source: main/trunk/greenstone3/src/java/org/greenstone/gsdl3/util/BasicDocumentDatabase.java@ 29089

Last change on this file since 29089 was 29089, checked in by kjdon, 10 years ago

added a method to retrieve a piece of metadata for the doc node. Used by AbstractBrowse to get mdoffset info
File size: 9.3 KB
Line 
1/*
2 * BasicDocumentDatabase.java
3 * Copyright (C) 2002 New Zealand Digital Library, http://www.nzdl.org
4 *
5 * This program is free software; you can redistribute it and/or modify
6 * the Free Software Foundation; either version 2 of the License, or
7 * (at your option) any later version.
8 *
9 * This program is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 * GNU General Public License for more details.
13 *
14 * You should have received a copy of the GNU General Public License
15 * along with this program; if not, write to the Free Software
16 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
17 */
18package org.greenstone.gsdl3.util;
19
20// Greenstone classes
21import org.greenstone.gsdl3.util.OID;
22import org.greenstone.gsdl3.util.DBInfo;
23import org.greenstone.gsdl3.util.GSXML;
24import org.greenstone.gsdl3.util.SimpleCollectionDatabase;
25import org.greenstone.gsdl3.util.GSFile;
26
27// XML classes
28import org.w3c.dom.Document;
29import org.w3c.dom.Element;
30import org.w3c.dom.NodeList;
31
32// java
33import java.util.Vector;
34import java.util.ArrayList;
35import java.util.HashMap;
36import java.util.Map;
37import java.util.Set;
38import java.util.StringTokenizer;
39import java.util.Iterator;
40import java.io.File;
41
42import org.apache.commons.lang3.StringUtils;
43import org.apache.log4j.*;
44
45public class BasicDocumentDatabase extends AbstractBasicDocument
46{
47 // collection database
48 protected SimpleCollectionDatabase coll_db = null;
49
50 static Logger logger = Logger.getLogger(org.greenstone.gsdl3.util.BasicDocumentDatabase.class.getName());
51
52
53 /** constructor */
54 public BasicDocumentDatabase(String database_type, String site_home,
55 String cluster_name, String index_stem)
56 {
57 super();
58
59 coll_db = new SimpleCollectionDatabase(database_type);
60 if (!coll_db.databaseOK()) {
61 logger.error("Couldn't create the collection database of type "+database_type);
62 }
63
64 // Open database for querying
65 String coll_db_file = GSFile.collectionDatabaseFile(site_home, cluster_name, index_stem, database_type);
66 if (!this.coll_db.openDatabase(coll_db_file, SimpleCollectionDatabase.READ)) {
67 logger.error("Could not open collection database!");
68 coll_db = null;
69 }
70 }
71
72 public boolean isValid()
73 {
74 return (coll_db != null);
75 }
76
77 public void cleanUp() {
78 this.coll_db.closeDatabase();
79 }
80
81
82 public DBInfo getInfo(String main_key) {
83 if (this.coll_db==null) {
84 // Most likely cause is that this installation of Greenstone3 has not
85 // been compiled with support for this database type
86 return null;
87 }
88
89 return coll_db.getInfo(main_key);
90 }
91
92
93 /** returns the document type of the doc that the specified node
94 belongs to. should be one of
95 GSXML.DOC_TYPE_SIMPLE,
96 GSXML.DOC_TYPE_PAGED,
97 GSXML.DOC_TYPE_HIERARCHY
98 */
99 public String getDocType(String node_id){
100 DBInfo info = this.coll_db.getInfo(node_id);
101 if (info == null) {
102 return GSXML.DOC_TYPE_SIMPLE;
103 }
104 String doc_type = info.getInfo("doctype");
105 if (!doc_type.equals("")&&!doc_type.equals("doc")) {
106 return doc_type;
107 }
108
109 String top_id = OID.getTop(node_id);
110 boolean is_top = (top_id.equals(node_id) ? true : false);
111
112 String children = info.getInfo("contains");
113 boolean is_leaf = (children.equals("") ? true : false);
114
115 if (is_top && is_leaf) { // a single section document
116 return GSXML.DOC_TYPE_SIMPLE;
117 }
118
119 // now we just check the top node
120 if (!is_top) { // we need to look at the top info
121 info = this.coll_db.getInfo(top_id);
122 }
123 if (info == null) {
124 return GSXML.DOC_TYPE_HIERARCHY;
125 }
126
127 String childtype = info.getInfo("childtype");
128 if (childtype.equals("Paged")) {
129 return GSXML.DOC_TYPE_PAGED;
130 }
131 if (childtype.equals("PagedHierarchy")) {
132
133 return GSXML.DOC_TYPE_PAGED_HIERARCHY;
134 }
135 return GSXML.DOC_TYPE_HIERARCHY;
136
137 }
138
139 /**
140 * returns the structural information asked for. info_type may be one of
141 * INFO_NUM_SIBS, INFO_NUM_CHILDREN, INFO_SIB_POS, INFO_DOC_TYPE
142 */
143 public String getStructureInfo(String doc_id, String info_type){
144 String value = "";
145 if (info_type.equals(INFO_NUM_SIBS))
146 {
147 String parent_id = OID.getParent(doc_id);
148 if (parent_id.equals(doc_id))
149 {
150 value = "0";
151 }
152 else
153 {
154 value = String.valueOf(getNumChildren(parent_id));
155 }
156 return value;
157 }
158
159 if (info_type.equals(INFO_NUM_CHILDREN))
160 {
161 return String.valueOf(getNumChildren(doc_id));
162 }
163
164 if (info_type.equals(INFO_SIB_POS))
165 {
166 String parent_id = OID.getParent(doc_id);
167 if (parent_id.equals(doc_id))
168 {
169 return "-1";
170 }
171
172 DBInfo info = this.coll_db.getInfo(parent_id);
173 if (info == null)
174 {
175 return "-1";
176 }
177
178 String contains = info.getInfo("contains");
179 contains = StringUtils.replace(contains, "\"", parent_id);
180 String[] children = contains.split(";");
181 for (int i = 0; i < children.length; i++)
182 {
183 String child_id = children[i];
184 if (child_id.equals(doc_id))
185 {
186 return String.valueOf(i + 1); // make it from 1 to length
187
188 }
189 }
190
191 return "-1";
192 }
193 if (info_type.equals(INFO_DOC_TYPE))
194
195 {
196 return getDocType(doc_id);
197 }
198 return null;
199
200 }
201
202 /** returns true if the node has child nodes */
203 public boolean hasChildren(String node_id){
204 DBInfo info = this.coll_db.getInfo(node_id);
205 if (info == null) {
206 return false;
207 }
208 String contains = info.getInfo("contains");
209 if (contains.equals("")) {
210 return false;
211 }
212 return true;
213 }
214
215 public int getNumChildren(String node_id) {
216 DBInfo info = this.coll_db.getInfo(node_id);
217 if (info == null)
218 {
219 return 0;
220 }
221 String contains = info.getInfo("contains");
222 if (contains.equals(""))
223 {
224 return 0;
225 }
226 String[] children = contains.split(";");
227 return children.length;
228
229
230 }
231 /** returns a list of the child ids in order, null if no children
232 */
233 public ArrayList<String> getChildrenIds(String node_id) {
234 DBInfo info = this.coll_db.getInfo(node_id);
235 if (info == null)
236 {
237 return null;
238 }
239
240 String contains = info.getInfo("contains");
241 if (contains.equals(""))
242 {
243 return null;
244 }
245 ArrayList<String> children = new ArrayList<String>();
246 StringTokenizer st = new StringTokenizer(contains, ";");
247 while (st.hasMoreTokens())
248 {
249 String child_id = StringUtils.replace(st.nextToken(), "\"", node_id);
250 children.add(child_id);
251 }
252 return children;
253
254
255 }
256
257 public String getMetadata(String node_id, String meta_name) {
258 DBInfo info = this.coll_db.getInfo(node_id);
259 if (info == null)
260 {
261 return null;
262 }
263 return info.getInfo(meta_name);
264 }
265
266 /** returns true if the node has a parent */
267 public boolean hasParent(String node_id){
268 String parent = OID.getParent(node_id);
269 if (parent.equals(node_id)) {
270 return false;
271 }
272 return true;
273 }
274 /**
275 * returns the node id of the parent node, null if no parent
276 */
277 public String getParentId(String node_id) {
278 String parent = OID.getParent(node_id);
279 if (parent.equals(node_id))
280 {
281 return null;
282 }
283 return parent;
284
285 }
286
287 /**
288 * returns the node id of the root node of the document containing node_id
289 */
290 public String getRootId(String node_id) {
291 return OID.getTop(node_id);
292 }
293
294 /** convert indexer internal id to Greenstone oid */
295 public String internalNum2OID(long docnum)
296 {
297 return this.coll_db.docnum2OID(docnum);
298 }
299
300 public String internalNum2OID(String docnum)
301 {
302 return this.coll_db.docnum2OID(docnum);
303 }
304
305
306 /**
307 * adds all the children of doc_id to the doc element, and if
308 * recursive=true, adds all their children as well
309 */
310 public void addDescendants(Element doc, String doc_id, boolean recursive)
311 {
312 ArrayList<String> child_ids = getChildrenIds(doc_id);
313 if (child_ids == null)
314 return;
315 for (int i = 0; i < child_ids.size(); i++)
316 {
317 String child_id = child_ids.get(i);
318 Element child_elem = createDocNode(doc.getOwnerDocument(), child_id);
319 doc.appendChild(child_elem);
320 if (recursive && (!child_elem.getAttribute(GSXML.NODE_TYPE_ATT).equals(GSXML.NODE_TYPE_LEAF) || child_elem.getAttribute(GSXML.DOC_TYPE_ATT).equals(GSXML.DOC_TYPE_PAGED)))
321 {
322 addDescendants(child_elem, child_id, recursive);
323 }
324 }
325 }
326
327 /**
328 * adds all the siblings of current_id to the parent element. returns the
329 * new current element
330 */
331 public Element addSiblings(Element parent_node, String parent_id, String current_id)
332 {
333 Element current_node = GSXML.getFirstElementChild(parent_node);//(Element)parent_node.getFirstChild();
334 if (current_node == null)
335 {
336 // create a sensible error message
337 logger.error(" there should be a first child.");
338 return null;
339 }
340 // remove the current child,- will add it in later in its correct place
341 parent_node.removeChild(current_node);
342
343 // add in all the siblings,
344 addDescendants(parent_node, parent_id, false);
345
346 // find the node that is now the current node
347 // this assumes that the new node that was created is the same as
348 // the old one that was removed - we may want to replace the new one
349 // with the old one.
350 Element new_current = GSXML.getNamedElement(parent_node, current_node.getNodeName(), GSXML.NODE_ID_ATT, current_id);
351 return new_current;
352 }
353
354 /** returns the list of sibling ids, including the specified node_id */
355 public ArrayList<String> getSiblingIds(String node_id){
356 String parent_id = getParentId(node_id);
357 if (parent_id == null)
358 {
359 return null;
360 }
361 return getChildrenIds(parent_id);
362
363 }
364
365}
366
367
Note: See TracBrowser for help on using the repository browser.