source: main/branches/3.04flax1.0/greenstone3/src/java/org/greenstone/gsdl3/service/GS2MGPPRetrieve.java@ 21777

Last change on this file since 21777 was 21777, checked in by xiao, 14 years ago

migrant changes Kathy made on the main-trunk copy to the copy of 3.04flax1.0, which fixed the un-wellformness of returned documents in xml form when browsing/searching in the library

  • Property svn:keywords set to Author Date Id Revision
File size: 4.2 KB
Line 
1/*
2 * GS2MGPPRetrieve.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.mgpp.*;
23import org.greenstone.gsdl3.core.GSException;
24import org.greenstone.gsdl3.util.GSFile;
25import org.greenstone.gsdl3.util.GSXML;
26
27// XML classes
28import org.w3c.dom.Element;
29import org.w3c.dom.Text;
30
31// General Java classes
32import java.io.File;
33
34import org.apache.log4j.*;
35
36public class GS2MGPPRetrieve
37 extends AbstractGS2DocumentRetrieve {
38 static Logger logger = Logger.getLogger(org.greenstone.gsdl3.service.GS2MGPPRetrieve.class.getName());
39
40 // Parameters used
41 private static final String LEVEL_PARAM = "level";
42
43 // Elements used in the config file that are specific to this class
44 private static final String DEFAULT_LEVEL_ELEM = "defaultLevel";
45
46 private static MGPPRetrieveWrapper mgpp_src = null;
47
48 private String default_level = null;
49 private String mgpp_textdir = null;
50
51 public GS2MGPPRetrieve() {
52 if(mgpp_src == null) {
53 mgpp_src = new MGPPRetrieveWrapper();
54 }
55 }
56
57 public void cleanUp() {
58 super.cleanUp();
59 }
60
61 /** configure this service */
62 public boolean configure(Element info, Element extra_info) {
63 if (!super.configure(info, extra_info)){
64 return false;
65 }
66
67 // Do specific configuration
68 logger.info("Configuring GS2MGPPRetrieve...");
69
70 // Get the default level out of <defaultLevel> (buildConfig.xml)
71 Element def = (Element) GSXML.getChildByTagName(info, DEFAULT_LEVEL_ELEM);
72 if (def != null) {
73 this.default_level = def.getAttribute(GSXML.SHORTNAME_ATT);
74 }
75 if (this.default_level == null || this.default_level.equals("")) {
76 logger.error("default level not specified!");
77 return false;
78 }
79
80 // The location of the MGPP text files
81 mgpp_textdir = GSFile.collectionBaseDir(this.site_home, this.cluster_name) +
82 File.separatorChar + GSFile.collectionTextPath(this.index_stem);
83
84 // Do generic configuration
85 return true;
86
87 }
88
89 /** returns the content of a node
90 * should return a nodeContent element:
91 * <nodeContent>text content or other elements</nodeContent>
92 */
93 protected Element getNodeContent(String doc_id, String lang) throws GSException {
94 long doc_num = this.coll_db.OID2DocnumLong(doc_id);
95 if (doc_num == -1) {
96 logger.error("OID "+doc_id +" couldn't be converted to mgpp num");
97 return null;
98 }
99 Element content_node = this.doc.createElement(GSXML.NODE_CONTENT_ELEM);
100 synchronized (mgpp_src) {
101 String doc_content = "";
102 try {
103
104 doc_content = mgpp_src.getDocument(this.mgpp_textdir,
105 this.default_level,
106 doc_num);
107
108 if (doc_content != null) {
109 doc_content = resolveTextMacros(doc_content, doc_id, lang);
110 }
111 // remove the <Doc></Doc> and <Sec></Sec> tags
112 //doc_content = doc_content.replace("<Doc>", "").replace("</Doc>", "").replace("<Sec>", "").replace("</Sec>", "");
113 doc_content = doc_content.replaceAll("</?(Doc|Sec)>", "");
114
115 } catch (Exception e) {
116 logger.info("exception happended with mgpp_src.getDocument()" + e);
117 doc_content = "this is the content for section hash id "+ doc_id+", mgpp doc num "+doc_num+"\n";
118
119 }
120 Text t = this.doc.createTextNode(doc_content);
121 content_node.appendChild(t);
122 return content_node;
123 }//end of synchronized
124 }
125
126
127}
Note: See TracBrowser for help on using the repository browser.