1 | /**********************************************************************
|
---|
2 | *
|
---|
3 | * Indexer.java
|
---|
4 | *
|
---|
5 | * Copyright 2004 The New Zealand Digital Library Project
|
---|
6 | *
|
---|
7 | * A component of the Greenstone digital library software
|
---|
8 | * from the New Zealand Digital Library Project at the
|
---|
9 | * University of Waikato, New Zealand.
|
---|
10 | *
|
---|
11 | * This program is free software; you can redistribute it and/or modify
|
---|
12 | * it under the terms of the GNU General Public License as published by
|
---|
13 | * the Free Software Foundation; either version 2 of the License, or
|
---|
14 | * (at your option) any later version.
|
---|
15 | *
|
---|
16 | * This program is distributed in the hope that it will be useful,
|
---|
17 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
18 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
19 | * GNU General Public License for more details.
|
---|
20 | *
|
---|
21 | * You should have received a copy of the GNU General Public License
|
---|
22 | * along with this program; if not, write to the Free Software
|
---|
23 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
24 | *
|
---|
25 | *********************************************************************/
|
---|
26 | package org.greenstone.LuceneWrapper;
|
---|
27 |
|
---|
28 |
|
---|
29 | import org.xml.sax.Attributes;
|
---|
30 | import org.xml.sax.helpers.DefaultHandler;
|
---|
31 | import org.xml.sax.InputSource;
|
---|
32 | import org.xml.sax.SAXException;
|
---|
33 | import org.xml.sax.XMLReader;
|
---|
34 |
|
---|
35 | import javax.xml.parsers.SAXParser;
|
---|
36 | import javax.xml.parsers.SAXParserFactory;
|
---|
37 |
|
---|
38 | import org.apache.lucene.document.Document;
|
---|
39 | import org.apache.lucene.document.Field;
|
---|
40 | import org.apache.lucene.index.IndexWriter;
|
---|
41 | import org.apache.lucene.analysis.standard.StandardAnalyzer;
|
---|
42 |
|
---|
43 | import java.util.Stack;
|
---|
44 | import java.io.FileInputStream;
|
---|
45 | import java.io.File;
|
---|
46 | import java.io.StringReader;
|
---|
47 | import java.net.URL;
|
---|
48 |
|
---|
49 |
|
---|
50 |
|
---|
51 | public class Indexer extends DefaultHandler
|
---|
52 | {
|
---|
53 | IndexWriter writer_ = null;
|
---|
54 | SAXParser sax_parser_ = null;
|
---|
55 | String doc_tag_level_ = null;
|
---|
56 |
|
---|
57 | Stack stack_ = null;
|
---|
58 | String path_ = "";
|
---|
59 |
|
---|
60 | Document current_doc_ = null;
|
---|
61 | String current_node_ = "";
|
---|
62 | String indexable_current_node_ = "";
|
---|
63 | String current_contents_ = "";
|
---|
64 |
|
---|
65 | protected String file_id_ = null;
|
---|
66 |
|
---|
67 | /** pass in true if want to create a new index, false if want to use the existing one */
|
---|
68 | public Indexer (String doc_tag_level, File index_dir, boolean create)
|
---|
69 | {
|
---|
70 | doc_tag_level_ = doc_tag_level;
|
---|
71 |
|
---|
72 | try {
|
---|
73 | stack_ = new Stack();
|
---|
74 | SAXParserFactory sax_factory = SAXParserFactory.newInstance();
|
---|
75 | sax_parser_ = sax_factory.newSAXParser();
|
---|
76 |
|
---|
77 | XMLReader reader = sax_parser_.getXMLReader();
|
---|
78 | reader.setFeature("http://xml.org/sax/features/validation", false);
|
---|
79 |
|
---|
80 | writer_ = new IndexWriter(index_dir.getPath(), new StandardAnalyzer(), create);
|
---|
81 | // by default, will only index 10,000 words per document
|
---|
82 | // Can throw out_of_memory errors
|
---|
83 | writer_.setMaxFieldLength(Integer.MAX_VALUE);
|
---|
84 | if (create) {
|
---|
85 | writer_.optimize();
|
---|
86 | }
|
---|
87 |
|
---|
88 | } catch (Exception e) {
|
---|
89 | // do nothing!
|
---|
90 | }
|
---|
91 | }
|
---|
92 |
|
---|
93 | /** index one document */
|
---|
94 | public void index (String file_id, File file)
|
---|
95 | {
|
---|
96 | file_id_ = file_id;
|
---|
97 | path_ = "";
|
---|
98 | String base_path = file.getPath();
|
---|
99 | base_path = base_path.substring(0, base_path.lastIndexOf(File.separatorChar));
|
---|
100 |
|
---|
101 | try {
|
---|
102 | sax_parser_.parse(new InputSource(new FileInputStream(file)), this);
|
---|
103 | }
|
---|
104 | catch (Exception e) {
|
---|
105 | println("parse error:");
|
---|
106 | e.printStackTrace();
|
---|
107 | }
|
---|
108 | }
|
---|
109 |
|
---|
110 | /** index one document stored as string*/
|
---|
111 | public void index (String xml_text)
|
---|
112 | {
|
---|
113 | file_id_ = "<xml doc on stdin>";
|
---|
114 | path_ = "";
|
---|
115 |
|
---|
116 | try {
|
---|
117 | sax_parser_.parse(new InputSource(new StringReader(xml_text)), this);
|
---|
118 | }
|
---|
119 | catch (Exception e) {
|
---|
120 | println("parse error:");
|
---|
121 | e.printStackTrace();
|
---|
122 | }
|
---|
123 | }
|
---|
124 |
|
---|
125 | public void finish()
|
---|
126 | {
|
---|
127 | /** optimise the index */
|
---|
128 | try {
|
---|
129 | writer_.optimize();
|
---|
130 | writer_.close();
|
---|
131 | }
|
---|
132 | catch (Exception e) {
|
---|
133 | }
|
---|
134 | }
|
---|
135 |
|
---|
136 | protected void print(String s)
|
---|
137 | {
|
---|
138 | System.out.print(s);
|
---|
139 | }
|
---|
140 |
|
---|
141 | protected void println(String s)
|
---|
142 | {
|
---|
143 | System.out.println(s);
|
---|
144 | }
|
---|
145 |
|
---|
146 | public void startDocument() throws SAXException
|
---|
147 | {
|
---|
148 | println("Starting to index " + file_id_);
|
---|
149 | print("[");
|
---|
150 | }
|
---|
151 |
|
---|
152 | public void endDocument() throws SAXException
|
---|
153 | {
|
---|
154 | println("]");
|
---|
155 | println("... indexing finished.");
|
---|
156 | }
|
---|
157 |
|
---|
158 | public void startElement(String uri, String localName, String qName, Attributes atts)
|
---|
159 | throws SAXException
|
---|
160 | {
|
---|
161 | path_ = appendPathLink(path_, qName, atts);
|
---|
162 |
|
---|
163 | if (qName.equals(doc_tag_level_)) {
|
---|
164 | pushOnStack(); // start new doc
|
---|
165 | current_node_ = qName;
|
---|
166 | String node_id = atts.getValue("gs2:id");
|
---|
167 |
|
---|
168 | print(" " + qName + ": " + node_id );
|
---|
169 | current_doc_.add(new Field("nodeID", node_id, Field.Store.YES, Field.Index.NO));
|
---|
170 | }
|
---|
171 |
|
---|
172 | if (XMLTagInfo.isIndexable(atts)) {
|
---|
173 | indexable_current_node_ = qName;
|
---|
174 | }
|
---|
175 | else {
|
---|
176 | indexable_current_node_ = "";
|
---|
177 | }
|
---|
178 |
|
---|
179 | }
|
---|
180 | public void endElement(String uri, String localName, String qName) throws SAXException
|
---|
181 | {
|
---|
182 | if (qName.equals(indexable_current_node_))
|
---|
183 | {
|
---|
184 | current_doc_.add(new Field(qName, current_contents_, Field.Store.NO, Field.Index.TOKENIZED, Field.TermVector.YES));
|
---|
185 | // We only need the term vector for the TX field
|
---|
186 | if (!qName.equals("TX"))
|
---|
187 | {
|
---|
188 | current_doc_.add(new Field("by" + qName, current_contents_, Field.Store.NO, Field.Index.UN_TOKENIZED, Field.TermVector.NO));
|
---|
189 | }
|
---|
190 |
|
---|
191 | current_contents_ = "";
|
---|
192 | }
|
---|
193 |
|
---|
194 | if (qName.equals(doc_tag_level_)) {
|
---|
195 | try {
|
---|
196 | writer_.addDocument(current_doc_);
|
---|
197 | }
|
---|
198 | catch (java.io.IOException e) {
|
---|
199 | e.printStackTrace();
|
---|
200 | }
|
---|
201 | popOffStack(); // end document
|
---|
202 | }
|
---|
203 |
|
---|
204 | path_ = removePathLink(path_);
|
---|
205 | }
|
---|
206 |
|
---|
207 | public void characters(char ch[], int start, int length) throws SAXException
|
---|
208 | {
|
---|
209 | String data = new String(ch, start, length).trim();
|
---|
210 | if (data.length() > 0 ) {
|
---|
211 | current_contents_ += data;
|
---|
212 | }
|
---|
213 | }
|
---|
214 |
|
---|
215 | protected String appendPathLink(String path, String qName, Attributes atts)
|
---|
216 | {
|
---|
217 |
|
---|
218 | path = path + "/"+qName;
|
---|
219 | if (atts.getLength()>0) {
|
---|
220 | String id = atts.getValue("gs2:id");
|
---|
221 | if (id != null) {
|
---|
222 | path += "[@gs2:id='"+id+"']";
|
---|
223 | }
|
---|
224 | else {
|
---|
225 | id = atts.getValue("gs3:id");
|
---|
226 | if (id != null) {
|
---|
227 | path += "[@gs3:id='"+id+"']";
|
---|
228 | }
|
---|
229 | }
|
---|
230 | }
|
---|
231 | return path;
|
---|
232 | }
|
---|
233 | protected String removePathLink(String path)
|
---|
234 | {
|
---|
235 |
|
---|
236 | int i=path.lastIndexOf('/');
|
---|
237 | if (i==-1) {
|
---|
238 | path="";
|
---|
239 | } else {
|
---|
240 | path = path.substring(0, i);
|
---|
241 | }
|
---|
242 | return path;
|
---|
243 | }
|
---|
244 | /** these are what we save on the stack */
|
---|
245 | private class MyDocument
|
---|
246 | {
|
---|
247 | public Document doc = null;
|
---|
248 | public String contents = null;
|
---|
249 | public String tagname = "";
|
---|
250 |
|
---|
251 | }
|
---|
252 |
|
---|
253 | protected void pushOnStack()
|
---|
254 | {
|
---|
255 | if (current_doc_ != null) {
|
---|
256 | MyDocument save = new MyDocument();
|
---|
257 | save.doc = current_doc_;
|
---|
258 | save.contents = current_contents_;
|
---|
259 | save.tagname = current_node_;
|
---|
260 | stack_.push(save);
|
---|
261 | }
|
---|
262 | current_doc_ = new Document();
|
---|
263 | current_contents_ = "";
|
---|
264 | current_node_ = "";
|
---|
265 | }
|
---|
266 |
|
---|
267 | protected void popOffStack()
|
---|
268 | {
|
---|
269 | if (!stack_.empty()) {
|
---|
270 | MyDocument saved = (MyDocument)stack_.pop();
|
---|
271 | current_doc_ = saved.doc;
|
---|
272 | current_contents_ = saved.contents;
|
---|
273 | current_node_ = saved.tagname;
|
---|
274 | } else {
|
---|
275 | current_doc_ = new Document();
|
---|
276 | current_contents_ = "";
|
---|
277 | current_node_ = "";
|
---|
278 | }
|
---|
279 | }
|
---|
280 |
|
---|
281 |
|
---|
282 | }
|
---|
283 |
|
---|
284 |
|
---|