1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
|
/* Copyright (C) 1999, 2000, 2001, 2005 Free Software Foundation
This file is part of libgcj.
This software is copyrighted work licensed under the terms of the
Libgcj License. Please consult the file "LIBGCJ_LICENSE" for
details. */
package gnu.gcj.convert;
import java.nio.charset.Charset;
public abstract class BytesToUnicode extends IOConverter
{
/** Buffer to read bytes from.
* The characters inbuffer[inpos] ... inbuffer[inlength-1] are available. */
public byte[] inbuffer;
/** Starting index in buffer to read bytes from. */
public int inpos;
/** End of valid bytes in buffer. */
public int inlength;
// The name of the default encoding.
static String defaultEncoding;
/* These keep a small cache of decoders for reuse. The array holds
the actual decoders. The currCachePos is the next value we are
going to replace in the cache. We don't just throw the data away
if the cache is full, because if the cache filled up with stuff
we don't need then the cache would be worthless. We instead
circulate through the cache the implement kind of an LRU
algorithm. */
private static final int CACHE_SIZE = 4; // A power of 2 for speed
private static BytesToUnicode[] decoderCache
= new BytesToUnicode[CACHE_SIZE];
private static int currCachePos = 0;
public abstract String getName();
public static BytesToUnicode getDefaultDecoder()
{
try
{
synchronized (BytesToUnicode.class)
{
if (defaultEncoding == null)
{
String encoding
= canonicalize (System.getProperty("file.encoding",
"8859_1"));
String className = "gnu.gcj.convert.Input_" + encoding;
try
{
Class defaultDecodingClass = Class.forName(className);
defaultEncoding = encoding;
}
catch (ClassNotFoundException ex)
{
throw new NoClassDefFoundError("missing default encoding "
+ encoding + " (class "
+ className
+ " not found)");
}
}
}
return getDecoder (defaultEncoding);
}
catch (Throwable ex)
{
return new Input_8859_1();
}
}
/** Get a byte-stream->char-stream converter given an encoding name. */
public static BytesToUnicode getDecoder (String encoding)
throws java.io.UnsupportedEncodingException
{
/* First hunt in our cache to see if we have a decoder that is
already allocated. */
String canonicalEncoding = canonicalize(encoding);
synchronized (BytesToUnicode.class)
{
int i;
for (i = 0; i < decoderCache.length; ++i)
{
if (decoderCache[i] != null
&& canonicalEncoding.equals(decoderCache[i].getName ()))
{
BytesToUnicode rv = decoderCache[i];
decoderCache[i] = null;
return rv;
}
}
}
// It's not in the cache, so now we have to do real work.
String className = "gnu.gcj.convert.Input_" + canonicalEncoding;
Class decodingClass;
try
{
decodingClass = Class.forName(className);
return (BytesToUnicode) decodingClass.newInstance();
}
catch (Throwable ex)
{
try
{
// We pass the original name to iconv and let it handle
// its own aliasing. Note that we intentionally prefer
// iconv over nio.
return new Input_iconv (encoding);
}
catch (Throwable _)
{
// Ignore, and try the next method.
}
try
{
return new BytesToCharsetAdaptor(Charset.forName(encoding));
}
catch (Throwable _)
{
throw new java.io.UnsupportedEncodingException(encoding
+ " (" + ex + ')');
}
}
}
/** Make input bytes available to the conversion.
* @param buffer source of input bytes
* @param pos index of first available byte
* @param length one more than index of last available byte
*/
public final void setInput(byte[] buffer, int pos, int length)
{
inbuffer = buffer;
inpos = pos;
inlength = length;
}
/** Convert bytes to chars.
* Input bytes are taken from this.inbuffer. The available input
* bytes start at inbuffer[inpos], and end at inbuffer[inlength-1].
* @param outbuffer buffer for the converted character
* @param outpos position in buffer to start putting converted characters
* @param count the maximum number of characters to convert
* @return number of chars placed in outbuffer.
* Also, this.inpos is incremented by the number of bytes consumed.
*
* (Note the asymmetry in that the input upper bound is inbuffer[inlength-1],
* while the output upper bound is outbuffer[outpos+count-1]. The
* justification is that inlength is like the count field of a
* BufferedInputStream, while the count parameter is like the
* length parameter of a read request.) The count parameter is
* also defined to be <= outbuffer.length - outpos (per the specification
* of the length parameter for a read request).
*/
public abstract int read (char[] outbuffer, int outpos, int count);
/** Indicate that the converter is resuable.
* This class keeps track of converters on a per-encoding basis.
* When done with an encoder you may call this method to indicate
* that it can be reused later.
*/
public void done ()
{
synchronized (BytesToUnicode.class)
{
this.inbuffer = null;
this.inpos = 0;
this.inlength = 0;
decoderCache[currCachePos] = this;
currCachePos = (currCachePos + 1) % CACHE_SIZE;
}
}
}
|
