1 /* OnDomainsDecideRule
2 *
3 * $Id: OnDomainsDecideRule.java 4649 2006-09-25 17:16:55Z paul_jack $
4 *
5 * Created on Apr 5, 2005
6 *
7 * Copyright (C) 2005 Internet Archive.
8 *
9 * This file is part of the Heritrix web crawler (crawler.archive.org).
10 *
11 * Heritrix is free software; you can redistribute it and/or modify
12 * it under the terms of the GNU Lesser Public License as published by
13 * the Free Software Foundation; either version 2.1 of the License, or
14 * any later version.
15 *
16 * Heritrix is distributed in the hope that it will be useful,
17 * but WITHOUT ANY WARRANTY; without even the implied warranty of
18 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 * GNU Lesser Public License for more details.
20 *
21 * You should have received a copy of the GNU Lesser Public License
22 * along with Heritrix; if not, write to the Free Software
23 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
24 */
25 package org.archive.crawler.deciderules;
26
27
28 import org.archive.util.SurtPrefixSet;
29
30
31 /***
32 * Rule applies configured decision to any URIs that
33 * are on one of the domains in the configured set of
34 * domains, filled from the seed set.
35 *
36 * @author gojomo
37 */
38 public class OnDomainsDecideRule extends SurtPrefixedDecideRule {
39
40 private static final long serialVersionUID = -3872369060554558805L;
41 //private static final Logger logger =
42 // Logger.getLogger(OnDomainsDecideRule.class.getName());
43 /***
44 * Usual constructor.
45 * @param name
46 */
47 public OnDomainsDecideRule(String name) {
48 super(name);
49 setDescription(
50 "OnDomainsDecideRule. Makes the configured decision " +
51 "for any URI which is inside one of the domains in the " +
52 "configured set of domains (derived from the seed" +
53 "list, with 'www' removed when present).");
54 // disable direct setting of SURTs-related options
55 //getElementFromDefinition(ATTR_SEEDS_AS_SURT_PREFIXES).setTransient(true);
56 //getElementFromDefinition(ATTR_SURTS_SOURCE_FILE).setTransient(true);
57 // leaving surts-dump as option helpful for debugging/learning, for now
58 //getElementFromDefinition(ATTR_SURTS_DUMP_FILE).setTransient(true);
59 }
60
61 /***
62 * Patch the SURT prefix set so that it only includes host-enforcing prefixes
63 *
64 * @see org.archive.crawler.deciderules.SurtPrefixedDecideRule#readPrefixes()
65 */
66 protected void readPrefixes() {
67 buildSurtPrefixSet();
68 surtPrefixes.convertAllPrefixesToDomains();
69 dumpSurtPrefixSet();
70 }
71
72 protected String prefixFrom(String uri) {
73 return SurtPrefixSet.convertPrefixToDomain(super.prefixFrom(uri));
74 }
75 }