context.hpp

ncbi源码

/*
 * ===========================================================================
 * PRODUCTION $Log: context.hpp,v $
 * PRODUCTION Revision 1000.1  2004/06/01 19:38:24  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.18
 * PRODUCTION
 * ===========================================================================
 */

#ifndef OBJTOOLS_FORMAT___CONTEXT__HPP
#define OBJTOOLS_FORMAT___CONTEXT__HPP

/*  $Id: context.hpp,v 1000.1 2004/06/01 19:38:24 gouriano Exp $
* ===========================================================================
*
*                            PUBLIC DOMAIN NOTICE
*               National Center for Biotechnology Information
*
*  This software/database is a "United States Government Work" under the
*  terms of the United States Copyright Act.  It was written as part of
*  the author's official duties as a United States Government employee and
*  thus cannot be copyrighted.  This software/database is freely available
*  to the public for use. The National Library of Medicine and the U.S.
*  Government have not placed any restriction on its use or reproduction.
*
*  Although all reasonable efforts have been taken to ensure the accuracy
*  and reliability of the software and data, the NLM and the U.S.
*  Government do not and cannot warrant the performance or results that
*  may be obtained by using this software or data. The NLM and the U.S.
*  Government disclaim all warranties, express or implied, including
*  warranties of performance, merchantability or fitness for any particular
*  purpose.
*
*  Please cite the author in any work or product based on this material.
*
* ===========================================================================
*
* Author:  Aaron Ucko, Mati Shomrat
*
* File Description:
*   new (early 2003) flat-file generator -- context needed when (pre)formatting
*
*/
#include <corelib/ncbistd.hpp>
#include <corelib/ncbiobj.hpp>

#include <objects/seq/Bioseq.hpp>
#include <objects/seq/Seq_inst.hpp>
#include <objects/seq/MolInfo.hpp>
#include <objects/seqloc/Seq_loc.hpp>
#include <objects/seqloc/Seq_id.hpp>
#include <objects/submit/Submit_block.hpp>
#include <objmgr/bioseq_handle.hpp>
#include <objmgr/seq_entry_handle.hpp>
#include <objmgr/annot_selector.hpp>
#include <objmgr/seq_loc_mapper.hpp>

#include <util/range.hpp>

#include <objtools/format/flat_file_config.hpp>
#include <objtools/format/items/reference_item.hpp>

#include <memory>

BEGIN_NCBI_SCOPE
BEGIN_SCOPE(objects)

class CScope;
class CMasterContext;
class CFlatFileContext;


/////////////////////////////////////////////////////////////////////////////
//
// CBioseqContext
//
// information on the bioseq being formatted

class CBioseqContext : public CObject
{
public:
    // types
    typedef CRef<CReferenceItem>    TRef;
    typedef vector<TRef>            TReferences;
    typedef CRange<TSeqPos>         TRange;

    // constructor
    CBioseqContext(const CBioseq_Handle& seq, CFlatFileContext& ffctx,
        CMasterContext* mctx = 0);
    // destructor
    ~CBioseqContext(void);

    // Get the bioseq's handle
    CBioseq_Handle& GetHandle(void) { return m_Handle; }
    CScope& GetScope(void) { return m_Handle.GetScope(); }

    // -- id information
    CSeq_id* GetPrimaryId(void) { return m_PrimaryId; }
    const CSeq_id& GetPreferredSynonym(const CSeq_id& id) const;
    const string& GetAccession(void) const { return m_Accession; }
    int  GetGI(void) const { return m_Gi; }
    
    // molecular type (nucleotide / protein)
    bool IsProt(void) const { return m_IsProt;  }
    bool IsNuc (void) const { return !m_IsProt; }

    CSeq_inst::TRepr  GetRepr   (void) const { return m_Repr;    }
    CSeq_inst::TMol   GetMol    (void) const { return m_Mol;     }
    const CMolInfo*   GetMolinfo(void) const { return m_Molinfo; }
    CMolInfo::TTech   GetTech   (void) const;
    CMolInfo::TBiomol GetBiomol (void) const;
    const CBioseq::TId& GetBioseqIds(void) const;

    // segmented bioseq
    bool IsSegmented(void) const { return m_Repr == CSeq_inst::eRepr_seg; }
    bool HasParts(void) const { return m_HasParts; }
    
    // part of a segmented bioseq
    bool IsPart(void) const { return m_IsPart; }
    SIZE_TYPE GetPartNumber   (void) const { return m_PartNumber; }
    SIZE_TYPE GetTotalNumParts(void) const;
    CMasterContext& GetMaster (void) { return *m_Master; }
    void SetMaster(CMasterContext& mctx);

    // delta sequence
    bool IsDelta(void) const { return m_Repr == CSeq_inst::eRepr_delta; }
    bool IsDeltaLitOnly(void) const { return m_IsDeltaLitOnly; }

    // Whole Genome Shotgun
    bool IsWGS      (void) const { return m_IsWGS;       }
    bool IsWGSMaster(void) const { return m_IsWGSMaster; }
    const string& GetWGSMasterAccn(void) const { return m_WGSMasterAccn; }
    const string& GetWGSMasterName(void) const { return m_WGSMasterName; }

    TReferences& SetReferences(void) { return m_References; }
    const TReferences& GetReferences(void) const { return m_References; }

    // range on the bioseq to be formatted. the location is either
    // whole or an interval (no complex locations allowed)
    const CSeq_loc& GetLocation(void) const { return *m_Location; }
    CSeq_loc_Mapper* GetMapper(void) { return m_Mapper; }

    bool DoContigStyle(void) const;
    bool ShowGBBSource(void) const { return m_ShowGBBSource; }

    bool IsInGPS    (void) const { return m_IsInGPS;     }  // Is in a gene-prod set?
    bool IsInNucProt(void) const { return m_IsInNucProt; }  // Is in a nuc-prot set?

    // type of bioseq?
    bool IsGED            (void) const { return m_IsGED;  }  // Genbank, EMBL or DDBJ
    bool IsEMBL           (void) const { return m_IsEMBL; }  // EMBL
    bool IsPDB            (void) const { return m_IsPDB;  }  // PDB
    bool IsSP             (void) const { return m_IsSP;   }  // SwissProt
    bool IsTPA            (void) const { return m_IsTPA;  }  // Third-Party Annotation
    bool IsPatent         (void) const { return m_IsPatent; }
    bool IsGbGenomeProject(void) const { return m_IsGbGenomeProject; } // AE
    bool IsNcbiCONDiv     (void) const { return m_IsNcbiCONDiv; }      // CH
    
    // RefSeq ID queries
    bool IsRefSeq(void) const { return m_IsRefSeq; }
    bool IsRSCompleteGenomic  (void) const;  // NC_
    bool IsRSIncompleteGenomic(void) const;  // NG_
    bool IsRSMRna             (void) const;  // NM_
    bool IsRSNonCodingRna     (void) const;  // NR_
    bool IsRSProtein          (void) const;  // NP_
    bool IsRSContig           (void) const;  // NT_
    bool IsRSIntermedWGS      (void) const;  // NW_
    bool IsRSPredictedMRna    (void) const;  // XM_
    bool IsRSPredictedNCRna   (void) const;  // XR_
    bool IsRSPredictedProtein (void) const;  // XP_
    bool IsRSWGSNuc           (void) const;  // NZ_
    bool IsRSWGSProt          (void) const;  // ZP_
    
    bool IsHup(void) const { return m_IsHup; }  // !!! should move to global?
    // global data from CFlatFileContext
    const CSubmit_block* GetSubmitBlock(void) const;
    const CSeq_entry_Handle& GetEntry(void) const;
    const CFlatFileConfig& Config(void) const;
    const SAnnotSelector* GetAnnotSelector(void) const;
    const CSeq_loc* GetMasterLocation(void) const;
    bool IsGenbankFormat(void) const;

private:
    void x_Init(const CBioseq_Handle& seq, const CSeq_loc* user_loc);
    void x_SetId(void);
    bool x_HasParts(void) const;
    bool x_IsDeltaLitOnly(void) const;
    bool x_IsPart(void) const;
    CBioseq_Handle x_GetMasterForPart(void) const;
    SIZE_TYPE x_GetPartNumber(void);
    bool x_IsInGPS(void) const;
    bool x_IsInNucProt(void) const;
    void x_SetLocation(const CSeq_loc* user_loc = 0);
    
    CSeq_inst::TRepr x_GetRepr(void) const;
    const CMolInfo* x_GetMolInfo(void) const;

    // data
    CBioseq_Handle        m_Handle;
    CRef<CSeq_id>         m_PrimaryId;
    string                m_Accession;
    string                m_WGSMasterAccn;
    string                m_WGSMasterName;

    CSeq_inst::TRepr      m_Repr;
    CSeq_inst::TMol       m_Mol;
    CConstRef<CMolInfo>   m_Molinfo; 

    // segmented bioseq
    bool        m_HasParts;
    // part of a segmented bioseq
    bool        m_IsPart;
    SIZE_TYPE   m_PartNumber;
    // delta bioseq
    bool        m_IsDeltaLitOnly;

    bool m_IsProt;      // Protein
    bool m_IsInGPS;     // Gene-Prod Set
    bool m_IsInNucProt; // Nuc-Prot Set
    bool m_IsGED;       // Genbank, Embl or Ddbj
    bool m_IsEMBL;      // EMBL
    bool m_IsPDB;       // PDB
    bool m_IsSP;        // SwissProt
    bool m_IsTPA;       // Third Party Annotation
    bool m_IsRefSeq;
    unsigned int m_RefseqInfo;
    bool m_IsGbGenomeProject;  // GenBank Genome project data
    bool m_IsNcbiCONDiv;       // NCBI CON division
    bool m_IsPatent;
    bool m_IsGI;
    bool m_IsWGS;
    bool m_IsWGSMaster;
    bool m_IsHup;
    int  m_Gi;
    bool m_ShowGBBSource;
    
    TReferences             m_References;
    CConstRef<CSeq_loc>     m_Location;
    CRef<CSeq_loc_Mapper>   m_Mapper;
    CFlatFileContext&       m_FFCtx;
    CRef<CMasterContext>    m_Master;
};


/////////////////////////////////////////////////////////////////////////////
//
// CMasterContext
//
// When formatting segmented bioseq CMasterContext holds information
// on the Master bioseq.

class CMasterContext : public CObject
{
public:
    // constructor
    CMasterContext(const CBioseq_Handle& master);
    // destructor
    ~CMasterContext(void);

    // Get the segmented bioseq's handle
    const CBioseq_Handle& GetHandle(void) const { return m_Handle;   }
    // Get the number of parts
    SIZE_TYPE GetNumParts          (void) const { return m_NumParts; }
    // Get the base name
    const string& GetBaseName      (void) const { return m_BaseName; }

    // Find the serial number of a part in the segmented bioseq
    SIZE_TYPE GetPartNumber(const CBioseq_Handle& part);

private:
    void x_SetBaseName(void);
    void x_SetNumParts(void);

    // data
    CBioseq_Handle    m_Handle;
    string            m_BaseName;
    SIZE_TYPE         m_NumParts;
};


/////////////////////////////////////////////////////////////////////////////
//
// CFlatFileContext

class CFlatFileContext : public CObject
{
public:
    // types
    typedef CRef<CBioseqContext>            TSection;
    typedef vector< CRef<CBioseqContext> >  TSections;

    // constructor