source: main/trunk/greenstone3/src/java/org/greenstone/gsdl3/service/GS2LuceneRetrieve.java@ 25649

Last change on this file since 25649 was 25649, checked in by sjm84, 12 years ago

Reformatting this file

  • Property svn:keywords set to Author Date Id Revision
File size: 5.4 KB
Line 
1/*
2 * GS2LuceneRetrieve.java
3 * Copyright (C) 2005 New Zealand Digital Library, http://www.nzdl.org
4 *
5 * This program 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.
9 *
10 * This program 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.
14 *
15 * You should have received a copy of the GNU General Public License
16 * along with this program; if not, write to the Free Software
17 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
18 */
19package org.greenstone.gsdl3.service;
20
21// Greenstone classes
22import org.greenstone.gsdl3.core.GSException;
23import org.greenstone.gsdl3.util.GSFile;
24import org.greenstone.gsdl3.util.GSXML;
25import org.greenstone.gsdl3.util.DBInfo;
26import org.greenstone.gsdl3.util.GSHTML;
27import org.greenstone.gsdl3.util.OID;
28// XML classes
29import org.w3c.dom.Document;
30import org.w3c.dom.Element;
31import org.w3c.dom.Text;
32
33// General Java classes
34import java.io.File;
35
36import org.apache.log4j.Logger;
37
38/**
39 * Retrieve documents from a gs2 lucene collection. Note that this doesn't
40 * actually use lucene, as the documents are stored in XML files
41 */
42public class GS2LuceneRetrieve extends AbstractGS2DocumentRetrieve
43{
44
45 static Logger logger = Logger.getLogger(org.greenstone.gsdl3.service.GS2LuceneRetrieve.class.getName());
46
47 protected static final String DOC_LEVEL = "Doc";
48 protected static final String SEC_LEVEL = "Sec";
49 protected static final String ID_ATT = "gs2:docOID";
50
51 // Parameters used
52 private static final String LEVEL_PARAM = "level";
53
54 // Elements used in the config file that are specific to this class
55 private static final String DEFAULT_LEVEL_ELEM = "defaultLevel";
56
57 private String default_level = null;
58 private String text_dir = null;
59
60 private boolean text_available = true;
61
62 public GS2LuceneRetrieve()
63 {
64 }
65
66 public void cleanUp()
67 {
68 super.cleanUp();
69 }
70
71 /** configure this service */
72 public boolean configure(Element info, Element extra_info)
73 {
74 if (!super.configure(info, extra_info))
75 {
76 return false;
77 }
78
79 // Do specific configuration
80 logger.info("Configuring GS2LuceneRetrieve...");
81
82 text_dir = GSFile.collectionIndexDir(this.site_home, this.cluster_name) + File.separatorChar + "text" + File.separatorChar;
83 if (!(new File(text_dir).isDirectory()))
84 {
85 logger.error("Text directory " + text_dir + " does not exist, will be unable to retrieve text for " + cluster_name);
86 text_available = false;
87 return true; // return true so that we still get the other services for the collection
88 }
89 // Get the default level out of <defaultLevel> (buildConfig.xml)
90 Element def = (Element) GSXML.getChildByTagName(info, DEFAULT_LEVEL_ELEM);
91 if (def != null)
92 {
93 this.default_level = def.getAttribute(GSXML.SHORTNAME_ATT);
94 }
95 if (this.default_level == null || this.default_level.equals(""))
96 {
97 logger.error("Default level not specified for " + this.cluster_name + ", assuming " + DOC_LEVEL);
98 this.default_level = DOC_LEVEL;
99 }
100
101 return true;
102
103 }
104
105 /**
106 * returns the content of a node should return a nodeContent element:
107 * <nodeContent>text content or other elements</nodeContent>
108 */
109 protected Element getNodeContent(String doc_id, String lang) throws GSException
110 {
111 String[] args = new String[1];
112 args[0] = doc_id;
113 String doc_content = getTextString("TextRetrievalError", lang, args);
114 try
115 {
116 if (!text_available)
117 {
118 throw new Exception("No text directory available");
119 }
120
121 DBInfo info = this.coll_db.getInfo(OID.getTop(doc_id));
122 if (info == null)
123 {
124 throw new Exception("Couldn't get database entry for " + OID.getTop(doc_id));
125 }
126
127 String archivedir = info.getInfo("archivedir");
128 File doc_xml_file = new File(text_dir + archivedir + File.separatorChar + "doc.xml");
129 if (!doc_xml_file.isFile())
130 {
131 throw new Exception("Doc XML file " + doc_xml_file.getPath() + " does not exist");
132 }
133 Document doc_xml_doc = this.converter.getDOM(doc_xml_file, "utf-8");
134 if (doc_xml_doc == null)
135 {
136 throw new Exception("Couldn't parse file " + doc_xml_file.getPath());
137 }
138 Element full_document = doc_xml_doc.getDocumentElement();
139 if (full_document == null)
140 {
141 throw new Exception("Couldn't parse file " + doc_xml_file.getPath());
142 }
143 Element current_section = null;
144 if (default_level.equals(DOC_LEVEL))
145 {
146 current_section = full_document;
147 }
148 else
149 {
150 current_section = GSXML.getNamedElement(full_document, SEC_LEVEL, ID_ATT, doc_id);
151 }
152 if (current_section == null)
153 {
154 throw new Exception("Couldn't find section " + doc_id + " in file " + doc_xml_file.getPath());
155 }
156 doc_content = GSXML.getNodeText(current_section);
157 if (doc_content == null)
158 {
159 doc_content = "";
160 }
161 else
162 {
163 doc_content = resolveTextMacros(doc_content, doc_id, lang);
164 }
165 }
166 catch (Exception e)
167 {
168 logger.error("Error trying to get document text for " + doc_id + " in collection " + this.cluster_name + ": " + e);
169 }
170
171 Element content_node = this.doc.createElement(GSXML.NODE_CONTENT_ELEM);
172 Text t = this.doc.createTextNode(doc_content);
173 content_node.appendChild(t);
174 return content_node;
175 }
176}
Note: See TracBrowser for help on using the repository browser.