01: /*
02: * WebSphinx web-crawling toolkit
03: *
04: * Copyright (c) 1998-2002 Carnegie Mellon University. All rights
05: * reserved.
06: *
07: * Redistribution and use in source and binary forms, with or without
08: * modification, are permitted provided that the following conditions
09: * are met:
10: *
11: * 1. Redistributions of source code must retain the above copyright
12: * notice, this list of conditions and the following disclaimer.
13: *
14: * 2. Redistributions in binary form must reproduce the above copyright
15: * notice, this list of conditions and the following disclaimer in
16: * the documentation and/or other materials provided with the
17: * distribution.
18: *
19: * THIS SOFTWARE IS PROVIDED BY CARNEGIE MELLON UNIVERSITY ``AS IS'' AND
20: * ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
21: * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
22: * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL CARNEGIE MELLON UNIVERSITY
23: * NOR ITS EMPLOYEES BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24: * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25: * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26: * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27: * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28: * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29: * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30: *
31: */
32:
33: package websphinx.workbench;
34:
35: import websphinx.*;
36:
37: public class ContentPredicate implements LinkPredicate, PagePredicate {
38: Pattern pattern;
39: boolean overHTML;
40:
41: public ContentPredicate(Pattern pattern, boolean overHTML) {
42: this .pattern = pattern;
43: this .overHTML = overHTML;
44: }
45:
46: public boolean equals(Object object) {
47: if (!(object instanceof ContentPredicate))
48: return false;
49: ContentPredicate p = (ContentPredicate) object;
50: return p.pattern.equals(pattern) && p.overHTML == overHTML;
51: }
52:
53: public Pattern getPattern() {
54: return pattern;
55: }
56:
57: public boolean getOverHTML() {
58: return overHTML;
59: }
60:
61: public void connected(Crawler crawler) {
62: }
63:
64: public void disconnected(Crawler crawler) {
65: }
66:
67: public boolean shouldVisit(Link link) {
68: return overHTML ? pattern.found(link) : pattern.found(link
69: .toText());
70: }
71:
72: public boolean shouldActOn(Page page) {
73: return overHTML ? pattern.found(page) : pattern.found(page
74: .toText());
75: }
76: }
|