Xapian: Internal Source Documentation: xapian-core: matcher/phrasepostlist.h Source File

00001 /* phrasepostlist.h: Return only items where terms are near or form a phrase
00002  *
00003  * ----START-LICENCE----
00004  * Copyright 1999,2000,2001 BrightStation PLC
00005  * Copyright 2003,2004,2005 Olly Betts
00006  * Copyright 2009 Lemur Consulting Ltd
00007  *
00008  * This program is free software; you can redistribute it and/or
00009  * modify it under the terms of the GNU General Public License as
00010  * published by the Free Software Foundation; either version 2 of the
00011  * License, or (at your option) any later version.
00012  *
00013  * This program is distributed in the hope that it will be useful,
00014  * but WITHOUT ANY WARRANTY; without even the implied warranty of
00015  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
00016  * GNU General Public License for more details.
00017  *
00018  * You should have received a copy of the GNU General Public License
00019  * along with this program; if not, write to the Free Software
00020  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
00021  * USA
00022  */
00023 
00024 #ifndef OM_HGUARD_PHRASEPOSTLIST_H
00025 #define OM_HGUARD_PHRASEPOSTLIST_H
00026 
00027 #include "selectpostlist.h"
00028 #include <vector>
00029 
00030 typedef Xapian::PositionIterator::Internal PositionList;
00031 
00039 class NearPostList : public SelectPostList {
00040     private:
00041         Xapian::termpos window;
00042         std::vector<PostList *> terms;
00043 
00044         bool test_doc();
00045         bool do_test(std::vector<PositionList *> &plists, Xapian::termcount i,
00046                      Xapian::termcount min, Xapian::termcount max);
00047     public:
00048         std::string get_description() const;
00049         Xapian::termcount get_wdf() const;
00050 
00051         Xapian::doccount get_termfreq_est() const
00052         {
00053             // No idea how to estimate this - FIXME
00054             return source->get_termfreq_est() / 2;
00055         }
00056 
00057         TermFreqs get_termfreq_est_using_stats(
00058             const Xapian::Weight::Internal & stats) const;
00059 
00060         NearPostList(PostList *source_, Xapian::termpos window_,
00061                      std::vector<PostList *>::const_iterator &terms_begin_,
00062                      std::vector<PostList *>::const_iterator &terms_end_)
00063             : SelectPostList(source_), terms(terms_begin_, terms_end_)
00064         {
00065             window = window_;
00066         }
00067 };
00068 
00076 class PhrasePostList : public SelectPostList {
00077     private:
00078         Xapian::termpos window;
00079         std::vector<PostList *> terms;
00080 
00081         bool test_doc();
00082         bool do_test(std::vector<PositionList *> &plists, Xapian::termcount i,
00083                      Xapian::termcount min, Xapian::termcount max);
00084     public:
00085         std::string get_description() const;
00086         Xapian::termcount get_wdf() const;
00087 
00088         Xapian::doccount get_termfreq_est() const
00089         {
00090             // No idea how to estimate this - FIXME
00091             return source->get_termfreq_est() / 3;
00092         }
00093 
00094         TermFreqs get_termfreq_est_using_stats(
00095             const Xapian::Weight::Internal & stats) const;
00096 
00097         PhrasePostList(PostList *source_, Xapian::termpos window_,
00098                        std::vector<PostList *>::const_iterator &terms_begin_,
00099                        std::vector<PostList *>::const_iterator &terms_end_)
00100             : SelectPostList(source_), terms(terms_begin_, terms_end_)
00101         {
00102             window = window_;
00103         }
00104 };
00105 
00106 #endif /* OM_HGUARD_PHRASEPOSTLIST_H */