/*

 * Copyright (c) 2000, 2013, 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.nio.charset;

import java.nio.ByteBuffer;

import java.nio.CharBuffer;

import java.nio.charset.spi.CharsetProvider;

import java.security.AccessController;

import java.security.PrivilegedAction;

import java.util.Arrays;

import java.util.Collections;

import java.util.HashSet;

import java.util.Iterator;

import java.util.Locale;

import java.util.Map;

import java.util.NoSuchElementException;

import java.util.Objects;

import java.util.Set;

import java.util.ServiceLoader;

import java.util.ServiceConfigurationError;

import java.util.SortedMap;

import java.util.TreeMap;

import sun.misc.ASCIICaseInsensitiveComparator;

import sun.nio.cs.StandardCharsets;

import sun.nio.cs.ThreadLocalCoders;

import sun.security.action.GetPropertyAction;

/**

 * A named mapping between sequences of sixteen-bit Unicode <a

 * href="../../lang/Character.html#unicode">code units</a> and sequences of

 * bytes.  This class defines methods for creating decoders and encoders and

 * for retrieving the various names associated with a charset.  Instances of

 * this class are immutable.

 *

 * <p> This class also defines static methods for testing whether a particular

 * charset is supported, for locating charset instances by name, and for

 * constructing a map that contains every charset for which support is

 * available in the current Java virtual machine.  Support for new charsets can

 * be added via the service-provider interface defined in the {@link

 * java.nio.charset.spi.CharsetProvider} class.

 *

 * <p> All of the methods defined in this class are safe for use by multiple

 * concurrent threads.

 *

 *

 * <a name="names"></a><a name="charenc"></a>

 * <h2>Charset names</h2>

 *

 * <p> Charsets are named by strings composed of the following characters:

 *

 * <ul>

 *

 *   <li> The uppercase letters {@code 'A'} through {@code 'Z'}

 *        (<code>'&#92;u0041'</code>&nbsp;through&nbsp;<code>'&#92;u005a'</code>),

 *

 *   <li> The lowercase letters {@code 'a'} through {@code 'z'}

 *        (<code>'&#92;u0061'</code>&nbsp;through&nbsp;<code>'&#92;u007a'</code>),

 *

 *   <li> The digits {@code '0'} through {@code '9'}

 *        (<code>'&#92;u0030'</code>&nbsp;through&nbsp;<code>'&#92;u0039'</code>),

 *

 *   <li> The dash character {@code '-'}

 *        (<code>'&#92;u002d'</code>,&nbsp;<small>HYPHEN-MINUS</small>),

 *

 *   <li> The plus character {@code '+'}

 *        (<code>'&#92;u002b'</code>,&nbsp;<small>PLUS SIGN</small>),

 *

 *   <li> The period character {@code '.'}

 *        (<code>'&#92;u002e'</code>,&nbsp;<small>FULL STOP</small>),

 *

 *   <li> The colon character {@code ':'}

 *        (<code>'&#92;u003a'</code>,&nbsp;<small>COLON</small>), and

 *

 *   <li> The underscore character {@code '_'}

 *        (<code>'&#92;u005f'</code>,&nbsp;<small>LOW&nbsp;LINE</small>).

 *

 * </ul>

 *

 * A charset name must begin with either a letter or a digit.  The empty string

 * is not a legal charset name.  Charset names are not case-sensitive; that is,

 * case is always ignored when comparing charset names.  Charset names

 * generally follow the conventions documented in <a

 * href="http://www.ietf.org/rfc/rfc2278.txt"><i>RFC&nbsp;2278:&nbsp;IANA Charset

 * Registration Procedures</i></a>.

 *

 * <p> Every charset has a <i>canonical name</i> and may also have one or more

 * <i>aliases</i>.  The canonical name is returned by the {@link #name() name} method

 * of this class.  Canonical names are, by convention, usually in upper case.

 * The aliases of a charset are returned by the {@link #aliases() aliases}

 * method.

 *

 * <p><a name="hn">Some charsets have an <i>historical name</i> that is defined for

 * compatibility with previous versions of the Java platform.</a>  A charset's

 * historical name is either its canonical name or one of its aliases.  The

 * historical name is returned by the {@code getEncoding()} methods of the

 * {@link java.io.InputStreamReader#getEncoding InputStreamReader} and {@link

 * java.io.OutputStreamWriter#getEncoding OutputStreamWriter} classes.

 *

 * <p><a name="iana"> </a>If a charset listed in the <a

 * href="http://www.iana.org/assignments/character-sets"><i>IANA Charset

 * Registry</i></a> is supported by an implementation of the Java platform then

 * its canonical name must be the name listed in the registry. Many charsets

 * are given more than one name in the registry, in which case the registry

 * identifies one of the names as <i>MIME-preferred</i>.  If a charset has more

 * than one registry name then its canonical name must be the MIME-preferred

 * name and the other names in the registry must be valid aliases.  If a

 * supported charset is not listed in the IANA registry then its canonical name

 * must begin with one of the strings {@code "X-"} or {@code "x-"}.

 *

 * <p> The IANA charset registry does change over time, and so the canonical

 * name and the aliases of a particular charset may also change over time.  To

 * ensure compatibility it is recommended that no alias ever be removed from a

 * charset, and that if the canonical name of a charset is changed then its

 * previous canonical name be made into an alias.

 *

 *

 * <h2>Standard charsets</h2>

 *

 *

 *

 * <p><a name="standard">Every implementation of the Java platform is required to support the

 * following standard charsets.</a>  Consult the release documentation for your

 * implementation to see if any other charsets are supported.  The behavior

 * of such optional charsets may differ between implementations.

 *

 * <blockquote><table width="80%" summary="Description of standard charsets">

 * <tr><th align="left">Charset</th><th align="left">Description</th></tr>

 * <tr><td valign=top>{@code US-ASCII}</td>

 *     <td>Seven-bit ASCII, a.k.a. {@code ISO646-US},

 *         a.k.a. the Basic Latin block of the Unicode character set</td></tr>

 * <tr><td valign=top><code>ISO-8859-1&nbsp;&nbsp;</code></td>

 *     <td>ISO Latin Alphabet No. 1, a.k.a. {@code ISO-LATIN-1}</td></tr>

 * <tr><td valign=top>{@code UTF-8}</td>

 *     <td>Eight-bit UCS Transformation Format</td></tr>

 * <tr><td valign=top>{@code UTF-16BE}</td>

 *     <td>Sixteen-bit UCS Transformation Format,

 *         big-endian byte&nbsp;order</td></tr>

 * <tr><td valign=top>{@code UTF-16LE}</td>

 *     <td>Sixteen-bit UCS Transformation Format,

 *         little-endian byte&nbsp;order</td></tr>

 * <tr><td valign=top>{@code UTF-16}</td>

 *     <td>Sixteen-bit UCS Transformation Format,

 *         byte&nbsp;order identified by an optional byte-order mark</td></tr>

 * </table></blockquote>

 *

 * <p> The {@code UTF-8} charset is specified by <a

 * href="http://www.ietf.org/rfc/rfc2279.txt"><i>RFC&nbsp;2279</i></a>; the

 * transformation format upon which it is based is specified in

 * Amendment&nbsp;2 of ISO&nbsp;10646-1 and is also described in the <a

 * href="http://www.unicode.org/unicode/standard/standard.html"><i>Unicode

 * Standard</i></a>.

 *

 * <p> The {@code UTF-16} charsets are specified by <a

 * href="http://www.ietf.org/rfc/rfc2781.txt"><i>RFC&nbsp;2781</i></a>; the

 * transformation formats upon which they are based are specified in

 * Amendment&nbsp;1 of ISO&nbsp;10646-1 and are also described in the <a

 * href="http://www.unicode.org/unicode/standard/standard.html"><i>Unicode

 * Standard</i></a>.

 *

 * <p> The {@code UTF-16} charsets use sixteen-bit quantities and are

 * therefore sensitive to byte order.  In these encodings the byte order of a

 * stream may be indicated by an initial <i>byte-order mark</i> represented by

 * the Unicode character <code>'&#92;uFEFF'</code>.  Byte-order marks are handled

 * as follows:

 *

 * <ul>

 *

 *   <li><p> When decoding, the {@code UTF-16BE} and {@code UTF-16LE}

 *   charsets interpret the initial byte-order marks as a <small>ZERO-WIDTH

 *   NON-BREAKING SPACE</small>; when encoding, they do not write

 *   byte-order marks. </p></li>

 *

 *   <li><p> When decoding, the {@code UTF-16} charset interprets the

 *   byte-order mark at the beginning of the input stream to indicate the

 *   byte-order of the stream but defaults to big-endian if there is no

 *   byte-order mark; when encoding, it uses big-endian byte order and writes

 *   a big-endian byte-order mark. </p></li>

 *

 * </ul>

 *

 * In any case, byte order marks occurring after the first element of an

 * input sequence are not omitted since the same code is used to represent

 * <small>ZERO-WIDTH NON-BREAKING SPACE</small>.

 *

 * <p> Every instance of the Java virtual machine has a default charset, which

 * may or may not be one of the standard charsets.  The default charset is

 * determined during virtual-machine startup and typically depends upon the

 * locale and charset being used by the underlying operating system. </p>

 *

 * <p>The {@link StandardCharsets} class defines constants for each of the

 * standard charsets.

 *

 * <h2>Terminology</h2>

 *

 * <p> The name of this class is taken from the terms used in

 * <a href="http://www.ietf.org/rfc/rfc2278.txt"><i>RFC&nbsp;2278</i></a>.

 * In that document a <i>charset</i> is defined as the combination of

 * one or more coded character sets and a character-encoding scheme.

 * (This definition is confusing; some other software systems define

 * <i>charset</i> as a synonym for <i>coded character set</i>.)

 *

 * <p> A <i>coded character set</i> is a mapping between a set of abstract

 * characters and a set of integers.  US-ASCII, ISO 8859-1,

 * JIS X 0201, and Unicode are examples of coded character sets.

 *

 * <p> Some standards have defined a <i>character set</i> to be simply a

 * set of abstract characters without an associated assigned numbering.

 * An alphabet is an example of such a character set.  However, the subtle

 * distinction between <i>character set</i> and <i>coded character set</i>

 * is rarely used in practice; the former has become a short form for the

 * latter, including in the Java API specification.

 *

 * <p> A <i>character-encoding scheme</i> is a mapping between one or more

 * coded character sets and a set of octet (eight-bit byte) sequences.

 * UTF-8, UTF-16, ISO 2022, and EUC are examples of

 * character-encoding schemes.  Encoding schemes are often associated with

 * a particular coded character set; UTF-8, for example, is used only to

 * encode Unicode.  Some schemes, however, are associated with multiple

 * coded character sets; EUC, for example, can be used to encode

 * characters in a variety of Asian coded character sets.

 *

 * <p> When a coded character set is used exclusively with a single

 * character-encoding scheme then the corresponding charset is usually

 * named for the coded character set; otherwise a charset is usually named

 * for the encoding scheme and, possibly, the locale of the coded

 * character sets that it supports.  Hence {@code US-ASCII} is both the

 * name of a coded character set and of the charset that encodes it, while

 * {@code EUC-JP} is the name of the charset that encodes the

 * JIS X 0201, JIS X 0208, and JIS X 0212

 * coded character sets for the Japanese language.

 *

 * <p> The native character encoding of the Java programming language is

 * UTF-16.  A charset in the Java platform therefore defines a mapping

 * between sequences of sixteen-bit UTF-16 code units (that is, sequences

 * of chars) and sequences of bytes. </p>

 *

 *

 * @author Mark Reinhold

 * @author JSR-51 Expert Group

 * @since 1.4

 *

 * @see CharsetDecoder

 * @see CharsetEncoder

 * @see java.nio.charset.spi.CharsetProvider

 * @see java.lang.Character

 */

public abstract class Charset

    implements Comparable<Charset>

{

    /* -- Static methods -- */

    static boolean atBugLevel(String bl) {              // package-private

        String level = bugLevel;

        if (level == null) {

            if (!sun.misc.VM.isBooted())

                return false;

            bugLevel = level = AccessController.doPrivileged(

                new GetPropertyAction("sun.nio.cs.bugLevel", ""));

        }

        return level.equals(bl);

    }

    /**

     * Checks that the given string is a legal charset name. </p>

     *

     * @param  s

     *         A purported charset name

     *

     * @throws  IllegalCharsetNameException

     *          If the given name is not a legal charset name

     */

    private static void checkName(String s) {

        int n = s.length();

        if (!atBugLevel("1.4")) {

            if (n == 0)

                throw new IllegalCharsetNameException(s);

        }

        for (int i = 0; i < n; i++) {

            char c = s.charAt(i);

            if (c >= 'A' && c <= 'Z') continue;

            if (c >= 'a' && c <= 'z') continue;

            if (c >= '0' && c <= '9') continue;

            if (c == '-' && i != 0) continue;

            if (c == '+' && i != 0) continue;

            if (c == ':' && i != 0) continue;

            if (c == '_' && i != 0) continue;

            if (c == '.' && i != 0) continue;

            throw new IllegalCharsetNameException(s);

        }

    }

    /* The standard set of charsets */

    private static CharsetProvider standardProvider = new StandardCharsets();

    // Cache of the most-recently-returned charsets,

    // along with the names that were used to find them

    //

    private static void cache(String charsetName, Charset cs) {

        cache2 = cache1;

        cache1 = new Object[] { charsetName, cs };

    }

    // Creates an iterator that walks over the available providers, ignoring

    // those whose lookup or instantiation causes a security exception to be

    // thrown.  Should be invoked with full privileges.

    //

    private static Iterator<CharsetProvider> providers() {

        return new Iterator<>() {

                ClassLoader cl = ClassLoader.getSystemClassLoader();

                ServiceLoader<CharsetProvider> sl =

                    ServiceLoader.load(CharsetProvider.class, cl);

                Iterator<CharsetProvider> i = sl.iterator();

                CharsetProvider next = null;

                private boolean getNext() {

                    while (next == null) {

                        try {

                            if (!i.hasNext())

                                return false;

                            next = i.next();

                        } catch (ServiceConfigurationError sce) {

                            if (sce.getCause() instanceof SecurityException) {

                                // Ignore security exceptions

                                continue;

                            }

                            throw sce;

                        }

                    }

                    return true;

                }

                public boolean hasNext() {

                    return getNext();

                }

                public CharsetProvider next() {

                    if (!getNext())

                        throw new NoSuchElementException();

                    CharsetProvider n = next;

                    next = null;

                    return n;

                }

                public void remove() {

                    throw new UnsupportedOperationException();

                }

            };

    }

    // Thread-local gate to prevent recursive provider lookups

    private static ThreadLocal<ThreadLocal<?>> gate =

            new ThreadLocal<ThreadLocal<?>>();

    private static Charset lookupViaProviders(final String charsetName) {

        // The runtime startup sequence looks up standard charsets as a

        // consequence of the VM's invocation of System.initializeSystemClass

        // in order to, e.g., set system properties and encode filenames.  At

        // that point the application class loader has not been initialized,

        // however, so we can't look for providers because doing so will cause

        // that loader to be prematurely initialized with incomplete

        // information.

        //

        if (!sun.misc.VM.isBooted())

            return null;

        if (gate.get() != null)

            // Avoid recursive provider lookups

            return null;

        try {

            gate.set(gate);

            return AccessController.doPrivileged(

                new PrivilegedAction<>() {

                    public Charset run() {

                        for (Iterator<CharsetProvider> i = providers();

                             i.hasNext();) {

                            CharsetProvider cp = i.next();

                            Charset cs = cp.charsetForName(charsetName);

                            if (cs != null)

                                return cs;

                        }

                        return null;

                    }

                });

        } finally {

            gate.set(null);

        }

    }

    /* The extended set of charsets */

    private static class ExtendedProviderHolder {

        static final CharsetProvider[] extendedProviders = extendedProviders();

        // returns ExtendedProvider, if installed

        private static CharsetProvider[] extendedProviders() {

            return AccessController.doPrivileged(new PrivilegedAction<>() {

                    public CharsetProvider[] run() {

                        CharsetProvider[] cps = new CharsetProvider[1];

                        int n = 0;

                        ServiceLoader<CharsetProvider> sl =

                            ServiceLoader.loadInstalled(CharsetProvider.class);

                        for (CharsetProvider cp : sl) {

                            if (n + 1 > cps.length) {

                                cps = Arrays.copyOf(cps, cps.length << 1);

                            }

                            cps[n++] = cp;

                        }

                        return n == cps.length ? cps : Arrays.copyOf(cps, n);

                    }});

        }

    }

    private static Charset lookupExtendedCharset(String charsetName) {

        if (!sun.misc.VM.isBooted())  // see lookupViaProviders()

            return null;

        CharsetProvider[] ecps = ExtendedProviderHolder.extendedProviders;

        for (CharsetProvider cp : ecps) {

            Charset cs = cp.charsetForName(charsetName);

            if (cs != null)

                return cs;

        }

        return null;

    }

    private static Charset lookup(String charsetName) {

        if (charsetName == null)

            throw new IllegalArgumentException("Null charset name");

        Object[] a;

        if ((a = cache1) != null && charsetName.equals(a[0]))

            return (Charset)a[1];

        // We expect most programs to use one Charset repeatedly.

        // We convey a hint to this effect to the VM by putting the

        // level 1 cache miss code in a separate method.

        return lookup2(charsetName);

    }

    private static Charset lookup2(String charsetName) {

        Object[] a;

        if ((a = cache2) != null && charsetName.equals(a[0])) {

            cache2 = cache1;

            cache1 = a;

            return (Charset)a[1];

        }

        Charset cs;

        if ((cs = standardProvider.charsetForName(charsetName)) != null ||

            (cs = lookupExtendedCharset(charsetName))           != null ||

            (cs = lookupViaProviders(charsetName))              != null)

        {

            cache(charsetName, cs);

            return cs;

        }

        /* Only need to check the name if we didn't find a charset for it */

        checkName(charsetName);

        return null;

    }

    /**

     * Tells whether the named charset is supported.

     *

     * @param  charsetName

     *         The name of the requested charset; may be either

     *         a canonical name or an alias

     *

     * @return  {@code true} if, and only if, support for the named charset

     *          is available in the current Java virtual machine

     *

     * @throws IllegalCharsetNameException

     *         If the given charset name is illegal

     *

     * @throws  IllegalArgumentException

     *          If the given {@code charsetName} is null

     */

    public static boolean isSupported(String charsetName) {

        return (lookup(charsetName) != null);