1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25 package org.archive.crawler.postprocessor;
26
27 /***
28 * A specialized ContentBasedWaitEvaluator. Comes preset with a regular
29 * expression that matches text documents. <code>^image/.*$</code>
30 *
31 * @author Kristinn Sigurdsson
32 *
33 * @see org.archive.crawler.postprocessor.ContentBasedWaitEvaluator
34 */
35 public class ImageWaitEvaluator extends ContentBasedWaitEvaluator {
36
37 private static final long serialVersionUID = -2762377129860398333L;
38
39 protected final static Long DEFAULT_INITIAL_WAIT_INTERVAL =
40 new Long(172800);
41
42 protected final static String DEFAULT_CONTENT_REGEXPR = "^image/.*$";
43
44 /***
45 * Constructor
46 *
47 * @param name The name of the module
48 */
49 public ImageWaitEvaluator(String name) {
50 super(name,"Evaluates how long to wait before fetching a URI again. " +
51 "Only handles CrawlURIs whose content type indicates a " +
52 "image document (^image/.*$). " +
53 "Typically, this processor should be in the post processing " +
54 "chain. It will pass if another wait evaluator has already " +
55 "processed the CrawlURI.",
56 DEFAULT_CONTENT_REGEXPR,
57 DEFAULT_INITIAL_WAIT_INTERVAL,
58 DEFAULT_MAX_WAIT_INTERVAL,
59 DEFAULT_MIN_WAIT_INTERVAL,
60 DEFAULT_UNCHANGED_FACTOR,
61 DEFAULT_CHANGED_FACTOR);
62 }
63
64
65 }