offset() + srcBegin, dst, dstBegin,
848 * Copies characters from this string into the destination byte array. Each
849 * byte receives the 8 low-order bits of the corresponding character. The
850 * eight high-order bits of each character are not copied and do not
851 * participate in the transfer in any way.
853 * <p> The first character to be copied is at index {@code srcBegin}; the
854 * last character to be copied is at index {@code srcEnd-1}. The total
855 * number of characters to be copied is {@code srcEnd-srcBegin}. The
856 * characters, converted to bytes, are copied into the subarray of {@code
857 * dst} starting at index {@code dstBegin} and ending at index:
860 * dstbegin + (srcEnd-srcBegin) - 1
861 * </pre></blockquote>
863 * @deprecated This method does not properly convert characters into
864 * bytes. As of JDK 1.1, the preferred way to do this is via the
865 * {@link #getBytes()} method, which uses the platform's default charset.
868 * Index of the first character in the string to copy
871 * Index after the last character in the string to copy
874 * The destination array
877 * The start offset in the destination array
879 * @throws IndexOutOfBoundsException
880 * If any of the following is true:
882 * <li> {@code srcBegin} is negative
883 * <li> {@code srcBegin} is greater than {@code srcEnd}
884 * <li> {@code srcEnd} is greater than the length of this String
885 * <li> {@code dstBegin} is negative
886 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
891 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
893 throw new StringIndexOutOfBoundsException(srcBegin);
895 if (srcEnd > length()) {
896 throw new StringIndexOutOfBoundsException(srcEnd);
898 if (srcBegin > srcEnd) {
899 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
902 int n = offset() + srcEnd;
903 int i = offset() + srcBegin;
904 char[] val = toCharArray(); /* avoid getfield opcode */
907 dst[j++] = (byte)val[i++];
912 * Encodes this {@code String} into a sequence of bytes using the named
913 * charset, storing the result into a new byte array.
915 * <p> The behavior of this method when this string cannot be encoded in
916 * the given charset is unspecified. The {@link
917 * java.nio.charset.CharsetEncoder} class should be used when more control
918 * over the encoding process is required.
921 * The name of a supported {@linkplain java.nio.charset.Charset
924 * @return The resultant byte array
926 * @throws UnsupportedEncodingException
927 * If the named charset is not supported
931 // public byte[] getBytes(String charsetName)
932 // throws UnsupportedEncodingException
934 // if (charsetName == null) throw new NullPointerException();
935 // return StringCoding.encode(charsetName, value, offset, count);
939 * Encodes this {@code String} into a sequence of bytes using the given
940 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
943 * <p> This method always replaces malformed-input and unmappable-character
944 * sequences with this charset's default replacement byte array. The
945 * {@link java.nio.charset.CharsetEncoder} class should be used when more
946 * control over the encoding process is required.
949 * The {@linkplain java.nio.charset.Charset} to be used to encode
952 * @return The resultant byte array
956 /* don't want dep on Charset
957 public byte[] getBytes(Charset charset) {
958 if (charset == null) throw new NullPointerException();
959 return StringCoding.encode(charset, value, offset, count);
964 * Encodes this {@code String} into a sequence of bytes using the
965 * platform's default charset, storing the result into a new byte array.
967 * <p> The behavior of this method when this string cannot be encoded in
968 * the default charset is unspecified. The {@link
969 * java.nio.charset.CharsetEncoder} class should be used when more control
970 * over the encoding process is required.
972 * @return The resultant byte array
976 public byte[] getBytes() {
977 byte[] arr = new byte[length()];
978 for (int i = 0; i < arr.length; i++) {
979 final char v = charAt(i);
986 * Compares this string to the specified object. The result is {@code
987 * true} if and only if the argument is not {@code null} and is a {@code
988 * String} object that represents the same sequence of characters as this
992 * The object to compare this {@code String} against
994 * @return {@code true} if the given object represents a {@code String}
995 * equivalent to this string, {@code false} otherwise
997 * @see #compareTo(String)
998 * @see #equalsIgnoreCase(String)
1000 @JavaScriptBody(args = { "self", "obj" }, body =
1001 "return obj.$instOf_java_lang_String && "
1002 + "self.toString() === obj.toString();"
1004 public boolean equals(Object anObject) {
1005 if (this == anObject) {
1008 if (anObject instanceof String) {
1009 String anotherString = (String)anObject;
1011 if (n == anotherString.length()) {
1012 char v1[] = toCharArray();
1013 char v2[] = anotherString.toCharArray();
1015 int j = anotherString.offset();
1017 if (v1[i++] != v2[j++])
1027 * Compares this string to the specified {@code StringBuffer}. The result
1028 * is {@code true} if and only if this {@code String} represents the same
1029 * sequence of characters as the specified {@code StringBuffer}.
1032 * The {@code StringBuffer} to compare this {@code String} against
1034 * @return {@code true} if this {@code String} represents the same
1035 * sequence of characters as the specified {@code StringBuffer},
1036 * {@code false} otherwise
1040 public boolean contentEquals(StringBuffer sb) {
1042 return contentEquals((CharSequence)sb);
1047 * Compares this string to the specified {@code CharSequence}. The result
1048 * is {@code true} if and only if this {@code String} represents the same
1049 * sequence of char values as the specified sequence.
1052 * The sequence to compare this {@code String} against
1054 * @return {@code true} if this {@code String} represents the same
1055 * sequence of char values as the specified sequence, {@code
1060 public boolean contentEquals(CharSequence cs) {
1061 if (length() != cs.length())
1063 // Argument is a StringBuffer, StringBuilder
1064 if (cs instanceof AbstractStringBuilder) {
1065 char v1[] = toCharArray();
1066 char v2[] = ((AbstractStringBuilder)cs).getValue();
1071 if (v1[i++] != v2[j++])
1076 // Argument is a String
1077 if (cs.equals(this))
1079 // Argument is a generic CharSequence
1080 char v1[] = toCharArray();
1085 if (v1[i++] != cs.charAt(j++))
1092 * Compares this {@code String} to another {@code String}, ignoring case
1093 * considerations. Two strings are considered equal ignoring case if they
1094 * are of the same length and corresponding characters in the two strings
1095 * are equal ignoring case.
1097 * <p> Two characters {@code c1} and {@code c2} are considered the same
1098 * ignoring case if at least one of the following is true:
1100 * <li> The two characters are the same (as compared by the
1101 * {@code ==} operator)
1102 * <li> Applying the method {@link
1103 * java.lang.Character#toUpperCase(char)} to each character
1104 * produces the same result
1105 * <li> Applying the method {@link
1106 * java.lang.Character#toLowerCase(char)} to each character
1107 * produces the same result
1110 * @param anotherString
1111 * The {@code String} to compare this {@code String} against
1113 * @return {@code true} if the argument is not {@code null} and it
1114 * represents an equivalent {@code String} ignoring case; {@code
1117 * @see #equals(Object)
1119 public boolean equalsIgnoreCase(String anotherString) {
1120 return (this == anotherString) ? true :
1121 (anotherString != null) && (anotherString.length() == length()) &&
1122 regionMatches(true, 0, anotherString, 0, length());
1126 * Compares two strings lexicographically.
1127 * The comparison is based on the Unicode value of each character in
1128 * the strings. The character sequence represented by this
1129 * <code>String</code> object is compared lexicographically to the
1130 * character sequence represented by the argument string. The result is
1131 * a negative integer if this <code>String</code> object
1132 * lexicographically precedes the argument string. The result is a
1133 * positive integer if this <code>String</code> object lexicographically
1134 * follows the argument string. The result is zero if the strings
1135 * are equal; <code>compareTo</code> returns <code>0</code> exactly when
1136 * the {@link #equals(Object)} method would return <code>true</code>.
1138 * This is the definition of lexicographic ordering. If two strings are
1139 * different, then either they have different characters at some index
1140 * that is a valid index for both strings, or their lengths are different,
1141 * or both. If they have different characters at one or more index
1142 * positions, let <i>k</i> be the smallest such index; then the string
1143 * whose character at position <i>k</i> has the smaller value, as
1144 * determined by using the < operator, lexicographically precedes the
1145 * other string. In this case, <code>compareTo</code> returns the
1146 * difference of the two character values at position <code>k</code> in
1147 * the two string -- that is, the value:
1149 * this.charAt(k)-anotherString.charAt(k)
1150 * </pre></blockquote>
1151 * If there is no index position at which they differ, then the shorter
1152 * string lexicographically precedes the longer string. In this case,
1153 * <code>compareTo</code> returns the difference of the lengths of the
1154 * strings -- that is, the value:
1156 * this.length()-anotherString.length()
1157 * </pre></blockquote>
1159 * @param anotherString the <code>String</code> to be compared.
1160 * @return the value <code>0</code> if the argument string is equal to
1161 * this string; a value less than <code>0</code> if this string
1162 * is lexicographically less than the string argument; and a
1163 * value greater than <code>0</code> if this string is
1164 * lexicographically greater than the string argument.
1166 public int compareTo(String anotherString) {
1167 int len1 = length();
1168 int len2 = anotherString.length();
1169 int n = Math.min(len1, len2);
1170 char v1[] = toCharArray();
1171 char v2[] = anotherString.toCharArray();
1173 int j = anotherString.offset();
1199 * A Comparator that orders <code>String</code> objects as by
1200 * <code>compareToIgnoreCase</code>. This comparator is serializable.
1202 * Note that this Comparator does <em>not</em> take locale into account,
1203 * and will result in an unsatisfactory ordering for certain locales.
1204 * The java.text package provides <em>Collators</em> to allow
1205 * locale-sensitive ordering.
1207 * @see java.text.Collator#compare(String, String)
1210 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1211 = new CaseInsensitiveComparator();
1213 private static int offset() {
1217 private static class CaseInsensitiveComparator
1218 implements Comparator<String>, java.io.Serializable {
1219 // use serialVersionUID from JDK 1.2.2 for interoperability
1220 private static final long serialVersionUID = 8575799808933029326L;
1222 public int compare(String s1, String s2) {
1223 int n1 = s1.length();
1224 int n2 = s2.length();
1225 int min = Math.min(n1, n2);
1226 for (int i = 0; i < min; i++) {
1227 char c1 = s1.charAt(i);
1228 char c2 = s2.charAt(i);
1230 c1 = Character.toUpperCase(c1);
1231 c2 = Character.toUpperCase(c2);
1233 c1 = Character.toLowerCase(c1);
1234 c2 = Character.toLowerCase(c2);
1236 // No overflow because of numeric promotion
1247 * Compares two strings lexicographically, ignoring case
1248 * differences. This method returns an integer whose sign is that of
1249 * calling <code>compareTo</code> with normalized versions of the strings
1250 * where case differences have been eliminated by calling
1251 * <code>Character.toLowerCase(Character.toUpperCase(character))</code> on
1254 * Note that this method does <em>not</em> take locale into account,
1255 * and will result in an unsatisfactory ordering for certain locales.
1256 * The java.text package provides <em>collators</em> to allow
1257 * locale-sensitive ordering.
1259 * @param str the <code>String</code> to be compared.
1260 * @return a negative integer, zero, or a positive integer as the
1261 * specified String is greater than, equal to, or less
1262 * than this String, ignoring case considerations.
1263 * @see java.text.Collator#compare(String, String)
1266 public int compareToIgnoreCase(String str) {
1267 return CASE_INSENSITIVE_ORDER.compare(this, str);
1271 * Tests if two string regions are equal.
1273 * A substring of this <tt>String</tt> object is compared to a substring
1274 * of the argument other. The result is true if these substrings
1275 * represent identical character sequences. The substring of this
1276 * <tt>String</tt> object to be compared begins at index <tt>toffset</tt>
1277 * and has length <tt>len</tt>. The substring of other to be compared
1278 * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The
1279 * result is <tt>false</tt> if and only if at least one of the following
1281 * <ul><li><tt>toffset</tt> is negative.
1282 * <li><tt>ooffset</tt> is negative.
1283 * <li><tt>toffset+len</tt> is greater than the length of this
1284 * <tt>String</tt> object.
1285 * <li><tt>ooffset+len</tt> is greater than the length of the other
1287 * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt>
1289 * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt>
1292 * @param toffset the starting offset of the subregion in this string.
1293 * @param other the string argument.
1294 * @param ooffset the starting offset of the subregion in the string
1296 * @param len the number of characters to compare.
1297 * @return <code>true</code> if the specified subregion of this string
1298 * exactly matches the specified subregion of the string argument;
1299 * <code>false</code> otherwise.
1301 public boolean regionMatches(int toffset, String other, int ooffset,
1303 char ta[] = toCharArray();
1304 int to = offset() + toffset;
1305 char pa[] = other.toCharArray();
1306 int po = other.offset() + ooffset;
1307 // Note: toffset, ooffset, or len might be near -1>>>1.
1308 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)length() - len)
1309 || (ooffset > (long)other.length() - len)) {
1313 if (ta[to++] != pa[po++]) {
1321 * Tests if two string regions are equal.
1323 * A substring of this <tt>String</tt> object is compared to a substring
1324 * of the argument <tt>other</tt>. The result is <tt>true</tt> if these
1325 * substrings represent character sequences that are the same, ignoring
1326 * case if and only if <tt>ignoreCase</tt> is true. The substring of
1327 * this <tt>String</tt> object to be compared begins at index
1328 * <tt>toffset</tt> and has length <tt>len</tt>. The substring of
1329 * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and
1330 * has length <tt>len</tt>. The result is <tt>false</tt> if and only if
1331 * at least one of the following is true:
1332 * <ul><li><tt>toffset</tt> is negative.
1333 * <li><tt>ooffset</tt> is negative.
1334 * <li><tt>toffset+len</tt> is greater than the length of this
1335 * <tt>String</tt> object.
1336 * <li><tt>ooffset+len</tt> is greater than the length of the other
1338 * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative
1339 * integer <i>k</i> less than <tt>len</tt> such that:
1341 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1342 * </pre></blockquote>
1343 * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative
1344 * integer <i>k</i> less than <tt>len</tt> such that:
1346 * Character.toLowerCase(this.charAt(toffset+k)) !=
1347 Character.toLowerCase(other.charAt(ooffset+k))
1348 * </pre></blockquote>
1351 * Character.toUpperCase(this.charAt(toffset+k)) !=
1352 * Character.toUpperCase(other.charAt(ooffset+k))
1353 * </pre></blockquote>
1356 * @param ignoreCase if <code>true</code>, ignore case when comparing
1358 * @param toffset the starting offset of the subregion in this
1360 * @param other the string argument.
1361 * @param ooffset the starting offset of the subregion in the string
1363 * @param len the number of characters to compare.
1364 * @return <code>true</code> if the specified subregion of this string
1365 * matches the specified subregion of the string argument;
1366 * <code>false</code> otherwise. Whether the matching is exact
1367 * or case insensitive depends on the <code>ignoreCase</code>
1370 public boolean regionMatches(boolean ignoreCase, int toffset,
1371 String other, int ooffset, int len) {
1372 char ta[] = toCharArray();
1373 int to = offset() + toffset;
1374 char pa[] = other.toCharArray();
1375 int po = other.offset() + ooffset;
1376 // Note: toffset, ooffset, or len might be near -1>>>1.
1377 if ((ooffset < 0) || (toffset < 0) || (toffset > (long)length() - len) ||
1378 (ooffset > (long)other.length() - len)) {
1388 // If characters don't match but case may be ignored,
1389 // try converting both characters to uppercase.
1390 // If the results match, then the comparison scan should
1392 char u1 = Character.toUpperCase(c1);
1393 char u2 = Character.toUpperCase(c2);
1397 // Unfortunately, conversion to uppercase does not work properly
1398 // for the Georgian alphabet, which has strange rules about case
1399 // conversion. So we need to make one last check before
1401 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1411 * Tests if the substring of this string beginning at the
1412 * specified index starts with the specified prefix.
1414 * @param prefix the prefix.
1415 * @param toffset where to begin looking in this string.
1416 * @return <code>true</code> if the character sequence represented by the
1417 * argument is a prefix of the substring of this object starting
1418 * at index <code>toffset</code>; <code>false</code> otherwise.
1419 * The result is <code>false</code> if <code>toffset</code> is
1420 * negative or greater than the length of this
1421 * <code>String</code> object; otherwise the result is the same
1422 * as the result of the expression
1424 * this.substring(toffset).startsWith(prefix)
1427 @JavaScriptBody(args = { "self", "find", "from" }, body=
1428 "find = find.toString();\n" +
1429 "return self.toString().substring(from, from + find.length) === find;\n"
1431 public boolean startsWith(String prefix, int toffset) {
1432 char ta[] = toCharArray();
1433 int to = offset() + toffset;
1434 char pa[] = prefix.toCharArray();
1435 int po = prefix.offset();
1436 int pc = prefix.length();
1437 // Note: toffset might be near -1>>>1.
1438 if ((toffset < 0) || (toffset > length() - pc)) {
1442 if (ta[to++] != pa[po++]) {
1450 * Tests if this string starts with the specified prefix.
1452 * @param prefix the prefix.
1453 * @return <code>true</code> if the character sequence represented by the
1454 * argument is a prefix of the character sequence represented by
1455 * this string; <code>false</code> otherwise.
1456 * Note also that <code>true</code> will be returned if the
1457 * argument is an empty string or is equal to this
1458 * <code>String</code> object as determined by the
1459 * {@link #equals(Object)} method.
1462 public boolean startsWith(String prefix) {
1463 return startsWith(prefix, 0);
1467 * Tests if this string ends with the specified suffix.
1469 * @param suffix the suffix.
1470 * @return <code>true</code> if the character sequence represented by the
1471 * argument is a suffix of the character sequence represented by
1472 * this object; <code>false</code> otherwise. Note that the
1473 * result will be <code>true</code> if the argument is the
1474 * empty string or is equal to this <code>String</code> object
1475 * as determined by the {@link #equals(Object)} method.
1477 public boolean endsWith(String suffix) {
1478 return startsWith(suffix, length() - suffix.length());
1482 * Returns a hash code for this string. The hash code for a
1483 * <code>String</code> object is computed as
1485 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1486 * </pre></blockquote>
1487 * using <code>int</code> arithmetic, where <code>s[i]</code> is the
1488 * <i>i</i>th character of the string, <code>n</code> is the length of
1489 * the string, and <code>^</code> indicates exponentiation.
1490 * (The hash value of the empty string is zero.)
1492 * @return a hash code value for this object.
1494 public int hashCode() {
1496 if (h == 0 && length() > 0) {
1498 char val[] = toCharArray();
1501 for (int i = 0; i < len; i++) {
1502 h = 31*h + val[off++];
1510 * Returns the index within this string of the first occurrence of
1511 * the specified character. If a character with value
1512 * <code>ch</code> occurs in the character sequence represented by
1513 * this <code>String</code> object, then the index (in Unicode
1514 * code units) of the first such occurrence is returned. For
1515 * values of <code>ch</code> in the range from 0 to 0xFFFF
1516 * (inclusive), this is the smallest value <i>k</i> such that:
1518 * this.charAt(<i>k</i>) == ch
1519 * </pre></blockquote>
1520 * is true. For other values of <code>ch</code>, it is the
1521 * smallest value <i>k</i> such that:
1523 * this.codePointAt(<i>k</i>) == ch
1524 * </pre></blockquote>
1525 * is true. In either case, if no such character occurs in this
1526 * string, then <code>-1</code> is returned.
1528 * @param ch a character (Unicode code point).
1529 * @return the index of the first occurrence of the character in the
1530 * character sequence represented by this object, or
1531 * <code>-1</code> if the character does not occur.
1533 public int indexOf(int ch) {
1534 return indexOf(ch, 0);
1538 * Returns the index within this string of the first occurrence of the
1539 * specified character, starting the search at the specified index.
1541 * If a character with value <code>ch</code> occurs in the
1542 * character sequence represented by this <code>String</code>
1543 * object at an index no smaller than <code>fromIndex</code>, then
1544 * the index of the first such occurrence is returned. For values
1545 * of <code>ch</code> in the range from 0 to 0xFFFF (inclusive),
1546 * this is the smallest value <i>k</i> such that:
1548 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1549 * </pre></blockquote>
1550 * is true. For other values of <code>ch</code>, it is the
1551 * smallest value <i>k</i> such that:
1553 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1554 * </pre></blockquote>
1555 * is true. In either case, if no such character occurs in this
1556 * string at or after position <code>fromIndex</code>, then
1557 * <code>-1</code> is returned.
1560 * There is no restriction on the value of <code>fromIndex</code>. If it
1561 * is negative, it has the same effect as if it were zero: this entire
1562 * string may be searched. If it is greater than the length of this
1563 * string, it has the same effect as if it were equal to the length of
1564 * this string: <code>-1</code> is returned.
1566 * <p>All indices are specified in <code>char</code> values
1567 * (Unicode code units).
1569 * @param ch a character (Unicode code point).
1570 * @param fromIndex the index to start the search from.
1571 * @return the index of the first occurrence of the character in the
1572 * character sequence represented by this object that is greater
1573 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1574 * if the character does not occur.
1576 @JavaScriptBody(args = { "self", "ch", "from" }, body =
1577 "if (typeof ch === 'number') ch = String.fromCharCode(ch);\n" +
1578 "return self.toString().indexOf(ch, from);\n"
1580 public int indexOf(int ch, int fromIndex) {
1581 if (fromIndex < 0) {
1583 } else if (fromIndex >= length()) {
1584 // Note: fromIndex might be near -1>>>1.
1588 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1589 // handle most cases here (ch is a BMP code point or a
1590 // negative value (invalid code point))
1591 final char[] value = this.toCharArray();
1592 final int offset = this.offset();
1593 final int max = offset + length();
1594 for (int i = offset + fromIndex; i < max ; i++) {
1595 if (value[i] == ch) {
1601 return indexOfSupplementary(ch, fromIndex);
1606 * Handles (rare) calls of indexOf with a supplementary character.
1608 private int indexOfSupplementary(int ch, int fromIndex) {
1609 if (Character.isValidCodePoint(ch)) {
1610 final char[] value = this.toCharArray();
1611 final int offset = this.offset();
1612 final char hi = Character.highSurrogate(ch);
1613 final char lo = Character.lowSurrogate(ch);
1614 final int max = offset + length() - 1;
1615 for (int i = offset + fromIndex; i < max; i++) {
1616 if (value[i] == hi && value[i+1] == lo) {
1625 * Returns the index within this string of the last occurrence of
1626 * the specified character. For values of <code>ch</code> in the
1627 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1628 * units) returned is the largest value <i>k</i> such that:
1630 * this.charAt(<i>k</i>) == ch
1631 * </pre></blockquote>
1632 * is true. For other values of <code>ch</code>, it is the
1633 * largest value <i>k</i> such that:
1635 * this.codePointAt(<i>k</i>) == ch
1636 * </pre></blockquote>
1637 * is true. In either case, if no such character occurs in this
1638 * string, then <code>-1</code> is returned. The
1639 * <code>String</code> is searched backwards starting at the last
1642 * @param ch a character (Unicode code point).
1643 * @return the index of the last occurrence of the character in the
1644 * character sequence represented by this object, or
1645 * <code>-1</code> if the character does not occur.
1647 public int lastIndexOf(int ch) {
1648 return lastIndexOf(ch, length() - 1);
1652 * Returns the index within this string of the last occurrence of
1653 * the specified character, searching backward starting at the
1654 * specified index. For values of <code>ch</code> in the range
1655 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1656 * value <i>k</i> such that:
1658 * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1659 * </pre></blockquote>
1660 * is true. For other values of <code>ch</code>, it is the
1661 * largest value <i>k</i> such that:
1663 * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1664 * </pre></blockquote>
1665 * is true. In either case, if no such character occurs in this
1666 * string at or before position <code>fromIndex</code>, then
1667 * <code>-1</code> is returned.
1669 * <p>All indices are specified in <code>char</code> values
1670 * (Unicode code units).
1672 * @param ch a character (Unicode code point).
1673 * @param fromIndex the index to start the search from. There is no
1674 * restriction on the value of <code>fromIndex</code>. If it is
1675 * greater than or equal to the length of this string, it has
1676 * the same effect as if it were equal to one less than the
1677 * length of this string: this entire string may be searched.
1678 * If it is negative, it has the same effect as if it were -1:
1680 * @return the index of the last occurrence of the character in the
1681 * character sequence represented by this object that is less
1682 * than or equal to <code>fromIndex</code>, or <code>-1</code>
1683 * if the character does not occur before that point.
1685 @JavaScriptBody(args = { "self", "ch", "from" }, body =
1686 "if (typeof ch === 'number') ch = String.fromCharCode(ch);\n" +
1687 "return self.toString().lastIndexOf(ch, from);"
1689 public int lastIndexOf(int ch, int fromIndex) {
1690 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1691 // handle most cases here (ch is a BMP code point or a
1692 // negative value (invalid code point))
1693 final char[] value = this.toCharArray();
1694 final int offset = this.offset();
1695 int i = offset + Math.min(fromIndex, length() - 1);
1696 for (; i >= offset ; i--) {
1697 if (value[i] == ch) {
1703 return lastIndexOfSupplementary(ch, fromIndex);
1708 * Handles (rare) calls of lastIndexOf with a supplementary character.
1710 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1711 if (Character.isValidCodePoint(ch)) {
1712 final char[] value = this.toCharArray();
1713 final int offset = this.offset();
1714 char hi = Character.highSurrogate(ch);
1715 char lo = Character.lowSurrogate(ch);
1716 int i = offset + Math.min(fromIndex, length() - 2);
1717 for (; i >= offset; i--) {
1718 if (value[i] == hi && value[i+1] == lo) {
1727 * Returns the index within this string of the first occurrence of the
1728 * specified substring.
1730 * <p>The returned index is the smallest value <i>k</i> for which:
1732 * this.startsWith(str, <i>k</i>)
1733 * </pre></blockquote>
1734 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1736 * @param str the substring to search for.
1737 * @return the index of the first occurrence of the specified substring,
1738 * or {@code -1} if there is no such occurrence.
1740 public int indexOf(String str) {
1741 return indexOf(str, 0);
1745 * Returns the index within this string of the first occurrence of the
1746 * specified substring, starting at the specified index.
1748 * <p>The returned index is the smallest value <i>k</i> for which:
1750 * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>)
1751 * </pre></blockquote>
1752 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1754 * @param str the substring to search for.
1755 * @param fromIndex the index from which to start the search.
1756 * @return the index of the first occurrence of the specified substring,
1757 * starting at the specified index,
1758 * or {@code -1} if there is no such occurrence.
1760 @JavaScriptBody(args = { "self", "str", "fromIndex" }, body =
1761 "return self.toString().indexOf(str.toString(), fromIndex);"
1763 public int indexOf(String str, int fromIndex) {
1764 return indexOf(toCharArray(), offset(), length(), str.toCharArray(), str.offset(), str.length(), fromIndex);
1768 * Code shared by String and StringBuffer to do searches. The
1769 * source is the character array being searched, and the target
1770 * is the string being searched for.
1772 * @param source the characters being searched.
1773 * @param sourceOffset offset of the source string.
1774 * @param sourceCount count of the source string.
1775 * @param target the characters being searched for.
1776 * @param targetOffset offset of the target string.
1777 * @param targetCount count of the target string.
1778 * @param fromIndex the index to begin searching from.
1780 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1781 char[] target, int targetOffset, int targetCount,
1783 if (fromIndex >= sourceCount) {
1784 return (targetCount == 0 ? sourceCount : -1);
1786 if (fromIndex < 0) {
1789 if (targetCount == 0) {
1793 char first = target[targetOffset];
1794 int max = sourceOffset + (sourceCount - targetCount);
1796 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1797 /* Look for first character. */
1798 if (source[i] != first) {
1799 while (++i <= max && source[i] != first);
1802 /* Found first character, now look at the rest of v2 */
1805 int end = j + targetCount - 1;
1806 for (int k = targetOffset + 1; j < end && source[j] ==
1807 target[k]; j++, k++);
1810 /* Found whole string. */
1811 return i - sourceOffset;
1819 * Returns the index within this string of the last occurrence of the
1820 * specified substring. The last occurrence of the empty string ""
1821 * is considered to occur at the index value {@code this.length()}.
1823 * <p>The returned index is the largest value <i>k</i> for which:
1825 * this.startsWith(str, <i>k</i>)
1826 * </pre></blockquote>
1827 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1829 * @param str the substring to search for.
1830 * @return the index of the last occurrence of the specified substring,
1831 * or {@code -1} if there is no such occurrence.
1833 public int lastIndexOf(String str) {
1834 return lastIndexOf(str, length());
1838 * Returns the index within this string of the last occurrence of the
1839 * specified substring, searching backward starting at the specified index.
1841 * <p>The returned index is the largest value <i>k</i> for which:
1843 * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>)
1844 * </pre></blockquote>
1845 * If no such value of <i>k</i> exists, then {@code -1} is returned.
1847 * @param str the substring to search for.
1848 * @param fromIndex the index to start the search from.
1849 * @return the index of the last occurrence of the specified substring,
1850 * searching backward from the specified index,
1851 * or {@code -1} if there is no such occurrence.
1853 @JavaScriptBody(args = { "self", "s", "from" }, body =
1854 "return self.toString().lastIndexOf(s.toString(), from);"
1856 public int lastIndexOf(String str, int fromIndex) {
1857 return lastIndexOf(toCharArray(), offset(), length(), str.toCharArray(), str.offset(), str.length(), fromIndex);
1861 * Code shared by String and StringBuffer to do searches. The
1862 * source is the character array being searched, and the target
1863 * is the string being searched for.
1865 * @param source the characters being searched.
1866 * @param sourceOffset offset of the source string.
1867 * @param sourceCount count of the source string.
1868 * @param target the characters being searched for.
1869 * @param targetOffset offset of the target string.
1870 * @param targetCount count of the target string.
1871 * @param fromIndex the index to begin searching from.
1873 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1874 char[] target, int targetOffset, int targetCount,
1877 * Check arguments; return immediately where possible. For
1878 * consistency, don't check for null str.
1880 int rightIndex = sourceCount - targetCount;
1881 if (fromIndex < 0) {
1884 if (fromIndex > rightIndex) {
1885 fromIndex = rightIndex;
1887 /* Empty string always matches. */
1888 if (targetCount == 0) {
1892 int strLastIndex = targetOffset + targetCount - 1;
1893 char strLastChar = target[strLastIndex];
1894 int min = sourceOffset + targetCount - 1;
1895 int i = min + fromIndex;
1897 startSearchForLastChar:
1899 while (i >= min && source[i] != strLastChar) {
1906 int start = j - (targetCount - 1);
1907 int k = strLastIndex - 1;
1910 if (source[j--] != target[k--]) {
1912 continue startSearchForLastChar;
1915 return start - sourceOffset + 1;
1920 * Returns a new string that is a substring of this string. The
1921 * substring begins with the character at the specified index and
1922 * extends to the end of this string. <p>
1925 * "unhappy".substring(2) returns "happy"
1926 * "Harbison".substring(3) returns "bison"
1927 * "emptiness".substring(9) returns "" (an empty string)
1928 * </pre></blockquote>
1930 * @param beginIndex the beginning index, inclusive.
1931 * @return the specified substring.
1932 * @exception IndexOutOfBoundsException if
1933 * <code>beginIndex</code> is negative or larger than the
1934 * length of this <code>String</code> object.
1936 public String substring(int beginIndex) {
1937 return substring(beginIndex, length());
1941 * Returns a new string that is a substring of this string. The
1942 * substring begins at the specified <code>beginIndex</code> and
1943 * extends to the character at index <code>endIndex - 1</code>.
1944 * Thus the length of the substring is <code>endIndex-beginIndex</code>.
1948 * "hamburger".substring(4, 8) returns "urge"
1949 * "smiles".substring(1, 5) returns "mile"
1950 * </pre></blockquote>
1952 * @param beginIndex the beginning index, inclusive.
1953 * @param endIndex the ending index, exclusive.
1954 * @return the specified substring.
1955 * @exception IndexOutOfBoundsException if the
1956 * <code>beginIndex</code> is negative, or
1957 * <code>endIndex</code> is larger than the length of
1958 * this <code>String</code> object, or
1959 * <code>beginIndex</code> is larger than
1960 * <code>endIndex</code>.
1962 @JavaScriptBody(args = { "self", "beginIndex", "endIndex" }, body =
1963 "return self.toString().substring(beginIndex, endIndex);"
1965 public String substring(int beginIndex, int endIndex) {
1966 if (beginIndex < 0) {
1967 throw new StringIndexOutOfBoundsException(beginIndex);
1969 if (endIndex > length()) {
1970 throw new StringIndexOutOfBoundsException(endIndex);
1972 if (beginIndex > endIndex) {
1973 throw new StringIndexOutOfBoundsException(endIndex - beginIndex);
1975 return ((beginIndex == 0) && (endIndex == length())) ? this :
1976 new String(toCharArray(), offset() + beginIndex, endIndex - beginIndex);
1980 * Returns a new character sequence that is a subsequence of this sequence.
1982 * <p> An invocation of this method of the form
1985 * str.subSequence(begin, end)</pre></blockquote>
1987 * behaves in exactly the same way as the invocation
1990 * str.substring(begin, end)</pre></blockquote>
1992 * This method is defined so that the <tt>String</tt> class can implement
1993 * the {@link CharSequence} interface. </p>
1995 * @param beginIndex the begin index, inclusive.
1996 * @param endIndex the end index, exclusive.
1997 * @return the specified subsequence.
1999 * @throws IndexOutOfBoundsException
2000 * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative,
2001 * if <tt>endIndex</tt> is greater than <tt>length()</tt>,
2002 * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt>
2007 public CharSequence subSequence(int beginIndex, int endIndex) {
2008 return this.substring(beginIndex, endIndex);
2012 * Concatenates the specified string to the end of this string.
2014 * If the length of the argument string is <code>0</code>, then this
2015 * <code>String</code> object is returned. Otherwise, a new
2016 * <code>String</code> object is created, representing a character
2017 * sequence that is the concatenation of the character sequence
2018 * represented by this <code>String</code> object and the character
2019 * sequence represented by the argument string.<p>
2022 * "cares".concat("s") returns "caress"
2023 * "to".concat("get").concat("her") returns "together"
2024 * </pre></blockquote>
2026 * @param str the <code>String</code> that is concatenated to the end
2027 * of this <code>String</code>.
2028 * @return a string that represents the concatenation of this object's
2029 * characters followed by the string argument's characters.
2031 public String concat(String str) {
2032 int otherLen = str.length();
2033 if (otherLen == 0) {
2036 char buf[] = new char[length() + otherLen];
2037 getChars(0, length(), buf, 0);
2038 str.getChars(0, otherLen, buf, length());
2039 return new String(buf, 0, length() + otherLen);
2043 * Returns a new string resulting from replacing all occurrences of
2044 * <code>oldChar</code> in this string with <code>newChar</code>.
2046 * If the character <code>oldChar</code> does not occur in the
2047 * character sequence represented by this <code>String</code> object,
2048 * then a reference to this <code>String</code> object is returned.
2049 * Otherwise, a new <code>String</code> object is created that
2050 * represents a character sequence identical to the character sequence
2051 * represented by this <code>String</code> object, except that every
2052 * occurrence of <code>oldChar</code> is replaced by an occurrence
2053 * of <code>newChar</code>.
2057 * "mesquite in your cellar".replace('e', 'o')
2058 * returns "mosquito in your collar"
2059 * "the war of baronets".replace('r', 'y')
2060 * returns "the way of bayonets"
2061 * "sparring with a purple porpoise".replace('p', 't')
2062 * returns "starring with a turtle tortoise"
2063 * "JonL".replace('q', 'x') returns "JonL" (no change)
2064 * </pre></blockquote>
2066 * @param oldChar the old character.
2067 * @param newChar the new character.
2068 * @return a string derived from this string by replacing every
2069 * occurrence of <code>oldChar</code> with <code>newChar</code>.
2071 @JavaScriptBody(args = { "self", "arg1", "arg2" }, body =
2072 "if (typeof arg1 === 'number') arg1 = String.fromCharCode(arg1);\n" +
2073 "if (typeof arg2 === 'number') arg2 = String.fromCharCode(arg2);\n" +
2074 "var s = self.toString();\n" +
2076 " var ret = s.replace(arg1, arg2);\n" +
2077 " if (ret === s) {\n" +
2083 public String replace(char oldChar, char newChar) {
2084 if (oldChar != newChar) {
2087 char[] val = toCharArray(); /* avoid getfield opcode */
2088 int off = offset(); /* avoid getfield opcode */
2091 if (val[off + i] == oldChar) {
2096 char buf[] = new char[len];
2097 for (int j = 0 ; j < i ; j++) {
2098 buf[j] = val[off+j];
2101 char c = val[off + i];
2102 buf[i] = (c == oldChar) ? newChar : c;
2105 return new String(buf, 0, len);
2112 * Tells whether or not this string matches the given <a
2113 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2115 * <p> An invocation of this method of the form
2116 * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the
2117 * same result as the expression
2119 * <blockquote><tt> {@link java.util.regex.Pattern}.{@link
2120 * java.util.regex.Pattern#matches(String,CharSequence)
2121 * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote>
2124 * the regular expression to which this string is to be matched
2126 * @return <tt>true</tt> if, and only if, this string matches the
2127 * given regular expression
2129 * @throws PatternSyntaxException
2130 * if the regular expression's syntax is invalid
2132 * @see java.util.regex.Pattern
2137 @JavaScriptBody(args = { "self", "regex" }, body =
2138 "self = self.toString();\n"
2139 + "var re = new RegExp(regex.toString());\n"
2140 + "var r = re.exec(self);\n"
2141 + "return r != null && r.length > 0 && self.length == r[0].length;"
2143 public boolean matches(String regex) {
2144 throw new UnsupportedOperationException();
2148 * Returns true if and only if this string contains the specified
2149 * sequence of char values.
2151 * @param s the sequence to search for
2152 * @return true if this string contains <code>s</code>, false otherwise
2153 * @throws NullPointerException if <code>s</code> is <code>null</code>
2156 public boolean contains(CharSequence s) {
2157 return indexOf(s.toString()) > -1;
2161 * Replaces the first substring of this string that matches the given <a
2162 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2163 * given replacement.
2165 * <p> An invocation of this method of the form
2166 * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2167 * yields exactly the same result as the expression
2170 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2171 * compile}(</tt><i>regex</i><tt>).{@link
2172 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2173 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst
2174 * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote>
2177 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2178 * replacement string may cause the results to be different than if it were
2179 * being treated as a literal replacement string; see
2180 * {@link java.util.regex.Matcher#replaceFirst}.
2181 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2182 * meaning of these characters, if desired.
2185 * the regular expression to which this string is to be matched
2186 * @param replacement
2187 * the string to be substituted for the first match
2189 * @return The resulting <tt>String</tt>
2191 * @throws PatternSyntaxException
2192 * if the regular expression's syntax is invalid
2194 * @see java.util.regex.Pattern
2199 public String replaceFirst(String regex, String replacement) {
2200 throw new UnsupportedOperationException();
2204 * Replaces each substring of this string that matches the given <a
2205 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2206 * given replacement.
2208 * <p> An invocation of this method of the form
2209 * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
2210 * yields exactly the same result as the expression
2213 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2214 * compile}(</tt><i>regex</i><tt>).{@link
2215 * java.util.regex.Pattern#matcher(java.lang.CharSequence)
2216 * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll
2217 * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote>
2220 * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
2221 * replacement string may cause the results to be different than if it were
2222 * being treated as a literal replacement string; see
2223 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2224 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2225 * meaning of these characters, if desired.
2228 * the regular expression to which this string is to be matched
2229 * @param replacement
2230 * the string to be substituted for each match
2232 * @return The resulting <tt>String</tt>
2234 * @throws PatternSyntaxException
2235 * if the regular expression's syntax is invalid
2237 * @see java.util.regex.Pattern
2242 public String replaceAll(String regex, String replacement) {
2243 throw new UnsupportedOperationException();
2247 * Replaces each substring of this string that matches the literal target
2248 * sequence with the specified literal replacement sequence. The
2249 * replacement proceeds from the beginning of the string to the end, for
2250 * example, replacing "aa" with "b" in the string "aaa" will result in
2251 * "ba" rather than "ab".
2253 * @param target The sequence of char values to be replaced
2254 * @param replacement The replacement sequence of char values
2255 * @return The resulting string
2256 * @throws NullPointerException if <code>target</code> or
2257 * <code>replacement</code> is <code>null</code>.
2260 public String replace(CharSequence target, CharSequence replacement) {
2261 throw new UnsupportedOperationException("This one should be supported, but without dep on rest of regexp");
2265 * Splits this string around matches of the given
2266 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2268 * <p> The array returned by this method contains each substring of this
2269 * string that is terminated by another substring that matches the given
2270 * expression or is terminated by the end of the string. The substrings in
2271 * the array are in the order in which they occur in this string. If the
2272 * expression does not match any part of the input then the resulting array
2273 * has just one element, namely this string.
2275 * <p> The <tt>limit</tt> parameter controls the number of times the
2276 * pattern is applied and therefore affects the length of the resulting
2277 * array. If the limit <i>n</i> is greater than zero then the pattern
2278 * will be applied at most <i>n</i> - 1 times, the array's
2279 * length will be no greater than <i>n</i>, and the array's last entry
2280 * will contain all input beyond the last matched delimiter. If <i>n</i>
2281 * is non-positive then the pattern will be applied as many times as
2282 * possible and the array can have any length. If <i>n</i> is zero then
2283 * the pattern will be applied as many times as possible, the array can
2284 * have any length, and trailing empty strings will be discarded.
2286 * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the
2287 * following results with these parameters:
2289 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2295 * <tr><td align=center>:</td>
2296 * <td align=center>2</td>
2297 * <td><tt>{ "boo", "and:foo" }</tt></td></tr>
2298 * <tr><td align=center>:</td>
2299 * <td align=center>5</td>
2300 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2301 * <tr><td align=center>:</td>
2302 * <td align=center>-2</td>
2303 * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
2304 * <tr><td align=center>o</td>
2305 * <td align=center>5</td>
2306 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2307 * <tr><td align=center>o</td>
2308 * <td align=center>-2</td>
2309 * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
2310 * <tr><td align=center>o</td>
2311 * <td align=center>0</td>
2312 * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
2313 * </table></blockquote>
2315 * <p> An invocation of this method of the form
2316 * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt>
2317 * yields the same result as the expression
2320 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
2321 * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link
2322 * java.util.regex.Pattern#split(java.lang.CharSequence,int)
2323 * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt>
2328 * the delimiting regular expression
2331 * the result threshold, as described above
2333 * @return the array of strings computed by splitting this string
2334 * around matches of the given regular expression
2336 * @throws PatternSyntaxException
2337 * if the regular expression's syntax is invalid
2339 * @see java.util.regex.Pattern
2344 public String[] split(String regex, int limit) {
2345 throw new UnsupportedOperationException("Needs regexp");
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 // 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 // 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 = "self", body = "return self.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 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 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 = "self", body = "return self.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 = "self", body = "return self.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 @JavaScriptBody(args = "self", body = "return self.toString().split('');")
2790 public char[] toCharArray() {
2791 char result[] = new char[length()];
2792 getChars(0, length(), result, 0);
2797 * Returns a formatted string using the specified format string and
2800 * <p> The locale always used is the one returned by {@link
2801 * java.util.Locale#getDefault() Locale.getDefault()}.
2804 * A <a href="../util/Formatter.html#syntax">format string</a>
2807 * Arguments referenced by the format specifiers in the format
2808 * string. If there are more arguments than format specifiers, the
2809 * extra arguments are ignored. The number of arguments is
2810 * variable and may be zero. The maximum number of arguments is
2811 * limited by the maximum dimension of a Java array as defined by
2812 * <cite>The Java™ Virtual Machine Specification</cite>.
2813 * The behaviour on a
2814 * <tt>null</tt> argument depends on the <a
2815 * href="../util/Formatter.html#syntax">conversion</a>.
2817 * @throws IllegalFormatException
2818 * If a format string contains an illegal syntax, a format
2819 * specifier that is incompatible with the given arguments,
2820 * insufficient arguments given the format string, or other
2821 * illegal conditions. For specification of all possible
2822 * formatting errors, see the <a
2823 * href="../util/Formatter.html#detail">Details</a> section of the
2824 * formatter class specification.
2826 * @throws NullPointerException
2827 * If the <tt>format</tt> is <tt>null</tt>
2829 * @return A formatted string
2831 * @see java.util.Formatter
2834 public static String format(String format, Object ... args) {
2835 throw new UnsupportedOperationException();
2839 * Returns a formatted string using the specified locale, format string,
2843 * The {@linkplain java.util.Locale locale} to apply during
2844 * formatting. If <tt>l</tt> is <tt>null</tt> then no localization
2848 * A <a href="../util/Formatter.html#syntax">format string</a>
2851 * Arguments referenced by the format specifiers in the format
2852 * string. If there are more arguments than format specifiers, the
2853 * extra arguments are ignored. The number of arguments is
2854 * variable and may be zero. The maximum number of arguments is
2855 * limited by the maximum dimension of a Java array as defined by
2856 * <cite>The Java™ Virtual Machine Specification</cite>.
2857 * The behaviour on a
2858 * <tt>null</tt> argument depends on the <a
2859 * href="../util/Formatter.html#syntax">conversion</a>.
2861 * @throws IllegalFormatException
2862 * If a format string contains an illegal syntax, a format
2863 * specifier that is incompatible with the given arguments,
2864 * insufficient arguments given the format string, or other
2865 * illegal conditions. For specification of all possible
2866 * formatting errors, see the <a
2867 * href="../util/Formatter.html#detail">Details</a> section of the
2868 * formatter class specification
2870 * @throws NullPointerException
2871 * If the <tt>format</tt> is <tt>null</tt>
2873 * @return A formatted string
2875 * @see java.util.Formatter
2878 // public static String format(Locale l, String format, Object ... args) {
2879 // return new Formatter(l).format(format, args).toString();
2883 * Returns the string representation of the <code>Object</code> argument.
2885 * @param obj an <code>Object</code>.
2886 * @return if the argument is <code>null</code>, then a string equal to
2887 * <code>"null"</code>; otherwise, the value of
2888 * <code>obj.toString()</code> is returned.
2889 * @see java.lang.Object#toString()
2891 public static String valueOf(Object obj) {
2892 return (obj == null) ? "null" : obj.toString();
2896 * Returns the string representation of the <code>char</code> array
2897 * argument. The contents of the character array are copied; subsequent
2898 * modification of the character array does not affect the newly
2901 * @param data a <code>char</code> array.
2902 * @return a newly allocated string representing the same sequence of
2903 * characters contained in the character array argument.
2905 public static String valueOf(char data[]) {
2906 return new String(data);
2910 * Returns the string representation of a specific subarray of the
2911 * <code>char</code> array argument.
2913 * The <code>offset</code> argument is the index of the first
2914 * character of the subarray. The <code>count</code> argument
2915 * specifies the length of the subarray. The contents of the subarray
2916 * are copied; subsequent modification of the character array does not
2917 * affect the newly created string.
2919 * @param data the character array.
2920 * @param offset the initial offset into the value of the
2921 * <code>String</code>.
2922 * @param count the length of the value of the <code>String</code>.
2923 * @return a string representing the sequence of characters contained
2924 * in the subarray of the character array argument.
2925 * @exception IndexOutOfBoundsException if <code>offset</code> is
2926 * negative, or <code>count</code> is negative, or
2927 * <code>offset+count</code> is larger than
2928 * <code>data.length</code>.
2930 public static String valueOf(char data[], int offset, int count) {
2931 return new String(data, offset, count);
2935 * Returns a String that represents the character sequence in the
2938 * @param data the character array.
2939 * @param offset initial offset of the subarray.
2940 * @param count length of the subarray.
2941 * @return a <code>String</code> that contains the characters of the
2942 * specified subarray of the character array.
2944 public static String copyValueOf(char data[], int offset, int count) {
2945 // All public String constructors now copy the data.
2946 return new String(data, offset, count);
2950 * Returns a String that represents the character sequence in the
2953 * @param data the character array.
2954 * @return a <code>String</code> that contains the characters of the
2957 public static String copyValueOf(char data[]) {
2958 return copyValueOf(data, 0, data.length);
2962 * Returns the string representation of the <code>boolean</code> argument.
2964 * @param b a <code>boolean</code>.
2965 * @return if the argument is <code>true</code>, a string equal to
2966 * <code>"true"</code> is returned; otherwise, a string equal to
2967 * <code>"false"</code> is returned.
2969 public static String valueOf(boolean b) {
2970 return b ? "true" : "false";
2974 * Returns the string representation of the <code>char</code>
2977 * @param c a <code>char</code>.
2978 * @return a string of length <code>1</code> containing
2979 * as its single character the argument <code>c</code>.
2981 public static String valueOf(char c) {
2983 return new String(data, 0, 1);
2987 * Returns the string representation of the <code>int</code> argument.
2989 * The representation is exactly the one returned by the
2990 * <code>Integer.toString</code> method of one argument.
2992 * @param i an <code>int</code>.
2993 * @return a string representation of the <code>int</code> argument.
2994 * @see java.lang.Integer#toString(int, int)
2996 public static String valueOf(int i) {
2997 return Integer.toString(i);
3001 * Returns the string representation of the <code>long</code> argument.
3003 * The representation is exactly the one returned by the
3004 * <code>Long.toString</code> method of one argument.
3006 * @param l a <code>long</code>.
3007 * @return a string representation of the <code>long</code> argument.
3008 * @see java.lang.Long#toString(long)
3010 public static String valueOf(long l) {
3011 return Long.toString(l);
3015 * Returns the string representation of the <code>float</code> argument.
3017 * The representation is exactly the one returned by the
3018 * <code>Float.toString</code> method of one argument.
3020 * @param f a <code>float</code>.
3021 * @return a string representation of the <code>float</code> argument.
3022 * @see java.lang.Float#toString(float)
3024 public static String valueOf(float f) {
3025 return Float.toString(f);
3029 * Returns the string representation of the <code>double</code> argument.
3031 * The representation is exactly the one returned by the
3032 * <code>Double.toString</code> method of one argument.
3034 * @param d a <code>double</code>.
3035 * @return a string representation of the <code>double</code> argument.
3036 * @see java.lang.Double#toString(double)
3038 public static String valueOf(double d) {
3039 return Double.toString(d);
3043 * Returns a canonical representation for the string object.
3045 * A pool of strings, initially empty, is maintained privately by the
3046 * class <code>String</code>.
3048 * When the intern method is invoked, if the pool already contains a
3049 * string equal to this <code>String</code> object as determined by
3050 * the {@link #equals(Object)} method, then the string from the pool is
3051 * returned. Otherwise, this <code>String</code> object is added to the
3052 * pool and a reference to this <code>String</code> object is returned.
3054 * It follows that for any two strings <code>s</code> and <code>t</code>,
3055 * <code>s.intern() == t.intern()</code> is <code>true</code>
3056 * if and only if <code>s.equals(t)</code> is <code>true</code>.
3058 * All literal strings and string-valued constant expressions are
3059 * interned. String literals are defined in section 3.10.5 of the
3060 * <cite>The Java™ Language Specification</cite>.
3062 * @return a string that has the same contents as this string, but is
3063 * guaranteed to be from a pool of unique strings.
3065 public native String intern();