Branch data     Line data    Source code

       1                 :            : /* phrasepostlist.h: Return only items where terms are near or form a phrase
       2                 :            :  *
       3                 :            :  * ----START-LICENCE----
       4                 :            :  * Copyright 1999,2000,2001 BrightStation PLC
       5                 :            :  * Copyright 2003,2004,2005 Olly Betts
       6                 :            :  * Copyright 2009 Lemur Consulting Ltd
       7                 :            :  *
       8                 :            :  * This program is free software; you can redistribute it and/or
       9                 :            :  * modify it under the terms of the GNU General Public License as
      10                 :            :  * published by the Free Software Foundation; either version 2 of the
      11                 :            :  * License, or (at your option) any later version.
      12                 :            :  *
      13                 :            :  * This program is distributed in the hope that it will be useful,
      14                 :            :  * but WITHOUT ANY WARRANTY; without even the implied warranty of
      15                 :            :  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
      16                 :            :  * GNU General Public License for more details.
      17                 :            :  *
      18                 :            :  * You should have received a copy of the GNU General Public License
      19                 :            :  * along with this program; if not, write to the Free Software
      20                 :            :  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
      21                 :            :  * USA
      22                 :            :  */
      23                 :            : 
      24                 :            : #ifndef OM_HGUARD_PHRASEPOSTLIST_H
      25                 :            : #define OM_HGUARD_PHRASEPOSTLIST_H
      26                 :            : 
      27                 :            : #include "selectpostlist.h"
      28                 :            : #include <vector>
      29                 :            : 
      30                 :            : typedef Xapian::PositionIterator::Internal PositionList;
      31                 :            : 
      32                 :            : /** a postlist comprising several postlists NEARed together.
      33                 :            :  *
      34                 :            :  *  This postlist returns a posting if and only if it is in all of the
      35                 :            :  *  sub-postlists and all the terms occur within a specified distance of
      36                 :            :  *  each other somewhere in the document.  The weight for a posting is the
      37                 :            :  *  sum of the weights of the sub-postings.
      38                 :            :  */
      39 [ +  - ][ #  # ]:        288 : class NearPostList : public SelectPostList {
      40                 :            :     private:
      41                 :            :         Xapian::termpos window;
      42                 :            :         std::vector<PostList *> terms;
      43                 :            : 
      44                 :            :         bool test_doc();
      45                 :            :         bool do_test(std::vector<PositionList *> &plists, Xapian::termcount i,
      46                 :            :                      Xapian::termcount min, Xapian::termcount max);
      47                 :            :     public:
      48                 :            :         std::string get_description() const;
      49                 :            :         Xapian::termcount get_wdf() const;
      50                 :            : 
      51                 :        272 :         Xapian::doccount get_termfreq_est() const
      52                 :            :         {
      53                 :            :             // No idea how to estimate this - FIXME
      54                 :        272 :             return source->get_termfreq_est() / 2;
      55                 :            :         }
      56                 :            : 
      57                 :            :         TermFreqs get_termfreq_est_using_stats(
      58                 :            :             const Xapian::Weight::Internal & stats) const;
      59                 :            : 
      60                 :        288 :         NearPostList(PostList *source_, Xapian::termpos window_,
      61                 :            :                      std::vector<PostList *>::const_iterator &terms_begin_,
      62                 :            :                      std::vector<PostList *>::const_iterator &terms_end_)
      63                 :        288 :             : SelectPostList(source_), terms(terms_begin_, terms_end_)
      64                 :            :         {
      65                 :        288 :             window = window_;
      66                 :        288 :         }
      67                 :            : };
      68                 :            : 
      69                 :            : /** A postlist comprising several postlists PHRASEd together.
      70                 :            :  *
      71                 :            :  *  This postlist returns a posting if and only if it is in all of the
      72                 :            :  *  sub-postlists and all the terms occur IN THE GIVEN ORDER within a
      73                 :            :  *  specified distance of each other somewhere in the document.  The weight
      74                 :            :  *  for a posting is the sum of the weights of the sub-postings.
      75                 :            :  */
      76 [ +  - ][ #  # ]:        176 : class PhrasePostList : public SelectPostList {
      77                 :            :     private:
      78                 :            :         Xapian::termpos window;
      79                 :            :         std::vector<PostList *> terms;
      80                 :            : 
      81                 :            :         bool test_doc();
      82                 :            :         bool do_test(std::vector<PositionList *> &plists, Xapian::termcount i,
      83                 :            :                      Xapian::termcount min, Xapian::termcount max);
      84                 :            :     public:
      85                 :            :         std::string get_description() const;
      86                 :            :         Xapian::termcount get_wdf() const;
      87                 :            : 
      88                 :        176 :         Xapian::doccount get_termfreq_est() const
      89                 :            :         {
      90                 :            :             // No idea how to estimate this - FIXME
      91                 :        176 :             return source->get_termfreq_est() / 3;
      92                 :            :         }
      93                 :            : 
      94                 :            :         TermFreqs get_termfreq_est_using_stats(
      95                 :            :             const Xapian::Weight::Internal & stats) const;
      96                 :            : 
      97                 :        176 :         PhrasePostList(PostList *source_, Xapian::termpos window_,
      98                 :            :                        std::vector<PostList *>::const_iterator &terms_begin_,
      99                 :            :                        std::vector<PostList *>::const_iterator &terms_end_)
     100                 :        176 :             : SelectPostList(source_), terms(terms_begin_, terms_end_)
     101                 :            :         {
     102                 :        176 :             window = window_;
     103                 :        176 :         }
     104                 :            : };
     105                 :            : 
     106                 :            : #endif /* OM_HGUARD_PHRASEPOSTLIST_H */