src/database.h

/*****************************************************************************
* This file is provided under the Creative Commons Attribution 3.0 license.
*
* You are free to share, copy, distribute, transmit, or adapt this work
* PROVIDED THAT you attribute the work to the authors listed below.
* For more information, please see the following web page:
* http://creativecommons.org/licenses/by/3.0/
*
* This file is a component of the Sleipnir library for functional genomics,
* authored by:
* Curtis Huttenhower (chuttenh@princeton.edu)
* Mark Schroeder
* Maria D. Chikina
* Olga G. Troyanskaya (ogt@princeton.edu, primary contact)
*
* If you use this library, the included executable tools, or any related
* code in your work, please cite the following publication:
* Curtis Huttenhower, Mark Schroeder, Maria D. Chikina, and
* Olga G. Troyanskaya.
* "The Sleipnir library for computational functional genomics"
*****************************************************************************/
#ifndef DATABASE_H
#define DATABASE_H

#include "databasei.h"

namespace Sleipnir {

class IBayesNet;

class CDatabase : CDatabaseImpl {
public:

    bool Open( const std::vector<std::string>& vecstrGenes, const std::string& strInputDirectory,
        const IBayesNet* pBayesNet, const std::string& strOutputDirectory, size_t iFiles, const map<string, size_t>& mapstriZeros);


    //Qian
    bool Open( const std::vector<std::string>& vecstrGenes, const std::vector<std::string>& vecstrDatasets,
        const std::string& strInputDirectory, const std::string& strOutputDirectory, size_t iFiles, const map<string, size_t>& mapstriZeros);

    //Qian
    CDatabase(bool isNibble) : CDatabaseImpl(isNibble){
    }

    bool Reorganize(const char*, const size_t&);


    bool GetGene(const string &, vector<unsigned char>&) const;
    bool GetGene(const size_t &, vector<unsigned char>&) const;


    bool Open( const std::string& strInputDirectory );


    bool Get( size_t iOne, size_t iTwo, std::vector<unsigned char>& vecbData ) const {

        return m_vecpDBs[ iOne % m_vecpDBs.size( ) ]->Get( iOne / m_vecpDBs.size( ), iTwo, vecbData ); }

    bool Get( size_t iGene, std::vector<unsigned char>& vecbData, bool fReplace = false ) const {

        return m_vecpDBs[ iGene % m_vecpDBs.size( ) ]->Get( iGene / m_vecpDBs.size( ), vecbData, fReplace ); }

    bool Get( size_t iGene, const std::vector<size_t>& veciGenes,
        std::vector<unsigned char>& vecbData, bool fReplace = false ) const {

        return m_vecpDBs[ iGene % m_vecpDBs.size( ) ]->Get( iGene / m_vecpDBs.size( ), veciGenes, vecbData,
            fReplace ); }

    size_t GetGenes( ) const {

        return m_mapstriGenes.size( ); }

    size_t GetGene( const std::string& strGene ) const {

        return CDatabaseImpl::GetGene( strGene ); }

    const std::string& GetGene( size_t iGene ) const {
        static const std::string    c_strEmpty  = "";

        return ( m_vecpDBs.empty( ) ? c_strEmpty : m_vecpDBs[ iGene % m_vecpDBs.size( ) ]->GetGene( iGene /
            m_vecpDBs.size( ) ) ); }

    size_t GetDatasets( ) const {

        return ( m_vecpDBs.empty( ) ? 0 : m_vecpDBs[ 0 ]->GetDatasets( ) ); }

    //Used by SeekMiner and SeekServer
    bool Open(const string &, const vector<string> &, const size_t &, const size_t &);
    bool Open(const char *, const vector<string> &, const size_t &, const size_t &);


    void SetMemmap( bool fMemmap ) {

        m_fMemmap = fMemmap; }

    void SetBlockOut( size_t iSize ) {

        m_iBlockOut = iSize; }

    void SetBlockIn( size_t iSize ) {

        m_iBlockIn = iSize; }

    void SetBuffer( bool fBuffer ) {

        m_fBuffer = fBuffer; }
};

}

#endif // DATABASE_H