flat_head.cpp

来自「ncbi源码」· C++ 代码 · 共 759 行 · 第 1/2 页

            }
        }
        ITERATE (set<CBioseq_Handle>, it, sources) {
            m_DBSource.push_back(x_FormatDBSourceID
                                 (*FindBestChoice(it->GetBioseqCore()->GetId(),
                                                  s_ScoreForDBSource)));
        }
        if (sources.empty()) {
            m_DBSource.push_back(x_FormatDBSourceID(*id));
        }
        break;
    }
    default:
        m_DBSource.push_back("UNKNOWN");
    }
}


string CFlatHead::x_FormatDBSourceID(const CSeq_id& id) {
    switch (id.Which()) {
    case CSeq_id::e_Local:
    {
        const CObject_id& oi = id.GetLocal();
        return (oi.IsStr() ? oi.GetStr() : NStr::IntToString(oi.GetId()));
    }
    case CSeq_id::e_Gi:
        return "gi: " + NStr::IntToString(id.GetGi());
    case CSeq_id::e_Pdb:
    {
        const CPDB_seq_id& pdb = id.GetPdb();
        string s("pdb: "), sep;
        if ( !pdb.GetMol().Get().empty() ) {
            s += "molecule " + pdb.GetMol().Get();
            sep = ",";
        }
        if (pdb.GetChain() > 0) {
            s += sep + "chain " + NStr::IntToString(pdb.GetChain());
            sep = ",";
        }
        if (pdb.IsSetRel()) {
            s += sep + "release ";
            m_Context->GetFormatter().FormatDate(pdb.GetRel(), s);
            sep = ",";
        }
        return s;
    }
    default:
    {
        const CTextseq_id* tsid = id.GetTextseq_Id();
        if ( !tsid ) {
            return kEmptyStr;
        }
        string s, sep, comma;
        switch (id.Which()) {
        case CSeq_id::e_Embl:       s = "embl ";        comma = ",";  break;
        case CSeq_id::e_Other:      s = "REFSEQ: ";                   break;
        case CSeq_id::e_Swissprot:  s = "swissprot: ";  comma = ",";  break;
        case CSeq_id::e_Pir:        s = "pir: ";                      break;
        case CSeq_id::e_Prf:        s = "prf: ";                      break;
        default:                    break;
        }
        if (tsid->IsSetName()) {
            s += "locus " + tsid->GetName();
            sep = " ";
        } else {
            comma.erase();
        }
        if (tsid->IsSetAccession()) {
            string acc = tsid->GetAccession();
            if (tsid->IsSetVersion()) {
                acc += '.' + NStr::IntToString(tsid->GetVersion());
            }
            s += comma + sep + "accession "
                + m_Context->GetFormatter().GetAccnLink(acc);
            sep = " ";
        }
        if (tsid->IsSetRelease()) {
            s += sep + "release " + tsid->GetRelease();
        }
        if (id.IsSwissprot()) {
            s += ';';
        }
        return s;
    }
    }
}


void CFlatHead::x_AddPIRBlock(void)
{
    for (CSeqdesc_CI dsc(m_Context->GetHandle(), CSeqdesc::e_Pir);
         dsc;  ++dsc) {
        m_ProteinBlock = &*dsc;
        break;
    }
    if ( !m_ProteinBlock ) {
        return;
    }
    const CPIR_block& pir = m_ProteinBlock->GetPir();
    if (pir.IsSetHost()) {
        m_DBSource.push_back("host: " + pir.GetHost());
    }
    if (pir.IsSetSource()) {
        m_DBSource.push_back("source: " + pir.GetSource());
    }
    if (pir.IsSetSummary()) {
        m_DBSource.push_back("summary: " + pir.GetSummary());
    }
    if (pir.IsSetGenetic()) {
        m_DBSource.push_back("genetic: " + pir.GetGenetic());
    }
    if (pir.IsSetIncludes()) {
        m_DBSource.push_back("includes: " + pir.GetIncludes());
    }
    if (pir.IsSetPlacement()) {
        m_DBSource.push_back("placement: " + pir.GetPlacement());
    }
    if (pir.IsSetSuperfamily()) {
        m_DBSource.push_back("superfamily: " + pir.GetSuperfamily());
    }
    if (pir.IsSetCross_reference()) {
        m_DBSource.push_back("xref: " + pir.GetCross_reference());
    }
    if (pir.IsSetDate()) {
        m_DBSource.push_back("PIR dates: " + pir.GetDate());
    }
    if (pir.GetHad_punct()) {
        m_DBSource.push_back("punctuation in sequence");
    }
    if (pir.IsSetSeqref()) {
        list<string> xrefs;
        ITERATE (CPIR_block::TSeqref, it, pir.GetSeqref()) {
            const char* type = 0;
            switch ((*it)->Which()) {
            case CSeq_id::e_Genbank:    type = "genbank ";    break;
            case CSeq_id::e_Embl:       type = "embl ";       break;
            case CSeq_id::e_Pir:        type = "pir ";        break;
            case CSeq_id::e_Swissprot:  type = "swissprot ";  break;
            case CSeq_id::e_Gi:         type = "gi: ";        break;
            case CSeq_id::e_Ddbj:       type = "ddbj ";       break;
            case CSeq_id::e_Prf:        type = "prf ";        break;
            default:                    break;
            }
            if (type) {
                xrefs.push_back(type + (*it)->GetSeqIdString(true));
            }
        }
        if ( !xrefs.empty() ) {
            m_DBSource.push_back("xrefs: " + NStr::Join(xrefs, ", "));
        }
    }
    NON_CONST_ITERATE (list<string>, it, m_DBSource) {
        // The C version puts newlines before these for some reason
        *it += (&*it == &m_DBSource.back() ? '.' : ';');
    }
}


void CFlatHead::x_AddSPBlock(void)
{
    for (CSeqdesc_CI dsc(m_Context->GetHandle(), CSeqdesc::e_Sp);
         dsc;  ++dsc) {
        m_ProteinBlock = &*dsc;
        break;
    }
    if ( !m_ProteinBlock ) {
        return;
    }
    const CSP_block& sp = m_ProteinBlock->GetSp();
    switch (sp.GetClass()) {
    case CSP_block::eClass_standard:
        m_DBSource.push_back("class: standard.");
        break;
    case CSP_block::eClass_prelim:
        m_DBSource.push_back("class: preliminary.");
        break;
    default:
        break;
    }
    // laid out slightly differently from the C version, but I think that's
    // a bug in the latter (which runs some things together)
    if (sp.IsSetExtra_acc()  &&  !sp.GetExtra_acc().empty() ) {
        m_DBSource.push_back("extra_accessions:"
                             + NStr::Join(sp.GetExtra_acc(), ","));
    }
    if (sp.GetImeth()) {
        m_DBSource.push_back("seq starts with Met");
    }
    if (sp.IsSetPlasnm()  &&  !sp.GetPlasnm().empty() ) {
        m_DBSource.push_back("plasmid:" + NStr::Join(sp.GetPlasnm(), ","));
    }
    if (sp.IsSetCreated()) {
        string s("created: ");
        sp.GetCreated().GetDate(&s, "%3N %D %Y");
        m_DBSource.push_back(s + '.');
    }
    if (sp.IsSetSequpd()) {
        string s("sequence updated: ");
        sp.GetSequpd().GetDate(&s, "%3N %D %Y");
        m_DBSource.push_back(s + '.');
    }
    if (sp.IsSetAnnotupd()) {
        string s("annotation updated: ");
        sp.GetAnnotupd().GetDate(&s, "%3N %D %Y");
        m_DBSource.push_back(s + '.');
    }
    if (sp.IsSetSeqref()  &&  !sp.GetSeqref().empty() ) {
        list<string> xrefs;
        ITERATE (CSP_block::TSeqref, it, sp.GetSeqref()) {
            const char* s = 0;
            switch ((*it)->Which()) {
            case CSeq_id::e_Genbank:  s = "genbank accession ";          break;
            case CSeq_id::e_Embl:     s = "embl accession ";             break;
            case CSeq_id::e_Pir:      s = "pir locus ";                  break;
            case CSeq_id::e_Swissprot: s = "swissprot accession ";       break;
            case CSeq_id::e_Gi:       s = "gi: ";                        break;
            case CSeq_id::e_Ddbj:     s = "ddbj accession ";             break;
            case CSeq_id::e_Prf:      s = "prf accession ";              break;
            case CSeq_id::e_Pdb:      s = "pdb accession ";              break;
            case CSeq_id::e_Tpg:   s = "genbank third party accession "; break;
            case CSeq_id::e_Tpe:      s = "embl third party accession "; break;
            case CSeq_id::e_Tpd:      s = "ddbj third party accession "; break;
            default:                  break;
            }
            if (s) {
                string acc = (*it)->GetSeqIdString(true);
                xrefs.push_back(s +m_Context->GetFormatter().GetAccnLink(acc));
            }
        }
        if ( !xrefs.empty() ) {
            m_DBSource.push_back("xrefs: " + NStr::Join(xrefs, ", "));
        }
    }
    if (sp.IsSetDbref()  &&  !sp.GetDbref().empty() ) {
        list<string> xrefs;
        ITERATE (CSP_block::TDbref, it, sp.GetDbref()) {
            const CObject_id& tag = (*it)->GetTag();
            string            id  = (tag.IsStr() ? tag.GetStr()
                                     : NStr::IntToString(tag.GetId()));
            if ((*it)->GetDb() == "MIM") {
                xrefs.push_back
                    ("MIM <a href=\""
                     "http://www.ncbi.nlm.nih.gov/entrez/dispomim.cgi?id=" + id
                     + "\">" + id + "</a>");
            } else {
                xrefs.push_back((*it)->GetDb() + id); // no space(!)
            }
        }
        m_DBSource.push_back
            ("xrefs (non-sequence databases): " + NStr::Join(xrefs, ", "));
    }
}


void CFlatHead::x_AddPRFBlock(void)
{
    for (CSeqdesc_CI dsc(m_Context->GetHandle(), CSeqdesc::e_Prf);
         dsc;  ++dsc) {
        m_ProteinBlock = &*dsc;
        break;
    }
    if ( !m_ProteinBlock ) {
        return;
    }
    const CPRF_block& prf = m_ProteinBlock->GetPrf();
    if (prf.IsSetExtra_src()) {
        const CPRF_ExtraSrc& es = prf.GetExtra_src();
        if (es.IsSetHost()) {
            m_DBSource.push_back("host: " + es.GetHost());
        }
        if (es.IsSetPart()) {
            m_DBSource.push_back("part: " + es.GetPart());
        }
        if (es.IsSetState()) {
            m_DBSource.push_back("state: " + es.GetState());
        }
        if (es.IsSetStrain()) {
            m_DBSource.push_back("strain: " + es.GetStrain());
        }
        if (es.IsSetTaxon()) {
            m_DBSource.push_back("taxonomy: " + es.GetTaxon());
        }
    }
    NON_CONST_ITERATE (list<string>, it, m_DBSource) {
        *it += (&*it == &m_DBSource.back() ? '.' : ';');
    }
}


void CFlatHead::x_AddPDBBlock(void)
{
    for (CSeqdesc_CI dsc(m_Context->GetHandle(), CSeqdesc::e_Pdb);
         dsc;  ++dsc) {
        m_ProteinBlock = &*dsc;
        break;
    }
    if ( !m_ProteinBlock ) {
        return;
    }
    const CPDB_block& pdb = m_ProteinBlock->GetPdb();
    {{
        string s("deposition: ");
        m_Context->GetFormatter().FormatDate(pdb.GetDeposition(), s);
        m_DBSource.push_back(s);
    }}
    m_DBSource.push_back("class: " + pdb.GetClass());
    if (!pdb.GetSource().empty() ) {
        m_DBSource.push_back("source: " + NStr::Join(pdb.GetSource(), ", "));
    }
    if (pdb.IsSetExp_method()) {
        m_DBSource.push_back("Exp. method: " + pdb.GetExp_method());
    }
    if (pdb.IsSetReplace()) {
        const CPDB_replace& rep = pdb.GetReplace();
        if ( !rep.GetIds().empty() ) {
            m_DBSource.push_back
                ("ids replaced: " + NStr::Join(pdb.GetSource(), ", "));
        }
        string s("replacement date: ");
        m_Context->GetFormatter().FormatDate(rep.GetDate(), s);
        m_DBSource.push_back(s);
    }
    NON_CONST_ITERATE (list<string>, it, m_DBSource) {
        *it += (&*it == &m_DBSource.back() ? '.' : ';');
    }
}


END_SCOPE(objects)
END_NCBI_SCOPE

/*
* ===========================================================================
*
* $Log: flat_head.cpp,v $
* Revision 1000.2  2004/06/01 19:43:17  gouriano
* PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.8
*
* Revision 1.8  2004/05/21 21:42:53  gorelenk
* Added PCH ncbi_pch.hpp
*
* Revision 1.7  2004/04/05 15:56:15  grichenk
* Redesigned CAnnotTypes_CI: moved all data and data collecting
* functions to CAnnotDataCollector. CAnnotTypes_CI is no more
* inherited from SAnnotSelector.
*
* Revision 1.6  2003/07/22 18:04:13  dicuccio
* Fixed access of unset optional variables
*
* Revision 1.5  2003/06/02 16:06:42  dicuccio
* Rearranged src/objects/ subtree.  This includes the following shifts:
*     - src/objects/asn2asn --> arc/app/asn2asn
*     - src/objects/testmedline --> src/objects/ncbimime/test
*     - src/objects/objmgr --> src/objmgr
*     - src/objects/util --> src/objmgr/util
*     - src/objects/alnmgr --> src/objtools/alnmgr
*     - src/objects/flat --> src/objtools/flat
*     - src/objects/validator --> src/objtools/validator
*     - src/objects/cddalignview --> src/objtools/cddalignview
* In addition, libseq now includes six of the objects/seq... libs, and libmmdb
* replaces the three libmmdb? libs.
*
* Revision 1.4  2003/03/21 18:49:17  ucko
* Turn most structs into (accessor-requiring) classes; replace some
* formerly copied fields with pointers to the original data.
*
* Revision 1.3  2003/03/18 21:56:06  grichenk
* Removed obsolete class CAnnot_CI
*
* Revision 1.2  2003/03/11 15:37:51  kuznets
* iterate -> ITERATE
*
* Revision 1.1  2003/03/10 16:39:09  ucko
* Initial check-in of new flat-file generator
*
*
* ===========================================================================
*/