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
|
/**
* Copyright (c) 2008, SnakeYAML
*
* Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except
* in compliance with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software distributed under the License
* is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express
* or implied. See the License for the specific language governing permissions and limitations under
* the License.
*/
package org.yaml.snakeyaml.reader;
/**
* version: 1.1 / 2007-01-25 - changed BOM recognition ordering (longer boms first)
*
* Original pseudocode : Thomas Weidenfeller Implementation tweaked: Aki Nieminen Implementation
* changed: Andrey Somov UTF-32 removed because it is not supported by YAML no default encoding
*
* http://www.unicode.org/unicode/faq/utf_bom.html BOMs: 00 00 FE FF = UTF-32, big-endian FF FE 00
* 00 = UTF-32, little-endian EF BB BF = UTF-8, FE FF = UTF-16, big-endian FF FE = UTF-16,
* little-endian
*
* Win2k Notepad: Unicode format = UTF-16LE
***/
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.PushbackInputStream;
import java.io.Reader;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CodingErrorAction;
import java.nio.charset.StandardCharsets;
/**
* Generic unicode textreader, which will use BOM mark to identify the encoding to be used. If BOM
* is not found then use a given default or system encoding.
*/
public class UnicodeReader extends Reader {
private static final Charset UTF8 = StandardCharsets.UTF_8;
private static final Charset UTF16BE = StandardCharsets.UTF_16BE;
private static final Charset UTF16LE = StandardCharsets.UTF_16LE;
PushbackInputStream internalIn;
InputStreamReader internalIn2 = null;
private static final int BOM_SIZE = 3;
/**
* @param in InputStream to be read
*/
public UnicodeReader(InputStream in) {
internalIn = new PushbackInputStream(in, BOM_SIZE);
}
/**
* Get stream encoding or NULL if stream is uninitialized. Call init() or read() method to
* initialize it.
*
* @return the name of the character encoding being used by this stream.
*/
public String getEncoding() {
return internalIn2.getEncoding();
}
/**
* Read-ahead four bytes and check for BOM marks. Extra bytes are unread back to the stream, only
* BOM bytes are skipped.
*
* @throws IOException if InputStream cannot be created
*/
protected void init() throws IOException {
if (internalIn2 != null) {
return;
}
Charset encoding;
byte[] bom = new byte[BOM_SIZE];
int n, unread;
n = internalIn.read(bom, 0, bom.length);
if ((bom[0] == (byte) 0xEF) && (bom[1] == (byte) 0xBB) && (bom[2] == (byte) 0xBF)) {
encoding = UTF8;
unread = n - 3;
} else if ((bom[0] == (byte) 0xFE) && (bom[1] == (byte) 0xFF)) {
encoding = UTF16BE;
unread = n - 2;
} else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE)) {
encoding = UTF16LE;
unread = n - 2;
} else {
// Unicode BOM mark not found, unread all bytes
encoding = UTF8;
unread = n;
}
if (unread > 0) {
internalIn.unread(bom, (n - unread), unread);
}
// Use given encoding
CharsetDecoder decoder = encoding.newDecoder().onUnmappableCharacter(CodingErrorAction.REPORT);
internalIn2 = new InputStreamReader(internalIn, decoder);
}
public void close() throws IOException {
init();
internalIn2.close();
}
public int read(char[] cbuf, int off, int len) throws IOException {
init();
return internalIn2.read(cbuf, off, len);
}
}
|
