xapian-core/weight/weight.cc

   1 /** @file
   2  * @brief Xapian::Weight base class
   3  */
   4 /* Copyright (C) 2007,2008,2009,2014,2017,2019 Olly Betts
   5  * Copyright (C) 2009 Lemur Consulting Ltd
   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 "xapian/weight.h"
  25
  26 #include "api/leafpostlist.h"
  27 #include "weightinternal.h"
  28
  29 #include "omassert.h"
  30 #include "debuglog.h"
  31
  32 #include "xapian/error.h"
  33
  34 using namespace std;
  35
  36 namespace Xapian {
  37
  38 void
  39 Weight::init_(const Internal & stats, Xapian::termcount query_length)
  40 {
  41     LOGCALL_VOID(MATCH, "Weight::init_", stats | query_length);
  42     collection_size_ = stats.collection_size;
  43     rset_size_ = stats.rset_size;
  44     if (stats_needed & AVERAGE_LENGTH)
  45         average_length_ = stats.get_average_length();
  46     if (stats_needed & DOC_LENGTH_MAX)
  47         doclength_upper_bound_ = stats.db.get_doclength_upper_bound();
  48     if (stats_needed & DOC_LENGTH_MIN)
  49         doclength_lower_bound_ = stats.db.get_doclength_lower_bound();
  50     collectionfreq_ = 0;
  51     wdf_upper_bound_ = 0;
  52     termfreq_ = 0;
  53     reltermfreq_ = 0;
  54     query_length_ = query_length;
  55     wqf_ = 1;
  56     init(0.0);
  57 }
  58
  59 void
  60 Weight::init_(const Internal & stats, Xapian::termcount query_length,
  61               const string & term, Xapian::termcount wqf, double factor,
  62               void* postlist_void)
  63 {
  64     LOGCALL_VOID(MATCH, "Weight::init_", stats | query_length | term | wqf | factor | postlist_void);
  65     collection_size_ = stats.collection_size;
  66     rset_size_ = stats.rset_size;
  67     if (stats_needed & AVERAGE_LENGTH)
  68         average_length_ = stats.get_average_length();
  69     if (stats_needed & DOC_LENGTH_MAX)
  70         doclength_upper_bound_ = stats.db.get_doclength_upper_bound();
  71     if (stats_needed & DOC_LENGTH_MIN)
  72         doclength_lower_bound_ = stats.db.get_doclength_lower_bound();
  73     if (stats_needed & WDF_MAX) {
  74         if (usual(postlist_void != nullptr)) {
  75             auto postlist = static_cast<LeafPostList*>(postlist_void);
  76             wdf_upper_bound_ = postlist->get_wdf_upper_bound();
  77         } else {
  78             wdf_upper_bound_ = stats.db.get_wdf_upper_bound(term);
  79         }
  80     }
  81     if (stats_needed & (TERMFREQ | RELTERMFREQ | COLLECTION_FREQ)) {
  82         bool ok = stats.get_stats(term,
  83                                   termfreq_, reltermfreq_, collectionfreq_);
  84         (void)ok;
  85         Assert(ok);
  86     }
  87     query_length_ = query_length;
  88     wqf_ = wqf;
  89     init(factor);
  90 }
  91
  92 void
  93 Weight::init_(const Internal & stats, Xapian::termcount query_length,
  94               const string & term, Xapian::termcount wqf, double factor)
  95 {
  96     init_(stats, query_length, term, wqf, factor, nullptr);
  97 }
  98
  99 void
 100 Weight::init_(const Internal & stats, Xapian::termcount query_length,
 101               double factor, Xapian::doccount termfreq,
 102               Xapian::doccount reltermfreq, Xapian::termcount collection_freq)
 103 {
 104     LOGCALL_VOID(MATCH, "Weight::init_", stats | query_length | factor | termfreq | reltermfreq | collection_freq);
 105     // Synonym case.
 106     collection_size_ = stats.collection_size;
 107     rset_size_ = stats.rset_size;
 108     if (stats_needed & AVERAGE_LENGTH)
 109         average_length_ = stats.get_average_length();
 110     if (stats_needed & (DOC_LENGTH_MAX | WDF_MAX)) {
 111         doclength_upper_bound_ = stats.db.get_doclength_upper_bound();
 112         // The doclength is an upper bound on the wdf.  This is obviously true
 113         // for normal terms, but SynonymPostList ensures that it is also true
 114         // for synonym terms by clamping the wdf values returned to the
 115         // doclength.
 116         //
 117         // (This clamping is only actually necessary in cases where a constituent
 118         // term of the synonym is repeated.)
 119         wdf_upper_bound_ = doclength_upper_bound_;
 120     }
 121     if (stats_needed & DOC_LENGTH_MIN)
 122         doclength_lower_bound_ = stats.db.get_doclength_lower_bound();
 123
 124     termfreq_ = termfreq;
 125     reltermfreq_ = reltermfreq;
 126     query_length_ = query_length;
 127     collectionfreq_ = collection_freq;
 128     wqf_ = 1;
 129     init(factor);
 130 }
 131
 132 Weight::~Weight() { }
 133
 134 string
 135 Weight::name() const
 136 {
 137     return string();
 138 }
 139
 140 string
 141 Weight::serialise() const
 142 {
 143     throw Xapian::UnimplementedError("serialise() not supported for this Xapian::Weight subclass");
 144 }
 145
 146 Weight *
 147 Weight::unserialise(const string &) const
 148 {
 149     throw Xapian::UnimplementedError("unserialise() not supported for this Xapian::Weight subclass");
 150 }
 151
 152 }