KickJava   Java API By Example, From Geeks To Geeks.

Java > Open Source Codes > org > archive > crawler > fetcher > HeritrixHttpMethodRetryHandler


1 /* HttpRecorderGetMethod
2 *
3  * Created on Sep 29, 2004
4 *
5 * Copyright (C) 2003 Internet Archive.
6 *
7 * This file is part of the Heritrix web crawler (crawler.archive.org).
8 *
9 * 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.fetcher;
24
25 import java.io.IOException JavaDoc;
26 import java.net.SocketTimeoutException JavaDoc;
27
28 import org.apache.commons.httpclient.HttpMethod;
29 import org.apache.commons.httpclient.HttpMethodRetryHandler;
30 import org.apache.commons.httpclient.NoHttpResponseException;
31 import org.apache.commons.httpclient.methods.PostMethod;
32
33 /**
34  * Retry handler that tries ten times to establish connection and then once
35  * established, if a GET method, tries ten times to get response (If POST,
36  * it tries once only).
37  *
38  * Its unsafe retrying POSTs. See 'Rule of Thumb' under 'Method Recovery'
39  * here: <a HREF="http://jakarta.apache.org/commons/httpclient/tutorial.html">
40  * HttpClient Tutorial</a>.
41  *
42  * @author stack
43  * @version $Date: 2005/06/12 17:59:14 $, $Revision: 1.2 $
44  */
45 public class HeritrixHttpMethodRetryHandler implements HttpMethodRetryHandler {
46     private static final int DEFAULT_RETRY_COUNT = 10;
47     
48     private final int maxRetryCount;
49     
50     /**
51      * Constructor.
52      */
53     public HeritrixHttpMethodRetryHandler() {
54         this(DEFAULT_RETRY_COUNT);
55     }
56     
57     /**
58      * Constructor.
59      * @param maxRetryCount Maximum amount of times to retry.
60      */
61     public HeritrixHttpMethodRetryHandler(int maxRetryCount) {
62         this.maxRetryCount = maxRetryCount;
63     }
64     
65     public boolean retryMethod(HttpMethod method, IOException JavaDoc exception,
66             int executionCount) {
67         if(exception instanceof SocketTimeoutException JavaDoc) {
68             // already waited for the configured amount of time with no reply;
69 // do not retry further until next go round
70 return false;
71         }
72         if (executionCount >= this.maxRetryCount) {
73             // Do not retry if over max retry count
74 return false;
75         }
76         if (exception instanceof NoHttpResponseException) {
77             // Retry if the server dropped connection on us
78 return true;
79         }
80         if (!method.isRequestSent() && (!(method instanceof PostMethod))) {
81             // Retry if the request has not been sent fully or
82 // if it's OK to retry methods that have been sent
83 return true;
84         }
85         // otherwise do not retry
86 return false;
87     }
88 }
89
Popular Tags