Source Code Cross Referenced for Page.java in  » Search-Engine » oxyus » org » oxyus » crawler » 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 » Search Engine » oxyus » org.oxyus.crawler 
Source Cross Referenced  Class Diagram Java Document (Java Doc) 


001:        /*
002:         * $Id: Page.java,v 1.12 2004/10/10 14:25:23 csaltos Exp $
003:         * 
004:         * Copyright 2001 PUCE [http://www.puce.edu.ec]
005:         *
006:         * Licensed under the Apache License, Version 2.0 (the "License");
007:         * you may not use this file except in compliance with the License.
008:         * You may obtain a copy of the License at
009:         *
010:         *     http://www.apache.org/licenses/LICENSE-2.0
011:         *
012:         * Unless required by applicable law or agreed to in writing, software
013:         * distributed under the License is distributed on an "AS IS" BASIS,
014:         * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015:         * See the License for the specific language governing permissions and
016:         * limitations under the License.
017:         */
018:
019:        package org.oxyus.crawler;
020:
021:        import java.io.BufferedInputStream;
022:        import java.io.IOException;
023:        import java.io.InputStream;
024:        import java.net.ConnectException;
025:        import java.net.HttpURLConnection;
026:        import java.net.MalformedURLException;
027:        import java.net.URL;
028:        import java.net.UnknownHostException;
029:        import java.sql.PreparedStatement;
030:        import java.sql.ResultSet;
031:        import java.sql.SQLException;
032:        import java.sql.Statement;
033:
034:        import org.apache.log4j.Logger;
035:        import org.apache.lucene.document.Document;
036:        import org.oxyus.crawler.parser.HTMLParser;
037:        import org.oxyus.store.Store;
038:        import org.oxyus.util.Path;
039:
040:        /**
041:         * Page persistance.
042:         *
043:         * @author Carlos Saltos (csaltos[@]users.sourceforge.net)
044:         */
045:        public class Page {
046:
047:            protected Logger log;
048:
049:            /**
050:             * Page state for signal a page not collected
051:             */
052:            public static int PAGE_NOT_COLLECTED = 0;
053:
054:            /**
055:             * Page state for signal a page beign collected
056:             */
057:            public static int PAGE_COLLECTING = 1;
058:
059:            /**
060:             * Page state for signal a page already collected
061:             */
062:            public static int PAGE_COLLECTED = 2;
063:
064:            /**
065:             * Primary key
066:             */
067:            protected int code;
068:
069:            /**
070:             * Server this page belongs
071:             */
072:            protected Server server;
073:
074:            /**
075:             * Page collecting state
076:             */
077:            protected int state;
078:
079:            /**
080:             * Ruta de la page.
081:             */
082:            protected String path;
083:
084:            /**
085:             * Connection to oxyus repository
086:             */
087:            protected Store store;
088:
089:            /**
090:             * Crawling scope
091:             */
092:            protected Scope scope;
093:
094:            /**
095:             * Creates a page
096:             */
097:            public Page() {
098:                log = Logger.getLogger(Page.class);
099:                server = new Server();
100:                reset();
101:            }
102:
103:            /**
104:             * Reset the internal properties
105:             */
106:            public void reset() {
107:                setCode(-1);
108:                setState(PAGE_NOT_COLLECTED);
109:                setPath(null);
110:                if (server != null) {
111:                    server.reset();
112:                }
113:            }
114:
115:            public void read() throws SQLException {
116:                boolean success = false;
117:                if (store == null) {
118:                    throw new SQLException("Connection not opened");
119:                }
120:                PreparedStatement statement = store
121:                        .prepareStatement("select code_server, state, path "
122:                                + "from ox_page where code_page = ?");
123:                statement.setInt(1, this .getCode());
124:                ResultSet result = statement.executeQuery();
125:                if (result.next()) {
126:                    setState(result.getInt("state"));
127:                    setPath(result.getString("path"));
128:                    // Load the server
129:                    this .server = new Server();
130:                    this .server.setStore(this .store);
131:                    this .server.setCode(result.getInt("code_server"));
132:                    this .server.read();
133:                    success = true;
134:                }
135:                result.close();
136:                statement.close();
137:                if (!success) {
138:                    throw new SQLException("Page not found");
139:                }
140:            }
141:
142:            /**
143:             * Reads the next page in not collected state.
144:             */
145:            public boolean nextForCollect() throws CrawlingException {
146:                try {
147:                    boolean hasNextForCollect = false;
148:                    if (store == null) {
149:                        throw new SQLException("Connection not opened");
150:                    }
151:                    PreparedStatement statement = store
152:                            .prepareStatement("select code_page from ox_page where state = ?");
153:                    statement.setInt(1, Page.PAGE_NOT_COLLECTED);
154:                    ResultSet result = statement.executeQuery();
155:                    if (result.next()) {
156:                        this .setCode(result.getInt("code_page"));
157:                        hasNextForCollect = true;
158:                    }
159:                    result.close();
160:                    statement.close();
161:                    // If a next page for collect was located, read it
162:                    if (hasNextForCollect) {
163:                        this .read();
164:                    }
165:                    return hasNextForCollect;
166:                } catch (SQLException sqle) {
167:                    log.error("Unable to get the next page for collect", sqle);
168:                    throw new CrawlingException(
169:                            "Unable to get the next page for " + "collect",
170:                            sqle);
171:                }
172:            }
173:
174:            /**
175:             * Calculate a page address based in a link without add it to the crawler
176:             * scope
177:             */
178:            public void recordLink(String link) {
179:                recordLink(link, false);
180:            }
181:
182:            /**
183:             * Calculate a page address based in a link with the posibility to
184:             * add it to the crawler scope
185:             */
186:            public void recordLink(String link, boolean addToRules) {
187:                if (link == null) {
188:                    log.warn("Attemp to record a null link");
189:                    return;
190:                }
191:                link = link.trim();
192:                if (link.equals("")) {
193:                    log.warn("Attemp to record an empty link");
194:                    return;
195:                }
196:                URL url = null;
197:                // Test if the link is an absolute URL address
198:                try {
199:                    url = new URL(link);
200:                } catch (MalformedURLException e) {
201:                    // The link is not a correct absolute address
202:                    url = null;
203:                }
204:                // If the link is not an absolute URL address, so create a complete
205:                // URL address using this link as a reference
206:                if (url == null) {
207:                    if (server == null) {
208:                        log.error("Server NULL registering address: " + link);
209:                        return;
210:                    }
211:                    try {
212:                        // If the link begins with / is a local absolute link, so
213:                        // try to create the URL with the direct link
214:                        if (link.charAt(0) == '/') {
215:                            url = new URL(server.getProtocol() + "://"
216:                                    + server.getHost() + ":" + server.getPort()
217:                                    + link);
218:                        } else {
219:                            // Try to construct a relative address using the link
220:                            String prefix = getPath();
221:                            if (prefix == null) {
222:                                log
223:                                        .error("Path not established registering address: "
224:                                                + link);
225:                                return;
226:                            }
227:                            int length = prefix.length();
228:                            if (length == 0) {
229:                                log
230:                                        .error("Path not established registering address: "
231:                                                + link);
232:                                return;
233:                            }
234:                            if (prefix.charAt(length - 1) != '/') {
235:                                int lastSlash = prefix.lastIndexOf('/');
236:                                if (lastSlash == -1) {
237:                                    log
238:                                            .error("Path error registering address: "
239:                                                    + link);
240:                                    return;
241:                                }
242:                                prefix = prefix.substring(0, lastSlash + 1);
243:                            }
244:                            url = new URL("http://" + server.getHost() + ":"
245:                                    + server.getPort()
246:                                    + Path.normalize(prefix + link));
247:                        }
248:                    } catch (MalformedURLException e) {
249:                        log
250:                                .warn("Attemp to create an URL address using the link '"
251:                                        + link + "' has failed");
252:                        return;
253:                    }
254:                }
255:                // Creates a server and page persistance objects and stores them
256:                if (url.getProtocol().toLowerCase().equals("http")) {
257:                    if (addToRules) {
258:                        scope.acceptDomain(url.getHost());
259:                    }
260:                    if (scope.inScope(url.getHost())) {
261:                        Server server = new Server();
262:                        server.setStore(store);
263:                        server.setProtocol(url.getProtocol());
264:                        server.setHost(url.getHost());
265:                        server.setPort(url.getPort());
266:                        log.debug("Port " + server.getPort());
267:                        try {
268:                            Page page = new Page();
269:                            page.setStore(store);
270:                            page.setServer(server);
271:                            page.setPath(url.getPath());
272:                            page.setState(Page.PAGE_NOT_COLLECTED);
273:                            // Store the page with no duplication
274:                            page.locateOrCreate();
275:                        } catch (SQLException e) {
276:                            log.error("Error registering page: "
277:                                    + url.toExternalForm(), e);
278:                        }
279:                    }
280:                }
281:            }
282:
283:            /**
284:             * Stores this new page is the path is not duplicated for the same server
285:             */
286:            public void locateOrCreate() throws SQLException {
287:                if (store == null) {
288:                    throw new SQLException("Connection not opened");
289:                }
290:                if (this .getServer() == null) {
291:                    throw new SQLException("Server not specified");
292:                }
293:                if (this .getPath() == null) {
294:                    throw new SQLException("Path not specified");
295:                }
296:                // Locate the server or create it if no exists
297:                this .getServer().locateOrCreate();
298:                // Check if the path is not duplicated in the same server
299:                PreparedStatement statement = store
300:                        .prepareStatement("select code_page from ox_page, ox_server where "
301:                                + "ox_page.code_server = ox_server.code_server and "
302:                                + "ox_server.code_server = ? and " + "path = ?");
303:                statement.setInt(1, this .getServer().getCode());
304:                statement.setString(2, this .getPath());
305:                ResultSet result = statement.executeQuery();
306:                if (result.next()) {
307:                    // If a page with the same path exists for the same server
308:                    // only loads its code and return
309:                    this .setCode(result.getInt("code_page"));
310:                    result.close();
311:                    statement.close();
312:                    return;
313:                }
314:                // If no match page found creates it with not collected state
315:                this .setCode(store.nextCode("page"));
316:                statement = store
317:                        .prepareStatement("insert into ox_page(code_page, code_server, state, path) "
318:                                + "values(?,?,?,?)");
319:                statement.setInt(1, this .getCode());
320:                statement.setInt(2, this .getServer().getCode());
321:                statement.setInt(3, Page.PAGE_NOT_COLLECTED);
322:                statement.setString(4, this .getPath());
323:                statement.executeUpdate();
324:                statement.close();
325:            }
326:
327:            /**
328:             * Sets the page state in PAGE_COLLECTING
329:             */
330:            public void markAsCollecting() throws CrawlingException {
331:                Statement sentencia = null;
332:                if (store == null) {
333:                    throw new CrawlingException("Connection not opened");
334:                }
335:                try {
336:                    sentencia = store.createStatement();
337:                    if (sentencia == null) {
338:                        throw new CrawlingException("Unable to create sentence");
339:                    }
340:                    sentencia.executeUpdate("UPDATE ox_page SET state='"
341:                            + PAGE_COLLECTING + "' WHERE code_page="
342:                            + getCode());
343:                    try {
344:                        sentencia.close();
345:                    } catch (SQLException e) {
346:                        log.error("Unable to close the sentence correctly");
347:                    }
348:                } catch (SQLException e) {
349:                    throw new CrawlingException("Error closing page", e);
350:                }
351:            }
352:
353:            /**
354:             * Sets the page state in PAGE_COLLECTED.
355:             */
356:            public void markAsCollected() throws CrawlingException {
357:                Statement sentencia = null;
358:                if (store == null) {
359:                    throw new CrawlingException("Connection not opened");
360:                }
361:                try {
362:                    sentencia = store.createStatement();
363:                    if (sentencia == null) {
364:                        throw new CrawlingException("Unable to create sentence");
365:                    }
366:                    sentencia
367:                            .executeUpdate("UPDATE ox_page SET state='"
368:                                    + PAGE_COLLECTED + "' WHERE code_page="
369:                                    + getCode());
370:                    try {
371:                        sentencia.close();
372:                    } catch (SQLException e) {
373:                        log.error("Unable to close the sentence correctly");
374:                    }
375:                } catch (SQLException e) {
376:                    throw new CrawlingException("Error closing page", e);
377:                }
378:            }
379:
380:            public Document index() throws CrawlingException {
381:                log.debug("BEGINIG indexing page [code=" + getCode() + "] ...");
382:                URL url = null;
383:                InputStream in = null;
384:                String contentType = null;
385:                try {
386:                    // Reconstruct the page's url
387:                    url = new URL(getServer().getProtocol() + "://"
388:                            + getServer().getHost() + ":"
389:                            + getServer().getPort() + getPath());
390:                    // Open an HTTP connection with the page's url
391:                    HttpURLConnection pageContent = (HttpURLConnection) url
392:                            .openConnection();
393:                    // If the response code of the page's connection is not ok
394:                    // continue collecting the next page
395:                    if (pageContent.getResponseCode() != HttpURLConnection.HTTP_OK) {
396:                        log.debug("page pk[" + getCode() + ","
397:                                + url.toExternalForm() + "] is invalid");
398:                        return null;
399:                    }
400:                    // If a redirection is detected store it as a new address
401:                    // and continue collecting the next page
402:                    String redireccion = pageContent.getHeaderField("location");
403:                    if (redireccion != null) {
404:                        log.debug("Page " + url.toExternalForm()
405:                                + " redirected to " + redireccion);
406:                        recordLink(redireccion);
407:                        return null;
408:                    }
409:                    contentType = pageContent.getContentType();
410:                    in = new BufferedInputStream(pageContent.getInputStream(),
411:                            32768); // TODO: Add a constant
412:                } catch (MalformedURLException e) {
413:                    log.error("Invalid page address", e);
414:                } catch (ConnectException e) {
415:                    if (getServer() != null) {
416:                        log.error("Unable to connect to page: "
417:                                + getServer().getProtocol() + "://"
418:                                + getServer().getHost() + ":"
419:                                + getServer().getPort() + getPath(), e);
420:                    }
421:                } catch (UnknownHostException uhe) {
422:                    log.warn("Unknow host indexing page " + getURL(), uhe);
423:                } catch (IOException e) {
424:                    log.warn("Unable to index page " + getURL(), e);
425:                }
426:
427:                Document doc = generateDocument(contentType, in);
428:
429:                log.debug("END indexing page [code=" + getCode() + "]");
430:
431:                return doc;
432:
433:            }
434:
435:            public Document generateDocument(String contentType, InputStream in)
436:                    throws CrawlingException {
437:                Document doc = null;
438:                if (contentType.indexOf("text/html") == 0) {
439:                    doc = new HTMLParser(this ).collect(in);
440:                } else {
441:                    log.warn("No indexor for content type " + contentType);
442:                }
443:                return doc;
444:            }
445:
446:            public String getURL() {
447:                String address = null;
448:                if (server.getProtocol() != null && server.getHost() != null
449:                        && this .getPath() != null) {
450:                    address = server.getProtocol() + "://" + server.getHost()
451:                            + ":" + server.getPort() + this .getPath();
452:                }
453:                return address;
454:            }
455:
456:            public void setStore(Store connection) {
457:                this .store = connection;
458:                if (server != null) {
459:                    server.setStore(connection);
460:                }
461:            }
462:
463:            public int getCode() {
464:                return code;
465:            }
466:
467:            public void setCode(int code) {
468:                this .code = code;
469:            }
470:
471:            public Server getServer() {
472:                return server;
473:            }
474:
475:            public void setServer(Server server) {
476:                this .server = server;
477:            }
478:
479:            public int getState() {
480:                return state;
481:            }
482:
483:            public void setState(int state) {
484:                if (state != PAGE_NOT_COLLECTED && state != PAGE_COLLECTING
485:                        && state != PAGE_COLLECTED) {
486:                    log.error("Invalid page state " + state);
487:                    throw new IllegalArgumentException("Invalid page state"
488:                            + state);
489:                }
490:                this .state = state;
491:            }
492:
493:            public String getPath() {
494:                return path;
495:            }
496:
497:            public void setPath(String path) {
498:                // TODO: shrink path
499:                this .path = path;
500:                if (path != null) {
501:                    this .path = path.trim();
502:                }
503:            }
504:
505:            public Scope getScope() {
506:                return scope;
507:            }
508:
509:            public void setScope(Scope dominiosPermitidos) {
510:                this.scope = dominiosPermitidos;
511:            }
512:
513:        }
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.