xapian-core/backends/honey/honey_postlisttable.cc

   1 /** @file honey_postlisttable.cc
   2  * @brief Subclass of HoneyTable which holds postlists.
   3  */
   4 /* Copyright (C) 2007,2008,2009,2010,2013,2014,2015,2016,2017 Olly Betts
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License
  17  * along with this program; if not, write to the Free Software
  18  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA
  19  */
  20
  21 #include <config.h>
  22
  23 #include "honey_postlisttable.h"
  24
  25 #include "honey_cursor.h"
  26 #include "honey_database.h"
  27 #include "honey_postlist.h"
  28 #include "honey_postlist_encodings.h"
  29
  30 #include <memory>
  31
  32 using namespace std;
  33
  34 HoneyPostList*
  35 HoneyPostListTable::open_post_list(const HoneyDatabase* db,
  36                                    const std::string& term,
  37                                    bool need_pos) const
  38 {
  39     Assert(!term.empty());
  40     // Try to position cursor first so we avoid creating HoneyPostList objects
  41     // for terms which don't exist.
  42     unique_ptr<HoneyCursor> cursor(cursor_get());
  43     if (!cursor->find_exact(Honey::make_postingchunk_key(term))) {
  44         // FIXME: Return NULL here and handle that in Query::Internal
  45         // postlist() methods as we build the PostList tree.
  46         // return NULL;
  47         return new HoneyPostList(db, term, NULL);
  48     }
  49
  50     if (need_pos)
  51         return new HoneyPosPostList(db, term, cursor.release());
  52     return new HoneyPostList(db, term, cursor.release());
  53 }
  54
  55 void
  56 HoneyPostListTable::get_freqs(const std::string& term,
  57                               Xapian::doccount* termfreq_ptr,
  58                               Xapian::termcount* collfreq_ptr) const
  59 {
  60     string chunk;
  61     if (!get_exact_entry(Honey::make_postingchunk_key(term), chunk)) {
  62         if (termfreq_ptr) *termfreq_ptr = 0;
  63         if (collfreq_ptr) *collfreq_ptr = 0;
  64         return;
  65     }
  66
  67     const char* p = chunk.data();
  68     const char* pend = p + chunk.size();
  69     Xapian::doccount tf;
  70     Xapian::termcount cf;
  71     if (!decode_initial_chunk_header_freqs(&p, pend, tf, cf))
  72         throw Xapian::DatabaseCorruptError("Postlist initial chunk header");
  73     if (termfreq_ptr) *termfreq_ptr = tf;
  74     if (collfreq_ptr) *collfreq_ptr = cf;
  75 }
  76
  77 void
  78 HoneyPostListTable::get_used_docid_range(Xapian::docid& first,
  79                                          Xapian::docid& last) const
  80 {
  81     unique_ptr<HoneyCursor> cursor;
  82     if (cursor->find_entry_ge(string("\0\xe0", 2))) {
  83         first = 1;
  84     } else {
  85         // doccount == 0 should be handled by our caller.
  86         Assert(!cursor->after_end());
  87         const char* p = cursor->current_key.data();
  88         const char* pend = p + cursor->current_key.size();
  89         p += 2;
  90         if (p[-2] != '\0' ||
  91             p[-1] != '\xe0' ||
  92             !unpack_uint_preserving_sort(&p, pend, &first) ||
  93             p != pend) {
  94             // Note that our caller checks for doccount == 0 and handles that.
  95             throw Xapian::DatabaseCorruptError("Bad first doclen chunk");
  96         }
  97     }
  98
  99     cursor->find_entry_lt(string("\0\xe1", 2));
 100     cursor->read_tag();
 101     if (cursor->current_key.size() == 2) {
 102         // Must be a single doclen chunk starting at 1.
 103         AssertEq(cursor->current_key[0], '\0');
 104         AssertEq(cursor->current_key[1], '\xe0');
 105         last = cursor->current_tag.size() >> 2;
 106     } else {
 107         const char* p = cursor->current_key.data();
 108         const char* pend = p + cursor->current_key.size();
 109         p += 2;
 110         if (p[-2] != '\0' ||
 111             p[-1] != '\xe0' ||
 112             !unpack_uint_preserving_sort(&p, pend, &last) ||
 113             p != pend) {
 114             throw Xapian::DatabaseCorruptError("Bad final doclen chunk");
 115         }
 116         last += (cursor->current_tag.size() >> 2) - 1;
 117     }
 118 }