2
|
1 |
/*
|
|
2 |
* Copyright 1996-1997 Sun Microsystems, Inc. All Rights Reserved.
|
|
3 |
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
|
|
4 |
*
|
|
5 |
* This code is free software; you can redistribute it and/or modify it
|
|
6 |
* under the terms of the GNU General Public License version 2 only, as
|
|
7 |
* published by the Free Software Foundation. Sun designates this
|
|
8 |
* particular file as subject to the "Classpath" exception as provided
|
|
9 |
* by Sun in the LICENSE file that accompanied this code.
|
|
10 |
*
|
|
11 |
* This code is distributed in the hope that it will be useful, but WITHOUT
|
|
12 |
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
13 |
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
14 |
* version 2 for more details (a copy is included in the LICENSE file that
|
|
15 |
* accompanied this code).
|
|
16 |
*
|
|
17 |
* You should have received a copy of the GNU General Public License version
|
|
18 |
* 2 along with this work; if not, write to the Free Software Foundation,
|
|
19 |
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
|
20 |
*
|
|
21 |
* Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
|
|
22 |
* CA 95054 USA or visit www.sun.com if you need additional information or
|
|
23 |
* have any questions.
|
|
24 |
*/
|
|
25 |
package sun.io;
|
|
26 |
|
|
27 |
|
|
28 |
/**
|
|
29 |
* UCS2 (UTF16) -> UCS Transformation Format 8 (UTF-8) converter
|
|
30 |
* It's represented like below.
|
|
31 |
*
|
|
32 |
* # Bits Bit pattern
|
|
33 |
* 1 7 0xxxxxxx
|
|
34 |
* 2 11 110xxxxx 10xxxxxx
|
|
35 |
* 3 16 1110xxxx 10xxxxxx 10xxxxxx
|
|
36 |
* 4 21 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
|
|
37 |
* 5 26 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
|
|
38 |
* 6 31 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
|
|
39 |
*
|
|
40 |
* UCS2 uses 1-3 / UTF16 uses 1-4 / UCS4 uses 1-6
|
|
41 |
*/
|
|
42 |
|
|
43 |
public class CharToByteUTF8 extends CharToByteConverter {
|
|
44 |
|
|
45 |
private char highHalfZoneCode;
|
|
46 |
|
|
47 |
public int flush(byte[] output, int outStart, int outEnd)
|
|
48 |
throws MalformedInputException
|
|
49 |
{
|
|
50 |
if (highHalfZoneCode != 0) {
|
|
51 |
highHalfZoneCode = 0;
|
|
52 |
badInputLength = 0;
|
|
53 |
throw new MalformedInputException();
|
|
54 |
}
|
|
55 |
byteOff = charOff = 0;
|
|
56 |
return 0;
|
|
57 |
}
|
|
58 |
|
|
59 |
/**
|
|
60 |
* Character conversion
|
|
61 |
*/
|
|
62 |
public int convert(char[] input, int inOff, int inEnd,
|
|
63 |
byte[] output, int outOff, int outEnd)
|
|
64 |
throws ConversionBufferFullException, MalformedInputException
|
|
65 |
{
|
|
66 |
char inputChar;
|
|
67 |
byte[] outputByte = new byte[6];
|
|
68 |
int inputSize;
|
|
69 |
int outputSize;
|
|
70 |
|
|
71 |
charOff = inOff;
|
|
72 |
byteOff = outOff;
|
|
73 |
|
|
74 |
if (highHalfZoneCode != 0) {
|
|
75 |
inputChar = highHalfZoneCode;
|
|
76 |
highHalfZoneCode = 0;
|
|
77 |
if (input[inOff] >= 0xdc00 && input[inOff] <= 0xdfff) {
|
|
78 |
// This is legal UTF16 sequence.
|
|
79 |
int ucs4 = (highHalfZoneCode - 0xd800) * 0x400
|
|
80 |
+ (input[inOff] - 0xdc00) + 0x10000;
|
|
81 |
output[0] = (byte)(0xf0 | ((ucs4 >> 18)) & 0x07);
|
|
82 |
output[1] = (byte)(0x80 | ((ucs4 >> 12) & 0x3f));
|
|
83 |
output[2] = (byte)(0x80 | ((ucs4 >> 6) & 0x3f));
|
|
84 |
output[3] = (byte)(0x80 | (ucs4 & 0x3f));
|
|
85 |
charOff++;
|
|
86 |
highHalfZoneCode = 0;
|
|
87 |
} else {
|
|
88 |
// This is illegal UTF16 sequence.
|
|
89 |
badInputLength = 0;
|
|
90 |
throw new MalformedInputException();
|
|
91 |
}
|
|
92 |
}
|
|
93 |
|
|
94 |
while(charOff < inEnd) {
|
|
95 |
inputChar = input[charOff];
|
|
96 |
if (inputChar < 0x80) {
|
|
97 |
outputByte[0] = (byte)inputChar;
|
|
98 |
inputSize = 1;
|
|
99 |
outputSize = 1;
|
|
100 |
} else if (inputChar < 0x800) {
|
|
101 |
outputByte[0] = (byte)(0xc0 | ((inputChar >> 6) & 0x1f));
|
|
102 |
outputByte[1] = (byte)(0x80 | (inputChar & 0x3f));
|
|
103 |
inputSize = 1;
|
|
104 |
outputSize = 2;
|
|
105 |
} else if (inputChar >= 0xd800 && inputChar <= 0xdbff) {
|
|
106 |
// this is <high-half zone code> in UTF-16
|
|
107 |
if (charOff + 1 >= inEnd) {
|
|
108 |
highHalfZoneCode = inputChar;
|
|
109 |
break;
|
|
110 |
}
|
|
111 |
// check next char is valid <low-half zone code>
|
|
112 |
char lowChar = input[charOff + 1];
|
|
113 |
if (lowChar < 0xdc00 || lowChar > 0xdfff) {
|
|
114 |
badInputLength = 1;
|
|
115 |
throw new MalformedInputException();
|
|
116 |
}
|
|
117 |
int ucs4 = (inputChar - 0xd800) * 0x400 + (lowChar - 0xdc00)
|
|
118 |
+ 0x10000;
|
|
119 |
outputByte[0] = (byte)(0xf0 | ((ucs4 >> 18)) & 0x07);
|
|
120 |
outputByte[1] = (byte)(0x80 | ((ucs4 >> 12) & 0x3f));
|
|
121 |
outputByte[2] = (byte)(0x80 | ((ucs4 >> 6) & 0x3f));
|
|
122 |
outputByte[3] = (byte)(0x80 | (ucs4 & 0x3f));
|
|
123 |
outputSize = 4;
|
|
124 |
inputSize = 2;
|
|
125 |
} else {
|
|
126 |
outputByte[0] = (byte)(0xe0 | ((inputChar >> 12)) & 0x0f);
|
|
127 |
outputByte[1] = (byte)(0x80 | ((inputChar >> 6) & 0x3f));
|
|
128 |
outputByte[2] = (byte)(0x80 | (inputChar & 0x3f));
|
|
129 |
inputSize = 1;
|
|
130 |
outputSize = 3;
|
|
131 |
}
|
|
132 |
if (byteOff + outputSize > outEnd) {
|
|
133 |
throw new ConversionBufferFullException();
|
|
134 |
}
|
|
135 |
for (int i = 0; i < outputSize; i++) {
|
|
136 |
output[byteOff++] = outputByte[i];
|
|
137 |
}
|
|
138 |
charOff += inputSize;
|
|
139 |
}
|
|
140 |
return byteOff - outOff;
|
|
141 |
}
|
|
142 |
|
|
143 |
public boolean canConvert(char ch) {
|
|
144 |
return true;
|
|
145 |
}
|
|
146 |
|
|
147 |
public int getMaxBytesPerChar() {
|
|
148 |
return 3;
|
|
149 |
}
|
|
150 |
|
|
151 |
public void reset() {
|
|
152 |
byteOff = charOff = 0;
|
|
153 |
highHalfZoneCode = 0;
|
|
154 |
}
|
|
155 |
|
|
156 |
public String getCharacterEncoding() {
|
|
157 |
return "UTF8";
|
|
158 |
}
|
|
159 |
}
|