xapian-core/api/leafpostlist.h

   1 /** @file leafpostlist.h
   2  * @brief Abstract base class for leaf postlists.
   3  */
   4 /* Copyright (C) 2007,2009,2011,2013,2015,2016,2017 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 #ifndef XAPIAN_INCLUDED_LEAFPOSTLIST_H
  23 #define XAPIAN_INCLUDED_LEAFPOSTLIST_H
  24
  25 #include "postlist.h"
  26
  27 #include <string>
  28
  29 namespace Xapian {
  30     class Weight;
  31 }
  32
  33 /** Abstract base class for leaf postlists.
  34  *
  35  *  This class provides the following features in addition to the PostList
  36  *  class:
  37  */
  38 class LeafPostList : public PostList {
  39     /// Don't allow assignment.
  40     void operator=(const LeafPostList &);
  41
  42     /// Don't allow copying.
  43     LeafPostList(const LeafPostList &);
  44
  45   protected:
  46     const Xapian::Weight * weight;
  47
  48     /// The term name for this postlist (empty for an alldocs postlist).
  49     std::string term;
  50
  51     /// Only constructable as a base class for derived classes.
  52     explicit LeafPostList(const std::string & term_)
  53         : weight(0), term(term_) { }
  54
  55   public:
  56     ~LeafPostList();
  57
  58     /** Set the weighting scheme to use during matching.
  59      *
  60      *  If this isn't called, get_weight() and recalc_maxweight() will both
  61      *  return 0.
  62      *
  63      *  You should not call this more than once on a particular object.
  64      *
  65      *  @param weight_  The weighting object to use.  Must not be NULL.
  66      */
  67     void set_termweight(const Xapian::Weight * weight_) {
  68         // This method shouldn't be called more than once on the same object.
  69         Assert(!weight);
  70         weight = weight_;
  71     }
  72
  73     double resolve_lazy_termweight(Xapian::Weight * weight_,
  74                                    Xapian::Weight::Internal * stats,
  75                                    Xapian::termcount qlen,
  76                                    Xapian::termcount wqf,
  77                                    double factor)
  78     {
  79         weight_->init_(*stats, qlen, term, wqf, factor);
  80         // There should be an existing LazyWeight set already.
  81         Assert(weight);
  82         const Xapian::Weight * const_weight_ = weight_;
  83         std::swap(weight, const_weight_);
  84         delete const_weight_;
  85         stats->termfreqs[term].max_part += weight->get_maxpart();
  86         return stats->termfreqs[term].max_part;
  87     }
  88
  89     /** Return the exact term frequency.
  90      *
  91      *  Leaf postlists have an exact termfreq, which get_termfreq_min(),
  92      *  get_termfreq_max(), and get_termfreq_est() all report.
  93      */
  94     virtual Xapian::doccount get_termfreq() const = 0;
  95
  96     Xapian::doccount get_termfreq_min() const;
  97     Xapian::doccount get_termfreq_max() const;
  98     Xapian::doccount get_termfreq_est() const;
  99
 100     double get_weight(Xapian::termcount doclen,
 101                       Xapian::termcount unique_terms) const;
 102
 103     double recalc_maxweight();
 104
 105     TermFreqs get_termfreq_est_using_stats(
 106         const Xapian::Weight::Internal & stats) const;
 107
 108     Xapian::termcount count_matching_subqs() const;
 109
 110     void gather_position_lists(OrPositionList* orposlist);
 111
 112     /** Open another postlist from the same database.
 113      *
 114      *  @param term_    The term to open a postlist for (must not be an empty
 115      *                  string).  If term_ is near to this postlist's term,
 116      *                  then this can be a lot more efficient (and if it isn't
 117      *                  very near, there's not much of a penalty).  Using this
 118      *                  method can make a wildcard expansion much more memory
 119      *                  efficient.
 120      *
 121      *  @param need_pos Does the postlist need to support read_position_list()?
 122      *                  Note that open_position_list() may still be called even
 123      *                  if need_pos is false.
 124      *
 125      *  @return         The new postlist object, or NULL if not supported
 126      *                  (in which case the caller should probably open the
 127      *                  postlist via the database instead).
 128      */
 129     virtual LeafPostList * open_nearby_postlist(const std::string & term_,
 130                                                 bool need_pos) const;
 131
 132     /** Set the term name.
 133      *
 134      *  This is useful when we optimise a term matching all documents to an
 135      *  all documents postlist under OP_SYNONYM, as the term name is used by
 136      *  LeafPostList::get_termfreq_est_using_stats() to locate the appropriate
 137      *  TermFreqs object.
 138      */
 139     void set_term(const std::string & term_) { term = term_; }
 140 };
 141
 142 #endif // XAPIAN_INCLUDED_LEAFPOSTLIST_H