xapian-core/weight/tradweight.cc

   1 /** @file
   2  * @brief Xapian::TradWeight class - the "traditional" probabilistic formula
   3  */
   4 /* Copyright (C) 2009,2010,2011,2012,2014,2015,2017,2024 Olly Betts
   5  *
   6  * This program is free software; you can redistribute it and/or
   7  * modify it under the terms of the GNU General Public License as
   8  * published by the Free Software Foundation; either version 2 of the
   9  * License, or (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 #include <config.h>
  22
  23 #include "xapian/weight.h"
  24 #include "weightinternal.h"
  25
  26 #include "debuglog.h"
  27 #include "omassert.h"
  28 #include "serialise-double.h"
  29
  30 #include "xapian/error.h"
  31
  32 #include <algorithm>
  33 #include <cmath>
  34
  35 using namespace std;
  36
  37 namespace Xapian {
  38
  39 TradWeight *
  40 TradWeight::clone() const
  41 {
  42     return new TradWeight(param_k);
  43 }
  44
  45 void
  46 TradWeight::init(double factor)
  47 {
  48     if (factor == 0.0) {
  49         // This object is for the term-independent contribution, and that's
  50         // always zero for this scheme.
  51         return;
  52     }
  53
  54     Xapian::doccount tf = get_termfreq();
  55
  56     double tw = 0;
  57     if (get_rset_size() != 0) {
  58         Xapian::doccount reltermfreq = get_reltermfreq();
  59
  60         // There can't be more relevant documents indexed by a term than there
  61         // are documents indexed by that term.
  62         AssertRel(reltermfreq,<=,tf);
  63
  64         // There can't be more relevant documents indexed by a term than there
  65         // are relevant documents.
  66         AssertRel(reltermfreq,<=,get_rset_size());
  67
  68         Xapian::doccount reldocs_not_indexed = get_rset_size() - reltermfreq;
  69
  70         // There can't be more relevant documents not indexed by a term than
  71         // there are documents not indexed by that term.
  72         AssertRel(reldocs_not_indexed,<=,get_collection_size() - tf);
  73
  74         Xapian::doccount Q = get_collection_size() - reldocs_not_indexed;
  75
  76         Xapian::doccount nonreldocs_indexed = tf - reltermfreq;
  77         double numerator = (reltermfreq + 0.5) * (Q - tf + 0.5);
  78         double denom = (reldocs_not_indexed + 0.5) * (nonreldocs_indexed + 0.5);
  79         tw = numerator / denom;
  80     } else {
  81         tw = (get_collection_size() - tf + 0.5) / (tf + 0.5);
  82     }
  83
  84     AssertRel(tw,>,0);
  85
  86     // The "official" formula can give a negative termweight in unusual cases
  87     // (without an RSet, when a term indexes more than half the documents in
  88     // the database).  These negative weights aren't actually helpful, and it
  89     // is common for implementations to replace them with a small positive
  90     // weight or similar.
  91     //
  92     // Truncating to zero doesn't seem a great approach in practice as it
  93     // means that some terms in the query can have no effect at all on the
  94     // ranking, and that some results can have zero weight, both of which
  95     // are seem surprising.
  96     //
  97     // Xapian 1.0.x and earlier adjusted the termweight for any term indexing
  98     // more than a third of documents, which seems rather "intrusive".  That's
  99     // what the code currently enabled does, but perhaps it would be better to
 100     // do something else. (FIXME)
 101 #if 0
 102     if (rare(tw <= 1.0)) {
 103         termweight = 0;
 104     } else {
 105         termweight = log(tw) * factor;
 106     }
 107 #else
 108     if (tw < 2) tw = tw * 0.5 + 1;
 109     termweight = log(tw) * factor;
 110 #endif
 111
 112     LOGVALUE(WTCALC, termweight);
 113
 114     if (param_k == 0) {
 115         // If param_k is 0 then the document length doesn't affect the weight.
 116         len_factor = 0;
 117     } else {
 118         len_factor = get_average_length();
 119         // len_factor can be zero if all documents are empty (or the database is
 120         // empty!)
 121         if (len_factor != 0) len_factor = param_k / len_factor;
 122     }
 123
 124     LOGVALUE(WTCALC, len_factor);
 125 }
 126
 127 string
 128 TradWeight::name() const
 129 {
 130     return "trad";
 131 }
 132
 133 string
 134 TradWeight::serialise() const
 135 {
 136     return serialise_double(param_k);
 137 }
 138
 139 TradWeight *
 140 TradWeight::unserialise(const string & s) const
 141 {
 142     const char *ptr = s.data();
 143     const char *end = ptr + s.size();
 144     double k = unserialise_double(&ptr, end);
 145     if (rare(ptr != end))
 146         throw Xapian::SerialisationError("Extra data in TradWeight::unserialise()");
 147     return new TradWeight(k);
 148 }
 149
 150 double
 151 TradWeight::get_sumpart(Xapian::termcount wdf, Xapian::termcount len,
 152                         Xapian::termcount, Xapian::termcount) const
 153 {
 154     double wdf_double = wdf;
 155     return termweight * (wdf_double / (len * len_factor + wdf_double));
 156 }
 157
 158 double
 159 TradWeight::get_maxpart() const
 160 {
 161     double wdf_max = get_wdf_upper_bound();
 162     Xapian::termcount doclen_lb = get_doclength_lower_bound();
 163     return termweight * (wdf_max / (doclen_lb * len_factor + wdf_max));
 164 }
 165
 166 static inline void
 167 parameter_error(const char* message, const char* params)
 168 {
 169     Xapian::Weight::Internal::parameter_error(message, "trad", params);
 170 }
 171
 172 TradWeight*
 173 TradWeight::create_from_parameters(const char* params) const
 174 {
 175     const char* p = params;
 176     if (*p == '\0')
 177         return new Xapian::TradWeight();
 178     double k = 1.0;
 179     if (!Xapian::Weight::Internal::double_param(&p, &k))
 180         parameter_error("Parameter is invalid", params);
 181     if (*p)
 182         parameter_error("Extra data after parameter", params);
 183     return new Xapian::TradWeight(k);
 184 }
 185
 186 }