1 |
771 |
jeremybenn |
/* CharsetDecoder.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., 51 Franklin Street, Fifth Floor, Boston, MA
|
19 |
|
|
02110-1301 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 |
|
|
|
43 |
|
|
/**
|
44 |
|
|
* @author Jesse Rosenstock
|
45 |
|
|
* @since 1.4
|
46 |
|
|
*/
|
47 |
|
|
public abstract class CharsetDecoder
|
48 |
|
|
{
|
49 |
|
|
private static final int STATE_RESET = 0;
|
50 |
|
|
private static final int STATE_CODING = 1;
|
51 |
|
|
private static final int STATE_END = 2;
|
52 |
|
|
private static final int STATE_FLUSHED = 3;
|
53 |
|
|
|
54 |
|
|
private static final String DEFAULT_REPLACEMENT = "\uFFFD";
|
55 |
|
|
|
56 |
|
|
private final Charset charset;
|
57 |
|
|
private final float averageCharsPerByte;
|
58 |
|
|
private final float maxCharsPerByte;
|
59 |
|
|
private String replacement;
|
60 |
|
|
|
61 |
|
|
private int state = STATE_RESET;
|
62 |
|
|
|
63 |
|
|
private CodingErrorAction malformedInputAction
|
64 |
|
|
= CodingErrorAction.REPORT;
|
65 |
|
|
private CodingErrorAction unmappableCharacterAction
|
66 |
|
|
= CodingErrorAction.REPORT;
|
67 |
|
|
|
68 |
|
|
private CharsetDecoder (Charset cs, float averageCharsPerByte,
|
69 |
|
|
float maxCharsPerByte, String replacement)
|
70 |
|
|
{
|
71 |
|
|
if (averageCharsPerByte <= 0.0f)
|
72 |
|
|
throw new IllegalArgumentException ("Non-positive averageCharsPerByte");
|
73 |
|
|
if (maxCharsPerByte <= 0.0f)
|
74 |
|
|
throw new IllegalArgumentException ("Non-positive maxCharsPerByte");
|
75 |
|
|
|
76 |
|
|
this.charset = cs;
|
77 |
|
|
this.averageCharsPerByte
|
78 |
|
|
= averageCharsPerByte;
|
79 |
|
|
this.maxCharsPerByte
|
80 |
|
|
= maxCharsPerByte;
|
81 |
|
|
this.replacement = replacement;
|
82 |
|
|
implReplaceWith (replacement);
|
83 |
|
|
}
|
84 |
|
|
|
85 |
|
|
protected CharsetDecoder (Charset cs, float averageCharsPerByte,
|
86 |
|
|
float maxCharsPerByte)
|
87 |
|
|
{
|
88 |
|
|
this (cs, averageCharsPerByte, maxCharsPerByte, DEFAULT_REPLACEMENT);
|
89 |
|
|
}
|
90 |
|
|
|
91 |
|
|
public final float averageCharsPerByte ()
|
92 |
|
|
{
|
93 |
|
|
return averageCharsPerByte;
|
94 |
|
|
}
|
95 |
|
|
|
96 |
|
|
public final Charset charset ()
|
97 |
|
|
{
|
98 |
|
|
return charset;
|
99 |
|
|
}
|
100 |
|
|
|
101 |
|
|
public final CharBuffer decode (ByteBuffer in)
|
102 |
|
|
throws CharacterCodingException
|
103 |
|
|
{
|
104 |
|
|
// XXX: Sun's Javadoc seems to contradict itself saying an
|
105 |
|
|
// IllegalStateException is thrown "if a decoding operation is already
|
106 |
|
|
// in progress" and also that "it resets this Decoder".
|
107 |
|
|
// Should we check to see that the state is reset, or should we
|
108 |
|
|
// call reset()?
|
109 |
|
|
if (state != STATE_RESET)
|
110 |
|
|
throw new IllegalStateException ();
|
111 |
|
|
|
112 |
|
|
// REVIEW: Using max instead of average may allocate a very large
|
113 |
|
|
// buffer. Maybe we should do something more efficient?
|
114 |
|
|
int remaining = in.remaining ();
|
115 |
|
|
int n = (int) (remaining * maxCharsPerByte ());
|
116 |
|
|
CharBuffer out = CharBuffer.allocate (n);
|
117 |
|
|
|
118 |
|
|
if (remaining == 0)
|
119 |
|
|
{
|
120 |
|
|
state = STATE_FLUSHED;
|
121 |
|
|
return out;
|
122 |
|
|
}
|
123 |
|
|
|
124 |
|
|
CoderResult cr = decode (in, out, true);
|
125 |
|
|
if (cr.isError ())
|
126 |
|
|
cr.throwException ();
|
127 |
|
|
|
128 |
|
|
cr = flush (out);
|
129 |
|
|
if (cr.isError ())
|
130 |
|
|
cr.throwException ();
|
131 |
|
|
|
132 |
|
|
reset();
|
133 |
|
|
out.flip ();
|
134 |
|
|
|
135 |
|
|
// Unfortunately, resizing the actual charbuffer array is required.
|
136 |
|
|
char[] resized = new char[out.remaining()];
|
137 |
|
|
out.get(resized);
|
138 |
|
|
return CharBuffer.wrap(resized);
|
139 |
|
|
}
|
140 |
|
|
|
141 |
|
|
public final CoderResult decode (ByteBuffer in, CharBuffer out,
|
142 |
|
|
boolean endOfInput)
|
143 |
|
|
{
|
144 |
|
|
int newState = endOfInput ? STATE_END : STATE_CODING;
|
145 |
|
|
// XXX: Need to check for "previous step was an invocation [not] of
|
146 |
|
|
// this method with a value of true for the endOfInput parameter but
|
147 |
|
|
// a return value indicating an incomplete decoding operation"
|
148 |
|
|
// XXX: We will not check the previous return value, just
|
149 |
|
|
// that the previous call passed true for endOfInput
|
150 |
|
|
if (state != STATE_RESET && state != STATE_CODING
|
151 |
|
|
&& !(endOfInput && state == STATE_END))
|
152 |
|
|
throw new IllegalStateException ();
|
153 |
|
|
state = newState;
|
154 |
|
|
|
155 |
|
|
for (;;)
|
156 |
|
|
{
|
157 |
|
|
CoderResult cr;
|
158 |
|
|
try
|
159 |
|
|
{
|
160 |
|
|
cr = decodeLoop (in, out);
|
161 |
|
|
}
|
162 |
|
|
catch (RuntimeException e)
|
163 |
|
|
{
|
164 |
|
|
throw new CoderMalfunctionError (e);
|
165 |
|
|
}
|
166 |
|
|
|
167 |
|
|
if (cr.isOverflow ())
|
168 |
|
|
return cr;
|
169 |
|
|
|
170 |
|
|
if (cr.isUnderflow ())
|
171 |
|
|
{
|
172 |
|
|
if (endOfInput && in.hasRemaining ())
|
173 |
|
|
cr = CoderResult.malformedForLength (in.remaining ());
|
174 |
|
|
else
|
175 |
|
|
return cr;
|
176 |
|
|
}
|
177 |
|
|
|
178 |
|
|
CodingErrorAction action = cr.isMalformed ()
|
179 |
|
|
? malformedInputAction
|
180 |
|
|
: unmappableCharacterAction;
|
181 |
|
|
|
182 |
|
|
if (action == CodingErrorAction.REPORT)
|
183 |
|
|
return cr;
|
184 |
|
|
|
185 |
|
|
if (action == CodingErrorAction.REPLACE)
|
186 |
|
|
{
|
187 |
|
|
if (out.remaining () < replacement.length ())
|
188 |
|
|
return CoderResult.OVERFLOW;
|
189 |
|
|
out.put (replacement);
|
190 |
|
|
}
|
191 |
|
|
|
192 |
|
|
in.position (in.position () + cr.length ());
|
193 |
|
|
}
|
194 |
|
|
}
|
195 |
|
|
|
196 |
|
|
protected abstract CoderResult decodeLoop (ByteBuffer in, CharBuffer out);
|
197 |
|
|
|
198 |
|
|
public Charset detectedCharset ()
|
199 |
|
|
{
|
200 |
|
|
throw new UnsupportedOperationException ();
|
201 |
|
|
}
|
202 |
|
|
|
203 |
|
|
public final CoderResult flush (CharBuffer out)
|
204 |
|
|
{
|
205 |
|
|
// It seems weird that you can flush after reset, but Sun's javadoc
|
206 |
|
|
// says an IllegalStateException is thrown "If the previous step of the
|
207 |
|
|
// current decoding operation was an invocation neither of the reset
|
208 |
|
|
// method nor ... of the three-argument decode method with a value of
|
209 |
|
|
// true for the endOfInput parameter."
|
210 |
|
|
// Further note that flush() only requires that there not be
|
211 |
|
|
// an IllegalStateException if the previous step was a call to
|
212 |
|
|
// decode with true as the last argument. It does not require
|
213 |
|
|
// that the call succeeded. decode() does require that it succeeded.
|
214 |
|
|
// XXX: test this to see if reality matches javadoc
|
215 |
|
|
if (state != STATE_RESET && state != STATE_END)
|
216 |
|
|
throw new IllegalStateException ();
|
217 |
|
|
|
218 |
|
|
state = STATE_FLUSHED;
|
219 |
|
|
return implFlush (out);
|
220 |
|
|
}
|
221 |
|
|
|
222 |
|
|
protected CoderResult implFlush (CharBuffer out)
|
223 |
|
|
{
|
224 |
|
|
return CoderResult.UNDERFLOW;
|
225 |
|
|
}
|
226 |
|
|
|
227 |
|
|
public final CharsetDecoder onMalformedInput (CodingErrorAction newAction)
|
228 |
|
|
{
|
229 |
|
|
if (newAction == null)
|
230 |
|
|
throw new IllegalArgumentException ("Null action");
|
231 |
|
|
|
232 |
|
|
malformedInputAction = newAction;
|
233 |
|
|
implOnMalformedInput (newAction);
|
234 |
|
|
return this;
|
235 |
|
|
}
|
236 |
|
|
|
237 |
|
|
protected void implOnMalformedInput (CodingErrorAction newAction)
|
238 |
|
|
{
|
239 |
|
|
// default implementation does nothing
|
240 |
|
|
}
|
241 |
|
|
|
242 |
|
|
protected void implOnUnmappableCharacter (CodingErrorAction newAction)
|
243 |
|
|
{
|
244 |
|
|
// default implementation does nothing
|
245 |
|
|
}
|
246 |
|
|
|
247 |
|
|
protected void implReplaceWith (String newReplacement)
|
248 |
|
|
{
|
249 |
|
|
// default implementation does nothing
|
250 |
|
|
}
|
251 |
|
|
|
252 |
|
|
protected void implReset ()
|
253 |
|
|
{
|
254 |
|
|
// default implementation does nothing
|
255 |
|
|
}
|
256 |
|
|
|
257 |
|
|
public boolean isAutoDetecting ()
|
258 |
|
|
{
|
259 |
|
|
return false;
|
260 |
|
|
}
|
261 |
|
|
|
262 |
|
|
public boolean isCharsetDetected ()
|
263 |
|
|
{
|
264 |
|
|
throw new UnsupportedOperationException ();
|
265 |
|
|
}
|
266 |
|
|
|
267 |
|
|
public CodingErrorAction malformedInputAction ()
|
268 |
|
|
{
|
269 |
|
|
return malformedInputAction;
|
270 |
|
|
}
|
271 |
|
|
|
272 |
|
|
public final float maxCharsPerByte ()
|
273 |
|
|
{
|
274 |
|
|
return maxCharsPerByte;
|
275 |
|
|
}
|
276 |
|
|
|
277 |
|
|
public final CharsetDecoder onUnmappableCharacter
|
278 |
|
|
(CodingErrorAction newAction)
|
279 |
|
|
{
|
280 |
|
|
if (newAction == null)
|
281 |
|
|
throw new IllegalArgumentException ("Null action");
|
282 |
|
|
|
283 |
|
|
unmappableCharacterAction = newAction;
|
284 |
|
|
implOnUnmappableCharacter (newAction);
|
285 |
|
|
return this;
|
286 |
|
|
}
|
287 |
|
|
|
288 |
|
|
public final String replacement ()
|
289 |
|
|
{
|
290 |
|
|
return replacement;
|
291 |
|
|
}
|
292 |
|
|
|
293 |
|
|
public final CharsetDecoder replaceWith (String newReplacement)
|
294 |
|
|
{
|
295 |
|
|
if (newReplacement == null)
|
296 |
|
|
throw new IllegalArgumentException ("Null replacement");
|
297 |
|
|
if (newReplacement.length () == 0)
|
298 |
|
|
throw new IllegalArgumentException ("Empty replacement");
|
299 |
|
|
// XXX: what about maxCharsPerByte?
|
300 |
|
|
|
301 |
|
|
this.replacement = newReplacement;
|
302 |
|
|
implReplaceWith (newReplacement);
|
303 |
|
|
return this;
|
304 |
|
|
}
|
305 |
|
|
|
306 |
|
|
public final CharsetDecoder reset ()
|
307 |
|
|
{
|
308 |
|
|
state = STATE_RESET;
|
309 |
|
|
implReset ();
|
310 |
|
|
return this;
|
311 |
|
|
}
|
312 |
|
|
|
313 |
|
|
public CodingErrorAction unmappableCharacterAction ()
|
314 |
|
|
{
|
315 |
|
|
return unmappableCharacterAction;
|
316 |
|
|
}
|
317 |
|
|
}
|