blob: 3a495242bebefd67b7894086ccfda8e4a347fadd (
plain) (
blame)
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
|
/*******************************************************************************
* Copyright (c) 2001, 2004 IBM Corporation and others.
* All rights reserved. This program and the accompanying materials
* are made available under the terms of the Eclipse Public License v1.0
* which accompanies this distribution, and is available at
* http://www.eclipse.org/legal/epl-v10.html
*
* Contributors:
* IBM Corporation - initial API and implementation
* Jens Lukowski/Innoopract - initial renaming/restructuring
*
*******************************************************************************/
package org.eclipse.wst.xml.core.internal.contenttype;
import java.io.IOException;
import org.eclipse.wst.sse.core.internal.encoding.EncodingMemento;
import org.eclipse.wst.sse.core.internal.encoding.IResourceCharsetDetector;
public class XMLResourceEncodingDetector extends AbstractResourceEncodingDetector implements IResourceCharsetDetector {
private XMLHeadTokenizer fTokenizer;
private boolean fDeclDetected = false;
private boolean fInitialWhiteSpace = false;
private boolean canHandleAsUnicodeStream(String tokenType) {
boolean canHandleAsUnicodeStream = false;
if (tokenType == EncodingParserConstants.UTF83ByteBOM) {
canHandleAsUnicodeStream = true;
String enc = "UTF-8"; //$NON-NLS-1$
createEncodingMemento(enc, EncodingMemento.DETECTED_STANDARD_UNICODE_BYTES);
fEncodingMemento.setUTF83ByteBOMUsed(true);
}
else if (tokenType == EncodingParserConstants.UTF16BE) {
canHandleAsUnicodeStream = true;
String enc = "UTF-16BE"; //$NON-NLS-1$
createEncodingMemento(enc, EncodingMemento.DETECTED_STANDARD_UNICODE_BYTES);
}
else if (tokenType == EncodingParserConstants.UTF16LE) {
canHandleAsUnicodeStream = true;
String enc = "UTF-16"; //$NON-NLS-1$
createEncodingMemento(enc, EncodingMemento.DETECTED_STANDARD_UNICODE_BYTES);
}
return canHandleAsUnicodeStream;
}
public String getSpecDefaultEncoding() {
// by default, UTF-8 as per XML spec
final String enc = "UTF-8"; //$NON-NLS-1$
return enc;
}
/**
* @return Returns the tokenizer.
*/
private XMLHeadTokenizer getTokenizer() {
// TODO: need to work on 'reset' in tokenizer, so new instance isn't
// always needed
// if (fTokenizer == null) {
fTokenizer = new XMLHeadTokenizer();
// }
return fTokenizer;
}
private boolean isLegalString(String valueTokenType) {
if (valueTokenType == null)
return false;
else
return valueTokenType.equals(EncodingParserConstants.StringValue) || valueTokenType.equals(EncodingParserConstants.UnDelimitedStringValue) || valueTokenType.equals(EncodingParserConstants.InvalidTerminatedStringValue) || valueTokenType.equals(EncodingParserConstants.InvalidTermintatedUnDelimitedStringValue);
}
protected void parseInput() throws IOException {
XMLHeadTokenizer tokenizer = getTokenizer();
tokenizer.reset(fReader);
HeadParserToken token = null;
String tokenType = null;
do {
token = tokenizer.getNextToken();
tokenType = token.getType();
// handle xml content type detection
if (tokenType == XMLHeadTokenizerConstants.XMLDeclStart) {
fDeclDetected = true;
String declText = token.getText();
if (declText.startsWith("<?")) { //$NON-NLS-1$
fInitialWhiteSpace = false;
}
else {
fInitialWhiteSpace = true;
}
}
// handle encoding detection
if (canHandleAsUnicodeStream(tokenType)) {
// side effect of canHandle is to create appropriate memento
}
else {
if (tokenType == XMLHeadTokenizerConstants.XMLDelEncoding) {
if (tokenizer.hasMoreTokens()) {
token = tokenizer.getNextToken();
tokenType = token.getType();
if (isLegalString(tokenType)) {
String enc = token.getText();
if (enc != null && enc.length() > 0) {
createEncodingMemento(enc, EncodingMemento.FOUND_ENCODING_IN_CONTENT);
}
}
}
}
}
}
while (tokenizer.hasMoreTokens());
}
public boolean isDeclDetected() {
if (!fHeaderParsed) {
try {
parseInput();
}
catch (IOException e) {
fDeclDetected = false;
}
// we keep track of if header's already been
// parse, so can make
// multiple 'get' calls, without causing
// reparsing.
fHeaderParsed = true;
}
// fDeclDetected is set as part of parsing.
return fDeclDetected;
}
public boolean hasInitialWhiteSpace() {
return fInitialWhiteSpace;
}
protected void resetAll() {
super.resetAll();
fDeclDetected = false;
fInitialWhiteSpace = false;
}
}
|
