xapian-core/matcher/maxpostlist.h

   1 /** @file
   2  * @brief N-way OR postlist with wt=max(wt_i)
   3  */
   4 /* Copyright (C) 2007,2009,2010,2011,2012,2013 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_MAXPOSTLIST_H
  23 #define XAPIAN_INCLUDED_MAXPOSTLIST_H
  24
  25 #include "multimatch.h"
  26 #include "api/postlist.h"
  27 #include <algorithm>
  28
  29 class MultiMatch;
  30
  31 /// N-way OR postlist with wt=max(wt_i).
  32 class MaxPostList : public PostList {
  33     /// Don't allow assignment.
  34     void operator=(const MaxPostList &);
  35
  36     /// Don't allow copying.
  37     MaxPostList(const MaxPostList &);
  38
  39     /// The current docid, or zero if we haven't started or are at_end.
  40     Xapian::docid did;
  41
  42     /// The number of sub-postlists.
  43     size_t n_kids;
  44
  45     /// Array of pointers to sub-postlists.
  46     PostList ** plist;
  47
  48     /// Cached answer to get_maxweight.
  49     double max_cached;
  50
  51     /// The number of documents in the database.
  52     Xapian::doccount db_size;
  53
  54     /// Pointer to the matcher object, so we can report pruning.
  55     MultiMatch *matcher;
  56
  57     /// Erase a sub-postlist.
  58     void erase_sublist(size_t i) {
  59         delete plist[i];
  60         --n_kids;
  61         for (size_t j = i; j < n_kids; ++j) {
  62             plist[j] = plist[j + 1];
  63         }
  64         matcher->recalc_maxweight();
  65     }
  66
  67   public:
  68     /** Construct from 2 random-access iterators to a container of PostList*,
  69      *  a pointer to the matcher, and the document collection size.
  70      */
  71     template<class RandomItor>
  72     MaxPostList(RandomItor pl_begin, RandomItor pl_end,
  73                 MultiMatch * matcher_, Xapian::doccount db_size_)
  74         : did(0), n_kids(pl_end - pl_begin), plist(NULL),
  75           max_cached(0), db_size(db_size_), matcher(matcher_)
  76     {
  77         plist = new PostList * [n_kids];
  78         std::copy(pl_begin, pl_end, plist);
  79     }
  80
  81     ~MaxPostList();
  82
  83     Xapian::doccount get_termfreq_min() const;
  84
  85     Xapian::doccount get_termfreq_max() const;
  86
  87     Xapian::doccount get_termfreq_est() const;
  88
  89     double get_maxweight() const;
  90
  91     Xapian::docid get_docid() const;
  92
  93     Xapian::termcount get_doclength() const;
  94
  95     Xapian::termcount get_unique_terms() const;
  96
  97     double get_weight() const;
  98
  99     bool at_end() const;
 100
 101     double recalc_maxweight();
 102
 103     PositionList * read_position_list() {
 104         return NULL;
 105     }
 106
 107     PostList* next(double w_min);
 108
 109     PostList* skip_to(Xapian::docid, double w_min);
 110
 111     std::string get_description() const;
 112
 113     /** get_wdf() for MaxPostlist returns the sum of the wdfs of the
 114      *  sub postlists which match the current docid.
 115      *
 116      *  The wdf isn't really meaningful in many situations, but if the lists
 117      *  are being combined as a synonym we want the sum of the wdfs, so we do
 118      *  that in general.
 119      */
 120     Xapian::termcount get_wdf() const;
 121
 122     // Note - we don't need to implement get_termfreq_est_using_stats() because
 123     // an OP_MAX when used as a child of a synonym will be optimised to an OR.
 124
 125     Xapian::termcount count_matching_subqs() const;
 126 };
 127
 128 #endif // XAPIAN_INCLUDED_MAXPOSTLIST_H