1 /* Copyright (C) 2001, 2002 The Mir-coders group
3 * This file is part of Mir.
5 * Mir is free software; you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License as published by
7 * the Free Software Foundation; either version 2 of the License, or
8 * (at your option) any later version.
10 * Mir is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 * GNU General Public License for more details.
15 * You should have received a copy of the GNU General Public License
16 * along with Mir; if not, write to the Free Software
17 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
19 * In addition, as a special exception, The Mir-coders gives permission to link
20 * the code of this program with the com.oreilly.servlet library, any library
21 * licensed under the Apache Software License, The Sun (tm) Java Advanced
22 * Imaging library (JAI), The Sun JIMI library (or with modified versions of
23 * the above that use the same license as the above), and distribute linked
24 * combinations including the two. You must obey the GNU General Public
25 * License in all respects for all of the code used other than the above
26 * mentioned libraries. If you modify this file, you may extend this exception
27 * to your version of the file, but you are not obligated to do so. If you do
28 * not wish to do so, delete this exception statement from your version.
31 package mircoders.producer;
36 import org.apache.lucene.analysis.standard.StandardAnalyzer;
37 import org.apache.lucene.index.*;
38 import org.apache.lucene.document.Document;
39 import org.apache.lucene.document.Field;
40 import org.apache.lucene.store.FSDirectory;
42 import freemarker.template.*;
47 import mir.producer.*;
48 //import mir.generator.*;
49 import mircoders.global.*;
50 import mircoders.localizer.*;
52 import mir.entity.adapter.*;
53 import mircoders.entity.*;
54 import mircoders.storage.*;
55 import mircoders.search.*;
58 public class IndexingProducerNode implements ProducerNode {
59 private String contentKey;
60 private String indexPath;
63 public IndexingProducerNode(String aContentKey, String pathToIndex) {
64 contentKey = aContentKey;
65 indexPath=pathToIndex;
68 public void produce(Map aValueMap, String aVerb, LoggerWrapper aLogger) throws ProducerFailure {
69 IndexWriter indexWriter = null;
76 startTime = System.currentTimeMillis();
81 index = ParameterExpander.expandExpression(aValueMap, indexPath);
82 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 " + index);
93 // create an index here if one did not already exist
94 if (! (IndexReader.indexExists(index))){
95 aLogger.error("Didn't find existing index, so I'm making one in "+index);
96 IndexWriter indexCreator = new IndexWriter(index,new StandardAnalyzer(),true);
100 IndexUtil.unindexEntity((EntityContent) entity,index);
102 indexWriter = new IndexWriter(index, new StandardAnalyzer(), false);
103 Document theDoc = new Document();
105 // Keyword is stored and indexed, but not tokenized
106 // Text is tokenized,stored, indexed
107 // Unindexed is not tokenized or indexed, only stored
108 // Unstored is tokenized and indexed, but not stored
110 //this initialization should go somewhere global like an xml file....
112 (new KeywordSearchTerm("id","","id","","id")).index(theDoc,entity);
114 (new KeywordSearchTerm("webdb_create_formatted","search_date","webdb_create_formatted","webdb_create_formatted","webdb_create_formatted")).index(theDoc,entity);
116 (new UnIndexedSearchTerm("","","","where","where")).indexValue(theDoc,entity.getValue("publish_path")+entity.getValue("id")+".shtml");
118 (new TextSearchTerm("creator","search_creator","creator","creator","creator")).index(theDoc,entity);
119 (new TextSearchTerm("title","search_title","title","title","title")).index(theDoc,entity);
120 (new UnIndexedSearchTerm("description","search_content","description","description","description")).index(theDoc,entity);
121 (new UnIndexedSearchTerm("webdb_create","search_irrelevant","creationDate","creationDate","creationDate")).index(theDoc,entity);
123 (new ContentSearchTerm("content_data","search_content","content","","")).indexValue(theDoc,
124 entity.getValue("content_data")+ " "
125 + entity.getValue("description")+ " "
126 + entity.getValue("title")
129 (new TopicSearchTerm()).index(theDoc,entity);
131 (new ImagesSearchTerm()).index(theDoc,entity);
133 (new AudioSearchTerm()).index(theDoc,entity);
135 (new VideoSearchTerm()).index(theDoc,entity);
138 //comments-just aggregate all relevant fields
139 //removed until i get a chance to do this right
141 //String commentsAggregate = "";
142 //TemplateModel comments=entity.get("to_comments");
143 //if (comments != null){
144 // while (((TemplateListModel)comments).hasNext()){
145 // TemplateModel aComment = ((TemplateListModel)comments).next();
146 // commentsAggregate = commentsAggregate + " " + ((TemplateHashModel)aComment).get("title").toString()
147 // + " " + ((TemplateHashModel)aComment).get("creator").toString()
148 // + " " + ((TemplateHashModel)aComment).get("text").toString();
151 //theDoc.add(Field.UnStored("comments",commentsAggregate));
153 indexWriter.addDocument(theDoc);
157 catch (Throwable t) {
158 aLogger.error("Error while indexing content: " + t.getMessage());
159 t.printStackTrace(new PrintWriter(new LoggerToWriterAdapter(aLogger, LoggerWrapper.DEBUG_MESSAGE)));
162 if (indexWriter != null){
166 catch (Throwable t) {
167 aLogger.warn("Error while closing indexWriter: " + t.getMessage());
172 FSDirectory theIndexDir=FSDirectory.getDirectory(index,false);
173 if (IndexReader.isLocked(theIndexDir)){
174 IndexReader.unlock(theIndexDir);
177 catch (Throwable t) {
178 aLogger.warn("Error while unlocking index: " + t.getMessage());
185 endTime = System.currentTimeMillis();
187 aLogger.info(" IndexTime: " + (endTime-startTime) + " ms<br>");