1 | /*
|
---|
2 | * GS2MGRetrieve.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 | */
|
---|
19 | package org.greenstone.gsdl3.service;
|
---|
20 |
|
---|
21 | // Greenstone classes
|
---|
22 | import org.greenstone.mg.*;
|
---|
23 | import org.greenstone.gsdl3.core.GSException;
|
---|
24 | import org.greenstone.gsdl3.util.GSFile;
|
---|
25 | import org.greenstone.gsdl3.util.GSXML;
|
---|
26 |
|
---|
27 | // XML classes
|
---|
28 | import org.w3c.dom.Element;
|
---|
29 | import org.w3c.dom.Text;
|
---|
30 |
|
---|
31 | // General Java classes
|
---|
32 | import java.io.File;
|
---|
33 |
|
---|
34 | import org.apache.log4j.*;
|
---|
35 |
|
---|
36 | public class GS2MGRetrieve
|
---|
37 | extends AbstractGS2DocumentRetrieve
|
---|
38 | {
|
---|
39 | static Logger logger = Logger.getLogger(org.greenstone.gsdl3.service.GS2MGRetrieve.class.getName());
|
---|
40 |
|
---|
41 | // Elements used in the config file that are specific to this class
|
---|
42 | private static final String DEFAULT_INDEX_ELEM = "defaultIndex";
|
---|
43 | private static final String INDEX_LIST_ELEM = "indexList";
|
---|
44 | private static final String INDEX_ELEM = "index";
|
---|
45 |
|
---|
46 | private MGWrapper mg_src = null;
|
---|
47 | private String mg_basedir = null;
|
---|
48 | private String mg_textdir = null;
|
---|
49 | private String default_index = null;
|
---|
50 | private boolean has_default_index = false;
|
---|
51 |
|
---|
52 | public GS2MGRetrieve() {
|
---|
53 | this.mg_src = new MGWrapper();
|
---|
54 | }
|
---|
55 |
|
---|
56 | public void cleanUp() {
|
---|
57 | super.cleanUp();
|
---|
58 | this.mg_src.unloadIndexData();
|
---|
59 | }
|
---|
60 |
|
---|
61 | /** configure this service */
|
---|
62 | public boolean configure(Element info, Element extra_info)
|
---|
63 | {
|
---|
64 | if (!super.configure(info, extra_info)){
|
---|
65 | return false;
|
---|
66 | }
|
---|
67 |
|
---|
68 | // Do specific configuration
|
---|
69 | logger.info("Configuring GS2MGRetrieve...");
|
---|
70 |
|
---|
71 | // Get the default index out of <defaultIndex> (buildConfig.xml)
|
---|
72 | Element def = (Element) GSXML.getChildByTagName(info, DEFAULT_INDEX_ELEM);
|
---|
73 | if (def != null) {
|
---|
74 | this.default_index = def.getAttribute(GSXML.NAME_ATT);
|
---|
75 | }
|
---|
76 | if (this.default_index == null || this.default_index.equals("")) {
|
---|
77 | logger.error("default index is not specified, the content of a document will not be retrieved");
|
---|
78 | has_default_index = false;
|
---|
79 | return true;
|
---|
80 | //}
|
---|
81 | }
|
---|
82 | logger.debug("Default index: " + this.default_index);
|
---|
83 |
|
---|
84 | // The location of the MG index and text files
|
---|
85 | mg_basedir = GSFile.collectionBaseDir(this.site_home, this.cluster_name) + File.separatorChar; // Needed by MG
|
---|
86 | mg_textdir = GSFile.collectionTextPath(this.index_stem);
|
---|
87 | // index is only needed to start up MG, not used so just use the default index
|
---|
88 | String indexpath = GSFile.collectionIndexPath(this.index_stem, this.default_index);
|
---|
89 | this.mg_src.setIndex(indexpath);
|
---|
90 | has_default_index = true;
|
---|
91 | return true;
|
---|
92 | }
|
---|
93 |
|
---|
94 | /** returns the content of a node
|
---|
95 | * should return a nodeContent element:
|
---|
96 | * <nodeContent>text content or other elements</nodeContent>
|
---|
97 | */
|
---|
98 | protected Element getNodeContent(String doc_id, String lang) throws GSException {
|
---|
99 | long doc_num = this.gdbm_src.OID2Docnum(doc_id);
|
---|
100 | if (doc_num == -1) {
|
---|
101 | logger.error("OID "+doc_id +" couldn't be converted to mg num");
|
---|
102 | return null;
|
---|
103 | }
|
---|
104 | Element content_node = this.doc.createElement(GSXML.NODE_CONTENT_ELEM);
|
---|
105 |
|
---|
106 |
|
---|
107 | String doc_content = null;
|
---|
108 |
|
---|
109 | if (has_default_index ){
|
---|
110 | doc_content = this.mg_src.getDocument(this.mg_basedir,
|
---|
111 | this.mg_textdir, doc_num);
|
---|
112 | }
|
---|
113 |
|
---|
114 | if (doc_content!=null) {
|
---|
115 | // remove any ctrl-c or ctrl-b
|
---|
116 | doc_content = doc_content.replaceAll("\u0002|\u0003", "");
|
---|
117 | // replace _httpimg_ with the correct address
|
---|
118 | doc_content = resolveTextMacros(doc_content, doc_id, lang);
|
---|
119 | //GSXML.addDocText(this.doc, doc, doc_content);
|
---|
120 | } else {
|
---|
121 | logger.error("the doc content was null, not getting that section\n");
|
---|
122 | doc_content = "couldn't retrieve content for this section, please check the log file for more detail\n";
|
---|
123 | }
|
---|
124 | Text t = this.doc.createTextNode(doc_content);
|
---|
125 | content_node.appendChild(t);
|
---|
126 | return content_node;
|
---|
127 |
|
---|
128 | }
|
---|
129 |
|
---|
130 |
|
---|
131 | }
|
---|