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
|
/*******************************************************************************
* Copyright (c) 2001, 2006 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.dtd.core.internal.content;
import java.io.IOException;
import java.io.InputStream;
import java.io.Reader;
import org.eclipse.core.runtime.QualifiedName;
import org.eclipse.core.runtime.content.IContentDescriber;
import org.eclipse.core.runtime.content.IContentDescription;
import org.eclipse.core.runtime.content.ITextContentDescriber;
import org.eclipse.wst.sse.core.internal.encoding.EncodingMemento;
import org.eclipse.wst.sse.core.internal.encoding.IContentDescriptionExtended;
import org.eclipse.wst.sse.core.internal.encoding.IResourceCharsetDetector;
import org.eclipse.wst.xml.core.internal.contenttype.XMLResourceEncodingDetector;
public final class ContentDescriberForDTD implements ITextContentDescriber {
final private static QualifiedName[] SUPPORTED_OPTIONS = {IContentDescription.CHARSET, IContentDescription.BYTE_ORDER_MARK, IContentDescriptionExtended.DETECTED_CHARSET, IContentDescriptionExtended.UNSUPPORTED_CHARSET, IContentDescriptionExtended.APPROPRIATE_DEFAULT};
public int describe(InputStream contents, IContentDescription description) throws IOException {
int result = IContentDescriber.INDETERMINATE;
if (description == null) {
result = computeValidity(contents);
}
else {
calculateSupportedOptions(contents, description);
result = computeValidity(contents);
}
return result;
}
public int describe(Reader contents, IContentDescription description) throws IOException {
int result = IContentDescriber.INDETERMINATE;
if (description == null) {
result = computeValidity(contents);
}
else {
calculateSupportedOptions(contents, description);
result = computeValidity(contents);
}
return result;
}
public QualifiedName[] getSupportedOptions() {
return SUPPORTED_OPTIONS;
}
private void calculateSupportedOptions(InputStream contents, IContentDescription description) throws IOException {
if (isRelevent(description)) {
IResourceCharsetDetector detector = getDetector();
detector.set(contents);
handleCalculations(description, detector);
}
}
/**
* @param contents
* @param description
* @throws IOException
*/
private void calculateSupportedOptions(Reader contents, IContentDescription description) throws IOException {
if (isRelevent(description)) {
IResourceCharsetDetector detector = getDetector();
detector.set(contents);
handleCalculations(description, detector);
}
}
private int computeValidity(InputStream inputStream) {
// currently no specific check for validilty
// based on contents.
return IContentDescriber.INDETERMINATE;
}
private int computeValidity(Reader reader) {
// currently no specific check for validilty
// based on contents.
return IContentDescriber.INDETERMINATE;
}
// same rules as for XML
private IResourceCharsetDetector getDetector() {
return new XMLResourceEncodingDetector();
}
/**
* @param description
* @param detector
* @throws IOException
*/
private void handleCalculations(IContentDescription description, IResourceCharsetDetector detector) throws IOException {
// note: if we're asked for one, we set them all. I need to be sure if
// called
// mulitiple times (one for each, say) that we don't waste time
// processing same
// content again.
EncodingMemento encodingMemento = ((XMLResourceEncodingDetector) detector).getEncodingMemento();
// TODO: I need to verify to see if this BOM work is always done
// by text type.
Object detectedByteOrderMark = encodingMemento.getUnicodeBOM();
if (detectedByteOrderMark != null) {
Object existingByteOrderMark = description.getProperty(IContentDescription.BYTE_ORDER_MARK);
// not sure why would ever be different, so if is different, may
// need to "push" up into base.
if (!detectedByteOrderMark.equals(existingByteOrderMark))
description.setProperty(IContentDescription.BYTE_ORDER_MARK, detectedByteOrderMark);
}
if (!encodingMemento.isValid()) {
// note: after setting here, its the mere presence of
// IContentDescriptionExtended.UNSUPPORTED_CHARSET
// in the resource's description that can be used to determine if
// invalid
// in those cases, the "detected" property contains an
// "appropriate default" to use.
description.setProperty(IContentDescriptionExtended.UNSUPPORTED_CHARSET, encodingMemento.getInvalidEncoding());
description.setProperty(IContentDescriptionExtended.APPROPRIATE_DEFAULT, encodingMemento.getAppropriateDefault());
}
Object detectedCharset = encodingMemento.getDetectedCharsetName();
Object javaCharset = encodingMemento.getJavaCharsetName();
// we always include detected, if its different than java
handleDetectedSpecialCase(description, detectedCharset, javaCharset);
if (javaCharset != null) {
Object existingCharset = description.getProperty(IContentDescription.CHARSET);
if (javaCharset.equals(existingCharset)) {
handleDetectedSpecialCase(description, detectedCharset, javaCharset);
}
else {
// we may need to add what we found, but only need to add
// if different from default.the
Object defaultCharset = getDetector().getSpecDefaultEncoding();
if (defaultCharset != null) {
if (!defaultCharset.equals(javaCharset)) {
description.setProperty(IContentDescription.CHARSET, javaCharset);
}
}
else {
// assuming if there is no spec default, we always need to
// add, I'm assuming
description.setProperty(IContentDescription.CHARSET, javaCharset);
}
}
}
}
private void handleDetectedSpecialCase(IContentDescription description, Object detectedCharset, Object javaCharset) {
// since equal, we don't need to add, but if our detected version is
// different than
// javaCharset, then we should add it. This will happen, for example,
// if there's
// differences in case, or differences due to override properties
if (detectedCharset != null) {
// if (!detectedCharset.equals(javaCharset)) {
// description.setProperty(IContentDescriptionExtended.DETECTED_CHARSET,
// detectedCharset);
// }
// Once we detected a charset, we should set the property even
// though it's the same as javaCharset
// because there are clients that rely on this property to
// determine if the charset is actually detected in file or not.
description.setProperty(IContentDescriptionExtended.DETECTED_CHARSET, detectedCharset);
}
}
/**
* @param description
* @return
*/
private boolean isRelevent(IContentDescription description) {
boolean result = false;
if (description == null)
result = false;
else if (description.isRequested(IContentDescription.BYTE_ORDER_MARK))
result = true;
else if (description.isRequested(IContentDescription.CHARSET))
result = true;
else if (description.isRequested(IContentDescriptionExtended.APPROPRIATE_DEFAULT))
result = true;
else if (description.isRequested(IContentDescriptionExtended.DETECTED_CHARSET))
result = true;
else if (description.isRequested(IContentDescriptionExtended.UNSUPPORTED_CHARSET))
result = true;
return result;
}
}
|
