xapian-letor/api/feature_internal.h

   1 /** @file
   2  * @brief Internals of Feature class
   3  */
   4 /* Copyright (C) 2019 Vaibhav Kansagara
   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
  19  * USA
  20  */
  21
  22 #ifndef XAPIAN_INCLUDED_FEATURE_INTERNAL_H
  23 #define XAPIAN_INCLUDED_FEATURE_INTERNAL_H
  24
  25 #include "xapian-letor/feature.h"
  26 #include "xapian-letor/featurelist.h"
  27
  28 #include <map>
  29
  30 namespace Xapian {
  31
  32 /** Class defining internals of Feature class. */
  33 class Feature::Internal : public Xapian::Internal::intrusive_base {
  34     friend class Feature;
  35
  36     /// Xapian::Database using which features will be calculated.
  37     Database feature_db;
  38
  39     /// Xapian::Query using which features will be calculated.
  40     Query feature_query;
  41
  42     /// Xapian::Document using which features will be calculated.
  43     Document feature_doc;
  44
  45     /// Frequency of the Query Terms in the specified documents.
  46     std::map<std::string, Xapian::termcount> termfreq;
  47
  48     /// Inverse Document Frequency of Query terms in the database.
  49     std::map<std::string, double> inverse_doc_freq;
  50
  51     /** Length of the document as number of terms for different parts like
  52      *  'title', 'body' and 'whole'.
  53      */
  54     std::map<std::string, Xapian::termcount> doc_length;
  55
  56     /** Length of the collection in number of terms for different parts like
  57      * 'title', 'body' and 'whole'.
  58      */
  59     std::map<std::string, Xapian::termcount> collection_length;
  60
  61     /// Frequency of the Query Terms in the whole database
  62     std::map<std::string, Xapian::termcount> collection_termfreq;
  63
  64   public:
  65     /// Default constructor
  66     Internal() {}
  67
  68     /// Constructor creating an object instantiated with db,query and doc
  69     Internal(const Xapian::Database& db, const Xapian::Query& query,
  70              const Xapian::Document& doc)
  71          : feature_db(db), feature_query(query), feature_doc(doc) {}
  72
  73     /// get database
  74     Database get_database() const {
  75         return feature_db;
  76     }
  77
  78     /// get query
  79     Query get_query() const {
  80         return feature_query;
  81     }
  82
  83     /// get document
  84     Document get_document() const {
  85         return feature_doc;
  86     }
  87
  88     /// Get termfreq
  89     Xapian::termcount get_termfreq(const std::string& term) const;
  90
  91     /// Get inverse_doc_freq
  92     double get_inverse_doc_freq(const std::string& term) const;
  93
  94     /// Get doc_length
  95     Xapian::termcount get_doc_length(const std::string& term) const;
  96
  97     /// Get collection_length
  98     Xapian::termcount get_collection_length(const std::string& term) const;
  99
 100     /// Get collection_termfreq
 101     Xapian::termcount get_collection_termfreq(const std::string& term) const;
 102
 103     /// Set the term frequency to use for Feature building.
 104     void set_termfreq(std::map<std::string, Xapian::termcount>&& tf) {
 105         termfreq = tf;
 106     }
 107
 108     /// Set the inverse_doc_freq to use for Feature building.
 109     void set_inverse_doc_freq(std::map<std::string, double>&& idf) {
 110         inverse_doc_freq = idf;
 111     }
 112
 113     /** Set the doc_length to use for Feature building.
 114      *
 115      *  This is used by Feature::Internal while populating Statistics.
 116      */
 117     void set_doc_length(std::map<std::string, Xapian::termcount>&& doc_len) {
 118         doc_length = doc_len;
 119     }
 120
 121     /// Set the collection_length to use for Feature building.
 122     void set_collection_length(std::map<std::string,
 123                                         Xapian::termcount>&& collection_len) {
 124         collection_length = collection_len;
 125     }
 126
 127     /// Set the collection_termfreq to use for Feature building.
 128     void set_collection_termfreq(std::map<std::string,
 129                                           Xapian::termcount>&& collection_tf) {
 130         collection_termfreq = collection_tf;
 131     }
 132 };
 133
 134 }
 135
 136 #endif // XAPIAN_INCLUDED_FEATURE_INTERNAL_H