Java Reference
In-Depth Information
import com.heatonresearch.httprecipes.spider.workload.*;
/**
* The Heaton Research Spider
* Copyright 2007 by Heaton Research, Inc.
*
* HTTP Programming Recipes for Java ISBN: 0-9773206-6-9
* http://www.heatonresearch.com/articles/series/16/
*
* SQLWorkloadManager: This workload manager stores the URL
* lists in an SQL database. This workload manager uses two
* tables, which can be created as follows:
*
* CREATE TABLE 'spider_host' (
* 'host_id' int(10) unsigned NOT NULL auto_increment,
* 'host' varchar(255) NOT NULL default '',
* 'status' varchar(1) NOT NULL default '',
* 'urls_done' int(11) NOT NULL,
* 'urls_error' int(11) NOT NULL,
* PRIMARY KEY ('host_id')
* )
*
* CREATE TABLE 'spider_workload' (
* 'workload_id' int(10) unsigned NOT NULL auto_increment,
* 'host' int(10) unsigned NOT NULL,
* 'url' varchar(2083) NOT NULL default '',
* 'status' varchar(1) NOT NULL default '',
* 'depth' int(10) unsigned NOT NULL,
* 'url_hash' int(11) NOT NULL,
* 'source_id' int(11) NOT NULL,
* PRIMARY KEY ('workload_id'),
* KEY 'status' ('status'),
* KEY 'url_hash' ('url_hash'),
* KEY 'host' ('host')
* )
*
*
* This class is released under the:
* GNU Lesser General Public License (LGPL)
* http://www.gnu.org/copyleft/lesser.html
*
* @author Jeff Heaton
* @version 1.1
*/
public class SQLWorkloadManager implements WorkloadManager
{
Search WWH ::




Custom Search