xapian-core/include/xapian/compactor.h

   1 /** @file compactor.h
   2  * @brief Compact a database, or merge and compact several.
   3  */
   4 /* Copyright (C) 2003,2004,2005,2006,2007,2008,2009,2010,2011,2013,2014 Olly Betts
   5  * Copyright (C) 2008 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
  20  * USA
  21  */
  22
  23 #ifndef XAPIAN_INCLUDED_COMPACTOR_H
  24 #define XAPIAN_INCLUDED_COMPACTOR_H
  25
  26 #if !defined XAPIAN_IN_XAPIAN_H && !defined XAPIAN_LIB_BUILD
  27 # error "Never use <xapian/compactor.h> directly; include <xapian.h> instead."
  28 #endif
  29
  30 #include <xapian/intrusive_ptr.h>
  31 #include <xapian/visibility.h>
  32 #include <string>
  33
  34 namespace Xapian {
  35
  36 /** Compact a database, or merge and compact several.
  37  */
  38 class XAPIAN_VISIBILITY_DEFAULT Compactor {
  39   public:
  40     /// Class containing the implementation.
  41     class Internal;
  42
  43     typedef enum { STANDARD, FULL, FULLER } compaction_level;
  44
  45   private:
  46     /// @internal Reference counted internals.
  47     Xapian::Internal::intrusive_ptr<Internal> internal;
  48
  49   public:
  50     Compactor();
  51
  52     virtual ~Compactor();
  53
  54     /** Set the block size to use for tables in the output database.
  55      *
  56      *  @param block_size       The block size to use.  Valid block sizes are
  57      *                          currently powers of two between 2048 and 65536,
  58      *                          with the default being 8192, but the valid
  59      *                          sizes and default may change in the future.
  60      */
  61     void set_block_size(size_t block_size);
  62
  63     /** Set whether to preserve existing document id values.
  64      *
  65      *  @param renumber The default is true, which means that document ids will
  66      *                  be renumbered - currently by applying the same offset
  67      *                  to all the document ids in a particular source
  68      *                  database.
  69      *
  70      *                  If false, then the document ids must be unique over all
  71      *                  source databases.  Currently the ranges of document ids
  72      *                  in each source must not overlap either, though this
  73      *                  restriction may be removed in the future.
  74      */
  75     void set_renumber(bool renumber);
  76
  77     /** Set whether to merge postlists in multiple passes.
  78      *
  79      *  @param multipass        If true and merging more than 3 databases,
  80      *  merge the postlists in multiple passes, which is generally faster but
  81      *  requires more disk space for temporary files.  By default we don't do
  82      *  this.
  83      */
  84     void set_multipass(bool multipass);
  85
  86     /** Set the compaction level.
  87      *
  88      *  @param compaction Available values are:
  89      *  - Xapian::Compactor::STANDARD - Don't split items unnecessarily.
  90      *  - Xapian::Compactor::FULL     - Split items whenever it saves space
  91      *    (the default).
  92      *  - Xapian::Compactor::FULLER   - Allow oversize items to save more space
  93      *    (not recommended if you ever plan to update the compacted database).
  94      */
  95     void set_compaction_level(compaction_level compaction);
  96
  97     /** Set where to write the output.
  98      *
  99      *  @param destdir  Output path.  This can be the same as an input if that
 100      *                  input is a stub database (in which case the database(s)
 101      *                  listed in the stub will be compacted to a new database
 102      *                  and then the stub will be atomically updated to point
 103      *                  to this new database).
 104      */
 105     void set_destdir(const std::string & destdir);
 106
 107     /** Add a source database.
 108      *
 109      *  @param srcdir   The path to the source database to add.
 110      */
 111     void add_source(const std::string & srcdir);
 112
 113     /// Perform the actual compaction/merging operation.
 114     void compact();
 115
 116     /** Update progress.
 117      *
 118      *  Subclass this method if you want to get progress updates during
 119      *  compaction.  This is called for each table first with empty status,
 120      *  And then one or more times with non-empty status.
 121      *
 122      *  The default implementation does nothing.
 123      *
 124      *  @param table    The table currently being compacted.
 125      *  @param status   A status message.
 126      */
 127     virtual void
 128     set_status(const std::string & table, const std::string & status);
 129
 130     /** Resolve multiple user metadata entries with the same key.
 131      *
 132      *  When merging, if the same user metadata key is set in more than one
 133      *  input, then this method is called to allow this to be resolving in
 134      *  an appropriate way.
 135      *
 136      *  The default implementation just returns tags[0].
 137      *
 138      *  For multipass this will currently get called multiple times for the
 139      *  same key if there are duplicates to resolve in each pass, but this
 140      *  may change in the future.
 141      *
 142      *  @param key      The metadata key with duplicate entries.
 143      *  @param num_tags How many tags there are.
 144      *  @param tags     An array of num_tags strings containing the tags to
 145      *                  merge.
 146      */
 147     virtual std::string
 148     resolve_duplicate_metadata(const std::string & key,
 149                                size_t num_tags, const std::string tags[]);
 150 };
 151
 152 }
 153
 154 #endif /* XAPIAN_INCLUDED_COMPACTOR_H */