1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23 package org.archive.hcc.client;
24
25 /***
26 * Defines the interface for interacting with a completed crawl job.
27 * @author Daniel Bernstein (dbernstein@archive.org)
28 */
29 public interface CompletedCrawlJob extends CrawlJob {
30 /***
31 * Returns a crawl report which is some statistics summarizing
32 * the end state of the crawl.
33 * @return
34 * @throws ClusterException
35 */
36 public String getCrawlReport() throws ClusterException;
37 /***
38 * Returns a seed report which details final crawl status of all the seeds.
39 * @return
40 * @throws ClusterException
41 */
42
43 public String getSeedReport() throws ClusterException;
44
45 /***
46 * A count of bytes and docs collected by host.
47 * @return
48 * @throws ClusterException
49 */
50 public String getHostReport() throws ClusterException;
51
52 /***
53 * A count of docs per host per source seed.
54 * @return
55 * @throws ClusterException
56 */
57 public String getSourceReport() throws ClusterException;
58
59 /***
60 * A count of bytes and docs collected by mime type.
61 * @return
62 * @throws ClusterException
63 */
64
65 public String getMimeTypeReport() throws ClusterException;
66 }