/*

 * Copyright (c) 1994, 2010, Oracle and/or its affiliates. All rights reserved.

 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.

 *

 * This code is free software; you can redistribute it and/or modify it

 * under the terms of the GNU General Public License version 2 only, as

 * published by the Free Software Foundation.  Oracle designates this

 * particular file as subject to the "Classpath" exception as provided

 * by Oracle in the LICENSE file that accompanied this code.

 *

 * This code is distributed in the hope that it will be useful, but WITHOUT

 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

 * version 2 for more details (a copy is included in the LICENSE file that

 * accompanied this code).

 *

 * You should have received a copy of the GNU General Public License version

 * 2 along with this work; if not, write to the Free Software Foundation,

 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.

 *

 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA

 * or visit www.oracle.com if you need additional information or have any

 * questions.

 */

package java.lang;

import java.io.UnsupportedEncodingException;

import java.util.Comparator;

import org.apidesign.bck2brwsr.core.ExtraJavaScript;

import org.apidesign.bck2brwsr.core.JavaScriptBody;

import org.apidesign.bck2brwsr.core.JavaScriptOnly;

import org.apidesign.bck2brwsr.core.JavaScriptPrototype;

import org.apidesign.bck2brwsr.emul.lang.System;

/**

 * The <code>String</code> class represents character strings. All

 * string literals in Java programs, such as <code>"abc"</code>, are

 * implemented as instances of this class.

 * <p>

 * Strings are constant; their values cannot be changed after they

 * are created. String buffers support mutable strings.

 * Because String objects are immutable they can be shared. For example:

 * <p><blockquote><pre>

 *     String str = "abc";

 * </pre></blockquote><p>

 * is equivalent to:

 * <p><blockquote><pre>

 *     char data[] = {'a', 'b', 'c'};

 *     String str = new String(data);

 * </pre></blockquote><p>

 * Here are some more examples of how strings can be used:

 * <p><blockquote><pre>

 *     System.out.println("abc");

 *     String cde = "cde";

 *     System.out.println("abc" + cde);

 *     String c = "abc".substring(2,3);

 *     String d = cde.substring(1, 2);

 * </pre></blockquote>

 * <p>

 * The class <code>String</code> includes methods for examining

 * individual characters of the sequence, for comparing strings, for

 * searching strings, for extracting substrings, and for creating a

 * copy of a string with all characters translated to uppercase or to

 * lowercase. Case mapping is based on the Unicode Standard version

 * specified by the {@link java.lang.Character Character} class.

 * <p>

 * The Java language provides special support for the string

 * concatenation operator ( + ), and for conversion of

 * other objects to strings. String concatenation is implemented

 * through the <code>StringBuilder</code>(or <code>StringBuffer</code>)

 * class and its <code>append</code> method.

 * String conversions are implemented through the method

 * <code>toString</code>, defined by <code>Object</code> and

 * inherited by all classes in Java. For additional information on

 * string concatenation and conversion, see Gosling, Joy, and Steele,

 * <i>The Java Language Specification</i>.

 *

 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor

 * or method in this class will cause a {@link NullPointerException} to be

 * thrown.

 *

 * <p>A <code>String</code> represents a string in the UTF-16 format

 * in which <em>supplementary characters</em> are represented by <em>surrogate

 * pairs</em> (see the section <a href="Character.html#unicode">Unicode

 * Character Representations</a> in the <code>Character</code> class for

 * more information).

 * Index values refer to <code>char</code> code units, so a supplementary

 * character uses two positions in a <code>String</code>.

 * <p>The <code>String</code> class provides methods for dealing with

 * Unicode code points (i.e., characters), in addition to those for

 * dealing with Unicode code units (i.e., <code>char</code> values).

 *

 * @author  Lee Boynton

 * @author  Arthur van Hoff

 * @author  Martin Buchholz

 * @author  Ulf Zibis

 * @see     java.lang.Object#toString()

 * @see     java.lang.StringBuffer

 * @see     java.lang.StringBuilder

 * @see     java.nio.charset.Charset

 * @since   JDK1.0

 */

@ExtraJavaScript(

    resource="/org/apidesign/vm4brwsr/emul/lang/java_lang_String.js",

    processByteCode=true

)

@JavaScriptPrototype(container = "String.prototype", prototype = "new String")

public final class String

    implements java.io.Serializable, Comparable<String>, CharSequence

{

    /** real string to delegate to */

    private Object r;

    /** use serialVersionUID from JDK 1.0.2 for interoperability */

    private static final long serialVersionUID = -6849794470754667710L;

    static {

        registerToString();

    }

    @JavaScriptBody(args = {}, body = 

          "var p = vm.java_lang_String(false);\n"

        + "p.toString = function() {\nreturn this._r().toString();\n};\n"

        + "p.valueOf = function() {\nreturn this._r().valueOf();\n}\n"

    )

    private static native void registerToString();

    /**

     * Class String is special cased within the Serialization Stream Protocol.

     *

     * A String instance is written initially into an ObjectOutputStream in the

     * following format:

     * <pre>

     *      <code>TC_STRING</code> (utf String)

     * </pre>

     * The String is written by method <code>DataOutput.writeUTF</code>.

     * A new handle is generated to  refer to all future references to the

     * string instance within the stream.

     */

//    private static final ObjectStreamField[] serialPersistentFields =

//        new ObjectStreamField[0];

    /**

     * Initializes a newly created {@code String} object so that it represents

     * an empty character sequence.  Note that use of this constructor is

     * unnecessary since Strings are immutable.

     */

    public String() {

        this.r = "";

    }

    /**

     * Initializes a newly created {@code String} object so that it represents

     * the same sequence of characters as the argument; in other words, the

     * newly created string is a copy of the argument string. Unless an

     * explicit copy of {@code original} is needed, use of this constructor is

     * unnecessary since Strings are immutable.

     *

     * @param  original

     *         A {@code String}

     */

    public String(String original) {

        this.r = original.toString();

    }

    /**

     * Allocates a new {@code String} so that it represents the sequence of

     * characters currently contained in the character array argument. The

     * contents of the character array are copied; subsequent modification of

     * the character array does not affect the newly created string.

     *

     * @param  value

     *         The initial value of the string

     */

    @JavaScriptBody(args = { "charArr" }, body=

        "for (var i = 0; i < charArr.length; i++) {\n"

      + "  if (typeof charArr[i] === 'number') charArr[i] = String.fromCharCode(charArr[i]);\n"

      + "}\n"

      + "this._r(charArr.join(''));\n"

    )

    public String(char value[]) {

    }

    /**

     * Allocates a new {@code String} that contains characters from a subarray

     * of the character array argument. The {@code offset} argument is the

     * index of the first character of the subarray and the {@code count}

     * argument specifies the length of the subarray. The contents of the

     * subarray are copied; subsequent modification of the character array does

     * not affect the newly created string.

     *

     * @param  value

     *         Array that is the source of characters

     *

     * @param  offset

     *         The initial offset

     *

     * @param  count

     *         The length

     *

     * @throws  IndexOutOfBoundsException

     *          If the {@code offset} and {@code count} arguments index

     *          characters outside the bounds of the {@code value} array

     */

    public String(char value[], int offset, int count) {

        initFromCharArray(value, offset, count);

    }

    @JavaScriptBody(args = { "charArr", "off", "cnt" }, body =

        "var up = off + cnt;\n" +

        "for (var i = off; i < up; i++) {\n" +

        "  if (typeof charArr[i] === 'number') charArr[i] = String.fromCharCode(charArr[i]);\n" +

        "}\n" +

        "this._r(charArr.slice(off, up).join(\"\"));\n"

    )

    private native void initFromCharArray(char value[], int offset, int count);

    /**

     * Allocates a new {@code String} that contains characters from a subarray

     * of the <a href="Character.html#unicode">Unicode code point</a> array

     * argument.  The {@code offset} argument is the index of the first code

     * point of the subarray and the {@code count} argument specifies the

     * length of the subarray.  The contents of the subarray are converted to

     * {@code char}s; subsequent modification of the {@code int} array does not

     * affect the newly created string.

     *

     * @param  codePoints

     *         Array that is the source of Unicode code points

     *

     * @param  offset

     *         The initial offset

     *

     * @param  count

     *         The length

     *

     * @throws  IllegalArgumentException

     *          If any invalid Unicode code point is found in {@code

     *          codePoints}

     *

     * @throws  IndexOutOfBoundsException

     *          If the {@code offset} and {@code count} arguments index

     *          characters outside the bounds of the {@code codePoints} array

     *

     * @since  1.5

     */

    public String(int[] codePoints, int offset, int count) {

        if (offset < 0) {

            throw new StringIndexOutOfBoundsException(offset);

        }

        if (count < 0) {

            throw new StringIndexOutOfBoundsException(count);

        }

        // Note: offset or count might be near -1>>>1.

        if (offset > codePoints.length - count) {

            throw new StringIndexOutOfBoundsException(offset + count);

        }

        final int end = offset + count;

        // Pass 1: Compute precise size of char[]

        int n = count;

        for (int i = offset; i < end; i++) {

            int c = codePoints[i];

            if (Character.isBmpCodePoint(c))

                continue;

            else if (Character.isValidCodePoint(c))

                n++;

            else throw new IllegalArgumentException(Integer.toString(c));

        }

        // Pass 2: Allocate and fill in char[]

        final char[] v = new char[n];

        for (int i = offset, j = 0; i < end; i++, j++) {

            int c = codePoints[i];

            if (Character.isBmpCodePoint(c))

                v[j] = (char) c;

            else

                Character.toSurrogates(c, v, j++);

        }

        this.r = new String(v, 0, n);

    }

    /**

     * Allocates a new {@code String} constructed from a subarray of an array

     * of 8-bit integer values.

     *

     * <p> The {@code offset} argument is the index of the first byte of the

     * subarray, and the {@code count} argument specifies the length of the

     * subarray.

     *

     * <p> Each {@code byte} in the subarray is converted to a {@code char} as

     * specified in the method above.

     *

     * @deprecated This method does not properly convert bytes into characters.

     * As of JDK 1.1, the preferred way to do this is via the

     * {@code String} constructors that take a {@link

     * java.nio.charset.Charset}, charset name, or that use the platform's

     * default charset.

     *

     * @param  ascii

     *         The bytes to be converted to characters

     *

     * @param  hibyte

     *         The top 8 bits of each 16-bit Unicode code unit

     *

     * @param  offset

     *         The initial offset

     * @param  count

     *         The length

     *

     * @throws  IndexOutOfBoundsException

     *          If the {@code offset} or {@code count} argument is invalid

     *

     * @see  #String(byte[], int)

     * @see  #String(byte[], int, int, java.lang.String)

     * @see  #String(byte[], int, int, java.nio.charset.Charset)

     * @see  #String(byte[], int, int)

     * @see  #String(byte[], java.lang.String)

     * @see  #String(byte[], java.nio.charset.Charset)

     * @see  #String(byte[])

     */

    @Deprecated

    public String(byte ascii[], int hibyte, int offset, int count) {

        checkBounds(ascii, offset, count);

        char value[] = new char[count];

        if (hibyte == 0) {

            for (int i = count ; i-- > 0 ;) {

                value[i] = (char) (ascii[i + offset] & 0xff);

            }

        } else {

            hibyte <<= 8;

            for (int i = count ; i-- > 0 ;) {

                value[i] = (char) (hibyte | (ascii[i + offset] & 0xff));

            }

        }

        initFromCharArray(value, offset, count);

    }

    /**

     * Allocates a new {@code String} containing characters constructed from

     * an array of 8-bit integer values. Each character <i>c</i>in the

     * resulting string is constructed from the corresponding component

     * <i>b</i> in the byte array such that:

     *

     * <blockquote><pre>

     *     <b><i>c</i></b> == (char)(((hibyte &amp; 0xff) &lt;&lt; 8)

     *                         | (<b><i>b</i></b> &amp; 0xff))

     * </pre></blockquote>

     *

     * @deprecated  This method does not properly convert bytes into

     * characters.  As of JDK 1.1, the preferred way to do this is via the

     * {@code String} constructors that take a {@link

     * java.nio.charset.Charset}, charset name, or that use the platform's

     * default charset.

     *

     * @param  ascii

     *         The bytes to be converted to characters

     *

     * @param  hibyte

     *         The top 8 bits of each 16-bit Unicode code unit

     *

     * @see  #String(byte[], int, int, java.lang.String)

     * @see  #String(byte[], int, int, java.nio.charset.Charset)

     * @see  #String(byte[], int, int)

     * @see  #String(byte[], java.lang.String)

     * @see  #String(byte[], java.nio.charset.Charset)

     * @see  #String(byte[])

     */

    @Deprecated

    public String(byte ascii[], int hibyte) {

        this(ascii, hibyte, 0, ascii.length);

    }

    /* Common private utility method used to bounds check the byte array

     * and requested offset & length values used by the String(byte[],..)

     * constructors.

     */

    private static void checkBounds(byte[] bytes, int offset, int length) {

        if (length < 0)

            throw new StringIndexOutOfBoundsException(length);

        if (offset < 0)

            throw new StringIndexOutOfBoundsException(offset);

        if (offset > bytes.length - length)

            throw new StringIndexOutOfBoundsException(offset + length);

    }

    /**

     * Constructs a new {@code String} by decoding the specified subarray of

     * bytes using the specified charset.  The length of the new {@code String}

     * is a function of the charset, and hence may not be equal to the length

     * of the subarray.

     *

     * <p> The behavior of this constructor when the given bytes are not valid

     * in the given charset is unspecified.  The {@link

     * java.nio.charset.CharsetDecoder} class should be used when more control

     * over the decoding process is required.

     *

     * @param  bytes

     *         The bytes to be decoded into characters

     *

     * @param  offset

     *         The index of the first byte to decode

     *

     * @param  length

     *         The number of bytes to decode

     * @param  charsetName

     *         The name of a supported {@linkplain java.nio.charset.Charset

     *         charset}

     *

     * @throws  UnsupportedEncodingException

     *          If the named charset is not supported

     *

     * @throws  IndexOutOfBoundsException

     *          If the {@code offset} and {@code length} arguments index

     *          characters outside the bounds of the {@code bytes} array

     *

     * @since  JDK1.1

     */

    public String(byte bytes[], int offset, int length, String charsetName)

        throws UnsupportedEncodingException

    {

        this(checkUTF8(bytes, charsetName), offset, length);

    }

    /**

     * Constructs a new {@code String} by decoding the specified subarray of

     * bytes using the specified {@linkplain java.nio.charset.Charset charset}.

     * The length of the new {@code String} is a function of the charset, and

     * hence may not be equal to the length of the subarray.

     *

     * <p> This method always replaces malformed-input and unmappable-character

     * sequences with this charset's default replacement string.  The {@link

     * java.nio.charset.CharsetDecoder} class should be used when more control

     * over the decoding process is required.

     *

     * @param  bytes

     *         The bytes to be decoded into characters

     *

     * @param  offset

     *         The index of the first byte to decode

     *

     * @param  length

     *         The number of bytes to decode

     *

     * @param  charset

     *         The {@linkplain java.nio.charset.Charset charset} to be used to

     *         decode the {@code bytes}

     *

     * @throws  IndexOutOfBoundsException

     *          If the {@code offset} and {@code length} arguments index

     *          characters outside the bounds of the {@code bytes} array

     *

     * @since  1.6

     */

    /* don't want dependnecy on Charset

    public String(byte bytes[], int offset, int length, Charset charset) {

        if (charset == null)

            throw new NullPointerException("charset");

        checkBounds(bytes, offset, length);

        char[] v = StringCoding.decode(charset, bytes, offset, length);

        this.offset = 0;

        this.count = v.length;

        this.value = v;

    }

    */

    /**

     * Constructs a new {@code String} by decoding the specified array of bytes

     * using the specified {@linkplain java.nio.charset.Charset charset}.  The

     * length of the new {@code String} is a function of the charset, and hence

     * may not be equal to the length of the byte array.

     *

     * <p> The behavior of this constructor when the given bytes are not valid

     * in the given charset is unspecified.  The {@link

     * java.nio.charset.CharsetDecoder} class should be used when more control

     * over the decoding process is required.

     *

     * @param  bytes

     *         The bytes to be decoded into characters

     *

     * @param  charsetName

     *         The name of a supported {@linkplain java.nio.charset.Charset

     *         charset}

     *

     * @throws  UnsupportedEncodingException

     *          If the named charset is not supported

     *

     * @since  JDK1.1

     */

    public String(byte bytes[], String charsetName)

        throws UnsupportedEncodingException

    {

        this(bytes, 0, bytes.length, charsetName);

    }

    /**

     * Constructs a new {@code String} by decoding the specified array of

     * bytes using the specified {@linkplain java.nio.charset.Charset charset}.

     * The length of the new {@code String} is a function of the charset, and

     * hence may not be equal to the length of the byte array.

     *

     * <p> This method always replaces malformed-input and unmappable-character

     * sequences with this charset's default replacement string.  The {@link

     * java.nio.charset.CharsetDecoder} class should be used when more control

     * over the decoding process is required.

     *

     * @param  bytes

     *         The bytes to be decoded into characters

     *

     * @param  charset

     *         The {@linkplain java.nio.charset.Charset charset} to be used to

     *         decode the {@code bytes}

     *

     * @since  1.6

     */

    /* don't want dep on Charset

    public String(byte bytes[], Charset charset) {

        this(bytes, 0, bytes.length, charset);

    }

    */

    /**

     * Constructs a new {@code String} by decoding the specified subarray of

     * bytes using the platform's default charset.  The length of the new

     * {@code String} is a function of the charset, and hence may not be equal

     * to the length of the subarray.

     *

     * <p> The behavior of this constructor when the given bytes are not valid

     * in the default charset is unspecified.  The {@link

     * java.nio.charset.CharsetDecoder} class should be used when more control

     * over the decoding process is required.

     *

     * @param  bytes

     *         The bytes to be decoded into characters

     *

     * @param  offset

     *         The index of the first byte to decode

     *

     * @param  length

     *         The number of bytes to decode

     *

     * @throws  IndexOutOfBoundsException

     *          If the {@code offset} and the {@code length} arguments index

     *          characters outside the bounds of the {@code bytes} array

     *

     * @since  JDK1.1

     */

    public String(byte bytes[], int offset, int length) {

        checkBounds(bytes, offset, length);

        char[] v  = new char[length];

        int[] at = { offset };

        int end = offset + length;

        int chlen = 0;

        while (at[0] < end) {

            int ch = nextChar(bytes, at);

            v[chlen++] = (char)ch;

        }

        initFromCharArray(v, 0, chlen);

    }

    /**

     * Constructs a new {@code String} by decoding the specified array of bytes

     * using the platform's default charset.  The length of the new {@code

     * String} is a function of the charset, and hence may not be equal to the

     * length of the byte array.

     *

     * <p> The behavior of this constructor when the given bytes are not valid

     * in the default charset is unspecified.  The {@link

     * java.nio.charset.CharsetDecoder} class should be used when more control

     * over the decoding process is required.

     *

     * @param  bytes

     *         The bytes to be decoded into characters

     *

     * @since  JDK1.1

     */

    public String(byte bytes[]) {

        this(bytes, 0, bytes.length);

    }

    /**

     * Allocates a new string that contains the sequence of characters

     * currently contained in the string buffer argument. The contents of the

     * string buffer are copied; subsequent modification of the string buffer

     * does not affect the newly created string.

     *

     * @param  buffer

     *         A {@code StringBuffer}

     */

    public String(StringBuffer buffer) {

        this.r = buffer.toString();

    }

    /**

     * Allocates a new string that contains the sequence of characters

     * currently contained in the string builder argument. The contents of the

     * string builder are copied; subsequent modification of the string builder

     * does not affect the newly created string.

     *

     * <p> This constructor is provided to ease migration to {@code

     * StringBuilder}. Obtaining a string from a string builder via the {@code

     * toString} method is likely to run faster and is generally preferred.

     *

     * @param   builder

     *          A {@code StringBuilder}

     *

     * @since  1.5

     */

    public String(StringBuilder builder) {

        this.r = builder.toString();

    }

    /**

     * Returns the length of this string.

     * The length is equal to the number of <a href="Character.html#unicode">Unicode

     * code units</a> in the string.

     *

     * @return  the length of the sequence of characters represented by this

     *          object.

     */

    @JavaScriptBody(args = {}, body = "return this.toString().length;")

    public int length() {

        throw new UnsupportedOperationException();

    }

    /**

     * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>.

     *

     * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise

     * <tt>false</tt>

     *

     * @since 1.6

     */

    @JavaScriptBody(args = {}, body="return this.toString().length === 0;")

    public boolean isEmpty() {

        return length() == 0;

    }

    /**

     * Returns the <code>char</code> value at the

     * specified index. An index ranges from <code>0</code> to

     * <code>length() - 1</code>. The first <code>char</code> value of the sequence

     * is at index <code>0</code>, the next at index <code>1</code>,

     * and so on, as for array indexing.

     *

     * <p>If the <code>char</code> value specified by the index is a

     * <a href="Character.html#unicode">surrogate</a>, the surrogate

     * value is returned.

     *

     * @param      index   the index of the <code>char</code> value.

     * @return     the <code>char</code> value at the specified index of this string.

     *             The first <code>char</code> value is at index <code>0</code>.

     * @exception  IndexOutOfBoundsException  if the <code>index</code>

     *             argument is negative or not less than the length of this

     *             string.

     */

    @JavaScriptBody(args = { "index" }, 

        body = "return this.toString().charCodeAt(index);"

    )

    public char charAt(int index) {

        throw new UnsupportedOperationException();

    }

    /**

     * Returns the character (Unicode code point) at the specified

     * index. The index refers to <code>char</code> values

     * (Unicode code units) and ranges from <code>0</code> to

     * {@link #length()}<code> - 1</code>.

     *

     * <p> If the <code>char</code> value specified at the given index

     * is in the high-surrogate range, the following index is less

     * than the length of this <code>String</code>, and the

     * <code>char</code> value at the following index is in the

     * low-surrogate range, then the supplementary code point

     * corresponding to this surrogate pair is returned. Otherwise,

     * the <code>char</code> value at the given index is returned.

     *

     * @param      index the index to the <code>char</code> values

     * @return     the code point value of the character at the

     *             <code>index</code>

     * @exception  IndexOutOfBoundsException  if the <code>index</code>

     *             argument is negative or not less than the length of this

     *             string.

     * @since      1.5

     */

    public int codePointAt(int index) {

        if ((index < 0) || (index >= length())) {

            throw new StringIndexOutOfBoundsException(index);

        }

        return Character.codePointAtImpl(toCharArray(), offset() + index, offset() + length());

    }

    /**

     * Returns the character (Unicode code point) before the specified

     * index. The index refers to <code>char</code> values

     * (Unicode code units) and ranges from <code>1</code> to {@link

     * CharSequence#length() length}.

     *

     * <p> If the <code>char</code> value at <code>(index - 1)</code>

     * is in the low-surrogate range, <code>(index - 2)</code> is not

     * negative, and the <code>char</code> value at <code>(index -

     * 2)</code> is in the high-surrogate range, then the

     * supplementary code point value of the surrogate pair is

     * returned. If the <code>char</code> value at <code>index -

     * 1</code> is an unpaired low-surrogate or a high-surrogate, the

     * surrogate value is returned.

     *

     * @param     index the index following the code point that should be returned

     * @return    the Unicode code point value before the given index.

     * @exception IndexOutOfBoundsException if the <code>index</code>

     *            argument is less than 1 or greater than the length

     *            of this string.

     * @since     1.5

     */

    public int codePointBefore(int index) {

        int i = index - 1;

        if ((i < 0) || (i >= length())) {

            throw new StringIndexOutOfBoundsException(index);

        }

        return Character.codePointBeforeImpl(toCharArray(), offset() + index, offset());

    }

    /**

     * Returns the number of Unicode code points in the specified text

     * range of this <code>String</code>. The text range begins at the

     * specified <code>beginIndex</code> and extends to the

     * <code>char</code> at index <code>endIndex - 1</code>. Thus the

     * length (in <code>char</code>s) of the text range is

     * <code>endIndex-beginIndex</code>. Unpaired surrogates within

     * the text range count as one code point each.

     *

     * @param beginIndex the index to the first <code>char</code> of

     * the text range.

     * @param endIndex the index after the last <code>char</code> of

     * the text range.

     * @return the number of Unicode code points in the specified text

     * range

     * @exception IndexOutOfBoundsException if the

     * <code>beginIndex</code> is negative, or <code>endIndex</code>

     * is larger than the length of this <code>String</code>, or

     * <code>beginIndex</code> is larger than <code>endIndex</code>.

     * @since  1.5

     */

    public int codePointCount(int beginIndex, int endIndex) {

        if (beginIndex < 0 || endIndex > length() || beginIndex > endIndex) {

            throw new IndexOutOfBoundsException();

        }

        return Character.codePointCountImpl(toCharArray(), offset()+beginIndex, endIndex-beginIndex);

    }

    /**

     * Returns the index within this <code>String</code> that is

     * offset from the given <code>index</code> by

     * <code>codePointOffset</code> code points. Unpaired surrogates

     * within the text range given by <code>index</code> and

     * <code>codePointOffset</code> count as one code point each.

     *

     * @param index the index to be offset

     * @param codePointOffset the offset in code points

     * @return the index within this <code>String</code>

     * @exception IndexOutOfBoundsException if <code>index</code>

     *   is negative or larger then the length of this

     *   <code>String</code>, or if <code>codePointOffset</code> is positive

     *   and the substring starting with <code>index</code> has fewer

     *   than <code>codePointOffset</code> code points,

     *   or if <code>codePointOffset</code> is negative and the substring

     *   before <code>index</code> has fewer than the absolute value

     *   of <code>codePointOffset</code> code points.

     * @since 1.5

     */

    public int offsetByCodePoints(int index, int codePointOffset) {

        if (index < 0 || index > length()) {

            throw new IndexOutOfBoundsException();

        }

        return Character.offsetByCodePointsImpl(toCharArray(), offset(), length(),

                                                offset()+index, codePointOffset) - offset();

    }

    /**

     * Copy characters from this string into dst starting at dstBegin.

     * This method doesn't perform any range checking.

     */

    @JavaScriptBody(args = { "arr", "to" }, body = 

        "var s = this.toString();\n" +

        "for (var i = 0; i < s.length; i++) {\n" +

        "   arr[to++] = s[i];\n" +

        "}"

    )

    void getChars(char dst[], int dstBegin) {

        System.arraycopy(toCharArray(), offset(), dst, dstBegin, length());

    }

    /**

     * Copies characters from this string into the destination character

     * array.

     * <p>

     * The first character to be copied is at index <code>srcBegin</code>;

     * the last character to be copied is at index <code>srcEnd-1</code>

     * (thus the total number of characters to be copied is

     * <code>srcEnd-srcBegin</code>). The characters are copied into the

     * subarray of <code>dst</code> starting at index <code>dstBegin</code>

     * and ending at index:

     * <p><blockquote><pre>

     *     dstbegin + (srcEnd-srcBegin) - 1

     * </pre></blockquote>

     *

     * @param      srcBegin   index of the first character in the string

     *                        to copy.

     * @param      srcEnd     index after the last character in the string

     *                        to copy.

     * @param      dst        the destination array.

     * @param      dstBegin   the start offset in the destination array.

     * @exception IndexOutOfBoundsException If any of the following

     *            is true:

     *            <ul><li><code>srcBegin</code> is negative.

     *            <li><code>srcBegin</code> is greater than <code>srcEnd</code>

     *            <li><code>srcEnd</code> is greater than the length of this

     *                string

     *            <li><code>dstBegin</code> is negative

     *            <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than

     *                <code>dst.length</code></ul>

     */

    @JavaScriptBody(args = { "beg", "end", "arr", "dst" }, body=

        "var s = this.toString();\n" +

        "while (beg < end) {\n" +

        "  arr[dst++] = s.charCodeAt(beg++);\n" +

        "}\n"

    )

    public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {

        if (srcBegin < 0) {

            throw new StringIndexOutOfBoundsException(srcBegin);

        }

        if (srcEnd > length()) {

            throw new StringIndexOutOfBoundsException(srcEnd);

        }

        if (srcBegin > srcEnd) {

            throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);

        }

        System.arraycopy(toCharArray(), offset() + srcBegin, dst, dstBegin,

             srcEnd - srcBegin);

    }

    /**

     * Copies characters from this string into the destination byte array. Each

     * byte receives the 8 low-order bits of the corresponding character. The

     * eight high-order bits of each character are not copied and do not

     * participate in the transfer in any way.

     *

     * <p> The first character to be copied is at index {@code srcBegin}; the

     * last character to be copied is at index {@code srcEnd-1}.  The total

     * number of characters to be copied is {@code srcEnd-srcBegin}. The

     * characters, converted to bytes, are copied into the subarray of {@code

     * dst} starting at index {@code dstBegin} and ending at index:

     *

     * <blockquote><pre>

     *     dstbegin + (srcEnd-srcBegin) - 1

     * </pre></blockquote>

     *

     * @deprecated  This method does not properly convert characters into

     * bytes.  As of JDK 1.1, the preferred way to do this is via the

     * {@link #getBytes()} method, which uses the platform's default charset.

     *

     * @param  srcBegin

     *         Index of the first character in the string to copy

     *

     * @param  srcEnd

     *         Index after the last character in the string to copy

     *

     * @param  dst

     *         The destination array

     *

     * @param  dstBegin

     *         The start offset in the destination array

     *

     * @throws  IndexOutOfBoundsException

     *          If any of the following is true:

     *          <ul>

     *            <li> {@code srcBegin} is negative

     *            <li> {@code srcBegin} is greater than {@code srcEnd}

     *            <li> {@code srcEnd} is greater than the length of this String

     *            <li> {@code dstBegin} is negative

     *            <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code

     *                 dst.length}

     *          </ul>

     */

    @Deprecated

    public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {

        if (srcBegin < 0) {

            throw new StringIndexOutOfBoundsException(srcBegin);

        }

        if (srcEnd > length()) {

            throw new StringIndexOutOfBoundsException(srcEnd);

        }

        if (srcBegin > srcEnd) {

            throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);

        }

        int j = dstBegin;

        int n = offset() + srcEnd;

        int i = offset() + srcBegin;

        char[] val = toCharArray();   /* avoid getfield opcode */

        while (i < n) {

            dst[j++] = (byte)val[i++];

        }

    }

    /**

     * Encodes this {@code String} into a sequence of bytes using the named

     * charset, storing the result into a new byte array.

     *

     * <p> The behavior of this method when this string cannot be encoded in

     * the given charset is unspecified.  The {@link

     * java.nio.charset.CharsetEncoder} class should be used when more control

     * over the encoding process is required.

     *

     * @param  charsetName

     *         The name of a supported {@linkplain java.nio.charset.Charset

     *         charset}

     *

     * @return  The resultant byte array

     *

     * @throws  UnsupportedEncodingException

     *          If the named charset is not supported

     *

     * @since  JDK1.1

     */

    public byte[] getBytes(String charsetName)

        throws UnsupportedEncodingException

    {

        checkUTF8(null, charsetName);

        return getBytes();

    }

    /**

     * Encodes this {@code String} into a sequence of bytes using the given

     * {@linkplain java.nio.charset.Charset charset}, storing the result into a

     * new byte array.

     *

     * <p> This method always replaces malformed-input and unmappable-character

     * sequences with this charset's default replacement byte array.  The

     * {@link java.nio.charset.CharsetEncoder} class should be used when more

     * control over the encoding process is required.

     *

     * @param  charset

     *         The {@linkplain java.nio.charset.Charset} to be used to encode

     *         the {@code String}

     *

     * @return  The resultant byte array

     *

     * @since  1.6

     */

    /* don't want dep on Charset

    public byte[] getBytes(Charset charset) {

        if (charset == null) throw new NullPointerException();

        return StringCoding.encode(charset, value, offset, count);

    }

    */

    /**

     * Encodes this {@code String} into a sequence of bytes using the

     * platform's default charset, storing the result into a new byte array.

     *

     * <p> The behavior of this method when this string cannot be encoded in

     * the default charset is unspecified.  The {@link

     * java.nio.charset.CharsetEncoder} class should be used when more control

     * over the encoding process is required.

     *

     * @return  The resultant byte array

     *

     * @since      JDK1.1

     */

    public byte[] getBytes() {

        int len = length();

        byte[] arr = new byte[len];

        for (int i = 0, j = 0; j < len; j++) {

            final int v = charAt(j);

            if (v < 128) {

                arr[i++] = (byte) v;

                continue;

            }

            if (v < 0x0800) {

                arr = System.expandArray(arr, i + 1);

                arr[i++] = (byte) (0xC0 | (v >> 6));

                arr[i++] = (byte) (0x80 | (0x3F & v));

                continue;

            }

            arr = System.expandArray(arr, i + 2);

            arr[i++] = (byte) (0xE0 | (v >> 12));