01: /* StripUserinfoRule
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 'userinfo' found on http/https URLs.
29: * @author stack
30: * @version $Date: 2006-09-25 20:27:35 +0000 (Mon, 25 Sep 2006) $, $Revision: 4655 $
31: */
32: public class StripUserinfoRule extends BaseRule {
33:
34: private static final long serialVersionUID = -4271062607638914996L;
35:
36: private static final String DESCRIPTION = "Strip any 'userinfo' found. "
37: + "Use this rule to equate 'http://stack:psswrd@archive.org/index.htm'"
38: + " and 'http://archive.org/index.htm'. The resulting canonicalization"
39: + " returns 'http://archive.org/index.htm'. Removes any userinfo"
40: + " found. Operates on http/https/ftp/ftps schemes only.";
41:
42: /**
43: * Strip userinfo.
44: */
45: private static final Pattern REGEX = Pattern.compile(
46: "^((?:(?:https?)|(?:ftps?))://)(?:[^/]+@)(.*)$",
47: Pattern.CASE_INSENSITIVE);
48:
49: public StripUserinfoRule(String name) {
50: super (name, DESCRIPTION);
51: }
52:
53: public String canonicalize(String url, Object context) {
54: return doStripRegexMatch(url, REGEX.matcher(url));
55: }
56: }
|