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
|
/*
* $Id: LinkFilter.java,v 1.1 2003-02-01 02:10:19 cbj Exp $
* Copyright (C) 1999-2001 David Brownell
*
* This file is part of GNU JAXP, a library.
*
* GNU JAXP is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* GNU JAXP is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* As a special exception, if you link this library with other files to
* produce an executable, this library does not by itself cause the
* resulting executable to be covered by the GNU General Public License.
* This exception does not however invalidate any other reasons why the
* executable file might be covered by the GNU General Public License.
*/
package gnu.xml.pipeline;
import java.io.IOException;
import java.net.URL;
import java.util.Enumeration;
import java.util.Vector;
import org.xml.sax.Attributes;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
// $Id: LinkFilter.java,v 1.1 2003-02-01 02:10:19 cbj Exp $
/**
* Pipeline filter to remember XHTML links found in a document,
* so they can later be crawled. Fragments are not counted, and duplicates
* are ignored. Callers are responsible for filtering out URLs they aren't
* interested in. Events are passed through unmodified.
*
* <p> Input MUST include a setDocumentLocator() call, as it's used to
* resolve relative links in the absence of a "base" element. Input MUST
* also include namespace identifiers, since it is the XHTML namespace
* identifier which is used to identify the relevant elements.
*
* <p><em>FIXME:</em> handle xml:base attribute ... in association with
* a stack of base URIs. Similarly, recognize/support XLink data.
*
* @author David Brownell
* @version $Date: 2003-02-01 02:10:19 $
*/
public class LinkFilter extends EventFilter
{
// for storing URIs
private Vector vector = new Vector ();
// struct for "full" link record (tbd)
// these for troubleshooting original source:
// original uri
// uri as resolved (base, relative, etc)
// URI of originating doc
// line #
// original element + attrs (img src, desc, etc)
// XLink model of the link ... for inter-site pairups ?
private String baseURI;
private boolean siteRestricted = false;
//
// XXX leverage blacklist info (like robots.txt)
//
// XXX constructor w/param ... pipeline for sending link data
// probably XHTML --> XLink, providing info as sketched above
//
/**
* Constructs a new event filter, which collects links in private data
* structure for later enumeration.
*/
// constructor used by PipelineFactory
public LinkFilter ()
{
super.setContentHandler (this);
}
/**
* Constructs a new event filter, which collects links in private data
* structure for later enumeration and passes all events, unmodified,
* to the next consumer.
*/
// constructor used by PipelineFactory
public LinkFilter (EventConsumer next)
{
super (next);
super.setContentHandler (this);
}
/**
* Returns an enumeration of the links found since the filter
* was constructed, or since removeAllLinks() was called.
*
* @return enumeration of strings.
*/
public Enumeration getLinks ()
{
return vector.elements ();
}
/**
* Removes records about all links reported to the event
* stream, as if the filter were newly created.
*/
public void removeAllLinks ()
{
vector = new Vector ();
}
/**
* Collects URIs for (X)HTML content from elements which hold them.
*/
public void startElement (
String uri,
String localName,
String qName,
Attributes atts
) throws SAXException
{
String link;
// Recognize XHTML links.
if ("http://www.w3.org/1999/xhtml".equals (uri)) {
if ("a".equals (localName) || "base".equals (localName)
|| "area".equals (localName))
link = atts.getValue ("href");
else if ("iframe".equals (localName) || "frame".equals (localName))
link = atts.getValue ("src");
else if ("blockquote".equals (localName) || "q".equals (localName)
|| "ins".equals (localName) || "del".equals (localName))
link = atts.getValue ("cite");
else
link = null;
link = maybeAddLink (link);
// "base" modifies designated baseURI
if ("base".equals (localName) && link != null)
baseURI = link;
if ("iframe".equals (localName) || "img".equals (localName))
maybeAddLink (atts.getValue ("longdesc"));
}
super.startElement (uri, localName, qName, atts);
}
private String maybeAddLink (String link)
{
int index;
// ignore empty links and fragments inside docs
if (link == null)
return null;
if ((index = link.indexOf ("#")) >= 0)
link = link.substring (0, index);
if (link.equals (""))
return null;
try {
// get the real URI
URL base = new URL ((baseURI != null)
? baseURI
: getDocumentLocator ().getSystemId ());
URL url = new URL (base, link);
link = url.toString ();
// ignore duplicates
if (vector.contains (link))
return link;
// other than what "base" does, stick to original site:
if (siteRestricted) {
// don't switch protocols
if (!base.getProtocol ().equals (url.getProtocol ()))
return link;
// don't switch servers
if (base.getHost () != null
&& !base.getHost ().equals (url.getHost ()))
return link;
}
vector.addElement (link);
return link;
} catch (IOException e) {
// bad URLs we don't want
}
return null;
}
/**
* Reports an error if no Locator has been made available.
*/
public void startDocument ()
throws SAXException
{
if (getDocumentLocator () == null)
throw new SAXException ("no Locator!");
}
/**
* Forgets about any base URI information that may be recorded.
* Applications will often want to call removeAllLinks(), likely
* after examining the links which were reported.
*/
public void endDocument ()
throws SAXException
{
baseURI = null;
super.endDocument ();
}
}
|
