/* * Copyright (C) 2014 The Android Open Source Project * 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.io.UnsupportedEncodingException; import libcore.icu.NativeConverter; import java.nio.ByteBuffer; import java.nio.CharBuffer; import java.nio.charset.spi.CharsetProvider; import java.security.AccessController; import java.security.AccessControlException; import java.security.PrivilegedAction; import java.util.AbstractMap; import java.util.Collections; import java.util.HashMap; import java.util.HashSet; import java.util.Iterator; import java.util.Locale; import java.util.Map; import java.util.NoSuchElementException; 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.ThreadLocalCoders; import sun.security.action.GetPropertyAction; /** * A named mapping between sequences of sixteen-bit Unicode code units 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. * *

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. * *

All of the methods defined in this class are safe for use by multiple * concurrent threads. * * * *

Charset names

* *

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

* * 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 RFC 2278: IANA Charset * Registration Procedures. * *

Every charset has a canonical name and may also have one or more * aliases. 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. * *

Some charsets have an historical name that is defined for * compatibility with previous versions of the Java platform. A charset's * historical name is either its canonical name or one of its aliases. The * historical name is returned by the getEncoding() methods of the * {@link java.io.InputStreamReader#getEncoding InputStreamReader} and {@link * java.io.OutputStreamWriter#getEncoding OutputStreamWriter} classes. * *

If a charset listed in the IANA Charset * Registry 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 MIME-preferred. 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 "X-" or "x-". * *

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. * * *

Standard charsets

* * * *

Every implementation of the Java platform is required to support the * following standard charsets. 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. * *

* * * * * * * * * * * * * *
CharsetDescription
US-ASCIISeven-bit ASCII, a.k.a. ISO646-US, * a.k.a. the Basic Latin block of the Unicode character set
ISO-8859-1  ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1
UTF-8Eight-bit UCS Transformation Format
UTF-16BESixteen-bit UCS Transformation Format, * big-endian byte order
UTF-16LESixteen-bit UCS Transformation Format, * little-endian byte order
UTF-16Sixteen-bit UCS Transformation Format, * byte order identified by an optional byte-order mark
* *

The UTF-8 charset is specified by RFC 2279; the * transformation format upon which it is based is specified in * Amendment 2 of ISO 10646-1 and is also described in the Unicode * Standard. * *

The UTF-16 charsets are specified by RFC 2781; the * transformation formats upon which they are based are specified in * Amendment 1 of ISO 10646-1 and are also described in the Unicode * Standard. * *

The 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 byte-order mark represented by * the Unicode character '\uFEFF'. Byte-order marks are handled * as follows: * *

* * 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 * ZERO-WIDTH NON-BREAKING SPACE. * *

Android note: The Android platform default is always UTF-8. * *

The {@link StandardCharsets} class defines constants for each of the * standard charsets. * *

Terminology

* *

The name of this class is taken from the terms used in * RFC 2278. * In that document a charset 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 * charset as a synonym for coded character set.) * *

A coded character set 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. * *

Some standards have defined a character set 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 character set and coded character set * is rarely used in practice; the former has become a short form for the * latter, including in the Java API specification. * *

A character-encoding scheme 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. * *

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 US-ASCII is both the * name of a coded character set and of the charset that encodes it, while * 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. * *

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.

* * * @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 { /* -- Static methods -- */ private static volatile String bugLevel = null; 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.

* * @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 */ // Android-removed: We use ICU's list of standard charsets. // private static CharsetProvider standardProvider = new StandardCharsets(); // Cache of the most-recently-returned charsets, // along with the names that were used to find them // // cache1/2 usage is explained in the lookup method // private static volatile Map.Entry cache1 = null; // "Level 1" cache private static final HashMap cache2 = new HashMap<>(); // "Level 2" cache private static void cache(String charsetName, Charset cs) { synchronized(cache2) { String canonicalName = cs.name(); Charset canonicalCharset = cache2.get(canonicalName); if (canonicalCharset != null) { cs = canonicalCharset; } else { cache2.put(canonicalName, cs); for (String alias : cs.aliases()) { cache2.put(alias, cs); } } cache2.put(charsetName, cs); } cache1 = new AbstractMap.SimpleImmutableEntry<>(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 providers() { return new Iterator() { ServiceLoader sl = ServiceLoader.load(CharsetProvider.class); Iterator 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> gate = new 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 i = providers(); i.hasNext();) { CharsetProvider cp = i.next(); Charset cs = cp.charsetForName(charsetName); if (cs != null) return cs; } return null; } }); } finally { gate.set(null); } } // Android-removed: Remove support for the extended charset provider. // /* The extended set of charsets */ // private static Object extendedProviderLock = new Object(); // private static boolean extendedProviderProbed = false; // private static CharsetProvider extendedProvider = null; // // private static void probeExtendedProvider() { // AccessController.doPrivileged(new PrivilegedAction() { // public Object run() { // try { // Class epc // = Class.forName("sun.nio.cs.ext.ExtendedCharsets"); // extendedProvider = (CharsetProvider)epc.newInstance(); // } catch (ClassNotFoundException x) { // // Extended charsets not available // // (charsets.jar not present) // } catch (InstantiationException x) { // throw new Error(x); // } catch (IllegalAccessException x) { // throw new Error(x); // } // return null; // } // }); // } // // private static Charset lookupExtendedCharset(String charsetName) { // CharsetProvider ecp = null; // synchronized (extendedProviderLock) { // if (!extendedProviderProbed) { // probeExtendedProvider(); // extendedProviderProbed = true; // } // ecp = extendedProvider; // } // return (ecp != null) ? ecp.charsetForName(charsetName) : null; // } // We expect most programs to use one Charset repeatedly, so the most recently used Charset // instance is stored in the level 1 cache. We convey a hint to this effect to the VM by putting // the level 1 cache miss code in a separate method. Since charsetName is not necessarily in // canonical form, we store the mapping from both the canonical name and the aliases to the // instance in a map for level 2 cache. private static Charset lookup(String charsetName) { if (charsetName == null) throw new IllegalArgumentException("Null charset name"); final Map.Entry cached = cache1; if (cached != null && charsetName.equals(cached.getKey())) return cached.getValue(); return lookup2(charsetName); } private static Charset lookup2(String charsetName) { Charset cs; synchronized (cache2) { if ((cs = cache2.get(charsetName)) != null) { cache1 = new AbstractMap.SimpleImmutableEntry<>(charsetName, cs); return cs; } } // Android-changed: Drop support for "standard" and "extended" // providers. if ((cs = NativeConverter.charsetForName(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 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 charsetName is null */ public static boolean isSupported(String charsetName) { return (lookup(charsetName) != null); } /** * Returns a charset object for the named charset. * * @param charsetName * The name of the requested charset; may be either * a canonical name or an alias * * @return A charset object for the named charset * * @throws IllegalCharsetNameException * If the given charset name is illegal * * @throws IllegalArgumentException * If the given charsetName is null * * @throws UnsupportedCharsetException * If no support for the named charset is available * in this instance of the Java virtual machine */ public static Charset forName(String charsetName) { Charset cs = lookup(charsetName); if (cs != null) return cs; throw new UnsupportedCharsetException(charsetName); } /** * Equivalent to {@code forName} but only throws {@code UnsupportedEncodingException}, * which is all pre-nio code claims to throw. * * @hide internal use only */ public static Charset forNameUEE(String charsetName) throws UnsupportedEncodingException { try { return Charset.forName(charsetName); } catch (Exception cause) { UnsupportedEncodingException ex = new UnsupportedEncodingException(charsetName); ex.initCause(cause); throw ex; } } // Fold charsets from the given iterator into the given map, ignoring // charsets whose names already have entries in the map. // private static void put(Iterator i, Map m) { while (i.hasNext()) { Charset cs = i.next(); if (!m.containsKey(cs.name())) m.put(cs.name(), cs); } } /** * Constructs a sorted map from canonical charset names to charset objects. * *

The map returned by this method will have one entry for each charset * for which support is available in the current Java virtual machine. If * two or more supported charsets have the same canonical name then the * resulting map will contain just one of them; which one it will contain * is not specified.

* *

The invocation of this method, and the subsequent use of the * resulting map, may cause time-consuming disk or network I/O operations * to occur. This method is provided for applications that need to * enumerate all of the available charsets, for example to allow user * charset selection. This method is not used by the {@link #forName * forName} method, which instead employs an efficient incremental lookup * algorithm. * *

This method may return different results at different times if new * charset providers are dynamically made available to the current Java * virtual machine. In the absence of such changes, the charsets returned * by this method are exactly those that can be retrieved via the {@link * #forName forName} method.

* * @return An immutable, case-insensitive map from canonical charset names * to charset objects */ public static SortedMap availableCharsets() { return AccessController.doPrivileged( new PrivilegedAction>() { public SortedMap run() { TreeMap m = new TreeMap( ASCIICaseInsensitiveComparator.CASE_INSENSITIVE_ORDER); for (String charsetName : NativeConverter.getAvailableCharsetNames()) { Charset charset = NativeConverter.charsetForName(charsetName); m.put(charset.name(), charset); } // Android-changed: No more "standard" provider. // put(standardProvider.charsets(), m); for (Iterator i = providers(); i.hasNext();) { CharsetProvider cp = (CharsetProvider)i.next(); put(cp.charsets(), m); } return Collections.unmodifiableSortedMap(m); } }); } private static Charset defaultCharset; /** * Returns the default charset of this Java virtual machine. * *

Android note: The Android platform default is always UTF-8. * * @return A charset object for the default charset * * @since 1.5 */ public static Charset defaultCharset() { // Android-changed: Use UTF_8 unconditionally. synchronized (Charset.class) { if (defaultCharset == null) { defaultCharset = java.nio.charset.StandardCharsets.UTF_8; } return defaultCharset; } } /* -- Instance fields and methods -- */ private final String name; // tickles a bug in oldjavac private final String[] aliases; // tickles a bug in oldjavac private Set aliasSet = null; /** * Initializes a new charset with the given canonical name and alias * set. * * @param canonicalName * The canonical name of this charset * * @param aliases * An array of this charset's aliases, or null if it has no aliases * * @throws IllegalCharsetNameException * If the canonical name or any of the aliases are illegal */ protected Charset(String canonicalName, String[] aliases) { checkName(canonicalName); String[] as = (aliases == null) ? new String[0] : aliases; for (int i = 0; i < as.length; i++) checkName(as[i]); this.name = canonicalName; this.aliases = as; } /** * Returns this charset's canonical name. * * @return The canonical name of this charset */ public final String name() { return name; } /** * Returns a set containing this charset's aliases. * * @return An immutable set of this charset's aliases */ public final Set aliases() { if (aliasSet != null) return aliasSet; int n = aliases.length; HashSet hs = new HashSet(n); for (int i = 0; i < n; i++) hs.add(aliases[i]); aliasSet = Collections.unmodifiableSet(hs); return aliasSet; } /** * Returns this charset's human-readable name for the default locale. * *

The default implementation of this method simply returns this * charset's canonical name. Concrete subclasses of this class may * override this method in order to provide a localized display name.

* * @return The display name of this charset in the default locale */ public String displayName() { return name; } /** * Tells whether or not this charset is registered in the IANA Charset * Registry. * * @return true if, and only if, this charset is known by its * implementor to be registered with the IANA */ public final boolean isRegistered() { return !name.startsWith("X-") && !name.startsWith("x-"); } /** * Returns this charset's human-readable name for the given locale. * *

The default implementation of this method simply returns this * charset's canonical name. Concrete subclasses of this class may * override this method in order to provide a localized display name.

* * @param locale * The locale for which the display name is to be retrieved * * @return The display name of this charset in the given locale */ public String displayName(Locale locale) { return name; } /** * Tells whether or not this charset contains the given charset. * *

A charset C is said to contain a charset D if, * and only if, every character representable in D is also * representable in C. If this relationship holds then it is * guaranteed that every string that can be encoded in D can also be * encoded in C without performing any replacements. * *

That C contains D does not imply that each character * representable in C by a particular byte sequence is represented * in D by the same byte sequence, although sometimes this is the * case. * *

Every charset contains itself. * *

This method computes an approximation of the containment relation: * If it returns true then the given charset is known to be * contained by this charset; if it returns false, however, then * it is not necessarily the case that the given charset is not contained * in this charset. * * @param cs * The given charset * * @return true if the given charset is contained in this charset */ public abstract boolean contains(Charset cs); /** * Constructs a new decoder for this charset. * * @return A new decoder for this charset */ public abstract CharsetDecoder newDecoder(); /** * Constructs a new encoder for this charset. * * @return A new encoder for this charset * * @throws UnsupportedOperationException * If this charset does not support encoding */ public abstract CharsetEncoder newEncoder(); /** * Tells whether or not this charset supports encoding. * *

Nearly all charsets support encoding. The primary exceptions are * special-purpose auto-detect charsets whose decoders can determine * which of several possible encoding schemes is in use by examining the * input byte sequence. Such charsets do not support encoding because * there is no way to determine which encoding should be used on output. * Implementations of such charsets should override this method to return * false.

* * @return true if, and only if, this charset supports encoding */ public boolean canEncode() { return true; } /** * Convenience method that decodes bytes in this charset into Unicode * characters. * *

An invocation of this method upon a charset cs returns the * same result as the expression * *

     *     cs.newDecoder()
     *       .onMalformedInput(CodingErrorAction.REPLACE)
     *       .onUnmappableCharacter(CodingErrorAction.REPLACE)
     *       .decode(bb); 
* * except that it is potentially more efficient because it can cache * decoders between successive invocations. * *

This method always replaces malformed-input and unmappable-character * sequences with this charset's default replacement byte array. In order * to detect such sequences, use the {@link * CharsetDecoder#decode(java.nio.ByteBuffer)} method directly.

* * @param bb The byte buffer to be decoded * * @return A char buffer containing the decoded characters */ public final CharBuffer decode(ByteBuffer bb) { try { return ThreadLocalCoders.decoderFor(this) .onMalformedInput(CodingErrorAction.REPLACE) .onUnmappableCharacter(CodingErrorAction.REPLACE) .decode(bb); } catch (CharacterCodingException x) { throw new Error(x); // Can't happen } } /** * Convenience method that encodes Unicode characters into bytes in this * charset. * *

An invocation of this method upon a charset cs returns the * same result as the expression * *

     *     cs.newEncoder()
     *       .onMalformedInput(CodingErrorAction.REPLACE)
     *       .onUnmappableCharacter(CodingErrorAction.REPLACE)
     *       .encode(bb); 
* * except that it is potentially more efficient because it can cache * encoders between successive invocations. * *

This method always replaces malformed-input and unmappable-character * sequences with this charset's default replacement string. In order to * detect such sequences, use the {@link * CharsetEncoder#encode(java.nio.CharBuffer)} method directly.

* * @param cb The char buffer to be encoded * * @return A byte buffer containing the encoded characters */ public final ByteBuffer encode(CharBuffer cb) { try { return ThreadLocalCoders.encoderFor(this) .onMalformedInput(CodingErrorAction.REPLACE) .onUnmappableCharacter(CodingErrorAction.REPLACE) .encode(cb); } catch (CharacterCodingException x) { throw new Error(x); // Can't happen } } /** * Convenience method that encodes a string into bytes in this charset. * *

An invocation of this method upon a charset cs returns the * same result as the expression * *

     *     cs.encode(CharBuffer.wrap(s)); 
* * @param str The string to be encoded * * @return A byte buffer containing the encoded characters */ public final ByteBuffer encode(String str) { return encode(CharBuffer.wrap(str)); } /** * Compares this charset to another. * *

Charsets are ordered by their canonical names, without regard to * case.

* * @param that * The charset to which this charset is to be compared * * @return A negative integer, zero, or a positive integer as this charset * is less than, equal to, or greater than the specified charset */ public final int compareTo(Charset that) { return (name().compareToIgnoreCase(that.name())); } /** * Computes a hashcode for this charset. * * @return An integer hashcode */ public final int hashCode() { return name().hashCode(); } /** * Tells whether or not this object is equal to another. * *

Two charsets are equal if, and only if, they have the same canonical * names. A charset is never equal to any other type of object.

* * @return true if, and only if, this charset is equal to the * given object */ public final boolean equals(Object ob) { if (!(ob instanceof Charset)) return false; if (this == ob) return true; return name.equals(((Charset)ob).name()); } /** * Returns a string describing this charset. * * @return A string describing this charset */ public final String toString() { return name(); } }