UnicodeUtil.java
5.81 KB
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
package gcom.util;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.PushbackInputStream;
import java.io.UnsupportedEncodingException;
import java.io.Writer;
public class UnicodeUtil {
public static byte[] convert(byte[] bytes, String encout) throws Exception {
// Workaround for bug that will not be fixed by SUN
// http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=4508058
UnicodeInputStream uis = new UnicodeInputStream(new ByteArrayInputStream(bytes), "ASCII");
boolean unicodeOutputReqd = (getBOM(encout) != null) ? true : false;
String enc = uis.getEncoding();
String BOM = getBOM(enc); // get the BOM of the inputstream
if (BOM == null) {
// inputstream looks like ascii...
// create a BOM based on the outputstream
BOM = getBOM(encout);
}
uis.close();
ByteArrayOutputStream out = new ByteArrayOutputStream();
BufferedReader br = new BufferedReader(new InputStreamReader(new ByteArrayInputStream(bytes, uis.getBOMOffset(), bytes.length), enc));
Writer w = new BufferedWriter(new OutputStreamWriter(out, encout));
// dont write a BOM for ascii(out) as the OutputStreamWriter
// will not process it correctly.
if (BOM != null && unicodeOutputReqd) {
w.write(BOM);
}
char[] buffer = new char[4096];
int len;
while ((len = br.read(buffer)) != -1) {
w.write(buffer, 0, len);
}
br.close(); // Close the input.
w.close(); // Flush and close output.
return out.toByteArray();
}
public static String getBOM(String enc) throws UnsupportedEncodingException {
if ("UTF-8".equals(enc)) {
byte[] bom = new byte[3];
bom[0] = (byte) 0xEF;
bom[1] = (byte) 0xBB;
bom[2] = (byte) 0xBF;
return new String(bom, enc);
} else if ("UTF-16BE".equals(enc)) {
byte[] bom = new byte[2];
bom[0] = (byte) 0xFE;
bom[1] = (byte) 0xFF;
return new String(bom, enc);
} else if ("UTF-16LE".equals(enc)) {
byte[] bom = new byte[2];
bom[0] = (byte) 0xFF;
bom[1] = (byte) 0xFE;
return new String(bom, enc);
} else if ("UTF-32BE".equals(enc)) {
byte[] bom = new byte[4];
bom[0] = (byte) 0x00;
bom[1] = (byte) 0x00;
bom[2] = (byte) 0xFE;
bom[3] = (byte) 0xFF;
return new String(bom, enc);
} else if ("UTF-32LE".equals(enc)) {
byte[] bom = new byte[4];
bom[0] = (byte) 0x00;
bom[1] = (byte) 0x00;
bom[2] = (byte) 0xFF;
bom[3] = (byte) 0xFE;
return new String(bom, enc);
} else {
return null;
}
}
public static class UnicodeInputStream extends InputStream {
private PushbackInputStream internalIn;
private boolean isInited = false;
private int BOMOffset = -1;
private String defaultEnc;
private String encoding;
public static final int BOM_SIZE = 4;
public UnicodeInputStream(InputStream in, String defaultEnc) {
internalIn = new PushbackInputStream(in, BOM_SIZE);
this.defaultEnc = defaultEnc;
}
public String getDefaultEncoding() {
return defaultEnc;
}
public String getEncoding() {
if (!isInited) {
try {
init();
} catch (IOException ex) {
IllegalStateException ise = new IllegalStateException("Init method failed.");
ise.initCause(ise);
throw ise;
}
}
return encoding;
}
/**
* Read-ahead four bytes and check for BOM marks. Extra bytes are unread
* back to the stream, only BOM bytes are skipped.
*/
protected void init() throws IOException {
if (isInited)
return;
byte bom[] = new byte[BOM_SIZE];
int n, unread;
n = internalIn.read(bom, 0, bom.length);
if ((bom[0] == (byte) 0x00) && (bom[1] == (byte) 0x00) && (bom[2] == (byte) 0xFE) && (bom[3] == (byte) 0xFF)) {
encoding = "UTF-32BE";
unread = n - 4;
} else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE) && (bom[2] == (byte) 0x00) && (bom[3] == (byte) 0x00)) {
encoding = "UTF-32LE";
unread = n - 4;
} else if ((bom[0] == (byte) 0xEF) && (bom[1] == (byte) 0xBB) && (bom[2] == (byte) 0xBF)) {
encoding = "UTF-8";
unread = n - 3;
} else if ((bom[0] == (byte) 0xFE) && (bom[1] == (byte) 0xFF)) {
encoding = "UTF-16BE";
unread = n - 2;
} else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE)) {
encoding = "UTF-16LE";
unread = n - 2;
} else {
// Unicode BOM mark not found, unread all bytes
encoding = defaultEnc;
unread = n;
}
BOMOffset = BOM_SIZE - unread;
if (unread > 0)
internalIn.unread(bom, n - unread, unread);
isInited = true;
}
public void close() throws IOException {
// init();
isInited = true;
internalIn.close();
}
public int read() throws IOException {
// init();
isInited = true;
return internalIn.read();
}
public int getBOMOffset() {
return BOMOffset;
}
}
}