Source Code Cross Referenced for DomainScope.java in  » Web-Crawler » heritrix » org » archive » crawler » scope » 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.scope 
Source Cross Referenced  Class Diagram Java Document (Java Doc) 


001:        /* Copyright (C) 2003 Internet Archive.
002:         *
003:         * This file is part of the Heritrix web crawler (crawler.archive.org).
004:         *
005:         * Heritrix is free software; you can redistribute it and/or modify
006:         * it under the terms of the GNU Lesser Public License as published by
007:         * the Free Software Foundation; either version 2.1 of the License, or
008:         * any later version.
009:         *
010:         * Heritrix is distributed in the hope that it will be useful,
011:         * but WITHOUT ANY WARRANTY; without even the implied warranty of
012:         * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
013:         * GNU Lesser Public License for more details.
014:         *
015:         * You should have received a copy of the GNU Lesser Public License
016:         * along with Heritrix; if not, write to the Free Software
017:         * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
018:         *
019:         * BasicScope.java
020:         * Created on Oct 1, 2003
021:         *
022:         * $Header$
023:         */
024:        package org.archive.crawler.scope;
025:
026:        import java.util.Iterator;
027:        import java.util.logging.Logger;
028:
029:        import org.apache.commons.httpclient.URIException;
030:        import org.archive.crawler.deciderules.DecidingScope;
031:        import org.archive.crawler.filter.FilePatternFilter;
032:        import org.archive.crawler.filter.TransclusionFilter;
033:        import org.archive.crawler.framework.Filter;
034:        import org.archive.net.UURI;
035:
036:        /**
037:         * A core CrawlScope suitable for the most common
038:         * crawl needs.
039:         *
040:         * Roughly, its logic is that a URI is included if:
041:         *
042:         *    (( isSeed(uri) || focusFilter.accepts(uri) )
043:         *      || transitiveFilter.accepts(uri) )
044:         *     && ! excludeFilter.accepts(uri)
045:         *
046:         * The focusFilter may be specified by either:
047:         *   - adding a 'mode' attribute to the
048:         *     <code>scope</code> element. mode="broad" is equivalent
049:         *     to no focus; modes "path", "host", and "domain"
050:         *     imply a SeedExtensionFilter will be used, with
051:         *     the <code>scope</code> element providing its configuration
052:         *   - adding a <code>focus</code> subelement
053:         * If unspecified, the focusFilter will default to
054:         * an accepts-all filter.
055:         *
056:         * The transitiveFilter may be specified by supplying
057:         * a <code>transitive</code> subelement. If unspecified, a
058:         * TransclusionFilter will be used, with the <code>scope</code>
059:         * element providing its configuration.
060:         *
061:         * The excludeFilter may be specified by supplying
062:         * a <code>exclude</code> subelement. If unspecified, a
063:         * accepts-none filter will be used -- meaning that
064:         * no URIs will pass the filter and thus be excluded.
065:         *
066:         * @author gojomo
067:         * @deprecated As of release 1.10.0.  Replaced by {@link DecidingScope}.
068:         */
069:        public class DomainScope extends SeedCachingScope {
070:
071:            private static final long serialVersionUID = 648062105277258820L;
072:
073:            private static final Logger logger = Logger
074:                    .getLogger(DomainScope.class.getName());
075:
076:            public static final String ATTR_TRANSITIVE_FILTER = "transitiveFilter";
077:            public static final String ATTR_ADDITIONAL_FOCUS_FILTER = "additionalScopeFocus";
078:            public static final String DOT = ".";
079:
080:            Filter additionalFocusFilter;
081:            Filter transitiveFilter;
082:
083:            public DomainScope(String name) {
084:                super (name);
085:                setDescription("DomainScope: A scope for domain crawls *Deprecated* Use "
086:                        + "DecidingScope instead. Crawls made with this"
087:                        + " scope will be limited to the domain of its seeds. It will"
088:                        + " however reach subdomains of the seeds' original domains."
089:                        + " www[#].host is considered to be the same as host.");
090:                this .additionalFocusFilter = (Filter) addElementToDefinition(new FilePatternFilter(
091:                        ATTR_ADDITIONAL_FOCUS_FILTER));
092:                this .transitiveFilter = (Filter) addElementToDefinition(new TransclusionFilter(
093:                        ATTR_TRANSITIVE_FILTER));
094:            }
095:
096:            /**
097:             * @param o
098:             * @return True if transitive filter accepts passed object.
099:             */
100:            protected boolean transitiveAccepts(Object o) {
101:                return this .transitiveFilter.accepts(o);
102:            }
103:
104:            /**
105:             * Check if an URI is part of this scope.
106:             *
107:             * @param o An instance of UURI or of CandidateURI.
108:             * @return True if focus filter accepts passed object.
109:             */
110:            protected boolean focusAccepts(Object o) {
111:                UURI u = UURI.from(o);
112:                if (u == null) {
113:                    return false;
114:                }
115:                // Get the seeds to refresh and then get an iterator inside a
116:                // synchronization block.  The seeds list may get updated during our
117:                // iteration. This will throw a concurrentmodificationexception unless
118:                // we synchronize.
119:                String seedDomain = null;
120:                String candidateDomain = null;
121:
122:                // Get candidate domain where www[0-9]*\. is stripped.
123:                try {
124:                    candidateDomain = u.getHostBasename();
125:                } catch (URIException e1) {
126:                    logger
127:                            .severe("UURI getHostBasename failed for candidate URI: "
128:                                    + u);
129:                }
130:                if (candidateDomain == null) {
131:                    // either an opaque, unfetchable, or unparseable URI
132:                    return false;
133:                }
134:
135:                Iterator iter = seedsIterator();
136:                while (iter.hasNext()) {
137:                    UURI s = (UURI) iter.next();
138:                    // Get seed domain where www[0-9]*\. is stripped.
139:                    try {
140:                        seedDomain = s.getHostBasename();
141:                    } catch (URIException e) {
142:                        logger.severe("UURI getHostBasename failed for seed: "
143:                                + s);
144:                    }
145:                    if (seedDomain == null) {
146:                        // GetHost can come back null.  See bug item
147:                        // [ 910120 ] java.net.URI#getHost fails when leading digit
148:                        continue;
149:                    }
150:
151:                    // Check if stripped hosts are same.
152:                    if (seedDomain.equals(candidateDomain)) {
153:                        checkClose(iter);
154:                        return true;
155:                    }
156:
157:                    // Hosts are not same. Adjust seed basename to check if
158:                    // candidate domain ends with .seedDomain
159:                    seedDomain = DOT + seedDomain;
160:                    if (seedDomain.regionMatches(0, candidateDomain,
161:                            candidateDomain.length() - seedDomain.length(),
162:                            seedDomain.length())) {
163:                        // Domain suffix congruence
164:                        checkClose(iter);
165:                        return true;
166:                    } // Else keep trying other seeds
167:                }
168:                // if none found, fail
169:                checkClose(iter);
170:                return false;
171:            }
172:
173:            protected boolean additionalFocusAccepts(Object o) {
174:                return additionalFocusFilter.accepts(o);
175:            }
176:        }
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.