1 | /* Charset.java --
|
---|
2 | Copyright (C) 2002 Free Software Foundation, Inc.
|
---|
3 |
|
---|
4 | This file is part of GNU Classpath.
|
---|
5 |
|
---|
6 | GNU Classpath is free software; you can redistribute it and/or modify
|
---|
7 | it under the terms of the GNU General Public License as published by
|
---|
8 | the Free Software Foundation; either version 2, or (at your option)
|
---|
9 | any later version.
|
---|
10 |
|
---|
11 | GNU Classpath is distributed in the hope that it will be useful, but
|
---|
12 | WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
13 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
---|
14 | General Public License for more details.
|
---|
15 |
|
---|
16 | You should have received a copy of the GNU General Public License
|
---|
17 | along with GNU Classpath; see the file COPYING. If not, write to the
|
---|
18 | Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
|
---|
19 | 02111-1307 USA.
|
---|
20 |
|
---|
21 | Linking this library statically or dynamically with other modules is
|
---|
22 | making a combined work based on this library. Thus, the terms and
|
---|
23 | conditions of the GNU General Public License cover the whole
|
---|
24 | combination.
|
---|
25 |
|
---|
26 | As a special exception, the copyright holders of this library give you
|
---|
27 | permission to link this library with independent modules to produce an
|
---|
28 | executable, regardless of the license terms of these independent
|
---|
29 | modules, and to copy and distribute the resulting executable under
|
---|
30 | terms of your choice, provided that you also meet, for each linked
|
---|
31 | independent module, the terms and conditions of the license of that
|
---|
32 | module. An independent module is a module which is not derived from
|
---|
33 | or based on this library. If you modify this library, you may extend
|
---|
34 | this exception to your version of the library, but you are not
|
---|
35 | obligated to do so. If you do not wish to do so, delete this
|
---|
36 | exception statement from your version. */
|
---|
37 |
|
---|
38 | package java.nio.charset;
|
---|
39 |
|
---|
40 | import java.nio.ByteBuffer;
|
---|
41 | import java.nio.CharBuffer;
|
---|
42 | import java.nio.charset.spi.CharsetProvider;
|
---|
43 | import java.util.Collections;
|
---|
44 | import java.util.HashSet;
|
---|
45 | import java.util.Iterator;
|
---|
46 | import java.util.Locale;
|
---|
47 | import java.util.Set;
|
---|
48 | import java.util.SortedMap;
|
---|
49 | import java.util.TreeMap;
|
---|
50 | import gnu.java.nio.charset.Provider;
|
---|
51 |
|
---|
52 | /**
|
---|
53 | * @author Jesse Rosenstock
|
---|
54 | * @since 1.4
|
---|
55 | */
|
---|
56 | public abstract class Charset implements Comparable
|
---|
57 | {
|
---|
58 | private static CharsetEncoder cachedEncoder;
|
---|
59 | private static CharsetDecoder cachedDecoder;
|
---|
60 |
|
---|
61 | static
|
---|
62 | {
|
---|
63 | synchronized (Charset.class)
|
---|
64 | {
|
---|
65 | cachedEncoder = null;
|
---|
66 | cachedDecoder = null;
|
---|
67 | }
|
---|
68 | }
|
---|
69 |
|
---|
70 | private final String canonicalName;
|
---|
71 | private final String[] aliases;
|
---|
72 |
|
---|
73 | protected Charset (String canonicalName, String[] aliases)
|
---|
74 | {
|
---|
75 | checkName (canonicalName);
|
---|
76 | if (aliases != null)
|
---|
77 | {
|
---|
78 | int n = aliases.length;
|
---|
79 | for (int i = 0; i < n; ++i)
|
---|
80 | checkName (aliases[i]);
|
---|
81 | }
|
---|
82 |
|
---|
83 | this.canonicalName = canonicalName;
|
---|
84 | this.aliases = aliases;
|
---|
85 | }
|
---|
86 |
|
---|
87 | /**
|
---|
88 | * @throws IllegalCharsetNameException if the name is illegal
|
---|
89 | */
|
---|
90 | private static void checkName (String name)
|
---|
91 | {
|
---|
92 | int n = name.length ();
|
---|
93 |
|
---|
94 | if (n == 0)
|
---|
95 | throw new IllegalCharsetNameException (name);
|
---|
96 |
|
---|
97 | char ch = name.charAt (0);
|
---|
98 | if (!(('A' <= ch && ch <= 'Z')
|
---|
99 | || ('a' <= ch && ch <= 'z')
|
---|
100 | || ('0' <= ch && ch <= '9')))
|
---|
101 | throw new IllegalCharsetNameException (name);
|
---|
102 |
|
---|
103 | for (int i = 1; i < n; ++i)
|
---|
104 | {
|
---|
105 | ch = name.charAt (i);
|
---|
106 | if (!(('A' <= ch && ch <= 'Z')
|
---|
107 | || ('a' <= ch && ch <= 'z')
|
---|
108 | || ('0' <= ch && ch <= '9')
|
---|
109 | || ch == '-' || ch == '.' || ch == ':' || ch == '_'))
|
---|
110 | throw new IllegalCharsetNameException (name);
|
---|
111 | }
|
---|
112 | }
|
---|
113 |
|
---|
114 | public static boolean isSupported (String charsetName)
|
---|
115 | {
|
---|
116 | return charsetForName (charsetName) != null;
|
---|
117 | }
|
---|
118 |
|
---|
119 | public static Charset forName (String charsetName)
|
---|
120 | {
|
---|
121 | Charset cs = charsetForName (charsetName);
|
---|
122 | if (cs == null)
|
---|
123 | throw new UnsupportedCharsetException (charsetName);
|
---|
124 | return cs;
|
---|
125 | }
|
---|
126 |
|
---|
127 | /**
|
---|
128 | * Retrieves a charset for the given charset name.
|
---|
129 | *
|
---|
130 | * @return A charset object for the charset with the specified name, or
|
---|
131 | * <code>null</code> if no such charset exists.
|
---|
132 | *
|
---|
133 | * @throws IllegalCharsetNameException if the name is illegal
|
---|
134 | */
|
---|
135 | private static Charset charsetForName (String charsetName)
|
---|
136 | {
|
---|
137 | checkName (charsetName);
|
---|
138 | return provider ().charsetForName (charsetName);
|
---|
139 | }
|
---|
140 |
|
---|
141 | public static SortedMap availableCharsets ()
|
---|
142 | {
|
---|
143 | TreeMap charsets = new TreeMap (String.CASE_INSENSITIVE_ORDER);
|
---|
144 |
|
---|
145 | for (Iterator i = provider ().charsets (); i.hasNext (); )
|
---|
146 | {
|
---|
147 | Charset cs = (Charset) i.next ();
|
---|
148 | charsets.put (cs.name (), cs);
|
---|
149 | }
|
---|
150 |
|
---|
151 | return Collections.unmodifiableSortedMap (charsets);
|
---|
152 | }
|
---|
153 |
|
---|
154 | // XXX: we need to support multiple providers, reading them from
|
---|
155 | // java.nio.charset.spi.CharsetProvider in the resource directory
|
---|
156 | // META-INF/services
|
---|
157 | private static final CharsetProvider provider ()
|
---|
158 | {
|
---|
159 | return Provider.provider ();
|
---|
160 | }
|
---|
161 |
|
---|
162 | public final String name ()
|
---|
163 | {
|
---|
164 | return canonicalName;
|
---|
165 | }
|
---|
166 |
|
---|
167 | public final Set aliases ()
|
---|
168 | {
|
---|
169 | if (aliases == null)
|
---|
170 | return Collections.EMPTY_SET;
|
---|
171 |
|
---|
172 | // should we cache the aliasSet instead?
|
---|
173 | int n = aliases.length;
|
---|
174 | HashSet aliasSet = new HashSet (n);
|
---|
175 | for (int i = 0; i < n; ++i)
|
---|
176 | aliasSet.add (aliases[i]);
|
---|
177 | return Collections.unmodifiableSet (aliasSet);
|
---|
178 | }
|
---|
179 |
|
---|
180 | public String displayName ()
|
---|
181 | {
|
---|
182 | return canonicalName;
|
---|
183 | }
|
---|
184 |
|
---|
185 | public String displayName (Locale locale)
|
---|
186 | {
|
---|
187 | return canonicalName;
|
---|
188 | }
|
---|
189 |
|
---|
190 | public final boolean isRegistered ()
|
---|
191 | {
|
---|
192 | return (!canonicalName.startsWith ("x-")
|
---|
193 | && !canonicalName.startsWith ("X-"));
|
---|
194 | }
|
---|
195 |
|
---|
196 | public abstract boolean contains (Charset cs);
|
---|
197 |
|
---|
198 | public abstract CharsetDecoder newDecoder ();
|
---|
199 |
|
---|
200 | public abstract CharsetEncoder newEncoder ();
|
---|
201 |
|
---|
202 | public boolean canEncode ()
|
---|
203 | {
|
---|
204 | return true;
|
---|
205 | }
|
---|
206 |
|
---|
207 | public final ByteBuffer encode (CharBuffer cb)
|
---|
208 | {
|
---|
209 | try
|
---|
210 | {
|
---|
211 | // NB: This implementation serializes different threads calling
|
---|
212 | // Charset.encode(), a potential performance problem. It might
|
---|
213 | // be better to remove the cache, or use ThreadLocal to cache on
|
---|
214 | // a per-thread basis.
|
---|
215 | synchronized (Charset.class)
|
---|
216 | {
|
---|
217 | if (cachedEncoder == null)
|
---|
218 | {
|
---|
219 | cachedEncoder = newEncoder ()
|
---|
220 | .onMalformedInput (CodingErrorAction.REPLACE)
|
---|
221 | .onUnmappableCharacter (CodingErrorAction.REPLACE);
|
---|
222 | }
|
---|
223 |
|
---|
224 | return cachedEncoder.encode (cb);
|
---|
225 | }
|
---|
226 | }
|
---|
227 | catch (CharacterCodingException e)
|
---|
228 | {
|
---|
229 | throw new AssertionError (e);
|
---|
230 | }
|
---|
231 | }
|
---|
232 |
|
---|
233 | public final ByteBuffer encode (String str)
|
---|
234 | {
|
---|
235 | return encode (CharBuffer.wrap (str));
|
---|
236 | }
|
---|
237 |
|
---|
238 | public CharBuffer decode (ByteBuffer bb)
|
---|
239 | {
|
---|
240 | try
|
---|
241 | {
|
---|
242 | // NB: This implementation serializes different threads calling
|
---|
243 | // Charset.decode(), a potential performance problem. It might
|
---|
244 | // be better to remove the cache, or use ThreadLocal to cache on
|
---|
245 | // a per-thread basis.
|
---|
246 | synchronized (Charset.class)
|
---|
247 | {
|
---|
248 | if (cachedDecoder == null)
|
---|
249 | {
|
---|
250 | cachedDecoder = newDecoder ()
|
---|
251 | .onMalformedInput (CodingErrorAction.REPLACE)
|
---|
252 | .onUnmappableCharacter (CodingErrorAction.REPLACE);
|
---|
253 | }
|
---|
254 |
|
---|
255 | return cachedDecoder.decode (bb);
|
---|
256 | }
|
---|
257 | }
|
---|
258 | catch (CharacterCodingException e)
|
---|
259 | {
|
---|
260 | throw new AssertionError (e);
|
---|
261 | }
|
---|
262 | }
|
---|
263 |
|
---|
264 | public final int compareTo (Object ob)
|
---|
265 | {
|
---|
266 | return canonicalName.compareToIgnoreCase (((Charset) ob).canonicalName);
|
---|
267 | }
|
---|
268 |
|
---|
269 | public final int hashCode ()
|
---|
270 | {
|
---|
271 | return canonicalName.hashCode ();
|
---|
272 | }
|
---|
273 |
|
---|
274 | public final boolean equals (Object ob)
|
---|
275 | {
|
---|
276 | if (ob instanceof Charset)
|
---|
277 | return canonicalName.equalsIgnoreCase (((Charset) ob).canonicalName);
|
---|
278 | else
|
---|
279 | return false;
|
---|
280 | }
|
---|
281 |
|
---|
282 | public final String toString ()
|
---|
283 | {
|
---|
284 | return canonicalName;
|
---|
285 | }
|
---|
286 | }
|
---|