LinkEvent


1   /*
2    * WebSphinx web-crawling toolkit
3    *
4    * Copyright (c) 1998-2002 Carnegie Mellon University.  All rights
5    * reserved.
6    *
7    * Redistribution and use in source and binary forms, with or without
8    * modification, are permitted provided that the following conditions
9    * are met:
10   *
11   * 1. Redistributions of source code must retain the above copyright
12   *    notice, this list of conditions and the following disclaimer.
13   *
14   * 2. Redistributions in binary form must reproduce the above copyright
15   *    notice, this list of conditions and the following disclaimer in
16   *    the documentation and/or other materials provided with the
17   *    distribution.
18   *
19   * THIS SOFTWARE IS PROVIDED BY CARNEGIE MELLON UNIVERSITY ``AS IS'' AND
20   * ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
21   * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
22   * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL CARNEGIE MELLON UNIVERSITY
23   * NOR ITS EMPLOYEES BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24   * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25   * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26   * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27   * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28   * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29   * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30   *
31   */
32  
33  package websphinx;
34  
35  /**
36   * Link event.  A LinkEvent is issued when the crawler
37   * starts or stops retrieving a link, and when it makes
38   * a decision about a link.
39   */
40  public class LinkEvent 
41  {
42      Crawler crawler;
43      int id;
44      Link link;
45      Throwable   exception;
46  
47      /**
48       * No event occured on this link yet. Never delivered in a LinkEvent,
49       * but may be returned by link.getStatus().
50       */
51      public static final int NONE = 0;
52      
53      /**
54       * Link was rejected by shouldVisit()
55       */
56      public static final int SKIPPED = 1;
57  
58      /**
59       * Link has already been visited during the crawl, so it was skipped.
60       */
61      public static final int ALREADY_VISITED = 2;
62  
63      /**
64       * Link was accepted by walk() but exceeds the maximum depth from the start set.
65       */
66      public static final int TOO_DEEP = 3;
67  
68      /**
69       * Link was accepted by walk() and is waiting to be downloaded
70       */
71      public static final int QUEUED = 4;
72  
73      /**
74       * Link is being retrieved
75       */
76      public static final int RETRIEVING = 5;
77  
78      /**
79       * An error occurred in retrieving the page.
80       * The error can be obtained from getException().
81       */
82      public static final int ERROR = 6;
83  
84      /**
85       * Link has been retrieved
86       */
87      public static final int DOWNLOADED = 7;
88  
89      /**
90       * Link has been thoroughly processed by crawler
91       */
92      public static final int VISITED = 8;
93  
94      /**
95       * Map from id code (RETRIEVING) to name ("retrieving")
96       */
97      public static final String  [] eventName = {
98          "none",
99          "skipped",
100         "already visited",
101         "too deep",
102         "queued",
103         "retrieving",
104         "error",
105         "downloaded",
106         "visited"
107     };
108 
109     /**
110      * Make a LinkEvent.
111      * @param crawler Crawler that generated this event
112      * @param id event code, like LinkEvent.RETRIEVING
113      * @param link Link on which this event occurred
114      */
115     public LinkEvent (Crawler crawler, int id, Link link) {
116         this.crawler = crawler;
117         this.id = id;
118         this.link = link;
119     }
120 
121     /**
122      * Make a LinkEvent for an error.
123      * @param crawler Crawler that generated this event
124      * @param id Event code, usually ERROR
125      * @param link Link on which this event occurred
126      * @param exception Throwable 
127      */
128     public LinkEvent (Crawler crawler, int id, Link link, Throwable   exception) {
129         this.crawler = crawler;
130         this.id = id;
131         this.link = link;
132         this.exception = exception;
133     }
134 
135     /**
136      * Get crawler that generated the event
137      * @return crawler
138      */
139     public Crawler getCrawler () { 
140         return crawler;
141     }
142 
143     /**
144      * Get event id
145      * @return id
146      */
147     public int getID () { return id; }
148 
149     /**
150      * Get event name (string equivalent to its ID)
151      * @return id
152      */
153     public String   getName () { return eventName[id]; }
154 
155     /**
156      * Get link to which this event occurred.
157      * @return link
158      */
159     public Link getLink () { return link; }
160 
161     /**
162      * Get exception related to this event.  Valid when ID == ERROR.
163      * @return exception object
164      */
165     public Throwable   getException () { return exception; }
166 
167     /**
168      * Convert this event to a String describing it.
169      */
170     public String   toString () {
171         String   result;
172         if (id == ERROR)
173             result = exception.toString();
174         else
175             result = eventName[id];
176         result += " " + link.toDescription ();
177         return result;
178     }
179 }
180
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags