2 * Copyright (C) 2001, 2002 The Mir-coders group
4 * This file is part of Mir.
6 * Mir is free software; you can redistribute it and/or modify
7 * it under the terms of the GNU General Public License as published by
8 * the Free Software Foundation; either version 2 of the License, or
9 * (at your option) any later version.
11 * Mir is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License
17 * along with Mir; if not, write to the Free Software
18 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
20 * In addition, as a special exception, The Mir-coders gives permission to link
21 * the code of this program with the com.oreilly.servlet library, any library
22 * licensed under the Apache Software License, The Sun (tm) Java Advanced
23 * Imaging library (JAI), The Sun JIMI library (or with modified versions of
24 * the above that use the same license as the above), and distribute linked
25 * combinations including the two. You must obey the GNU General Public
26 * License in all respects for all of the code used other than the above
27 * mentioned libraries. If you modify this file, you may extend this exception
28 * to your version of the file, but you are not obligated to do so. If you do
29 * not wish to do so, delete this exception statement from your version.
32 package mircoders.producer;
37 import org.apache.lucene.analysis.standard.StandardAnalyzer;
38 import org.apache.lucene.index.*;
39 import org.apache.lucene.document.Document;
40 import org.apache.lucene.document.Field;
41 import org.apache.lucene.store.FSDirectory;
43 import freemarker.template.*;
48 import mir.producer.*;
49 //import mir.generator.*;
50 import mircoders.global.*;
51 import mircoders.localizer.*;
53 import mir.entity.adapter.*;
54 import mircoders.entity.*;
55 import mircoders.storage.*;
56 import mircoders.search.*;
59 public class IndexingProducerNode implements ProducerNode {
60 private String contentKey;
61 private String indexPath;
64 public IndexingProducerNode(String aContentKey, String pathToIndex) {
65 contentKey = aContentKey;
66 indexPath=pathToIndex;
69 public void produce(Map aValueMap, String aVerb, LoggerWrapper aLogger) throws ProducerFailure {
70 IndexReader indexReader = null;
71 IndexWriter indexWriter = null;
78 startTime = System.currentTimeMillis();
81 data = ParameterExpander.findValueForKey( aValueMap, contentKey );
83 if (! (data instanceof EntityAdapter)) {
84 throw new ProducerFailure("IndexingProducerNode: value of '"+contentKey+"' is not an EntityAdapter, but an " + data.getClass().getName(), null);
87 entity = ((EntityAdapter) data).getEntity();
88 if (! (entity instanceof EntityContent)) {
89 throw new ProducerFailure("IndexingProducerNode: value of '"+contentKey+"' is not a content EntityAdapter, but a " + entity.getClass().getName() + " adapter", null);
91 aLogger.info("Indexing " + (String) entity.getValue("id") + " into " + indexPath);
93 indexReader = IndexReader.open(indexPath);
94 indexReader.delete(new Term("id",entity.getValue("id")));
97 indexWriter = new IndexWriter(indexPath, new StandardAnalyzer(), false);
98 Document theDoc = new Document();
100 // Keyword is stored and indexed, but not tokenized
101 // Text is tokenized,stored, indexed
102 // Unindexed is not tokenized or indexed, only stored
103 // Unstored is tokenized and indexed, but not stored
105 //this initialization should go somewhere global like an xml file....
108 (new KeywordSearchTerm("id","","id","","id")).index(theDoc,entity);
109 (new KeywordSearchTerm("webdb_create_formatted","search_date","webdb_create_formatted","","webdb_create_formatted")).index(theDoc,entity);
111 (new UnIndexedSearchTerm("","","","where","where")).indexValue(theDoc,entity.getValue("publish_path")+entity.getValue("id")+".shtml");
113 (new TextSearchTerm("creator","search_creator","creator","","creator")).index(theDoc,entity);
114 (new TextSearchTerm("title","search_title","title","","title")).index(theDoc,entity);
115 (new TextSearchTerm("description","search_content","description","","description")).index(theDoc,entity);
117 (new UnStoredSearchTerm("content_data","search_content","content","","")).index(theDoc,entity);
119 (new TopicSearchTerm()).index(theDoc,entity);
121 (new ImagesSearchTerm()).index(theDoc,entity);
123 (new AudioSearchTerm()).index(theDoc,entity);
125 (new VideoSearchTerm()).index(theDoc,entity);
128 //comments-just aggregate all relevant fields
129 //removed until i get a chance to do this right
131 //String commentsAggregate = "";
132 //TemplateModel comments=entity.get("to_comments");
133 //if (comments != null){
134 // while (((TemplateListModel)comments).hasNext()){
135 // TemplateModel aComment = ((TemplateListModel)comments).next();
136 // commentsAggregate = commentsAggregate + " " + ((TemplateHashModel)aComment).get("title").toString()
137 // + " " + ((TemplateHashModel)aComment).get("creator").toString()
138 // + " " + ((TemplateHashModel)aComment).get("text").toString();
141 //theDoc.add(Field.UnStored("comments",commentsAggregate));
143 indexWriter.addDocument(theDoc);
147 catch (Throwable t) {
148 aLogger.error("Error while indexing content: " + t.getMessage());
149 t.printStackTrace(new PrintWriter(new LoggerToWriterAdapter(aLogger, LoggerWrapper.DEBUG_MESSAGE)));
150 //should remove index lock here.....jd
153 if (indexReader != null){
157 catch (Throwable t) {
158 aLogger.warn("Error while closing indexReader: " + t.getMessage());
163 if (indexWriter != null){
167 catch (Throwable t) {
168 aLogger.warn("Error while closing indexWriter: " + t.getMessage());
175 FSDirectory theIndexDir=FSDirectory.getDirectory(indexPath,false);
176 if (indexReader.isLocked(theIndexDir)){
177 indexReader.unlock(theIndexDir);
180 catch (Throwable t) {
181 aLogger.warn("Error while unlocking index: " + t.getMessage());
188 endTime = System.currentTimeMillis();
190 aLogger.info(" IndexTime: " + (endTime-startTime) + " ms<br>");