comment_item.cpp

来自「ncbi源码」· C++ 代码 · 共 893 行 · 第 1/2 页

                                                wgsaccn.substr(7);

    CNcbiOstrstream text;
    text << "The " << *taxname 
         << "whole genome shotgun (WGS) project has the project accession " 
         << wgsaccn << ".  This version of the project (" << version 
         << ") has the accession number " << ctx.GetWGSMasterName() << ",";
    if ( (*first != *last) ) {
        text << " and consists of sequences " << *first << "-" << *last;
    } else {
        text << " and consists of sequence " << *first;
    }

    return CNcbiOstrstreamToString(text);
}


string CCommentItem::GetStringForMolinfo(const CMolInfo& mi, CBioseqContext& ctx)
{
    _ASSERT(mi.CanGetCompleteness());

    bool is_prot = ctx.IsProt();

    switch ( mi.GetCompleteness() ) {
    case CMolInfo::eCompleteness_complete:
        return "COMPLETENESS: full length";

    case CMolInfo::eCompleteness_partial:
        return "COMPLETENESS: not full length";

    case CMolInfo::eCompleteness_no_left:
        return (is_prot ? "COMPLETENESS: incomplete on the amino end" :
                          "COMPLETENESS: incomplete on the 5' end");

    case CMolInfo::eCompleteness_no_right:
        return (is_prot ? "COMPLETENESS: incomplete on the carboxy end" :
                          "COMPLETENESS: incomplete on the 3' end");

    case CMolInfo::eCompleteness_no_ends:
        return "COMPLETENESS: incomplete on both ends";

    case CMolInfo::eCompleteness_has_left:
        return (is_prot ? "COMPLETENESS: complete on the amino end" :
                          "COMPLETENESS: complete on the 5' end");

    case CMolInfo::eCompleteness_has_right:
        return (is_prot ? "COMPLETENESS: complete on the carboxy end" :
                          "COMPLETENESS: complete on the 3' end");

    default:
        return "COMPLETENESS: unknown";
    }

    return kEmptyStr;
}


string CCommentItem::GetStringForHTGS(CBioseqContext& ctx)
{
    SDeltaSeqSummary summary;
    if ( ctx.GetRepr() == CSeq_inst::eRepr_delta ) {
        GetDeltaSeqSummary(ctx.GetHandle(), summary);
    }

    CMolInfo::TTech tech = ctx.GetTech();

    CNcbiOstrstream text;

    if ( tech == CMolInfo::eTech_htgs_0 ) {
        if ( summary.num_segs > 0 ) {
            text << "* NOTE: This record contains " << (summary.num_gaps + 1) << " individual~"
                 << "* sequencing reads that have not been assembled into~"
                 << "* contigs. Runs of N are used to separate the reads~"
                 << "* and the order in which they appear is completely~"
                 << "* arbitrary. Low-pass sequence sampling is useful for~"
                 << "* identifying clones that may be gene-rich and allows~"
                 << "* overlap relationships among clones to be deduced.~"
                 << "* However, it should not be assumed that this clone~"
                 << "* will be sequenced to completion. In the event that~"
                 << "* the record is updated, the accession number will~"
                 << "* be preserved.";
        }
        text << "~";
        text << summary.text;
    } else if ( tech == CMolInfo::eTech_htgs_1 ) {
        text << "* NOTE: This is a \"working draft\" sequence.";
        if ( summary.num_segs > 0 ) {
            text << " It currently~"
                 << "* consists of " << (summary.num_gaps + 1) << " contigs. The true order of the pieces~"
                 << "* is not known and their order in this sequence record is~"
                 << "* arbitrary. Gaps between the contigs are represented as~"
                 << "* runs of N, but the exact sizes of the gaps are unknown.";
        }
        text << "~* This record will be updated with the finished sequence~"
             << "* as soon as it is available and the accession number will~"
             << "* be preserved."
             << "~"
             << summary.text;
    } else if ( tech == CMolInfo::eTech_htgs_2 ) {
        text << "* NOTE: This is a \"working draft\" sequence.";
        if ( summary.num_segs > 0 ) {
            text << " It currently~* consists of " << (summary.num_gaps + 1) 
                 << " contigs. Gaps between the contigs~"
                 << "* are represented as runs of N. The order of the pieces~"
                 << "* is believed to be correct as given, however the sizes~"
                 << "* of the gaps between them are based on estimates that have~"
                 << "* provided by the submittor.";
        }
        text << "~* This sequence will be replaced~"
             << "* by the finished sequence as soon as it is available and~"
             << "* the accession number will be preserved."
             << "~"
             << summary.text;
    } else if ( !GetTechString(tech).empty() ) {
        text << "Method: " << GetTechString(tech) << ".";
    }

    return CNcbiOstrstreamToString(text);
}


string CCommentItem::GetStringForModelEvidance(const SModelEvidance& me)
{
    CNcbiOstrstream text;

    text << "MODEL " << "REFSEQ" << ":  " << "This record is predicted by "
         << "automated computational analysis. This record is derived from"
         << "an annotated genomic sequence (" << me.name << ")";
    if ( !me.method.empty() ) {
        text << " using gene prediction method: " << me.method;
    }

    if ( me.mrnaEv  ||  me.estEv ) {
        text << ", supported by ";
        if ( me.mrnaEv  &&  me.estEv ) {
            text << "mRNA and EST ";
        } else if ( me.mrnaEv ) {
            text << "mRNA ";
        } else {
            text << "EST ";
        }
        // !!! for html we need much more !!!
        text << "evidence";
    }

    text << "." << ExpandTildes("~Also see:~    ", eTilde_newline) 
         << "Documentation" 
         << ExpandTildes(" of NCBI's Annotation Process~    ", eTilde_newline);

    return CNcbiOstrstreamToString(text);
}


/***************************************************************************/
/*                                 PROTECTED                               */
/***************************************************************************/


void CCommentItem::x_GatherInfo(CBioseqContext& ctx)
{
    const CSeqdesc* desc = dynamic_cast<const CSeqdesc*>(GetObject());
    if ( desc != 0 ) {
        x_GatherDescInfo(*desc);
        return;
    }

    const CSeq_feat* feat = dynamic_cast<const CSeq_feat*>(GetObject());
    if ( feat != 0 ) {
        x_GatherFeatInfo(*feat, ctx);
    }
}


void CCommentItem::x_GatherDescInfo(const CSeqdesc& desc)
{
    string prefix, str, suffix;
    switch ( desc.Which() ) {
    case CSeqdesc::e_Comment:
        {{
            str = desc.GetComment();
        }}
        break;

    case CSeqdesc::e_Maploc:
        {{
            const CDbtag& dbtag = desc.GetMaploc();
            if ( dbtag.CanGetTag() ) {
                const CObject_id& oid = dbtag.GetTag();
                if ( oid.IsStr() ) {
                    prefix = "Map location: ";
                    str = oid.GetStr();
                } else if ( oid.IsId()  &&  dbtag.CanGetDb() ) {
                    prefix = "Map location: (Database ";
                    str = dbtag.GetDb();
                    suffix = "; id # " + NStr::IntToString(oid.GetId()) + ").";
                }
            }
        }}
        break;

    case CSeqdesc::e_Region:
        {{
            prefix = "Region: ";
            str = desc.GetRegion();
        }}
        break;
    default:
        break;
    }

    if ( str.empty() ) {
        return;
    }
    x_SetCommentWithURLlinks(prefix, str, suffix);
    
}


void CCommentItem::x_GatherFeatInfo(const CSeq_feat&, CBioseqContext&)
{
    // !!!
}


void CCommentItem::x_SetSkip(void)
{
    CFlatItem::x_SetSkip();
    swap(m_First, sm_FirstComment);
}


void CCommentItem::x_SetCommentWithURLlinks
(const string& prefix,
 const string& str,
 const string& suffix)
{
    // !!! test for html - find links within the comment string
    string comment = ExpandTildes(prefix + str + suffix, eTilde_newline);
    size_t pos = comment.find_last_not_of(" \n\t\r");
    if ( pos != NPOS ) {
        comment.erase(pos + 1);
    }
    if ( NStr::EndsWith(str, "..")  &&  !NStr::EndsWith(str, "...") ) {
        comment.erase(str.length() - 1);
    }
    if ( !NStr::EndsWith(str, ".") ) {
        comment += ".";
    }
    
    m_Comment =  comment;
}


/////////////////////////////////////////////////////////////////////////////
//
// Derived Classes

// --- CGenomeAnnotComment

CGenomeAnnotComment::CGenomeAnnotComment
(CBioseqContext& ctx,
 const string& build_num) :
    CCommentItem(ctx), m_GenomeBuildNumber(build_num)
{
    x_GatherInfo(ctx);
}


void CGenomeAnnotComment::x_GatherInfo(CBioseqContext&)
{
    CNcbiOstrstream text;

    text << "GENOME ANNOTATION " << "REFSEQ" << ":  ";
    if ( !m_GenomeBuildNumber.empty() ) {
         text << "Features on this sequence have been produced for build "
              << m_GenomeBuildNumber << " of the NCBI's genome annotation"
              << " [see " << "documentation" << "].";
    } else {
        text << "NCBI contigs are derived from assembled genomic sequence data."
             << "~Also see:~    " << "Documentation" 
             << " of NCBI's Annotation Process~ ";
    }
    
    x_SetComment(ExpandTildes(CNcbiOstrstreamToString(text), eTilde_newline));
}


// --- CHistComment

CHistComment::CHistComment
(EType type,
 const CSeq_hist& hist,
 CBioseqContext& ctx) : 
    CCommentItem(ctx), m_Type(type), m_Hist(&hist)
{
    x_GatherInfo(ctx);
    m_Hist.Reset();
}


string s_CreateHistCommentString
(const string& prefix,
 const string& suffix,
 const CSeq_hist_rec& hist)
{
    _ASSERT(hist.CanGetDate());
    _ASSERT(hist.CanGetIds());

    string date;
    hist.GetDate().GetDate(&date, "%3N %2D, %4Y");

    vector<int> gis;
    ITERATE (CSeq_hist_rec::TIds, id, hist.GetIds()) {
        if ( (*id)->IsGi() ) {
            gis.push_back((*id)->GetGi());
        }
    }

    CNcbiOstrstream text;

    text << prefix << ((gis.size() > 1) ? " or before " : " ") << date 
         << ' ' << suffix;

    if ( gis.empty() ) {
        text << " gi:?";
        return CNcbiOstrstreamToString(text);
    }

    for ( size_t count = 0; count < gis.size(); ++count ) {
        if ( count != 0 ) {
            text << ",";
        }
        text << " gi:" << NStr::IntToString(gis[count]);
    }
    text << '.';

    return CNcbiOstrstreamToString(text);
}

void CHistComment::x_GatherInfo(CBioseqContext&)
{
    _ASSERT(m_Hist);

    switch ( m_Type ) {
    case eReplaced_by:
        x_SetComment(s_CreateHistCommentString(
            "[WARNING] On",
            "this sequence was replaced by a newer version",
            m_Hist->GetReplaced_by()));
        break;
    case eReplaces:
        x_SetComment(s_CreateHistCommentString(
            "On",
            "this sequence version replaced",
            m_Hist->GetReplaces()));
        break;
    }
}


// --- CGsdbComment

CGsdbComment::CGsdbComment(const CDbtag& dbtag, CBioseqContext& ctx) :
    CCommentItem(ctx), m_Dbtag(&dbtag)
{
    x_GatherInfo(ctx);
}


void CGsdbComment::x_GatherInfo(CBioseqContext&)
{
    x_SetComment("GSDB:S:" + m_Dbtag->GetTag().GetId());
}


// --- CLocalIdComment

CLocalIdComment::CLocalIdComment(const CObject_id& oid, CBioseqContext& ctx) :
    CCommentItem(ctx), m_Oid(&oid)
{
    x_GatherInfo(ctx);
}


void CLocalIdComment::x_GatherInfo(CBioseqContext&)
{
    CNcbiOstrstream msg;

    switch ( m_Oid->Which() ) {
    case CObject_id::e_Id:
        msg << "LocalID: " << m_Oid->GetId();    
        break;
    case CObject_id::e_Str:
        if ( m_Oid->GetStr().length() < 100 ) {
            msg << "LocalID: " << m_Oid->GetStr();
        } else {
            msg << "LocalID string too large";
        }
        break;
    default:
        break;
    }
    x_SetComment(CNcbiOstrstreamToString(msg));
}


END_SCOPE(objects)
END_NCBI_SCOPE


/*
* ===========================================================================
*
* $Log: comment_item.cpp,v $
* Revision 1000.2  2004/06/01 19:43:50  gouriano
* PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.8
*
* Revision 1.8  2004/05/21 21:42:54  gorelenk
* Added PCH ncbi_pch.hpp
*
* Revision 1.7  2004/05/06 17:45:43  shomrat
* + CLocalIdComment
*
* Revision 1.6  2004/04/22 15:51:13  shomrat
* Changes in context
*
* Revision 1.5  2004/04/13 16:45:22  shomrat
* Fixed comment cleanup
*
* Revision 1.4  2004/03/26 17:22:51  shomrat
* Minor fixes to comment string
*
* Revision 1.3  2004/03/05 18:44:05  shomrat
* fixed RefTRack comments
*
* Revision 1.2  2003/12/18 17:43:31  shomrat
* context.hpp moved
*
* Revision 1.1  2003/12/17 20:18:17  shomrat
* Initial Revision (adapted from flat lib)
*
*
* ===========================================================================
*/