1 | /**********************************************************************
|
---|
2 | *
|
---|
3 | * SolrQueryWrapper.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.gsdl3.util;
|
---|
27 |
|
---|
28 |
|
---|
29 | import java.io.*;
|
---|
30 | import java.util.*;
|
---|
31 | import java.util.regex.*;
|
---|
32 |
|
---|
33 | import org.apache.log4j.Logger;
|
---|
34 |
|
---|
35 | import org.apache.solr.client.solrj.SolrQuery;
|
---|
36 | import org.apache.solr.client.solrj.SolrServer;
|
---|
37 | import org.apache.solr.client.solrj.SolrServerException;
|
---|
38 | import org.apache.solr.client.solrj.response.FacetField;
|
---|
39 | import org.apache.solr.client.solrj.response.FacetField.Count;
|
---|
40 | import org.apache.solr.client.solrj.response.QueryResponse;
|
---|
41 |
|
---|
42 | import org.apache.solr.common.SolrDocument;
|
---|
43 | import org.apache.solr.common.SolrDocumentList;
|
---|
44 | import org.apache.solr.common.params.ModifiableSolrParams;
|
---|
45 | import org.apache.solr.common.params.SolrParams;
|
---|
46 |
|
---|
47 | import org.greenstone.LuceneWrapper.SharedSoleneQuery;
|
---|
48 | import org.greenstone.LuceneWrapper.SharedSoleneQueryResult;
|
---|
49 |
|
---|
50 |
|
---|
51 | public class SolrQueryWrapper extends SharedSoleneQuery
|
---|
52 | {
|
---|
53 |
|
---|
54 | static Logger logger = Logger.getLogger(org.greenstone.gsdl3.util.SolrQueryWrapper.class.getName());
|
---|
55 |
|
---|
56 | /*
|
---|
57 | // Use the standard set of English stop words by default
|
---|
58 | static private String[] stop_words = GS2Analyzer.STOP_WORDS;
|
---|
59 |
|
---|
60 | private String full_indexdir="";
|
---|
61 |
|
---|
62 | private String default_conjunction_operator = "OR";
|
---|
63 | private String fuzziness = null;
|
---|
64 | private String sort_field = null;
|
---|
65 | private Sort sorter=new Sort();
|
---|
66 | private String filter_string = null;
|
---|
67 | private Filter filter = null;
|
---|
68 |
|
---|
69 | private QueryParser query_parser = null;
|
---|
70 | private QueryParser query_parser_no_stop_words = null;
|
---|
71 | */
|
---|
72 |
|
---|
73 | protected int max_docs = 100;
|
---|
74 |
|
---|
75 | SolrServer solr_core = null;
|
---|
76 |
|
---|
77 |
|
---|
78 | public SolrQueryWrapper() {
|
---|
79 | super();
|
---|
80 | }
|
---|
81 | /*
|
---|
82 | // Create one query parser with the standard set of stop words, and one with none
|
---|
83 |
|
---|
84 | query_parser = new QueryParser(TEXTFIELD, new GS2Analyzer(stop_words));
|
---|
85 | query_parser_no_stop_words = new QueryParser(TEXTFIELD, new GS2Analyzer(new String[] { }));
|
---|
86 | }
|
---|
87 | */
|
---|
88 |
|
---|
89 | public void setMaxDocs(int max_docs)
|
---|
90 | {
|
---|
91 | this.max_docs = max_docs;
|
---|
92 | }
|
---|
93 |
|
---|
94 | public void setSolrCore(SolrServer solr_core)
|
---|
95 | {
|
---|
96 | this.solr_core = solr_core;
|
---|
97 | }
|
---|
98 |
|
---|
99 |
|
---|
100 | public boolean initialise() {
|
---|
101 |
|
---|
102 | if (solr_core==null) {
|
---|
103 | utf8out.println("Solr Core not loaded in ");
|
---|
104 | utf8out.flush();
|
---|
105 | return false;
|
---|
106 | }
|
---|
107 | return true;
|
---|
108 |
|
---|
109 | }
|
---|
110 |
|
---|
111 | public SharedSoleneQueryResult runQuery(String query_string) {
|
---|
112 |
|
---|
113 | if (query_string == null || query_string.equals("")) {
|
---|
114 | utf8out.println("The query word is not indicated ");
|
---|
115 | utf8out.flush();
|
---|
116 | return null;
|
---|
117 | }
|
---|
118 |
|
---|
119 | SolrQueryResult solr_query_result=new SolrQueryResult();
|
---|
120 | solr_query_result.clear();
|
---|
121 |
|
---|
122 | ModifiableSolrParams solrParams = new ModifiableSolrParams();
|
---|
123 | solrParams.set("q", query_string);
|
---|
124 | solrParams.set("start", start_results);
|
---|
125 | solrParams.set("rows", (end_results - start_results) +1);
|
---|
126 | solrParams.set("fl","docOID score");
|
---|
127 |
|
---|
128 | /*
|
---|
129 | try {
|
---|
130 | Query query_including_stop_words = query_parser_no_stop_words.parse(query_string);
|
---|
131 | query_including_stop_words = query_including_stop_words.rewrite(reader);
|
---|
132 |
|
---|
133 | // System.err.println("********* query_string " + query_string + "****");
|
---|
134 |
|
---|
135 | Query query = parseQuery(reader, query_parser, query_string, fuzziness);
|
---|
136 | query = query.rewrite(reader);
|
---|
137 |
|
---|
138 | // Get the list of expanded query terms and their frequencies
|
---|
139 | // num docs matching, and total frequency
|
---|
140 | HashSet terms = new HashSet();
|
---|
141 | query.extractTerms(terms);
|
---|
142 |
|
---|
143 | HashMap doc_term_freq_map = new HashMap();
|
---|
144 |
|
---|
145 | Iterator iter = terms.iterator();
|
---|
146 | while (iter.hasNext()) {
|
---|
147 |
|
---|
148 | Term term = (Term) iter.next();
|
---|
149 |
|
---|
150 | // Get the term frequency over all the documents
|
---|
151 | TermDocs term_docs = reader.termDocs(term);
|
---|
152 | int term_freq = 0;
|
---|
153 | int match_docs = 0;
|
---|
154 | while (term_docs.next())
|
---|
155 | {
|
---|
156 | if (term_docs.freq() != 0)
|
---|
157 | {
|
---|
158 | term_freq += term_docs.freq();
|
---|
159 | match_docs++;
|
---|
160 |
|
---|
161 | // Calculate the document-level term frequency as well
|
---|
162 | Integer lucene_doc_num_obj = new Integer(term_docs.doc());
|
---|
163 | int doc_term_freq = 0;
|
---|
164 | if (doc_term_freq_map.containsKey(lucene_doc_num_obj))
|
---|
165 | {
|
---|
166 | doc_term_freq = ((Integer) doc_term_freq_map.get(lucene_doc_num_obj)).intValue();
|
---|
167 | }
|
---|
168 | doc_term_freq += term_docs.freq();
|
---|
169 |
|
---|
170 | doc_term_freq_map.put(lucene_doc_num_obj, new Integer(doc_term_freq));
|
---|
171 | }
|
---|
172 | }
|
---|
173 |
|
---|
174 | // Create a term
|
---|
175 | lucene_query_result.addTerm(term.text(), term.field(), match_docs, term_freq);
|
---|
176 | }
|
---|
177 |
|
---|
178 | // Get the list of stop words removed from the query
|
---|
179 | HashSet terms_including_stop_words = new HashSet();
|
---|
180 | query_including_stop_words.extractTerms(terms_including_stop_words);
|
---|
181 | Iterator terms_including_stop_words_iter = terms_including_stop_words.iterator();
|
---|
182 | while (terms_including_stop_words_iter.hasNext()) {
|
---|
183 | Term term = (Term) terms_including_stop_words_iter.next();
|
---|
184 | if (!terms.contains(term)) {
|
---|
185 | lucene_query_result.addStopWord(term.text());
|
---|
186 | }
|
---|
187 | }
|
---|
188 |
|
---|
189 | */
|
---|
190 |
|
---|
191 | try {
|
---|
192 | QueryResponse solrResponse = solr_core.query(solrParams);
|
---|
193 |
|
---|
194 | SolrDocumentList hits = solrResponse.getResults();
|
---|
195 |
|
---|
196 | if (hits != null) {
|
---|
197 |
|
---|
198 | logger.info("*** hits size = " + hits.size());
|
---|
199 | logger.info("*** num docs found = " + hits.getNumFound());
|
---|
200 |
|
---|
201 | logger.info("*** start results = " + start_results);
|
---|
202 | logger.info("*** end results = " + end_results);
|
---|
203 | logger.info("*** max docs = " + max_docs);
|
---|
204 |
|
---|
205 | // numDocsFound is the total number of mactching docs in the collection
|
---|
206 | // as opposed to the number of documents returned in the hits list
|
---|
207 |
|
---|
208 | solr_query_result.setTotalDocs((int)hits.getNumFound());
|
---|
209 |
|
---|
210 | solr_query_result.setStartResults(start_results);
|
---|
211 | solr_query_result.setEndResults(start_results + hits.size());
|
---|
212 |
|
---|
213 | // Output the matching documents
|
---|
214 | for (int i = 0; i < hits.size(); i++) {
|
---|
215 | SolrDocument doc = hits.get(i);
|
---|
216 |
|
---|
217 | // Need to think about how to support document term frequency. Make zero for now
|
---|
218 | int doc_term_freq = 0;
|
---|
219 | String docOID = (String)doc.get("docOID");
|
---|
220 | Float score = (Float)doc.get("score");
|
---|
221 |
|
---|
222 | logger.info("**** docOID = " + docOID);
|
---|
223 | logger.info("**** score = " + score);
|
---|
224 |
|
---|
225 | solr_query_result.addDoc(docOID, score.floatValue(), doc_term_freq);
|
---|
226 | }
|
---|
227 | }
|
---|
228 | else {
|
---|
229 | solr_query_result.setTotalDocs(0);
|
---|
230 |
|
---|
231 | solr_query_result.setStartResults(0);
|
---|
232 | solr_query_result.setEndResults(0);
|
---|
233 | }
|
---|
234 | }
|
---|
235 |
|
---|
236 | catch (SolrServerException server_exception) {
|
---|
237 | solr_query_result.setError(SolrQueryResult.SERVER_ERROR);
|
---|
238 | }
|
---|
239 |
|
---|
240 |
|
---|
241 | /*
|
---|
242 |
|
---|
243 | // do the query
|
---|
244 | // Simple case for getting all the matching documents
|
---|
245 | if (end_results == Integer.MAX_VALUE) {
|
---|
246 | // Perform the query (filter and sorter may be null)
|
---|
247 | Hits hits = searcher.search(query, filter, sorter);
|
---|
248 | lucene_query_result.setTotalDocs(hits.length());
|
---|
249 |
|
---|
250 | // Output the matching documents
|
---|
251 | lucene_query_result.setStartResults(start_results);
|
---|
252 | lucene_query_result.setEndResults(hits.length());
|
---|
253 |
|
---|
254 | for (int i = start_results; i <= hits.length(); i++) {
|
---|
255 | int lucene_doc_num = hits.id(i - 1);
|
---|
256 | Document doc = hits.doc(i - 1);
|
---|
257 | int doc_term_freq = 0;
|
---|
258 | Integer doc_term_freq_object = (Integer) doc_term_freq_map.get(new Integer(lucene_doc_num));
|
---|
259 | if (doc_term_freq_object != null)
|
---|
260 | {
|
---|
261 | doc_term_freq = doc_term_freq_object.intValue();
|
---|
262 | }
|
---|
263 | lucene_query_result.addDoc(doc.get("docOID").trim(), hits.score(i-1), doc_term_freq);
|
---|
264 | }
|
---|
265 | }
|
---|
266 |
|
---|
267 | // Slightly more complicated case for returning a subset of the matching documents
|
---|
268 | else {
|
---|
269 | // Perform the query (filter may be null)
|
---|
270 | TopFieldDocs hits = searcher.search(query, filter, end_results, sorter);
|
---|
271 | lucene_query_result.setTotalDocs(hits.totalHits);
|
---|
272 |
|
---|
273 | lucene_query_result.setStartResults(start_results);
|
---|
274 | lucene_query_result.setEndResults(end_results < hits.scoreDocs.length ? end_results: hits.scoreDocs.length);
|
---|
275 |
|
---|
276 | // Output the matching documents
|
---|
277 | for (int i = start_results; (i <= hits.scoreDocs.length && i <= end_results); i++) {
|
---|
278 | int lucene_doc_num = hits.scoreDocs[i - 1].doc;
|
---|
279 | Document doc = reader.document(lucene_doc_num);
|
---|
280 | int doc_term_freq = 0;
|
---|
281 | Integer doc_term_freq_object = (Integer) doc_term_freq_map.get(new Integer(lucene_doc_num));
|
---|
282 | if (doc_term_freq_object != null)
|
---|
283 | {
|
---|
284 | doc_term_freq = doc_term_freq_object.intValue();
|
---|
285 | }
|
---|
286 | lucene_query_result.addDoc(doc.get("docOID").trim(), hits.scoreDocs[i-1].score, doc_term_freq);
|
---|
287 | }
|
---|
288 | }
|
---|
289 | */
|
---|
290 |
|
---|
291 | return solr_query_result;
|
---|
292 | }
|
---|
293 | /*
|
---|
294 |
|
---|
295 | catch (ParseException parse_exception) {
|
---|
296 | lucene_query_result.setError(LuceneQueryResult.PARSE_ERROR);
|
---|
297 | }
|
---|
298 | catch (TooManyClauses too_many_clauses_exception) {
|
---|
299 | lucene_query_result.setError(LuceneQueryResult.TOO_MANY_CLAUSES_ERROR);
|
---|
300 | }
|
---|
301 | catch (IOException exception) {
|
---|
302 | lucene_query_result.setError(LuceneQueryResult.IO_ERROR);
|
---|
303 | exception.printStackTrace();
|
---|
304 | }
|
---|
305 | catch (Exception exception) {
|
---|
306 | lucene_query_result.setError(LuceneQueryResult.OTHER_ERROR);
|
---|
307 | exception.printStackTrace();
|
---|
308 | }
|
---|
309 | return lucene_query_result;
|
---|
310 | }
|
---|
311 |
|
---|
312 | public void setDefaultConjunctionOperator(String default_conjunction_operator) {
|
---|
313 | this.default_conjunction_operator = default_conjunction_operator.toUpperCase();
|
---|
314 | if (default_conjunction_operator.equals("AND")) {
|
---|
315 | query_parser.setDefaultOperator(query_parser.AND_OPERATOR);
|
---|
316 | query_parser_no_stop_words.setDefaultOperator(query_parser.AND_OPERATOR);
|
---|
317 | } else { // default is OR
|
---|
318 | query_parser.setDefaultOperator(query_parser.OR_OPERATOR);
|
---|
319 | query_parser_no_stop_words.setDefaultOperator(query_parser.OR_OPERATOR);
|
---|
320 | }
|
---|
321 |
|
---|
322 |
|
---|
323 | }
|
---|
324 | */
|
---|
325 |
|
---|
326 | public void cleanUp() {
|
---|
327 | super.cleanUp();
|
---|
328 | }
|
---|
329 |
|
---|
330 | }
|
---|
331 |
|
---|
332 |
|
---|