1 | /*
|
---|
2 | * GS2Browse.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.gsdl3.util.OID;
|
---|
23 | import org.greenstone.gsdl3.util.GSXML;
|
---|
24 | import org.greenstone.gsdl3.util.GSFile;
|
---|
25 | import org.greenstone.gsdl3.util.MacroResolver;
|
---|
26 | import org.greenstone.gsdl3.util.GS2MacroResolver;
|
---|
27 | import org.greenstone.gsdl3.util.SimpleCollectionDatabase;
|
---|
28 | import org.greenstone.gsdl3.util.DBInfo;
|
---|
29 | // XML classes
|
---|
30 | import org.w3c.dom.Document;
|
---|
31 | import org.w3c.dom.Element;
|
---|
32 | import org.w3c.dom.NodeList;
|
---|
33 |
|
---|
34 | // General Java classes
|
---|
35 | import java.util.ArrayList;
|
---|
36 | import java.util.StringTokenizer;
|
---|
37 | import java.util.Set;
|
---|
38 | import java.util.Iterator;
|
---|
39 |
|
---|
40 | import org.apache.log4j.*;
|
---|
41 |
|
---|
42 | /**
|
---|
43 | * Greenstone 2 collection classifier service
|
---|
44 | *
|
---|
45 | * @author <a href="mailto:[email protected]">Katherine Don</a>
|
---|
46 | * @author <a href="mailto:[email protected]">Michael Dewsnip</a>
|
---|
47 | */
|
---|
48 |
|
---|
49 | public class GS2Browse extends AbstractBrowse
|
---|
50 | {
|
---|
51 |
|
---|
52 | static Logger logger = Logger.getLogger(org.greenstone.gsdl3.service.GS2Browse.class.getName());
|
---|
53 |
|
---|
54 | protected SimpleCollectionDatabase coll_db = null;
|
---|
55 |
|
---|
56 | public GS2Browse()
|
---|
57 | {
|
---|
58 | }
|
---|
59 |
|
---|
60 | public void cleanUp()
|
---|
61 | {
|
---|
62 | super.cleanUp();
|
---|
63 | this.coll_db.closeDatabase();
|
---|
64 | }
|
---|
65 |
|
---|
66 | public boolean configure(Element info, Element extra_info)
|
---|
67 | {
|
---|
68 | if (!super.configure(info, extra_info))
|
---|
69 | {
|
---|
70 | return false;
|
---|
71 | }
|
---|
72 |
|
---|
73 | logger.info("Configuring GS2Browse...");
|
---|
74 | // the index stem is either specified in the config file or is the collection name
|
---|
75 | Element index_stem_elem = (Element) GSXML.getChildByTagName(info, GSXML.INDEX_STEM_ELEM);
|
---|
76 | String index_stem = null;
|
---|
77 | if (index_stem_elem != null)
|
---|
78 | {
|
---|
79 | index_stem = index_stem_elem.getAttribute(GSXML.NAME_ATT);
|
---|
80 | }
|
---|
81 | if (index_stem == null || index_stem.equals(""))
|
---|
82 | {
|
---|
83 | index_stem = this.cluster_name;
|
---|
84 | }
|
---|
85 |
|
---|
86 | // find out what kind of database we have
|
---|
87 | Element database_type_elem = (Element) GSXML.getChildByTagName(info, GSXML.DATABASE_TYPE_ELEM);
|
---|
88 | String database_type = null;
|
---|
89 | if (database_type_elem != null)
|
---|
90 | {
|
---|
91 | database_type = database_type_elem.getAttribute(GSXML.NAME_ATT);
|
---|
92 | }
|
---|
93 |
|
---|
94 | if (database_type == null || database_type.equals(""))
|
---|
95 | {
|
---|
96 | database_type = "gdbm"; // the default
|
---|
97 | }
|
---|
98 | coll_db = new SimpleCollectionDatabase(database_type);
|
---|
99 | if (!coll_db.databaseOK())
|
---|
100 | {
|
---|
101 | logger.error("Couldn't create the collection database of type " + database_type);
|
---|
102 | return false;
|
---|
103 | }
|
---|
104 |
|
---|
105 | // Open database for querying
|
---|
106 | String coll_db_file = GSFile.collectionDatabaseFile(this.site_home, this.cluster_name, index_stem, database_type);
|
---|
107 | if (!this.coll_db.openDatabase(coll_db_file, SimpleCollectionDatabase.READ))
|
---|
108 | {
|
---|
109 | logger.error("Could not open collection database!");
|
---|
110 | return false;
|
---|
111 | }
|
---|
112 | this.macro_resolver = new GS2MacroResolver(this.coll_db);
|
---|
113 | return true;
|
---|
114 | }
|
---|
115 |
|
---|
116 | /** if id ends in .fc, .pc etc, then translate it to the correct id */
|
---|
117 | protected String translateId(String node_id)
|
---|
118 | {
|
---|
119 | return OID.translateOID(this.coll_db, node_id); //return this.coll_db.translateOID(node_id);
|
---|
120 | }
|
---|
121 |
|
---|
122 | /**
|
---|
123 | * returns the document type of the doc that the specified node belongs to.
|
---|
124 | * should be one of GSXML.DOC_TYPE_SIMPLE, GSXML.DOC_TYPE_PAGED,
|
---|
125 | * GSXML.DOC_TYPE_HIERARCHY
|
---|
126 | */
|
---|
127 | protected String getDocType(String node_id)
|
---|
128 | {
|
---|
129 | DBInfo info = this.coll_db.getInfo(node_id);
|
---|
130 | if (info == null)
|
---|
131 | {
|
---|
132 | return GSXML.DOC_TYPE_SIMPLE;
|
---|
133 | }
|
---|
134 | String doc_type = info.getInfo("doctype");
|
---|
135 | if (!doc_type.equals("") && !doc_type.equals("doc"))
|
---|
136 | {
|
---|
137 | return doc_type;
|
---|
138 | }
|
---|
139 |
|
---|
140 | String top_id = OID.getTop(node_id);
|
---|
141 | boolean is_top = (top_id.equals(node_id) ? true : false);
|
---|
142 |
|
---|
143 | String children = info.getInfo("contains");
|
---|
144 | boolean is_leaf = (children.equals("") ? true : false);
|
---|
145 |
|
---|
146 | if (is_top && is_leaf)
|
---|
147 | { // a single section document
|
---|
148 | return GSXML.DOC_TYPE_SIMPLE;
|
---|
149 | }
|
---|
150 |
|
---|
151 | // now we just check the top node
|
---|
152 | if (!is_top)
|
---|
153 | { // we need to look at the top info
|
---|
154 | info = this.coll_db.getInfo(top_id);
|
---|
155 | }
|
---|
156 | if (info == null)
|
---|
157 | {
|
---|
158 | return GSXML.DOC_TYPE_HIERARCHY;
|
---|
159 | }
|
---|
160 |
|
---|
161 | String childtype = info.getInfo("childtype");
|
---|
162 | if (childtype.equals("Paged"))
|
---|
163 | {
|
---|
164 | return GSXML.DOC_TYPE_PAGED;
|
---|
165 | }
|
---|
166 | return GSXML.DOC_TYPE_HIERARCHY;
|
---|
167 |
|
---|
168 | }
|
---|
169 |
|
---|
170 | /**
|
---|
171 | * returns the id of the root node of the document containing node node_id.
|
---|
172 | * . may be the same as node_id
|
---|
173 | */
|
---|
174 | protected String getRootId(String node_id)
|
---|
175 | {
|
---|
176 | return OID.getTop(node_id);
|
---|
177 | }
|
---|
178 |
|
---|
179 | /** returns a list of the child ids in order, null if no children */
|
---|
180 | protected ArrayList<String> getChildrenIds(String node_id)
|
---|
181 | {
|
---|
182 | DBInfo info = this.coll_db.getInfo(node_id);
|
---|
183 | if (info == null)
|
---|
184 | {
|
---|
185 | return null;
|
---|
186 | }
|
---|
187 |
|
---|
188 | ArrayList<String> children = new ArrayList<String>();
|
---|
189 |
|
---|
190 | String contains = info.getInfo("contains");
|
---|
191 | StringTokenizer st = new StringTokenizer(contains, ";");
|
---|
192 | while (st.hasMoreTokens())
|
---|
193 | {
|
---|
194 | String child_id = st.nextToken().replaceAll("\"", node_id);
|
---|
195 | children.add(child_id);
|
---|
196 | }
|
---|
197 | return children;
|
---|
198 |
|
---|
199 | }
|
---|
200 |
|
---|
201 | /** returns the node id of the parent node, null if no parent */
|
---|
202 | protected String getParentId(String node_id)
|
---|
203 | {
|
---|
204 | String parent = OID.getParent(node_id);
|
---|
205 | if (parent.equals(node_id))
|
---|
206 | {
|
---|
207 | return null;
|
---|
208 | }
|
---|
209 | return parent;
|
---|
210 | }
|
---|
211 |
|
---|
212 | protected String getMetadata(String node_id, String key)
|
---|
213 | {
|
---|
214 | DBInfo info = this.coll_db.getInfo(node_id);
|
---|
215 | if (info == null)
|
---|
216 | {
|
---|
217 | return "";
|
---|
218 | }
|
---|
219 |
|
---|
220 | Set<String> keys = info.getKeys();
|
---|
221 | Iterator<String> it = keys.iterator();
|
---|
222 | while (it.hasNext())
|
---|
223 | {
|
---|
224 | String key_in = it.next();
|
---|
225 | String value = info.getInfo(key);
|
---|
226 | if (key_in.equals(key))
|
---|
227 | {
|
---|
228 | return value;
|
---|
229 | }
|
---|
230 | }
|
---|
231 |
|
---|
232 | return "";
|
---|
233 |
|
---|
234 | }
|
---|
235 |
|
---|
236 | /**
|
---|
237 | * get the metadata for the classifier node node_id returns a metadataList
|
---|
238 | * element: <metadataList><metadata
|
---|
239 | * name="xxx">value</metadata></metadataList> if all_metadata is true,
|
---|
240 | * returns all available metadata, otherwise just returns requested metadata
|
---|
241 | */
|
---|
242 | // assumes only one value per metadata
|
---|
243 | protected Element getMetadataList(String node_id, boolean all_metadata, ArrayList<String> metadata_names)
|
---|
244 | {
|
---|
245 | String lang = "en";
|
---|
246 | Element metadata_list = this.doc.createElement(GSXML.METADATA_ELEM + GSXML.LIST_MODIFIER);
|
---|
247 | DBInfo info = this.coll_db.getInfo(node_id);
|
---|
248 | if (info == null)
|
---|
249 | {
|
---|
250 | return null;
|
---|
251 | }
|
---|
252 | if (all_metadata)
|
---|
253 | {
|
---|
254 | // return everything out of the database
|
---|
255 | Set<String> keys = info.getKeys();
|
---|
256 | Iterator<String> it = keys.iterator();
|
---|
257 | while (it.hasNext())
|
---|
258 | {
|
---|
259 | String key = it.next();
|
---|
260 | String value = info.getInfo(key);
|
---|
261 | GSXML.addMetadata(this.doc, metadata_list, key, this.macro_resolver.resolve(value, lang, GS2MacroResolver.SCOPE_META, node_id));
|
---|
262 | }
|
---|
263 |
|
---|
264 | }
|
---|
265 | else
|
---|
266 | {
|
---|
267 | for (int i = 0; i < metadata_names.size(); i++)
|
---|
268 | {
|
---|
269 | String meta_name = metadata_names.get(i);
|
---|
270 | String value = (String) info.getInfo(meta_name);
|
---|
271 | GSXML.addMetadata(this.doc, metadata_list, meta_name, value);
|
---|
272 | }
|
---|
273 | }
|
---|
274 | return metadata_list;
|
---|
275 | }
|
---|
276 |
|
---|
277 | /**
|
---|
278 | * returns the structural information asked for. info_type may be one of
|
---|
279 | * INFO_NUM_SIBS, INFO_NUM_CHILDREN, INFO_SIB_POS
|
---|
280 | */
|
---|
281 | protected String getStructureInfo(String doc_id, String info_type)
|
---|
282 | {
|
---|
283 | String value = "";
|
---|
284 | if (info_type.equals(INFO_NUM_SIBS))
|
---|
285 | {
|
---|
286 | String parent_id = OID.getParent(doc_id);
|
---|
287 | if (parent_id.equals(doc_id))
|
---|
288 | {
|
---|
289 | value = "0";
|
---|
290 | }
|
---|
291 | else
|
---|
292 | {
|
---|
293 | value = String.valueOf(getNumChildren(parent_id));
|
---|
294 | }
|
---|
295 | return value;
|
---|
296 | }
|
---|
297 |
|
---|
298 | if (info_type.equals(INFO_NUM_CHILDREN))
|
---|
299 | {
|
---|
300 | return String.valueOf(getNumChildren(doc_id));
|
---|
301 | }
|
---|
302 |
|
---|
303 | if (info_type.equals(INFO_SIB_POS))
|
---|
304 | {
|
---|
305 | String parent_id = OID.getParent(doc_id);
|
---|
306 | if (parent_id.equals(doc_id))
|
---|
307 | {
|
---|
308 | return "-1";
|
---|
309 | }
|
---|
310 |
|
---|
311 | DBInfo info = this.coll_db.getInfo(parent_id);
|
---|
312 | if (info == null)
|
---|
313 | {
|
---|
314 | return "-1";
|
---|
315 | }
|
---|
316 |
|
---|
317 | String contains = info.getInfo("contains");
|
---|
318 | contains = contains.replaceAll("\"", parent_id);
|
---|
319 | String[] children = contains.split(";");
|
---|
320 | for (int i = 0; i < children.length; i++)
|
---|
321 | {
|
---|
322 | String child_id = children[i];
|
---|
323 | if (child_id.equals(doc_id))
|
---|
324 | {
|
---|
325 | return String.valueOf(i + 1); // make it from 1 to length
|
---|
326 |
|
---|
327 | }
|
---|
328 | }
|
---|
329 |
|
---|
330 | return "-1";
|
---|
331 | }
|
---|
332 | else
|
---|
333 | {
|
---|
334 | return null;
|
---|
335 | }
|
---|
336 |
|
---|
337 | }
|
---|
338 |
|
---|
339 | protected int getNumChildren(String node_id)
|
---|
340 | {
|
---|
341 | DBInfo info = this.coll_db.getInfo(node_id);
|
---|
342 | if (info == null)
|
---|
343 | {
|
---|
344 | return 0;
|
---|
345 | }
|
---|
346 | String contains = info.getInfo("contains");
|
---|
347 | if (contains.equals(""))
|
---|
348 | {
|
---|
349 | return 0;
|
---|
350 | }
|
---|
351 | String[] children = contains.split(";");
|
---|
352 | return children.length;
|
---|
353 | }
|
---|
354 |
|
---|
355 | /**
|
---|
356 | * returns true if the id refers to a document (rather than a classifier
|
---|
357 | * node)
|
---|
358 | */
|
---|
359 | protected boolean isDocumentId(String node_id)
|
---|
360 | {
|
---|
361 | if (node_id.startsWith("CL"))
|
---|
362 | {
|
---|
363 | return false;
|
---|
364 | }
|
---|
365 | return true;
|
---|
366 | }
|
---|
367 |
|
---|
368 | }
|
---|