[13556] | 1 | /**********************************************************************
|
---|
| 2 | *
|
---|
| 3 | * LuceneQueryResult.java
|
---|
| 4 | *
|
---|
| 5 | * Copyright 2007 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 |
|
---|
[13686] | 27 | package org.greenstone.LuceneWrapper;
|
---|
[13556] | 28 |
|
---|
| 29 | import java.util.Vector;
|
---|
| 30 |
|
---|
| 31 | /** a QueryResult class for a lucene search
|
---|
| 32 | *
|
---|
| 33 | */
|
---|
| 34 | public class LuceneQueryResult {
|
---|
| 35 |
|
---|
| 36 | public static final int NO_ERROR = 0;
|
---|
| 37 | public static final int PARSE_ERROR = 1;
|
---|
| 38 | public static final int TOO_MANY_CLAUSES_ERROR = 2;
|
---|
| 39 | public static final int IO_ERROR = 3;
|
---|
[13569] | 40 | public static final int OTHER_ERROR = 4;
|
---|
| 41 |
|
---|
[13556] | 42 | /** the list of DocInfo */
|
---|
| 43 | protected Vector docs_=null;
|
---|
| 44 | /** the list of TermInfo */
|
---|
| 45 | protected Vector terms_=null;
|
---|
| 46 | /** the list of stopwords found in the query */
|
---|
| 47 | protected Vector stopwords_ = null;
|
---|
| 48 | /** the total number of docs found - not necessarily the size of docs_*/
|
---|
| 49 | protected int total_num_docs_=0;
|
---|
| 50 | /** the start result number if we are retrieving only a portion of the results */
|
---|
| 51 | protected int start_results_ = 0;
|
---|
| 52 | /** the end result number if we are retrieving only a portion of the results */
|
---|
| 53 | protected int end_results_ = 0;
|
---|
| 54 | /** whether an error has occurred and what kind it is*/
|
---|
| 55 | protected int error_ = NO_ERROR;
|
---|
| 56 |
|
---|
| 57 | LuceneQueryResult() {
|
---|
| 58 | docs_ = new Vector();
|
---|
| 59 | terms_ = new Vector();
|
---|
| 60 | stopwords_ = new Vector();
|
---|
| 61 | }
|
---|
| 62 |
|
---|
| 63 | /** clear the info from the last query - should be called before setting any new docs/terms */
|
---|
| 64 | public void clear() {
|
---|
| 65 | total_num_docs_=0;
|
---|
| 66 | docs_.clear();
|
---|
| 67 | terms_.clear();
|
---|
| 68 | stopwords_.clear();
|
---|
| 69 | error_ = NO_ERROR;
|
---|
| 70 | }
|
---|
| 71 |
|
---|
| 72 | /** returns the result as a String - useful for printing out results */
|
---|
| 73 | public String toString() {
|
---|
| 74 |
|
---|
| 75 | String result = "";
|
---|
| 76 | result += "docs (ranks): ";
|
---|
| 77 | for (int i=0; i<docs_.size(); i++) {
|
---|
| 78 | result += ((DocInfo)docs_.elementAt(i)).toString()+", ";
|
---|
| 79 | }
|
---|
| 80 | result += "\nterms: ";
|
---|
| 81 | for (int i=0; i<terms_.size(); i++) {
|
---|
| 82 | result += ((TermInfo)terms_.elementAt(i)).toString()+", ";
|
---|
| 83 | }
|
---|
| 84 | result += "\nactual number of docs found = "+total_num_docs_;
|
---|
| 85 |
|
---|
| 86 | return result;
|
---|
| 87 | }
|
---|
| 88 | /** a shorter representation - just terms and total docs - not the
|
---|
| 89 | individual docnums and ranks */
|
---|
| 90 | public String toShortString() {
|
---|
| 91 | String result = "";
|
---|
| 92 | result += "\nterms: ";
|
---|
| 93 | for (int i=0; i<terms_.size(); i++) {
|
---|
| 94 | result += ((TermInfo)terms_.elementAt(i)).toString()+", ";
|
---|
| 95 | }
|
---|
| 96 | result += "\nactual number of docs found = "+total_num_docs_;
|
---|
| 97 | return result;
|
---|
| 98 | }
|
---|
| 99 |
|
---|
| 100 | public void setTotalDocs(int num) {
|
---|
| 101 | total_num_docs_=num;
|
---|
| 102 | }
|
---|
| 103 |
|
---|
| 104 | public void setStartResults(int start) {
|
---|
| 105 | start_results_ = start;
|
---|
| 106 | }
|
---|
| 107 |
|
---|
| 108 | public void setEndResults(int end) {
|
---|
| 109 | end_results_ = end;
|
---|
| 110 | }
|
---|
| 111 |
|
---|
[16443] | 112 | public void addDoc(String id, float rank)
|
---|
| 113 | {
|
---|
| 114 | docs_.add(new DocInfo(id, rank));
|
---|
[13556] | 115 | }
|
---|
| 116 |
|
---|
| 117 | public void addTerm(String term, String field, int match, int freq) {
|
---|
| 118 | TermInfo ti = new TermInfo();
|
---|
| 119 | ti.term_=term;
|
---|
| 120 | ti.field_=field;
|
---|
| 121 | ti.match_docs_=match;
|
---|
| 122 | ti.term_freq_=freq;
|
---|
| 123 | terms_.add(ti);
|
---|
| 124 | }
|
---|
| 125 | public void addStopWord(String stopword) {
|
---|
| 126 | stopwords_.add(stopword);
|
---|
| 127 | }
|
---|
| 128 | public Vector getDocs() {
|
---|
| 129 | return docs_;
|
---|
| 130 | }
|
---|
| 131 |
|
---|
| 132 | public int getError() {
|
---|
| 133 | return error_;
|
---|
| 134 | }
|
---|
| 135 |
|
---|
| 136 | public String getErrorString() {
|
---|
| 137 | if (error_ == PARSE_ERROR) {
|
---|
| 138 | return "PARSE_EXCEPTION";
|
---|
| 139 | }
|
---|
| 140 | if (error_ == TOO_MANY_CLAUSES_ERROR) {
|
---|
| 141 | return "TOO_MANY_CLAUSES";
|
---|
| 142 | }
|
---|
| 143 | if (error_ == IO_ERROR) {
|
---|
| 144 | return "IO_ERROR";
|
---|
| 145 | }
|
---|
| 146 | if (error_ == NO_ERROR) {
|
---|
| 147 | return "NO_ERROR";
|
---|
| 148 | }
|
---|
| 149 | return "UNKNOWN";
|
---|
| 150 | }
|
---|
| 151 |
|
---|
| 152 | public Vector getTerms() {
|
---|
| 153 | return terms_;
|
---|
| 154 | }
|
---|
| 155 |
|
---|
| 156 | public Vector getStopWords() {
|
---|
| 157 | return stopwords_;
|
---|
| 158 | }
|
---|
| 159 | public int getTotalDocs() {
|
---|
| 160 | return total_num_docs_;
|
---|
| 161 | }
|
---|
| 162 |
|
---|
| 163 | public void setError(int error) {
|
---|
| 164 | error_ = error;
|
---|
| 165 | }
|
---|
| 166 |
|
---|
| 167 | public String getXMLString() {
|
---|
| 168 | StringBuffer buffer = new StringBuffer();
|
---|
| 169 |
|
---|
| 170 | // terms
|
---|
| 171 | buffer.append("<QueryTermsInfo num=\"" + terms_.size() + "\"/>\n");
|
---|
| 172 | for (int i=0; i<terms_.size(); i++) {
|
---|
| 173 | buffer.append(((TermInfo)terms_.elementAt(i)).toXMLString()+"\n");
|
---|
| 174 | }
|
---|
| 175 |
|
---|
| 176 | // stopwords
|
---|
| 177 | for (int i=0; i<stopwords_.size(); i++) {
|
---|
| 178 | buffer.append("<StopWord value=\"" + (String)stopwords_.elementAt(i)+"\" />\n");
|
---|
| 179 | }
|
---|
| 180 |
|
---|
| 181 | // results
|
---|
| 182 | buffer.append("<MatchingDocsInfo num=\"" + total_num_docs_ + "\"/>\n");
|
---|
| 183 | buffer.append("<StartResults num=\"" + start_results_ + "\"/>\n");
|
---|
| 184 | buffer.append("<EndResults num=\"" + end_results_ + "\"/>\n");
|
---|
| 185 |
|
---|
| 186 | for (int i=0; i< docs_.size(); i++) {
|
---|
| 187 | buffer.append(((DocInfo)docs_.elementAt(i)).toXMLString()+"\n");
|
---|
| 188 | }
|
---|
| 189 |
|
---|
| 190 | return buffer.toString();
|
---|
| 191 | }
|
---|
| 192 |
|
---|
| 193 |
|
---|
| 194 | public class TermInfo {
|
---|
| 195 |
|
---|
| 196 | /** the term itself */
|
---|
| 197 | public String term_=null;
|
---|
| 198 | /** the field for which this term was queried */
|
---|
| 199 | public String field_=null;
|
---|
| 200 | /** the number of documents containing this term */
|
---|
| 201 | public int match_docs_=0;
|
---|
| 202 | /** overall term freq for this term */
|
---|
| 203 | public int term_freq_=0;
|
---|
| 204 |
|
---|
| 205 | public TermInfo() {
|
---|
| 206 | }
|
---|
| 207 |
|
---|
| 208 | /** output the class as a string */
|
---|
| 209 | public String toString() {
|
---|
| 210 | String result="";
|
---|
| 211 | result +="<"+field_+">\""+term_+" docs("+match_docs_;
|
---|
| 212 | result +=")freq("+term_freq_+")";
|
---|
| 213 | return result;
|
---|
| 214 | }
|
---|
| 215 |
|
---|
| 216 | /** output as an XML element */
|
---|
| 217 | public String toXMLString() {
|
---|
| 218 | return "<Term value=\"" + xmlSafe(term_) + "\" field=\"" + field_ + "\" freq=\"" + term_freq_ + "\" />";
|
---|
| 219 | }
|
---|
| 220 | }
|
---|
| 221 |
|
---|
[16443] | 222 |
|
---|
| 223 | public class DocInfo
|
---|
| 224 | {
|
---|
| 225 | public String id_ = "";
|
---|
| 226 | public float rank_ = 0;
|
---|
| 227 |
|
---|
| 228 | public DocInfo (String id, float rank)
|
---|
| 229 | {
|
---|
| 230 | id_ = id;
|
---|
| 231 | rank_ = rank;
|
---|
[13556] | 232 | }
|
---|
[16443] | 233 |
|
---|
| 234 | public String toString()
|
---|
| 235 | {
|
---|
| 236 | return "" + id_ + " (" + rank_ + ")";
|
---|
[13556] | 237 | }
|
---|
[16443] | 238 |
|
---|
| 239 | public String toXMLString()
|
---|
| 240 | {
|
---|
| 241 | return "<Match id=\"" + id_ + "\" rank=\"" + rank_ + "\" />";
|
---|
[13556] | 242 | }
|
---|
| 243 | }
|
---|
| 244 |
|
---|
[16443] | 245 |
|
---|
[13556] | 246 | // where should this go???
|
---|
| 247 | public static String xmlSafe(String text) {
|
---|
| 248 | text = text.replaceAll("&","&amp;");
|
---|
| 249 | text = text.replaceAll("<","&lt;");
|
---|
| 250 | text = text.replaceAll(">","&gt;");
|
---|
| 251 | text = text.replaceAll("'","&#039;");
|
---|
| 252 | text = text.replaceAll("\\\"","&quot;");
|
---|
| 253 | return text;
|
---|
| 254 | }
|
---|
| 255 |
|
---|
| 256 | }
|
---|