1 /* MemFPMergeUriUniqFilter
2 *
3 * $Id: MemFPMergeUriUniqFilter.java 4647 2006-09-22 18:39:39Z paul_jack $
4 *
5 * Created on Dec 14, 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.util;
26
27 import it.unimi.dsi.fastutil.longs.LongArrayList;
28 import it.unimi.dsi.fastutil.longs.LongIterator;
29
30 /***
31 * Crude all-in-memory FP-merging UriUniqFilter.
32 *
33 * @author gojomo
34 */
35 public class MemFPMergeUriUniqFilter extends FPMergeUriUniqFilter {
36 protected LongArrayList allFps = new LongArrayList();
37 protected LongArrayList newFps;
38
39 /* (non-Javadoc)
40 * @see org.archive.crawler.util.FPMergeUriUniqFilter#beginFpMerge()
41 */
42 protected LongIterator beginFpMerge() {
43 newFps = new LongArrayList((int) (allFps.size()+(pending()/2)));
44 return allFps.iterator();
45 }
46
47 /* (non-Javadoc)
48 * @see org.archive.crawler.util.FPMergeUriUniqFilter#addNewFp(java.lang.Long)
49 */
50 protected void addNewFp(long currFp) {
51 newFps.add(currFp);
52 }
53
54 /* (non-Javadoc)
55 * @see org.archive.crawler.util.FPMergeUriUniqFilter#finishFpMerge()
56 */
57 protected void finishFpMerge() {
58 allFps = newFps;
59 newFps = null;
60 }
61
62 /* (non-Javadoc)
63 * @see org.archive.crawler.datamodel.UriUniqFilter#count()
64 */
65 public long count() {
66 return allFps.size();
67 }
68
69 }