source: main/trunk/greenstone3/src/java/org/greenstone/gsdl3/util/BasicDocumentDatabase.java@ 26045

Last change on this file since 26045 was 26045, checked in by kjdon, 12 years ago

added lots more functions to the BasicDocument classes. Code has come from Browse and Retrieve services
File size: 9.1 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(Document doc,
55 String database_type, String site_home,
56 String cluster_name, String index_stem)
57 {
58 super(doc);
59
60 coll_db = new SimpleCollectionDatabase(database_type);
61 if (!coll_db.databaseOK()) {
62 logger.error("Couldn't create the collection database of type "+database_type);
63 }
64
65 // Open database for querying
66 String coll_db_file = GSFile.collectionDatabaseFile(site_home, cluster_name, index_stem, database_type);
67 if (!this.coll_db.openDatabase(coll_db_file, SimpleCollectionDatabase.READ)) {
68 logger.error("Could not open collection database!");
69 coll_db = null;
70 }
71 }
72
73 public boolean isValid()
74 {
75 return (coll_db != null);
76 }
77
78 public void cleanUp() {
79 this.coll_db.closeDatabase();
80 }
81
82
83 public DBInfo getInfo(String main_key) {
84 if (this.coll_db==null) {
85 // Most likely cause is that this installation of Greenstone3 has not
86 // been compiled with support for this database type
87 return null;
88 }
89
90 return coll_db.getInfo(main_key);
91 }
92
93
94 /** returns the document type of the doc that the specified node
95 belongs to. should be one of
96 GSXML.DOC_TYPE_SIMPLE,
97 GSXML.DOC_TYPE_PAGED,
98 GSXML.DOC_TYPE_HIERARCHY
99 */
100 public String getDocType(String node_id){
101 DBInfo info = this.coll_db.getInfo(node_id);
102 if (info == null) {
103 return GSXML.DOC_TYPE_SIMPLE;
104 }
105 String doc_type = info.getInfo("doctype");
106 if (!doc_type.equals("")&&!doc_type.equals("doc")) {
107 return doc_type;
108 }
109
110 String top_id = OID.getTop(node_id);
111 boolean is_top = (top_id.equals(node_id) ? true : false);
112
113 String children = info.getInfo("contains");
114 boolean is_leaf = (children.equals("") ? true : false);
115
116 if (is_top && is_leaf) { // a single section document
117 return GSXML.DOC_TYPE_SIMPLE;
118 }
119
120 // now we just check the top node
121 if (!is_top) { // we need to look at the top info
122 info = this.coll_db.getInfo(top_id);
123 }
124 if (info == null) {
125 return GSXML.DOC_TYPE_HIERARCHY;
126 }
127
128 String childtype = info.getInfo("childtype");
129 if (childtype.equals("Paged")) {
130 return GSXML.DOC_TYPE_PAGED;
131 }
132 if (childtype.equals("PagedHierarchy"))
133 {
134 return GSXML.DOC_TYPE_PAGED_HIERARCHY;
135 }
136 return GSXML.DOC_TYPE_HIERARCHY;
137
138 }
139
140 /**
141 * returns the structural information asked for. info_type may be one of
142 * INFO_NUM_SIBS, INFO_NUM_CHILDREN, INFO_SIB_POS, INFO_DOC_TYPE
143 */
144 public String getStructureInfo(String doc_id, String info_type){
145 String value = "";
146 if (info_type.equals(INFO_NUM_SIBS))
147 {
148 String parent_id = OID.getParent(doc_id);
149 if (parent_id.equals(doc_id))
150 {
151 value = "0";
152 }
153 else
154 {
155 value = String.valueOf(getNumChildren(parent_id));
156 }
157 return value;
158 }
159
160 if (info_type.equals(INFO_NUM_CHILDREN))
161 {
162 return String.valueOf(getNumChildren(doc_id));
163 }
164
165 if (info_type.equals(INFO_SIB_POS))
166 {
167 String parent_id = OID.getParent(doc_id);
168 if (parent_id.equals(doc_id))
169 {
170 return "-1";
171 }
172
173 DBInfo info = this.coll_db.getInfo(parent_id);
174 if (info == null)
175 {
176 return "-1";
177 }
178
179 String contains = info.getInfo("contains");
180 contains = StringUtils.replace(contains, "\"", parent_id);
181 String[] children = contains.split(";");
182 for (int i = 0; i < children.length; i++)
183 {
184 String child_id = children[i];
185 if (child_id.equals(doc_id))
186 {
187 return String.valueOf(i + 1); // make it from 1 to length
188
189 }
190 }
191
192 return "-1";
193 }
194 if (info_type.equals(INFO_DOC_TYPE))
195
196 {
197 return getDocType(doc_id);
198 }
199 return null;
200
201 }
202
203 /** returns true if the node has child nodes */
204 public boolean hasChildren(String node_id){
205 DBInfo info = this.coll_db.getInfo(node_id);
206 if (info == null) {
207 return false;
208 }
209 String contains = info.getInfo("contains");
210 if (contains.equals("")) {
211 return false;
212 }
213 return true;
214 }
215
216 public int getNumChildren(String node_id) {
217 DBInfo info = this.coll_db.getInfo(node_id);
218 if (info == null)
219 {
220 return 0;
221 }
222 String contains = info.getInfo("contains");
223 if (contains.equals(""))
224 {
225 return 0;
226 }
227 String[] children = contains.split(";");
228 return children.length;
229
230
231 }
232 /** returns a list of the child ids in order, null if no children
233 */
234 public ArrayList<String> getChildrenIds(String node_id) {
235 DBInfo info = this.coll_db.getInfo(node_id);
236 if (info == null)
237 {
238 return null;
239 }
240
241 String contains = info.getInfo("contains");
242 if (contains.equals(""))
243 {
244 return null;
245 }
246 ArrayList<String> children = new ArrayList<String>();
247 StringTokenizer st = new StringTokenizer(contains, ";");
248 while (st.hasMoreTokens())
249 {
250 String child_id = StringUtils.replace(st.nextToken(), "\"", node_id);
251 children.add(child_id);
252 }
253 return children;
254
255
256 }
257
258 /** returns true if the node has a parent */
259 public boolean hasParent(String node_id){
260 String parent = OID.getParent(node_id);
261 if (parent.equals(node_id)) {
262 return false;
263 }
264 return true;
265 }
266 /**
267 * returns the node id of the parent node, null if no parent
268 */
269 public String getParentId(String node_id) {
270 String parent = OID.getParent(node_id);
271 if (parent.equals(node_id))
272 {
273 return null;
274 }
275 return parent;
276
277 }
278
279 /**
280 * returns the node id of the root node of the document containing node_id
281 */
282 public String getRootId(String node_id) {
283 return OID.getTop(node_id);
284 }
285
286 /** convert indexer internal id to Greenstone oid */
287 public String internalNum2OID(long docnum)
288 {
289 return this.coll_db.docnum2OID(docnum);
290 }
291
292 public String internalNum2OID(String docnum)
293 {
294 return this.coll_db.docnum2OID(docnum);
295 }
296
297
298 /**
299 * adds all the children of doc_id to the doc element, and if
300 * recursive=true, adds all their children as well
301 */
302 public void addDescendants(Element doc, String doc_id, boolean recursive)
303 {
304 ArrayList<String> child_ids = getChildrenIds(doc_id);
305 if (child_ids == null)
306 return;
307 for (int i = 0; i < child_ids.size(); i++)
308 {
309 String child_id = child_ids.get(i);
310 Element child_elem = createDocNode(child_id);
311 doc.appendChild(child_elem);
312 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)))
313 {
314 addDescendants(child_elem, child_id, recursive);
315 }
316 }
317 }
318
319 /**
320 * adds all the siblings of current_id to the parent element. returns the
321 * new current element
322 */
323 public Element addSiblings(Element parent_node, String parent_id, String current_id)
324 {
325 Element current_node = GSXML.getFirstElementChild(parent_node);//(Element)parent_node.getFirstChild();
326 if (current_node == null)
327 {
328 // create a sensible error message
329 logger.error(" there should be a first child.");
330 return null;
331 }
332 // remove the current child,- will add it in later in its correct place
333 parent_node.removeChild(current_node);
334
335 // add in all the siblings,
336 addDescendants(parent_node, parent_id, false);
337
338 // find the node that is now the current node
339 // this assumes that the new node that was created is the same as
340 // the old one that was removed - we may want to replace the new one
341 // with the old one.
342 Element new_current = GSXML.getNamedElement(parent_node, current_node.getNodeName(), GSXML.NODE_ID_ATT, current_id);
343 return new_current;
344 }
345
346 /** returns the list of sibling ids, including the specified node_id */
347 public ArrayList<String> getSiblingIds(String node_id){
348 String parent_id = getParentId(node_id);
349 if (parent_id == null)
350 {
351 return null;
352 }
353 return getChildrenIds(parent_id);
354
355 }
356
357}
358
359
Note: See TracBrowser for help on using the repository browser.