Source Code Cross Referenced for BeanShellProcessor.java in  » Web-Crawler » heritrix » org » archive » crawler » processor » Java Source Code / Java DocumentationJava Source Code and Java Documentation

Java Source Code / Java Documentation
1. 6.0 JDK Core
2. 6.0 JDK Modules
3. 6.0 JDK Modules com.sun
4. 6.0 JDK Modules com.sun.java
5. 6.0 JDK Modules sun
6. 6.0 JDK Platform
7. Ajax
8. Apache Harmony Java SE
9. Aspect oriented
10. Authentication Authorization
11. Blogger System
12. Build
13. Byte Code
14. Cache
15. Chart
16. Chat
17. Code Analyzer
18. Collaboration
19. Content Management System
20. Database Client
21. Database DBMS
22. Database JDBC Connection Pool
23. Database ORM
24. Development
25. EJB Server geronimo
26. EJB Server GlassFish
27. EJB Server JBoss 4.2.1
28. EJB Server resin 3.1.5
29. ERP CRM Financial
30. ESB
31. Forum
32. GIS
33. Graphic Library
34. Groupware
35. HTML Parser
36. IDE
37. IDE Eclipse
38. IDE Netbeans
39. Installer
40. Internationalization Localization
41. Inversion of Control
42. Issue Tracking
43. J2EE
44. JBoss
45. JMS
46. JMX
47. Library
48. Mail Clients
49. Net
50. Parser
51. PDF
52. Portal
53. Profiler
54. Project Management
55. Report
56. RSS RDF
57. Rule Engine
58. Science
59. Scripting
60. Search Engine
61. Security
62. Sevlet Container
63. Source Control
64. Swing Library
65. Template Engine
66. Test Coverage
67. Testing
68. UML
69. Web Crawler
70. Web Framework
71. Web Mail
72. Web Server
73. Web Services
74. Web Services apache cxf 2.0.1
75. Web Services AXIS2
76. Wiki Engine
77. Workflow Engines
78. XML
79. XML UI
Java
Java Tutorial
Java Open Source
Jar File Download
Java Articles
Java Products
Java by API
Photoshop Tutorials
Maya Tutorials
Flash Tutorials
3ds-Max Tutorials
Illustrator Tutorials
GIMP Tutorials
C# / C Sharp
C# / CSharp Tutorial
C# / CSharp Open Source
ASP.Net
ASP.NET Tutorial
JavaScript DHTML
JavaScript Tutorial
JavaScript Reference
HTML / CSS
HTML CSS Reference
C / ANSI-C
C Tutorial
C++
C++ Tutorial
Ruby
PHP
Python
Python Tutorial
Python Open Source
SQL Server / T-SQL
SQL Server / T-SQL Tutorial
Oracle PL / SQL
Oracle PL/SQL Tutorial
PostgreSQL
SQL / MySQL
MySQL Tutorial
VB.Net
VB.Net Tutorial
Flash / Flex / ActionScript
VBA / Excel / Access / Word
XML
XML Tutorial
Microsoft Office PowerPoint 2007 Tutorial
Microsoft Office Excel 2007 Tutorial
Microsoft Office Word 2007 Tutorial
Java Source Code / Java Documentation » Web Crawler » heritrix » org.archive.crawler.processor 
Source Cross Referenced  Class Diagram Java Document (Java Doc) 


001:        /* BeanShellProcessor
002:         *
003:         * Created on Aug 4, 2006
004:         *
005:         * Copyright (C) 2006 Internet Archive.
006:         *
007:         * This file is part of the Heritrix web crawler (crawler.archive.org).
008:         *
009:         * Heritrix is free software; you can redistribute it and/or modify
010:         * it under the terms of the GNU Lesser Public License as published by
011:         * the Free Software Foundation; either version 2.1 of the License, or
012:         * any later version.
013:         *
014:         * Heritrix is distributed in the hope that it will be useful,
015:         * but WITHOUT ANY WARRANTY; without even the implied warranty of
016:         * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
017:         * GNU Lesser Public License for more details.
018:         *
019:         * You should have received a copy of the GNU Lesser Public License
020:         * along with Heritrix; if not, write to the Free Software
021:         * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
022:         */
023:        package org.archive.crawler.processor;
024:
025:        import java.io.File;
026:        import java.io.IOException;
027:        import java.util.Collections;
028:        import java.util.HashMap;
029:        import java.util.Map;
030:        import java.util.logging.Level;
031:        import java.util.logging.Logger;
032:
033:        import org.archive.crawler.datamodel.CrawlURI;
034:        import org.archive.crawler.datamodel.FetchStatusCodes;
035:        import org.archive.crawler.framework.Processor;
036:        import org.archive.crawler.settings.SimpleType;
037:        import org.archive.crawler.settings.Type;
038:
039:        import bsh.EvalError;
040:        import bsh.Interpreter;
041:
042:        /**
043:         * A processor which runs a BeanShell script on the CrawlURI.
044:         *
045:         * Script source may be provided via a file
046:         * local to the crawler. 
047:         * Script source should define
048:         * a method with one argument, 'run(curi)'. Each processed CrawlURI is
049:         * passed to this script method. 
050:         * 
051:         * Other variables available to the script include 'self' (this 
052:         * BeanShellProcessor instance) and 'controller' (the crawl's 
053:         * CrawlController instance). 
054:         * 
055:         * @author gojomo
056:         * @version $Date: 2006-09-25 20:19:54 +0000 (Mon, 25 Sep 2006) $, $Revision: 4654 $
057:         */
058:        public class BeanShellProcessor extends Processor implements 
059:                FetchStatusCodes {
060:
061:            private static final long serialVersionUID = 6926589944337050754L;
062:
063:            private static final Logger logger = Logger
064:                    .getLogger(BeanShellProcessor.class.getName());
065:
066:            /** setting for script file */
067:            public final static String ATTR_SCRIPT_FILE = "script-file";
068:
069:            /** whether each thread should have its own script runner (true), or
070:             * they should share a single script runner with synchronized access */
071:            public final static String ATTR_ISOLATE_THREADS = "isolate-threads";
072:
073:            protected ThreadLocal<Interpreter> threadInterpreter;
074:            protected Interpreter sharedInterpreter;
075:            public Map<Object, Object> sharedMap = Collections
076:                    .synchronizedMap(new HashMap<Object, Object>());
077:
078:            /**
079:             * Constructor.
080:             * @param name Name of this processor.
081:             */
082:            public BeanShellProcessor(String name) {
083:                super (
084:                        name,
085:                        "BeanShellProcessor. Runs the BeanShell script source "
086:                                + "(supplied directly or via a file path) against the "
087:                                + "current URI. Source should define a script method "
088:                                + "'process(curi)' which will be passed the current CrawlURI. "
089:                                + "The script may also access this BeanShellProcessor via"
090:                                + "the 'self' variable and the CrawlController via the "
091:                                + "'controller' variable.");
092:                Type t = addElementToDefinition(new SimpleType(
093:                        ATTR_SCRIPT_FILE, "BeanShell script file", ""));
094:                t.setOverrideable(false);
095:                t = addElementToDefinition(new SimpleType(
096:                        ATTR_ISOLATE_THREADS,
097:                        "Whether each ToeThread should get its own independent "
098:                                + "script context, or they should share synchronized access "
099:                                + "to one context. Default is true, meaning each threads "
100:                                + "gets its own isolated context.", true));
101:                t.setOverrideable(false);
102:
103:            }
104:
105:            protected synchronized void innerProcess(CrawlURI curi) {
106:                // depending on previous configuration, interpreter may 
107:                // be local to this thread or shared
108:                Interpreter interpreter = getInterpreter();
109:                synchronized (interpreter) {
110:                    // synchronization is harmless for local thread interpreter,
111:                    // necessary for shared interpreter
112:                    try {
113:                        interpreter.set("curi", curi);
114:                        interpreter.eval("process(curi)");
115:                    } catch (EvalError e) {
116:                        // TODO Auto-generated catch block
117:                        e.printStackTrace();
118:                    }
119:                }
120:            }
121:
122:            /**
123:             * Get the proper Interpreter instance -- either shared or local 
124:             * to this thread. 
125:             * @return Interpreter to use
126:             */
127:            protected Interpreter getInterpreter() {
128:                if (sharedInterpreter != null) {
129:                    return sharedInterpreter;
130:                }
131:                Interpreter interpreter = threadInterpreter.get();
132:                if (interpreter == null) {
133:                    interpreter = newInterpreter();
134:                    threadInterpreter.set(interpreter);
135:                }
136:                return interpreter;
137:            }
138:
139:            /**
140:             * Create a new Interpreter instance, preloaded with any supplied
141:             * source code or source file and the variables 'self' (this 
142:             * BeanShellProcessor) and 'controller' (the CrawlController). 
143:             * 
144:             * @return  the new Interpreter instance
145:             */
146:            protected Interpreter newInterpreter() {
147:                Interpreter interpreter = new Interpreter();
148:                try {
149:                    interpreter.set("self", this );
150:                    interpreter.set("controller", getController());
151:
152:                    String filePath = (String) getUncheckedAttribute(null,
153:                            ATTR_SCRIPT_FILE);
154:                    if (filePath.length() > 0) {
155:                        try {
156:                            File file = getSettingsHandler()
157:                                    .getPathRelativeToWorkingDirectory(filePath);
158:                            interpreter.source(file.getPath());
159:                        } catch (IOException e) {
160:                            logger.log(Level.SEVERE,
161:                                    "unable to read script file", e);
162:                        }
163:                    }
164:                } catch (EvalError e) {
165:                    // TODO Auto-generated catch block
166:                    e.printStackTrace();
167:                }
168:
169:                return interpreter;
170:            }
171:
172:            protected void initialTasks() {
173:                super .initialTasks();
174:                kickUpdate();
175:            }
176:
177:            /**
178:             * Setup (or reset) Intepreter variables, as appropraite based on 
179:             * thread-isolation setting. 
180:             */
181:            public void kickUpdate() {
182:                // TODO make it so running state (tallies, etc.) isn't lost on changes
183:                // unless unavoidable
184:                if ((Boolean) getUncheckedAttribute(null, ATTR_ISOLATE_THREADS)) {
185:                    sharedInterpreter = null;
186:                    threadInterpreter = new ThreadLocal<Interpreter>();
187:                } else {
188:                    sharedInterpreter = newInterpreter();
189:                    threadInterpreter = null;
190:                }
191:            }
192:        }
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.