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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
|
/* DecoderUTF8.java -- Decoder for the UTF-8 character encoding.
Copyright (C) 1998 Free Software Foundation, Inc.
This file is part of GNU Classpath.
GNU Classpath is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
GNU Classpath 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 for more details.
You should have received a copy of the GNU General Public License
along with GNU Classpath; see the file COPYING. If not, write to the
Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
02111-1307 USA.
As a special exception, if you link this library with other files to
produce an executable, this library does not by itself cause the
resulting executable to be covered by the GNU General Public License.
This exception does not however invalidate any other reasons why the
executable file might be covered by the GNU General Public License. */
package gnu.java.io.decode;
import java.io.InputStream;
import java.io.CharConversionException;
import java.io.IOException;
/**
* This class implements character decoding in the UCS Transformation
* Format 8 (UTF-8) encoding scheme. This is defined in RFC-2279.
* We only handle the 1-3 byte encodings for characters in the Unicode
* set.
*
* @version 0.0
*
* @author Aaron M. Renn (arenn@urbanophile.com)
*/
public class DecoderUTF8 extends Decoder
{
static
{
scheme_name = "UTF8";
scheme_description = "UCS Transformation Format 8 (see RFC-2279)";
}
/*************************************************************************/
/*
* Constructors
*/
public
DecoderUTF8(InputStream in)
{
super(in);
}
/*************************************************************************/
/*
* Instance Methods
*/
/**
* Counts the number of characters in a given byte array
*/
public int
charsInByteArray(byte[] buf, int offset, int len) throws CharConversionException
{
int num_chars = 0;
// Scan the buffer with minimal validation checks
for (int i = offset; i < len; i++)
{
// Three byte encoding case.
if ((buf[i] & 0xE0) == 0xE0) // 224
{
i += 2;
if (i >= buf.length)
throw new CharConversionException("Incomplete input");
++num_chars;
}
// Two byte encoding case
else if ((buf[i] & 0xC0) == 0xC0) // 192
{
++i;
if (i >= buf.length)
throw new CharConversionException("Incomplete input");
++num_chars;
}
// One byte encoding case
else if (buf[i] < 0x80) // 128
{
++num_chars;
}
else
{
throw new CharConversionException("Bad input encountered: " + buf[i]);
}
}
return(num_chars);
}
/*************************************************************************/
/**
* Transform the specified UTF8 encoded buffer to Unicode characters
*/
public char[]
convertToChars(byte[] buf, int buf_offset, int len, char cbuf[],
int cbuf_offset) throws CharConversionException
{
int val;
// Scan the buffer with full validation checks
for (int i = buf_offset; i < len; i++)
{
// Three byte encoding case.
if ((buf[i] & 0xE0) == 0xE0) // 224
{
if ((i + 2) >= buf.length)
throw new CharConversionException("Incomplete input");
val = (buf[i] & 0x0F) << 12;
++i;
if ((buf[i] & 0x80) != 0x80)
throw new CharConversionException("Bad input byte: " + buf[i]);
val |= (buf[i] & 0x3F) << 6;
++i;
if ((buf[i] & 0x80) != 0x80)
throw new CharConversionException("Bad input byte: " + buf[i]);
val |= (buf[i] & 0x3F);
}
// Two byte encoding case
else if ((buf[i] & 0xC0) == 0xC0) // 192
{
if ((i + 1) >= buf.length)
throw new CharConversionException("Incomplete input");
val = (buf[i] & 0x1F) << 6;
++i;
if ((buf[i] & 0x80) != 0x80)
throw new CharConversionException("Bad input byte: " + buf[i]);
val |= (buf[i] & 0x3F);
}
// One byte encoding case
else if (buf[i] < 0x80) // 128
{
val = buf[i];
}
else
{
throw new CharConversionException("Bad input encountered: " + buf[i]);
}
cbuf[cbuf_offset] = (char)val;
++cbuf_offset;
}
return(cbuf);
}
/*************************************************************************/
/**
* Reads chars from a UTF8 encoded byte stream
*/
public int
read(char[] cbuf, int offset, int len) throws IOException
{
int val;
// Note that this method of reading a single byte at a time is
// inefficient and should probably be replaced
for (int i = offset; i < len; i++)
{
// Read a byte
int b = in.read();
if (b == -1)
if (i == offset)
return(-1);
else
return(i - offset);
// Three byte encoding case.
if ((b & 0xE0) == 0xE0) // 224
{
val = (b & 0x0F) << 12;
if ((b = in.read()) == -1)
throw new CharConversionException("Pre-mature end of input");
if ((b & 0x80) != 0x80)
throw new CharConversionException("Bad input byte: " + b);
val |= (b & 0x3F) << 6;
if ((b = in.read()) == -1)
throw new CharConversionException("Pre-mature end of input");
if ((b & 0x80) != 0x80)
throw new CharConversionException("Bad input byte: " + b);
val |= (b & 0x3F);
}
// Two byte encoding case
else if ((b & 0xC0) == 0xC0) // 192
{
val = (b & 0x1F) << 6;
if ((b = in.read()) == -1)
throw new CharConversionException("Pre-mature end of input");
if ((b & 0x80) != 0x80)
throw new CharConversionException("Bad input byte: " + b);
val |= (b & 0x3F);
}
// One byte encoding case
else if (b < 0x80) // 128
{
val = b;
}
else
{
throw new CharConversionException("Bad input encountered: " + b);
}
cbuf[i] = (char)val;
}
return(len);
}
} // class DecoderUTF8
|
