locus_item.cpp

来自「ncbi源码」· C++ 代码 · 共 573 行 · 第 1/2 页

/*
 * ===========================================================================
 * PRODUCTION $Log: locus_item.cpp,v $
 * PRODUCTION Revision 1000.2  2004/06/01 19:45:04  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.9
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: locus_item.cpp,v 1000.2 2004/06/01 19:45:04 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:  Mati Shomrat, NCBI
*
* File Description:
*   flat-file generator -- locus item implementation
*
*/
#include <ncbi_pch.hpp>
#include <corelib/ncbistd.hpp>

#include <objects/general/Date.hpp>
#include <objects/seq/Bioseq.hpp>
#include <objects/seq/MolInfo.hpp>
#include <objects/seqloc/Textseq_id.hpp>
#include <objects/seqblock/GB_block.hpp>
#include <objects/seqblock/EMBL_block.hpp>
#include <objects/seqblock/SP_block.hpp>
#include <objects/seqblock/PDB_block.hpp>
#include <objects/seqblock/PDB_replace.hpp>
#include <objects/seqfeat/BioSource.hpp>
#include <objects/seqfeat/Org_ref.hpp>
#include <objects/seqfeat/OrgName.hpp>
#include <objects/seqfeat/SubSource.hpp>

#include <objmgr/scope.hpp>
#include <objmgr/seqdesc_ci.hpp>
#include <objmgr/feat_ci.hpp>
#include <objmgr/bioseq_handle.hpp>
#include <objmgr/util/sequence.hpp>

#include <objtools/format/formatter.hpp>
#include <objtools/format/text_ostream.hpp>
#include <objtools/format/items/locus_item.hpp>
#include <objtools/format/context.hpp>
#include "utils.hpp"


BEGIN_NCBI_SCOPE
BEGIN_SCOPE(objects)
USING_SCOPE(sequence);


CLocusItem::CLocusItem(CBioseqContext& ctx) :
    CFlatItem(&ctx),
    m_Length(0), m_Biomol(CMolInfo::eBiomol_unknown), m_Date("01-JAN-1900")
{
   x_GatherInfo(ctx);
}


void CLocusItem::Format
(IFormatter& formatter,
 IFlatTextOStream& text_os) const
{
    formatter.FormatLocus(*this, text_os); 
}


const string& CLocusItem::GetName(void) const
{
    return m_Name;
}


size_t CLocusItem::GetLength(void) const
{
    return m_Length;
}


CLocusItem::TStrand CLocusItem::GetStrand(void) const
{
    return m_Strand;
}


CLocusItem::TBiomol CLocusItem::GetBiomol(void) const
{
    return m_Biomol;
}


CLocusItem::TTopology CLocusItem::GetTopology (void) const
{
    return m_Topology;
}


const string& CLocusItem::GetDivision(void) const
{
    return m_Division;
}


const string& CLocusItem::GetDate(void) const
{
    return m_Date;
}


/***************************************************************************/
/*                                  PRIVATE                                */
/***************************************************************************/


void CLocusItem::x_GatherInfo(CBioseqContext& ctx)
{
    CSeqdesc_CI mi_desc(ctx.GetHandle(), CSeqdesc::e_Molinfo);
    if ( mi_desc ) {
        x_SetObject(mi_desc->GetMolinfo());
    }

    // NB: order of execution is important, as some values depend on others
    x_SetName(ctx);
    x_SetLength(ctx);
    x_SetBiomol(ctx);   // must come befoer x_SetStrand
    x_SetStrand(ctx);
    x_SetTopology(ctx);
    x_SetDivision(ctx);
    x_SetDate(ctx);
}


// Name

void CLocusItem::x_SetName(CBioseqContext& ctx)
{
    CBioseq_Handle::TBioseqCore seq  = ctx.GetHandle().GetBioseqCore();

    CConstRef<CSeq_id> id = FindBestChoice(seq->GetId(), CSeq_id::Score);
    const CTextseq_id* tsid = id->GetTextseq_Id();
    if ( tsid  &&  tsid->CanGetName() ) {
        m_Name = tsid->GetName();
    }
    if ( m_Name.empty()  ||  x_NameHasBadChars(m_Name) ) {
        m_Name = id->GetSeqIdString();
    }
}


bool CLocusItem::x_NameHasBadChars(const string& name) const
{
    ITERATE(string, iter, name) {
        if ( !isalnum(*iter) ) {
            return true;
        }
    }
    return false;
}


// Length

void CLocusItem::x_SetLength(CBioseqContext& ctx)
{
    m_Length = sequence::GetLength(ctx.GetLocation(), &ctx.GetScope());
}


// Strand

void CLocusItem::x_SetStrand(CBioseqContext& ctx)
{
    const CBioseq_Handle& bsh = ctx.GetHandle();
    
    CSeq_inst::TMol bmol = bsh.IsSetInst_Mol() ?
        bsh.GetInst_Mol() : CSeq_inst::eMol_not_set;

    m_Strand = bsh.IsSetInst_Strand() ?
        bsh.GetInst_Strand() : CSeq_inst::eStrand_not_set;
    if ( m_Strand == CSeq_inst::eStrand_other ) {
        m_Strand = CSeq_inst::eStrand_not_set;
    }

    // cleanup for formats other than GBSeq
    if ( !ctx.Config().IsFormatGBSeq() ) {
        // if ds-DNA don't show ds
        if ( bmol == CSeq_inst::eMol_dna  &&  m_Strand == CSeq_inst::eStrand_ds ) {
            m_Strand = CSeq_inst::eStrand_not_set;
        }
        
        // ss-any RNA don't show ss
        if ( (bmol > CSeq_inst::eMol_rna  ||  
            (m_Biomol >= CMolInfo::eBiomol_mRNA     &&
            m_Biomol <= CMolInfo::eBiomol_peptide))  &&
            m_Strand == CSeq_inst::eStrand_ss ) {
            m_Strand = CSeq_inst::eStrand_not_set;
        }
    }
}


// Biomol

void CLocusItem::x_SetBiomol(CBioseqContext& ctx)
{
    if ( ctx.IsProt() ) {
        return;
    }

    CSeq_inst::TMol bmol = ctx.GetHandle().GetBioseqMolType();
    
    if ( bmol > CSeq_inst::eMol_aa ) {
        bmol = CSeq_inst::eMol_not_set;
    }

    const CMolInfo* molinfo = dynamic_cast<const CMolInfo*>(GetObject());
    if ( molinfo  &&  molinfo->GetBiomol() <= CMolInfo::eBiomol_transcribed_RNA ) {
        m_Biomol = molinfo->GetBiomol();
    }

    if ( m_Biomol <= CMolInfo::eBiomol_genomic ) {
        if ( bmol == CSeq_inst::eMol_aa ) {
            m_Biomol = CMolInfo::eBiomol_peptide;
        } else if ( bmol == CSeq_inst::eMol_na ) {
            m_Biomol = CMolInfo::eBiomol_unknown;
        } else if ( bmol == CSeq_inst::eMol_rna ) {
            m_Biomol = CMolInfo::eBiomol_pre_RNA;
        } else {
            m_Biomol = CMolInfo::eBiomol_genomic;
        }
    } else if ( m_Biomol == CMolInfo::eBiomol_other_genetic ) {
        if ( bmol == CSeq_inst::eMol_rna ) {
            m_Biomol = CMolInfo::eBiomol_pre_RNA;
        }
    }
}


// Topology

void CLocusItem::x_SetTopology(CBioseqContext& ctx)
{
    const CBioseq_Handle& bsh = ctx.GetHandle();
    
    m_Topology = bsh.GetInst_Topology();
    // an interval is always linear
    if ( !ctx.GetLocation().IsWhole() ) {
        m_Topology = CSeq_inst::eTopology_linear;
    }
}


// Division

void CLocusItem::x_SetDivision(CBioseqContext& ctx)
{
    // contig style (old genome_view flag) forces CON division
    if ( ctx.DoContigStyle() ) {
        m_Division = "CON";
        return;
    }
    // "genome view" forces CON division
    if ( (ctx.IsSegmented()  &&  !ctx.HasParts())  ||