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
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
|
/*
* @(#)DocumentParser.java 1.29 05/11/17
*
* Copyright 2006 Sun Microsystems, Inc. All rights reserved.
* SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
*/
package javax.swing.text.html.parser;
import javax.swing.text.SimpleAttributeSet;
import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.HTML;
import javax.swing.text.ChangedCharSetException;
import java.util.*;
import java.io.*;
import java.net.*;
/**
* A Parser for HTML Documents (actually, you can specify a DTD, but
* you should really only use this class with the html dtd in swing).
* Reads an InputStream of HTML and
* invokes the appropriate methods in the ParserCallback class. This
* is the default parser used by HTMLEditorKit to parse HTML url's.
* <p>This will message the callback for all valid tags, as well as
* tags that are implied but not explicitly specified. For example, the
* html string (<p>blah) only has a p tag defined. The callback
* will see the following methods:
* <ol><li><i>handleStartTag(html, ...)</i></li>
* <li><i>handleStartTag(head, ...)</i></li>
* <li><i>handleEndTag(head)</i></li>
* <li><i>handleStartTag(body, ...)</i></li>
* <li>handleStartTag(p, ...)</i></li>
* <li>handleText(...)</li>
* <li><i>handleEndTag(p)</i></li>
* <li><i>handleEndTag(body)</i></li>
* <li><i>handleEndTag(html)</i></li>
* </ol>
* The items in <i>italic</i> are implied, that is, although they were not
* explicitly specified, to be correct html they should have been present
* (head isn't necessary, but it is still generated). For tags that
* are implied, the AttributeSet argument will have a value of
* <code>Boolean.TRUE</code> for the key
* <code>HTMLEditorKit.ParserCallback.IMPLIED</code>.
* <p>HTML.Attributes defines a type safe enumeration of html attributes.
* If an attribute key of a tag is defined in HTML.Attribute, the
* HTML.Attribute will be used as the key, otherwise a String will be used.
* For example <p foo=bar class=neat> has two attributes. foo is
* not defined in HTML.Attribute, where as class is, therefore the
* AttributeSet will have two values in it, HTML.Attribute.CLASS with
* a String value of 'neat' and the String key 'foo' with a String value of
* 'bar'.
* <p>The position argument will indicate the start of the tag, comment
* or text. Similiar to arrays, the first character in the stream has a
* position of 0. For tags that are
* implied the position will indicate
* the location of the next encountered tag. In the first example,
* the implied start body and html tags will have the same position as the
* p tag, and the implied end p, html and body tags will all have the same
* position.
* <p>As html skips whitespace the position for text will be the position
* of the first valid character, eg in the string '\n\n\nblah'
* the text 'blah' will have a position of 3, the newlines are skipped.
* <p>
* For attributes that do not have a value, eg in the html
* string <code><foo blah></code> the attribute <code>blah</code>
* does not have a value, there are two possible values that will be
* placed in the AttributeSet's value:
* <ul>
* <li>If the DTD does not contain an definition for the element, or the
* definition does not have an explicit value then the value in the
* AttributeSet will be <code>HTML.NULL_ATTRIBUTE_VALUE</code>.
* <li>If the DTD contains an explicit value, as in:
* <code><!ATTLIST OPTION selected (selected) #IMPLIED></code>
* this value from the dtd (in this case selected) will be used.
* </ul>
* <p>
* Once the stream has been parsed, the callback is notified of the most
* likely end of line string. The end of line string will be one of
* \n, \r or \r\n, which ever is encountered the most in parsing the
* stream.
*
* @version 1.29 11/17/05
* @author Sunita Mani
*/
public class DocumentParser extends javax.swing.text.html.parser.Parser {
private int inbody;
private int intitle;
private int inhead;
private int instyle;
private int inscript;
private boolean seentitle;
private HTMLEditorKit.ParserCallback callback = null;
private boolean ignoreCharSet = false;
private static final boolean debugFlag = false;
public DocumentParser(DTD dtd) {
super(dtd);
}
public void parse(Reader in, HTMLEditorKit.ParserCallback callback, boolean ignoreCharSet) throws IOException {
this.ignoreCharSet = ignoreCharSet;
this.callback = callback;
parse(in);
// end of line
callback.handleEndOfLineString(getEndOfLineString());
}
/**
* Handle Start Tag.
*/
protected void handleStartTag(TagElement tag) {
Element elem = tag.getElement();
if (elem == dtd.body) {
inbody++;
} else if (elem == dtd.html) {
} else if (elem == dtd.head) {
inhead++;
} else if (elem == dtd.title) {
intitle++;
} else if (elem == dtd.style) {
instyle++;
} else if (elem == dtd.script) {
inscript++;
}
if (debugFlag) {
if (tag.fictional()) {
debug("Start Tag: " + tag.getHTMLTag() + " pos: " + getCurrentPos());
} else {
debug("Start Tag: " + tag.getHTMLTag() + " attributes: " +
getAttributes() + " pos: " + getCurrentPos());
}
}
if (tag.fictional()) {
SimpleAttributeSet attrs = new SimpleAttributeSet();
attrs.addAttribute(HTMLEditorKit.ParserCallback.IMPLIED,
Boolean.TRUE);
callback.handleStartTag(tag.getHTMLTag(), attrs,
getBlockStartPosition());
} else {
callback.handleStartTag(tag.getHTMLTag(), getAttributes(),
getBlockStartPosition());
flushAttributes();
}
}
protected void handleComment(char text[]) {
if (debugFlag) {
debug("comment: ->" + new String(text) + "<-"
+ " pos: " + getCurrentPos());
}
callback.handleComment(text, getBlockStartPosition());
}
/**
* Handle Empty Tag.
*/
protected void handleEmptyTag(TagElement tag) throws ChangedCharSetException {
Element elem = tag.getElement();
if (elem == dtd.meta && !ignoreCharSet) {
SimpleAttributeSet atts = getAttributes();
if (atts != null) {
String content = (String)atts.getAttribute(HTML.Attribute.CONTENT);
if (content != null) {
if ("content-type".equalsIgnoreCase((String)atts.getAttribute(HTML.Attribute.HTTPEQUIV))) {
if (!content.equalsIgnoreCase("text/html") &&
!content.equalsIgnoreCase("text/plain")) {
throw new ChangedCharSetException(content, false);
}
} else if ("charset" .equalsIgnoreCase((String)atts.getAttribute(HTML.Attribute.HTTPEQUIV))) {
throw new ChangedCharSetException(content, true);
}
}
}
}
if (inbody != 0 || elem == dtd.meta || elem == dtd.base || elem == dtd.isindex || elem == dtd.style || elem == dtd.link) {
if (debugFlag) {
if (tag.fictional()) {
debug("Empty Tag: " + tag.getHTMLTag() + " pos: " + getCurrentPos());
} else {
debug("Empty Tag: " + tag.getHTMLTag() + " attributes: "
+ getAttributes() + " pos: " + getCurrentPos());
}
}
if (tag.fictional()) {
SimpleAttributeSet attrs = new SimpleAttributeSet();
attrs.addAttribute(HTMLEditorKit.ParserCallback.IMPLIED,
Boolean.TRUE);
callback.handleSimpleTag(tag.getHTMLTag(), attrs,
getBlockStartPosition());
} else {
callback.handleSimpleTag(tag.getHTMLTag(), getAttributes(),
getBlockStartPosition());
flushAttributes();
}
}
}
/**
* Handle End Tag.
*/
protected void handleEndTag(TagElement tag) {
Element elem = tag.getElement();
if (elem == dtd.body) {
inbody--;
} else if (elem == dtd.title) {
intitle--;
seentitle = true;
} else if (elem == dtd.head) {
inhead--;
} else if (elem == dtd.style) {
instyle--;
} else if (elem == dtd.script) {
inscript--;
}
if (debugFlag) {
debug("End Tag: " + tag.getHTMLTag() + " pos: " + getCurrentPos());
}
callback.handleEndTag(tag.getHTMLTag(), getBlockStartPosition());
}
/**
* Handle Text.
*/
protected void handleText(char data[]) {
if (data != null) {
if (inscript != 0) {
callback.handleComment(data, getBlockStartPosition());
return;
}
if (inbody != 0 || ((instyle != 0) ||
((intitle != 0) && !seentitle))) {
if (debugFlag) {
debug("text: ->" + new String(data) + "<-" + " pos: " + getCurrentPos());
}
callback.handleText(data, getBlockStartPosition());
}
}
}
/*
* Error handling.
*/
protected void handleError(int ln, String errorMsg) {
if (debugFlag) {
debug("Error: ->" + errorMsg + "<-" + " pos: " + getCurrentPos());
}
/* PENDING: need to improve the error string. */
callback.handleError(errorMsg, getCurrentPos());
}
/*
* debug messages
*/
private void debug(String msg) {
System.out.println(msg);
}
} |
