01: /* StripWWWRule
02: *
03: * Created on Oct 5, 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.canonicalize;
24:
25: import java.util.regex.Pattern;
26:
27: /**
28: * Strip any 'www' found on http/https URLs, IF they have some
29: * path/query component (content after third slash). (Top 'slash page'
30: * URIs are left unstripped, so that we prefer crawling redundant
31: * top pages to missing an entire site only available from either
32: * the www-full or www-less hostname, but not both).
33: * @author stack
34: * @version $Date: 2006-09-25 20:27:35 +0000 (Mon, 25 Sep 2006) $, $Revision: 4655 $
35: */
36: public class StripWWWRule extends BaseRule {
37:
38: private static final long serialVersionUID = -5416391108485746976L;
39:
40: private static final String DESCRIPTION = "Strip any 'www' found. "
41: + "Use this rule to equate 'http://www.archive.org/index.html' and"
42: + " 'http://archive.org/index.html'. The resulting canonicalization"
43: + " returns 'http://archive.org/index.html'. It removes any www's "
44: + "found, except on URIs that have no path/query component "
45: + "('slash' pages). Operates on http and https schemes only. "
46: + "Use the more general StripWWWNRule if you want to strip both 'www' "
47: + "and 'www01', 'www02', etc.";
48:
49: private static final Pattern REGEX = Pattern
50: .compile("(?i)^(https?://)(?:www\\.)([^/]*/.+)$");
51:
52: public StripWWWRule(String name) {
53: super (name, DESCRIPTION);
54: }
55:
56: public String canonicalize(String url, Object context) {
57: return doStripRegexMatch(url, REGEX.matcher(url));
58: }
59: }
|