xapian-core/matcher/maxpostlist.h

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