01: /* CanonicalizationRule
02: *
03: * Created on Oct 7, 2004
04: *
05: * Copyright (C) 2004 Internet Archive.
06: *
07: * This file is part of the Heritrix web crawler (crawler.archive.org).
08: *
09: * Heritrix is free software; you can redistribute it and/or modify
10: * it under the terms of the GNU Lesser Public License as published by
11: * the Free Software Foundation; either version 2.1 of the License, or
12: * any later version.
13: *
14: * Heritrix is distributed in the hope that it will be useful,
15: * but WITHOUT ANY WARRANTY; without even the implied warranty of
16: * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17: * GNU Lesser Public License for more details.
18: *
19: * You should have received a copy of the GNU Lesser Public License
20: * along with Heritrix; if not, write to the Free Software
21: * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
22: */
23: package org.archive.crawler.url;
24:
25: /**
26: * A rule to apply canonicalizing a url.
27: * @author stack
28: * @version $Date: 2004-10-08 17:39:42 +0000 (Fri, 08 Oct 2004) $, $Revision: 2627 $
29: */
30: public interface CanonicalizationRule {
31: /**
32: * Apply this canonicalization rule.
33: *
34: * @param url Url string we apply this rule to.
35: * @param context An object that will provide context for the settings
36: * system. The UURI of the URL we're canonicalizing is an example of
37: * an object that provides context.
38: * @return Result of applying this rule to passed <code>url</code>.
39: */
40: public String canonicalize(String url, Object context);
41:
42: /**
43: * @return Name of this rule.
44: */
45: public String getName();
46:
47: /**
48: * @param context An object that will provide context for the settings
49: * system. The UURI of the URL we're canonicalizing is an example of
50: * an object that provides context.
51: * @return True if this rule is enabled and to be run.
52: */
53: public boolean isEnabled(Object context);
54: }
|