/*

 * Copyright (c) 1996, 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.

 */

/*

 * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved

 * (C) Copyright IBM Corp. 1996 - 1998 - All Rights Reserved

 *

 * The original version of this source code and documentation

 * is copyrighted and owned by Taligent, Inc., a wholly-owned

 * subsidiary of IBM. These materials are provided under terms

 * of a License Agreement between Taligent and Sun. This technology

 * is protected by multiple US and International patents.

 *

 * This notice and attribution to Taligent may not be removed.

 * Taligent is a registered trademark of Taligent, Inc.

 *

 */

package java.util;

import java.io.IOException;

import java.io.ObjectInputStream;

import java.io.ObjectOutputStream;

import java.io.ObjectStreamField;

import java.io.Serializable;

import java.security.AccessController;

import java.text.MessageFormat;

import java.util.spi.LocaleNameProvider;

import sun.security.action.GetPropertyAction;

import sun.util.LocaleServiceProviderPool;

import sun.util.locale.AsciiUtil;

import sun.util.locale.BaseLocale;

import sun.util.locale.InternalLocaleBuilder;

import sun.util.locale.LanguageTag;

import sun.util.locale.LocaleExtensions;

import sun.util.locale.LocaleObjectCache;

import sun.util.locale.LocaleSyntaxException;

import sun.util.locale.ParseStatus;

import sun.util.locale.UnicodeLocaleExtension;

import sun.util.resources.LocaleData;

import sun.util.resources.OpenListResourceBundle;

/**

 * A <code>Locale</code> object represents a specific geographical, political,

 * or cultural region. An operation that requires a <code>Locale</code> to perform

 * its task is called <em>locale-sensitive</em> and uses the <code>Locale</code>

 * to tailor information for the user. For example, displaying a number

 * is a locale-sensitive operation— the number should be formatted

 * according to the customs and conventions of the user's native country,

 * region, or culture.

 *

 * <p> The <code>Locale</code> class implements identifiers

 * interchangeable with BCP 47 (IETF BCP 47, "Tags for Identifying

 * Languages"), with support for the LDML (UTS#35, "Unicode Locale

 * Data Markup Language") BCP 47-compatible extensions for locale data

 * exchange.

 *

 * <p> A <code>Locale</code> object logically consists of the fields

 * described below.

 *

 * <dl>

 *   <dt><a name="def_language"/><b>language</b></dt>

 *

 *   <dd>ISO 639 alpha-2 or alpha-3 language code, or registered

 *   language subtags up to 8 alpha letters (for future enhancements).

 *   When a language has both an alpha-2 code and an alpha-3 code, the

 *   alpha-2 code must be used.  You can find a full list of valid

 *   language codes in the IANA Language Subtag Registry (search for

 *   "Type: language").  The language field is case insensitive, but

 *   <code>Locale</code> always canonicalizes to lower case.</dd><br>

 *

 *   <dd>Well-formed language values have the form

 *   <code>[a-zA-Z]{2,8}</code>.  Note that this is not the the full

 *   BCP47 language production, since it excludes extlang.  They are

 *   not needed since modern three-letter language codes replace

 *   them.</dd><br>

 *

 *   <dd>Example: "en" (English), "ja" (Japanese), "kok" (Konkani)</dd><br>

 *

 *   <dt><a name="def_script"/><b>script</b></dt>

 *

 *   <dd>ISO 15924 alpha-4 script code.  You can find a full list of

 *   valid script codes in the IANA Language Subtag Registry (search

 *   for "Type: script").  The script field is case insensitive, but

 *   <code>Locale</code> always canonicalizes to title case (the first

 *   letter is upper case and the rest of the letters are lower

 *   case).</dd><br>

 *

 *   <dd>Well-formed script values have the form

 *   <code>[a-zA-Z]{4}</code></dd><br>

 *

 *   <dd>Example: "Latn" (Latin), "Cyrl" (Cyrillic)</dd><br>

 *

 *   <dt><a name="def_region"/><b>country (region)</b></dt>

 *

 *   <dd>ISO 3166 alpha-2 country code or UN M.49 numeric-3 area code.

 *   You can find a full list of valid country and region codes in the

 *   IANA Language Subtag Registry (search for "Type: region").  The

 *   country (region) field is case insensitive, but

 *   <code>Locale</code> always canonicalizes to upper case.</dd><br>

 *

 *   <dd>Well-formed country/region values have

 *   the form <code>[a-zA-Z]{2} | [0-9]{3}</code></dd><br>

 *

 *   <dd>Example: "US" (United States), "FR" (France), "029"

 *   (Caribbean)</dd><br>

 *

 *   <dt><a name="def_variant"/><b>variant</b></dt>

 *

 *   <dd>Any arbitrary value used to indicate a variation of a

 *   <code>Locale</code>.  Where there are two or more variant values

 *   each indicating its own semantics, these values should be ordered

 *   by importance, with most important first, separated by

 *   underscore('_').  The variant field is case sensitive.</dd><br>

 *

 *   <dd>Note: IETF BCP 47 places syntactic restrictions on variant

 *   subtags.  Also BCP 47 subtags are strictly used to indicate

 *   additional variations that define a language or its dialects that

 *   are not covered by any combinations of language, script and

 *   region subtags.  You can find a full list of valid variant codes

 *   in the IANA Language Subtag Registry (search for "Type: variant").

 *

 *   <p>However, the variant field in <code>Locale</code> has

 *   historically been used for any kind of variation, not just

 *   language variations.  For example, some supported variants

 *   available in Java SE Runtime Environments indicate alternative

 *   cultural behaviors such as calendar type or number script.  In

 *   BCP 47 this kind of information, which does not identify the

 *   language, is supported by extension subtags or private use

 *   subtags.</dd><br>

 *

 *   <dd>Well-formed variant values have the form <code>SUBTAG

 *   (('_'|'-') SUBTAG)*</code> where <code>SUBTAG =

 *   [0-9][0-9a-zA-Z]{3} | [0-9a-zA-Z]{5,8}</code>. (Note: BCP 47 only

 *   uses hyphen ('-') as a delimiter, this is more lenient).</dd><br>

 *

 *   <dd>Example: "polyton" (Polytonic Greek), "POSIX"</dd><br>

 *

 *   <dt><a name="def_extensions"/><b>extensions</b></dt>

 *

 *   <dd>A map from single character keys to string values, indicating

 *   extensions apart from language identification.  The extensions in

 *   <code>Locale</code> implement the semantics and syntax of BCP 47

 *   extension subtags and private use subtags. The extensions are

 *   case insensitive, but <code>Locale</code> canonicalizes all

 *   extension keys and values to lower case. Note that extensions

 *   cannot have empty values.</dd><br>

 *

 *   <dd>Well-formed keys are single characters from the set

 *   <code>[0-9a-zA-Z]</code>.  Well-formed values have the form

 *   <code>SUBTAG ('-' SUBTAG)*</code> where for the key 'x'

 *   <code>SUBTAG = [0-9a-zA-Z]{1,8}</code> and for other keys

 *   <code>SUBTAG = [0-9a-zA-Z]{2,8}</code> (that is, 'x' allows

 *   single-character subtags).</dd><br>

 *

 *   <dd>Example: key="u"/value="ca-japanese" (Japanese Calendar),

 *   key="x"/value="java-1-7"</dd>

 * </dl>

 *

 * <b>Note:</b> Although BCP 47 requires field values to be registered

 * in the IANA Language Subtag Registry, the <code>Locale</code> class

 * does not provide any validation features.  The <code>Builder</code>

 * only checks if an individual field satisfies the syntactic

 * requirement (is well-formed), but does not validate the value

 * itself.  See {@link Builder} for details.

 *

 * <h4><a name="def_locale_extension">Unicode locale/language extension</h4>

 *

 * <p>UTS#35, "Unicode Locale Data Markup Language" defines optional

 * attributes and keywords to override or refine the default behavior

 * associated with a locale.  A keyword is represented by a pair of

 * key and type.  For example, "nu-thai" indicates that Thai local

 * digits (value:"thai") should be used for formatting numbers

 * (key:"nu").

 *

 * <p>The keywords are mapped to a BCP 47 extension value using the

 * extension key 'u' ({@link #UNICODE_LOCALE_EXTENSION}).  The above

 * example, "nu-thai", becomes the extension "u-nu-thai".code

 *

 * <p>Thus, when a <code>Locale</code> object contains Unicode locale

 * attributes and keywords,

 * <code>getExtension(UNICODE_LOCALE_EXTENSION)</code> will return a

 * String representing this information, for example, "nu-thai".  The

 * <code>Locale</code> class also provides {@link

 * #getUnicodeLocaleAttributes}, {@link #getUnicodeLocaleKeys}, and

 * {@link #getUnicodeLocaleType} which allow you to access Unicode

 * locale attributes and key/type pairs directly.  When represented as

 * a string, the Unicode Locale Extension lists attributes

 * alphabetically, followed by key/type sequences with keys listed

 * alphabetically (the order of subtags comprising a key's type is

 * fixed when the type is defined)

 *

 * <p>A well-formed locale key has the form

 * <code>[0-9a-zA-Z]{2}</code>.  A well-formed locale type has the

 * form <code>"" | [0-9a-zA-Z]{3,8} ('-' [0-9a-zA-Z]{3,8})*</code> (it

 * can be empty, or a series of subtags 3-8 alphanums in length).  A

 * well-formed locale attribute has the form

 * <code>[0-9a-zA-Z]{3,8}</code> (it is a single subtag with the same

 * form as a locale type subtag).

 *

 * <p>The Unicode locale extension specifies optional behavior in

 * locale-sensitive services.  Although the LDML specification defines

 * various keys and values, actual locale-sensitive service

 * implementations in a Java Runtime Environment might not support any

 * particular Unicode locale attributes or key/type pairs.

 *

 * <h4>Creating a Locale</h4>

 *

 * <p>There are several different ways to create a <code>Locale</code>

 * object.

 *

 * <h5>Builder</h5>

 *

 * <p>Using {@link Builder} you can construct a <code>Locale</code> object

 * that conforms to BCP 47 syntax.

 *

 * <h5>Constructors</h5>

 *

 * <p>The <code>Locale</code> class provides three constructors:

 * <blockquote>

 * <pre>

 *     {@link #Locale(String language)}

 *     {@link #Locale(String language, String country)}

 *     {@link #Locale(String language, String country, String variant)}

 * </pre>

 * </blockquote>

 * These constructors allow you to create a <code>Locale</code> object

 * with language, country and variant, but you cannot specify

 * script or extensions.

 *

 * <h5>Factory Methods</h5>

 *

 * <p>The method {@link #forLanguageTag} creates a <code>Locale</code>

 * object for a well-formed BCP 47 language tag.

 *

 * <h5>Locale Constants</h5>

 *

 * <p>The <code>Locale</code> class provides a number of convenient constants

 * that you can use to create <code>Locale</code> objects for commonly used

 * locales. For example, the following creates a <code>Locale</code> object

 * for the United States:

 * <blockquote>

 * <pre>

 *     Locale.US

 * </pre>

 * </blockquote>

 *

 * <h4>Use of Locale</h4>

 *

 * <p>Once you've created a <code>Locale</code> you can query it for information

 * about itself. Use <code>getCountry</code> to get the country (or region)

 * code and <code>getLanguage</code> to get the language code.

 * You can use <code>getDisplayCountry</code> to get the

 * name of the country suitable for displaying to the user. Similarly,

 * you can use <code>getDisplayLanguage</code> to get the name of

 * the language suitable for displaying to the user. Interestingly,

 * the <code>getDisplayXXX</code> methods are themselves locale-sensitive

 * and have two versions: one that uses the default locale and one

 * that uses the locale specified as an argument.

 *

 * <p>The Java Platform provides a number of classes that perform locale-sensitive

 * operations. For example, the <code>NumberFormat</code> class formats

 * numbers, currency, and percentages in a locale-sensitive manner. Classes

 * such as <code>NumberFormat</code> have several convenience methods

 * for creating a default object of that type. For example, the

 * <code>NumberFormat</code> class provides these three convenience methods

 * for creating a default <code>NumberFormat</code> object:

 * <blockquote>

 * <pre>

 *     NumberFormat.getInstance()

 *     NumberFormat.getCurrencyInstance()

 *     NumberFormat.getPercentInstance()

 * </pre>

 * </blockquote>

 * Each of these methods has two variants; one with an explicit locale

 * and one without; the latter uses the default locale:

 * <blockquote>

 * <pre>

 *     NumberFormat.getInstance(myLocale)

 *     NumberFormat.getCurrencyInstance(myLocale)

 *     NumberFormat.getPercentInstance(myLocale)

 * </pre>

 * </blockquote>

 * A <code>Locale</code> is the mechanism for identifying the kind of object

 * (<code>NumberFormat</code>) that you would like to get. The locale is

 * <STRONG>just</STRONG> a mechanism for identifying objects,

 * <STRONG>not</STRONG> a container for the objects themselves.

 *

 * <h4>Compatibility</h4>

 *

 * <p>In order to maintain compatibility with existing usage, Locale's

 * constructors retain their behavior prior to the Java Runtime

 * Environment version 1.7.  The same is largely true for the

 * <code>toString</code> method. Thus Locale objects can continue to

 * be used as they were. In particular, clients who parse the output

 * of toString into language, country, and variant fields can continue

 * to do so (although this is strongly discouraged), although the

 * variant field will have additional information in it if script or

 * extensions are present.

 *

 * <p>In addition, BCP 47 imposes syntax restrictions that are not

 * imposed by Locale's constructors. This means that conversions

 * between some Locales and BCP 47 language tags cannot be made without

 * losing information. Thus <code>toLanguageTag</code> cannot

 * represent the state of locales whose language, country, or variant

 * do not conform to BCP 47.

 *

 * <p>Because of these issues, it is recommended that clients migrate

 * away from constructing non-conforming locales and use the

 * <code>forLanguageTag</code> and <code>Locale.Builder</code> APIs instead.

 * Clients desiring a string representation of the complete locale can

 * then always rely on <code>toLanguageTag</code> for this purpose.

 *

 * <h5><a name="special_cases_constructor"/>Special cases</h5>

 *

 * <p>For compatibility reasons, two

 * non-conforming locales are treated as special cases.  These are

 * <b><tt>ja_JP_JP</tt></b> and <b><tt>th_TH_TH</tt></b>. These are ill-formed

 * in BCP 47 since the variants are too short. To ease migration to BCP 47,

 * these are treated specially during construction.  These two cases (and only

 * these) cause a constructor to generate an extension, all other values behave

 * exactly as they did prior to Java 7.

 *

 * <p>Java has used <tt>ja_JP_JP</tt> to represent Japanese as used in

 * Japan together with the Japanese Imperial calendar. This is now

 * representable using a Unicode locale extension, by specifying the

 * Unicode locale key <tt>ca</tt> (for "calendar") and type

 * <tt>japanese</tt>. When the Locale constructor is called with the

 * arguments "ja", "JP", "JP", the extension "u-ca-japanese" is

 * automatically added.

 *

 * <p>Java has used <tt>th_TH_TH</tt> to represent Thai as used in

 * Thailand together with Thai digits. This is also now representable using

 * a Unicode locale extension, by specifying the Unicode locale key

 * <tt>nu</tt> (for "number") and value <tt>thai</tt>. When the Locale

 * constructor is called with the arguments "th", "TH", "TH", the

 * extension "u-nu-thai" is automatically added.

 *

 * <h5>Serialization</h5>

 *

 * <p>During serialization, writeObject writes all fields to the output

 * stream, including extensions.

 *

 * <p>During deserialization, readResolve adds extensions as described

 * in <a href="#special_cases_constructor">Special Cases</a>, only

 * for the two cases th_TH_TH and ja_JP_JP.

 *

 * <h5>Legacy language codes</h5>

 *

 * <p>Locale's constructor has always converted three language codes to

 * their earlier, obsoleted forms: <tt>he</tt> maps to <tt>iw</tt>,

 * <tt>yi</tt> maps to <tt>ji</tt>, and <tt>id</tt> maps to

 * <tt>in</tt>.  This continues to be the case, in order to not break

 * backwards compatibility.

 *

 * <p>The APIs added in 1.7 map between the old and new language codes,

 * maintaining the old codes internal to Locale (so that

 * <code>getLanguage</code> and <code>toString</code> reflect the old

 * code), but using the new codes in the BCP 47 language tag APIs (so

 * that <code>toLanguageTag</code> reflects the new one). This

 * preserves the equivalence between Locales no matter which code or

 * API is used to construct them. Java's default resource bundle

 * lookup mechanism also implements this mapping, so that resources

 * can be named using either convention, see {@link ResourceBundle.Control}.

 *

 * <h5>Three-letter language/country(region) codes</h5>

 *

 * <p>The Locale constructors have always specified that the language

 * and the country param be two characters in length, although in

 * practice they have accepted any length.  The specification has now

 * been relaxed to allow language codes of two to eight characters and

 * country (region) codes of two to three characters, and in

 * particular, three-letter language codes and three-digit region

 * codes as specified in the IANA Language Subtag Registry.  For

 * compatibility, the implementation still does not impose a length

 * constraint.

 *

 * @see Builder

 * @see ResourceBundle

 * @see java.text.Format

 * @see java.text.NumberFormat

 * @see java.text.Collator

 * @author Mark Davis

 * @since 1.1

 */

public final class Locale implements Cloneable, Serializable {

    static private final  Cache LOCALECACHE = new Cache();

    /** Useful constant for language.

     */

    static public final Locale ENGLISH = getInstance("en", "", "");

    /** Useful constant for language.

     */

    static public final Locale FRENCH = getInstance("fr", "", "");

    /** Useful constant for language.

     */

    static public final Locale GERMAN = getInstance("de", "", "");

    /** Useful constant for language.

     */

    static public final Locale ITALIAN = getInstance("it", "", "");

    /** Useful constant for language.

     */

    static public final Locale JAPANESE = getInstance("ja", "", "");

    /** Useful constant for language.

     */

    static public final Locale KOREAN = getInstance("ko", "", "");

    /** Useful constant for language.

     */

    static public final Locale CHINESE = getInstance("zh", "", "");

    /** Useful constant for language.

     */

    static public final Locale SIMPLIFIED_CHINESE = getInstance("zh", "CN", "");

    /** Useful constant for language.

     */

    static public final Locale TRADITIONAL_CHINESE = getInstance("zh", "TW", "");

    /** Useful constant for country.

     */

    static public final Locale FRANCE = getInstance("fr", "FR", "");

    /** Useful constant for country.

     */

    static public final Locale GERMANY = getInstance("de", "DE", "");

    /** Useful constant for country.

     */

    static public final Locale ITALY = getInstance("it", "IT", "");

    /** Useful constant for country.

     */

    static public final Locale JAPAN = getInstance("ja", "JP", "");

    /** Useful constant for country.

     */

    static public final Locale KOREA = getInstance("ko", "KR", "");

    /** Useful constant for country.

     */

    static public final Locale CHINA = SIMPLIFIED_CHINESE;

    /** Useful constant for country.

     */

    static public final Locale PRC = SIMPLIFIED_CHINESE;

    /** Useful constant for country.

     */

    static public final Locale TAIWAN = TRADITIONAL_CHINESE;

    /** Useful constant for country.

     */

    static public final Locale UK = getInstance("en", "GB", "");

    /** Useful constant for country.

     */

    static public final Locale US = getInstance("en", "US", "");

    /** Useful constant for country.

     */

    static public final Locale CANADA = getInstance("en", "CA", "");

    /** Useful constant for country.

     */

    static public final Locale CANADA_FRENCH = getInstance("fr", "CA", "");

    /**

     * Useful constant for the root locale.  The root locale is the locale whose

     * language, country, and variant are empty ("") strings.  This is regarded

     * as the base locale of all locales, and is used as the language/country