LuceneXMLIndexer


1   /*
2    * Copyright 1999-2004 The Apache Software Foundation.
3    * 
4    * Licensed under the Apache License, Version 2.0 (the "License");
5    * you may not use this file except in compliance with the License.
6    * You may obtain a copy of the License at
7    * 
8    *      http://www.apache.org/licenses/LICENSE-2.0
9    * 
10   * Unless required by applicable law or agreed to in writing, software
11   * distributed under the License is distributed on an "AS IS" BASIS,
12   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13   * See the License for the specific language governing permissions and
14   * limitations under the License.
15   */
16  package org.apache.cocoon.components.search;
17  
18  import org.apache.avalon.framework.component.Component;
19  import org.apache.cocoon.ProcessingException;
20  
21  import java.net.URL  ;
22  import java.util.List  ;
23  
24  /**
25   * The avalon behavioural component interface of generating
26   * lucene documents from an xml content.
27   *
28   * <p>
29   *  The well-known fields of a lucene documents are defined as
30   *  <code>*_FIELD</code> constants.
31   * </p>
32   * <p>
33   *  You may access generated lucene documents via
34   *  <code>allDocuments()</code>, or <code>iterator()</code>.
35   * </p>
36   * <p>
37   *  You trigger the generating of lucene documents via
38   *  <code>build()</code>.
39   * </p>
40   *
41   * @author <a HREF="mailto:berni_huber@a1.net">Bernhard Huber</a>
42   * @version CVS $Id: LuceneXMLIndexer.java 30932 2004-07-29 17:35:38Z vgritsenko $
43   */
44  public interface LuceneXMLIndexer extends Component
45  {
46  
47      /**
48       * The ROLE name of this avalon component.
49       * <p>
50       *   Its value if the FQN of this interface,
51       *   ie. <code>org.apache.cocoon.components.search.LuceneXMLIndexer</code>.
52       * </p>
53       *
54       * @since
55       */
56      String   ROLE = "org.apache.cocoon.components.search.LuceneXMLIndexer";
57  
58      /**
59       * A Lucene document field name, containing xml content text of all xml elements.
60       * <p>
61       *   A concrete implementation of this interface SHOULD
62       *   provides a field named body.
63       * </p>
64       * <p>
65       *   A concrete implementation MAY provide additional lucene
66       *   document fields.
67       * </p>
68       *
69       * @since
70       */
71      String   BODY_FIELD = "body";
72  
73      /**
74       * A Lucene document field name, containg the URI/URL of the indexed
75       * document.
76       * <p>
77       *   A concrete implementation of this interface SHOULD
78       *   provide a field named url.
79       * </p>
80       *
81       * @since
82       */
83      String   URL_FIELD = "url";
84  
85      /**
86       * A Lucene document field name, containg the a unique key of the indexed
87       * document.
88       * <p>
89       *  This document field is used internally to track document
90       *  changes, and updates.
91       * </p>
92       * <p>
93       *   A concrete implementation of this interface SHOULD
94       *   provide a field named uid.
95       * </p>
96       *
97       * @since
98       */
99      String   UID_FIELD = "uid";
100 
101     /**
102      * Build lucene documents from a URL.
103      * <p>
104      *   This method will read the content of the URL, and generates
105      *   one or more lucene documents. The generated lucence documents
106      *   can be fetched using methods allDocuments(), and iterator().
107      * </p>
108      *
109      * @param  url                      the content of this url gets indexed.
110      * @exception  ProcessingException  Description of Exception
111      * @since
112      */
113     List   build(URL   url) throws ProcessingException;
114 }
115
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags