PLearn 0.1
CompactFileVMatrix.h
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // CompactFileVMatrix.h
00004 //
00005 // Copyright (C) 2007 Olivier Breuleux
00006 //
00007 // Redistribution and use in source and binary forms, with or without
00008 // modification, are permitted provided that the following conditions are met:
00009 //
00010 //  1. Redistributions of source code must retain the above copyright
00011 //     notice, this list of conditions and the following disclaimer.
00012 //
00013 //  2. Redistributions in binary form must reproduce the above copyright
00014 //     notice, this list of conditions and the following disclaimer in the
00015 //     documentation and/or other materials provided with the distribution.
00016 //
00017 //  3. The name of the authors may not be used to endorse or promote
00018 //     products derived from this software without specific prior written
00019 //     permission.
00020 //
00021 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR
00022 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
00023 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
00024 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
00025 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
00026 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
00027 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
00028 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
00029 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
00030 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
00031 //
00032 // This file is part of the PLearn library. For more information on the PLearn
00033 // library, go to the PLearn Web site at www.plearn.org
00034 
00035 
00038 #ifndef CompactFileVMatrix_INC
00039 #define CompactFileVMatrix_INC
00040 
00041 #include "RowBufferedVMatrix.h"
00042 #include <plearn/db/getDataSet.h>
00043 #include <plearn/vmat/VMat.h>
00044 
00045 // While under development, we use this define to control
00046 // whether to use the NSPR 64 bit file access or the old std C FILE*
00047 #define USE_NSPR_FILE
00048 struct PRFileDesc;
00049 
00050 #define COMPACTFILEVMATRIX_HEADERLENGTH_MAX 1024
00051 
00052 namespace PLearn {
00053 using namespace std;
00054 
00055 
00059 struct GroupInfo {
00060     GroupInfo():
00061         type('\0'),
00062         length(-1),
00063         max(-1),
00064         bits_per_value(-1),
00065         active(false),
00066         compact_length(-1)
00067     {}
00068 
00069     GroupInfo(char type_, int length_, int max_, int bits_per_value_):
00070         type(type_),
00071         length(length_),
00072         max(max_),
00073         bits_per_value(bits_per_value_),
00074         active(false),
00075         compact_length(-1)
00076     {}
00077 
00078     char type; 
00079     int length; 
00080     int max; 
00081 
00082     int bits_per_value; 
00083     bool active; 
00084     int compact_length; 
00085 };
00086 
00087 
00090 class CompactFileVMatrix: public RowBufferedVMatrix
00091 {
00092 
00093 private:
00094     typedef RowBufferedVMatrix inherited;
00095     static VMatrixExtensionRegistrar* extension_registrar;
00096 
00097 protected:
00098     PPath filename_;
00099     Vec active_list_;
00100     bool in_ram_;
00101 
00102 
00103 #ifdef USE_NSPR_FILE
00104     PRFileDesc* f;
00105 #else
00106     FILE* f;
00107 #endif
00108 
00109     int header_length;
00110     int compact_width_; 
00111     TVec<GroupInfo> info;
00112     TVec<unsigned char> cache_index;
00113     mutable string cache;
00114 
00115 public:
00116 
00117     CompactFileVMatrix();
00118     CompactFileVMatrix(const PPath& filename); 
00119 
00120 protected:
00121 
00122     static void declareOptions(OptionList & ol);
00123     virtual void getNewRow(int i, const Vec& v) const;
00124 
00126     virtual void openCurrentFile();
00128     virtual void closeCurrentFile();
00129 
00130 public:
00131 
00133     virtual void updateHeader();
00134 
00136     virtual int nGroups() const;
00137     
00139     virtual char groupEncoding(int group) const;
00140 
00142     virtual int groupNFields(int group) const;
00143 
00145     virtual int groupNValues(int group) const;
00146 
00148     virtual int groupLength(int group) const;
00149 
00150     virtual void put(int i, int j, real value);
00151     virtual void putSubRow(int i, int j, Vec v);
00152     virtual void appendRow(Vec v);
00153     virtual void flush();
00154 
00155     virtual void build();
00156 
00157     static VMat instantiateFromPPath(const PPath& filename)
00158     {
00159         return VMat(new CompactFileVMatrix(filename));
00160     }
00161 
00162     PLEARN_DECLARE_OBJECT(CompactFileVMatrix);
00163 
00165     virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies);
00166 
00168     virtual ~CompactFileVMatrix();
00169 
00170 private:
00171 
00172     void build_();
00173     GroupInfo& getGroup(int group) const;
00174 
00175     // seek to element i,j in file
00176     void moveto(int i, int j=0) const;
00177     void cleanup();
00178 
00179 };
00180 
00181 DECLARE_OBJECT_PTR(CompactFileVMatrix);
00182 
00183 } // end of namespace PLearn
00184 #endif
00185 
00186 
00187 /*
00188   Local Variables:
00189   mode:c++
00190   c-basic-offset:4
00191   c-file-style:"stroustrup"
00192   c-file-offsets:((innamespace . 0)(inline-open . 0))
00193   indent-tabs-mode:nil
00194   fill-column:79
00195   End:
00196 */
00197 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines