xapian-core/weight/weightinternal.cc

   1 /** @file weightinternal.cc
   2  * @brief Xapian::Weight::Internal class, holding database and term statistics.
   3  */
   4 /* Copyright (C) 2007 Lemur Consulting Ltd
   5  * Copyright (C) 2009,2010,2011,2012,2013,2014,2015,2017 Olly Betts
   6  *
   7  * This program is free software; you can redistribute it and/or
   8  * modify it under the terms of the GNU General Public License as
   9  * published by the Free Software Foundation; either version 2 of the
  10  * License, or (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with this program; if not, write to the Free Software
  19  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
  20  */
  21
  22 #include <config.h>
  23
  24 #include "weightinternal.h"
  25
  26 #include "xapian/enquire.h"
  27
  28 #include "omassert.h"
  29 #include "api/rsetinternal.h"
  30 #include "str.h"
  31 #include "api/termlist.h"
  32
  33 #include <memory>
  34 #include <set>
  35
  36 using namespace std;
  37
  38 string
  39 TermFreqs::get_description() const {
  40     string desc("TermFreqs(termfreq=");
  41     desc += str(termfreq);
  42     desc += ", reltermfreq=";
  43     desc += str(reltermfreq);
  44     desc += ", collfreq=";
  45     desc += str(collfreq);
  46     desc += ", max_part=";
  47     desc += str(max_part);
  48     desc += ")";
  49     return desc;
  50 }
  51
  52 namespace Xapian {
  53
  54 Weight::Internal &
  55 Weight::Internal::operator+=(const Weight::Internal & inc)
  56 {
  57 #ifdef XAPIAN_ASSERTIONS
  58     Assert(!finalised);
  59     subdbs += inc.subdbs;
  60 #endif
  61     total_length += inc.total_length;
  62     collection_size += inc.collection_size;
  63     rset_size += inc.rset_size;
  64     total_term_count += inc.total_term_count;
  65
  66     // Add termfreqs and reltermfreqs
  67     map<string, TermFreqs>::const_iterator i;
  68     for (i = inc.termfreqs.begin(); i != inc.termfreqs.end(); ++i) {
  69         termfreqs[i->first] += i->second;
  70     }
  71     return *this;
  72 }
  73
  74 void
  75 Weight::Internal::accumulate_stats(const Xapian::Database::Internal &subdb,
  76                                    const Xapian::RSet &rset)
  77 {
  78 #ifdef XAPIAN_ASSERTIONS
  79     Assert(!finalised);
  80     ++subdbs;
  81 #endif
  82     total_length += subdb.get_total_length();
  83     collection_size += subdb.get_doccount();
  84     rset_size += rset.size();
  85
  86     total_term_count += subdb.get_doccount() * subdb.get_total_length();
  87     Xapian::TermIterator t;
  88     for (t = query.get_unique_terms_begin(); t != Xapian::TermIterator(); ++t) {
  89         const string & term = *t;
  90
  91         Xapian::doccount sub_tf;
  92         Xapian::termcount sub_cf;
  93         subdb.get_freqs(term, &sub_tf, &sub_cf);
  94         TermFreqs & tf = termfreqs[term];
  95         tf.termfreq += sub_tf;
  96         tf.collfreq += sub_cf;
  97     }
  98
  99     if (!rset.internal.get())
 100         return;
 101
 102     for (Xapian::docid did : rset.internal->docs) {
 103         Assert(did);
 104         // The query is likely to contain far fewer terms than the documents,
 105         // and we can skip the document's termlist, so look for each query term
 106         // in the document.
 107         unique_ptr<TermList> tl(subdb.open_term_list(did));
 108         map<string, TermFreqs>::iterator i;
 109         for (i = termfreqs.begin(); i != termfreqs.end(); ++i) {
 110             const string & term = i->first;
 111             TermList * ret = tl->skip_to(term);
 112             Assert(ret == NULL);
 113             (void)ret;
 114             if (tl->at_end())
 115                 break;
 116             if (term == tl->get_termname())
 117                 ++i->second.reltermfreq;
 118         }
 119     }
 120 }
 121
 122 string
 123 Weight::Internal::get_description() const
 124 {
 125     string desc = "Weight::Internal(totlen=";
 126     desc += str(total_length);
 127     desc += ", collection_size=";
 128     desc += str(collection_size);
 129     desc += ", rset_size=";
 130     desc += str(rset_size);
 131     desc += ", total_term_count=";
 132     desc += str(total_term_count);
 133 #ifdef XAPIAN_ASSERTIONS
 134     desc += ", subdbs=";
 135     desc += str(subdbs);
 136     desc += ", finalised=";
 137     desc += str(finalised);
 138 #endif
 139     desc += ", termfreqs={";
 140     map<string, TermFreqs>::const_iterator i;
 141     for (i = termfreqs.begin(); i != termfreqs.end(); ++i) {
 142         if (i != termfreqs.begin())
 143             desc += ", ";
 144         desc += i->first;
 145         desc += " => ";
 146         desc += i->second.get_description();
 147     }
 148     desc += "})";
 149     return desc;
 150 }
 151
 152 }