xapian-core/examples/simpleexpand.cc

   1 /** @file
   2  * @brief Simple example program demonstrating query expansion.
   3  */
   4 /* Copyright (C) 2007,2010,2015 Olly Betts
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License
  17  * along with this program; if not, write to the Free Software
  18  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA
  19  */
  20
  21 #ifdef HAVE_CONFIG_H
  22 # include <config.h>
  23 #endif
  24
  25 #include <xapian.h>
  26
  27 #include <iostream>
  28 #include <string>
  29
  30 #include <cstdlib> // For exit().
  31 #include <cstring>
  32
  33 using namespace std;
  34
  35 int
  36 main(int argc, char **argv)
  37 try {
  38     // We require at least two command line arguments.
  39     if (argc < 3) {
  40         int rc = 1;
  41         if (argv[1]) {
  42             if (strcmp(argv[1], "--version") == 0) {
  43                 cout << "simpleexpand" << endl;
  44                 exit(0);
  45             }
  46             if (strcmp(argv[1], "--help") == 0) {
  47                 rc = 0;
  48             }
  49         }
  50         cout << "Usage: " << argv[0] << " PATH_TO_DATABASE QUERY [-- [DOCID...]]" << endl;
  51         exit(rc);
  52     }
  53
  54     // Open the database for searching.
  55     Xapian::Database db(argv[1]);
  56
  57     // Start an enquire session.
  58     Xapian::Enquire enquire(db);
  59
  60     // Combine command line arguments up to "--" with spaces between
  61     // them, so that simple queries don't have to be quoted at the shell
  62     // level.
  63     string query_string(argv[2]);
  64     argv += 3;
  65     while (*argv && strcmp(*argv, "--") != 0) {
  66         query_string += ' ';
  67         query_string += *argv++;
  68     }
  69
  70     // Create an RSet with the listed docids in.
  71     Xapian::RSet rset;
  72     if (*argv) {
  73         while (*++argv) {
  74             rset.add_document(atoi(*argv));
  75         }
  76     }
  77
  78     // Parse the query string to produce a Xapian::Query object.
  79     Xapian::QueryParser qp;
  80     Xapian::Stem stemmer("english");
  81     qp.set_stemmer(stemmer);
  82     qp.set_database(db);
  83     qp.set_stemming_strategy(Xapian::QueryParser::STEM_SOME);
  84     Xapian::Query query = qp.parse_query(query_string);
  85     cout << "Parsed query is: " << query.get_description() << endl;
  86
  87     // Find the top 10 results for the query.
  88     enquire.set_query(query);
  89     Xapian::MSet matches = enquire.get_mset(0, 10, &rset);
  90
  91     // Display the results.
  92     cout << matches.get_matches_estimated() << " results found:" << endl;
  93
  94     for (Xapian::MSetIterator i = matches.begin(); i != matches.end(); ++i) {
  95         cout << i.get_rank() + 1 << ": " << i.get_weight() << " docid=" << *i
  96              << " [" << i.get_document().get_data() << "]\n\n";
  97     }
  98
  99     // If no relevant docids were given, invent an RSet containing the top 5
 100     // matches (or all the matches if there are less than 5).
 101     if (rset.empty()) {
 102         int c = 5;
 103         Xapian::MSetIterator i = matches.begin();
 104         while (c-- && i != matches.end()) {
 105             rset.add_document(*i);
 106             ++i;
 107         }
 108     }
 109
 110     // Generate an ESet containing terms that the user might want to add to
 111     // the query.
 112     Xapian::ESet eset = enquire.get_eset(10, rset);
 113
 114     // List the terms.
 115     Xapian::ESetIterator t;
 116     for (t = eset.begin(); t != eset.end(); ++t) {
 117         cout << *t << ": weight = " << t.get_weight() << endl;
 118     }
 119 } catch (const Xapian::Error &e) {
 120     cout << e.get_description() << endl;
 121     exit(1);
 122 }