Branch data     Line data    Source code

       1                 :            : /** @file synonympostlist.h
       2                 :            :  * @brief Combine subqueries, weighting as if they are synonyms
       3                 :            :  */
       4                 :            : /* Copyright 2007,2009 Lemur Consulting Ltd
       5                 :            :  * Copyright 2009 Olly Betts
       6                 :            :  *
       7                 :            :  * This program is free software; you can redistribute it and/or modify
       8                 :            :  * it under the terms of the GNU General Public License as published by
       9                 :            :  * the Free Software Foundation; either version 2 of the License, or
      10                 :            :  * (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_SYNONYMPOSTLIST_H
      23                 :            : #define XAPIAN_INCLUDED_SYNONYMPOSTLIST_H
      24                 :            : 
      25                 :            : #include "multimatch.h"
      26                 :            : #include "postlist.h"
      27                 :            : 
      28                 :            : /** A postlist comprising several postlists SYNONYMed together.
      29                 :            :  *
      30                 :            :  *  This postlist returns all postings in the OR of the sub postlists, but
      31                 :            :  *  returns weights as if they represented a single term.  The term frequency
      32                 :            :  *  portion of the weight is approximated.
      33                 :            :  */
      34                 :            : class SynonymPostList : public PostList {
      35                 :            :     /** The subtree, which starts as an OR of all the sub-postlists being
      36                 :            :      *  joined with Synonym, but may decay into something else.
      37                 :            :      */
      38                 :            :     PostList * subtree;
      39                 :            : 
      40                 :            :     /** The object which is using this postlist to perform a match.
      41                 :            :      *
      42                 :            :      *  This object needs to be notified when the tree changes such that the
      43                 :            :      *  maximum weights need to be recalculated.
      44                 :            :      */
      45                 :            :     MultiMatch * matcher;
      46                 :            : 
      47                 :            :     /// Weighting object used for calculating the synonym weights.
      48                 :            :     const Xapian::Weight * wt;
      49                 :            : 
      50                 :            :     /// Flag indicating whether the weighting object needs the doclength.
      51                 :            :     bool want_doclength;
      52                 :            : 
      53                 :            :     /// Flag indicating whether the weighting object needs the wdf.
      54                 :            :     bool want_wdf;
      55                 :            : 
      56                 :            :     /// Flag indicating if we've called recalc_maxweight on the subtree yet.
      57                 :            :     bool have_calculated_subtree_maxweights;
      58                 :            : 
      59                 :            :   public:
      60                 :        592 :     SynonymPostList(PostList * subtree_, MultiMatch * matcher_)
      61                 :            :         : subtree(subtree_), matcher(matcher_), wt(NULL),
      62                 :            :           want_doclength(false), want_wdf(false),
      63                 :        592 :           have_calculated_subtree_maxweights(false) { }
      64                 :            : 
      65                 :            :     ~SynonymPostList();
      66                 :            : 
      67                 :            :     /** Set the weight object to be used for the synonym postlist.
      68                 :            :      *
      69                 :            :      *  Ownership of the weight object passes to the synonym postlist - the
      70                 :            :      *  caller must not delete it after use.
      71                 :            :      */
      72                 :            :     void set_weight(const Xapian::Weight * wt_);
      73                 :            : 
      74                 :            :     PostList *next(Xapian::weight w_min);
      75                 :            :     PostList *skip_to(Xapian::docid did, Xapian::weight w_min);
      76                 :            : 
      77                 :            :     Xapian::weight get_weight() const;
      78                 :            :     Xapian::weight get_maxweight() const;
      79                 :            :     Xapian::weight recalc_maxweight();
      80                 :            : 
      81                 :            :     // The following methods just call through to the subtree.
      82                 :            :     Xapian::termcount get_wdf() const;
      83                 :            :     Xapian::doccount get_termfreq_min() const;
      84                 :            :     Xapian::doccount get_termfreq_est() const;
      85                 :            :     Xapian::doccount get_termfreq_max() const;
      86                 :            :     // Note - we don't need to implement get_termfreq_est_using_stats()
      87                 :            :     // because a synonym when used as a child of a synonym will be optimised
      88                 :            :     // to an OR.
      89                 :            :     Xapian::docid get_docid() const;
      90                 :            :     Xapian::termcount get_doclength() const;
      91                 :            :     bool at_end() const;
      92                 :            : 
      93                 :            :     Xapian::termcount count_matching_subqs() const;
      94                 :            : 
      95                 :            :     std::string get_description() const;
      96                 :            : };
      97                 :            : 
      98                 :            : #endif /* XAPIAN_INCLUDED_SYNONYMPOSTLIST_H */