flat_feature.cpp

来自「ncbi源码」· C++ 代码 · 共 822 行 · 第 1/2 页

    DO_NOTE(gene_syn);
    DO_NOTE(trna_codons);
    DO_NOTE(prot_desc);
    DO_NOTE(prot_note);
    DO_NOTE(prot_comment);
    DO_NOTE(prot_method);
    DO_NOTE(figure);
    DO_NOTE(maploc);
    DO_NOTE(prot_conflict);
    DO_NOTE(prot_missing);
    DO_NOTE(seqfeat_note);
    DO_NOTE(exception_note);
    DO_NOTE(region);
    // DO_NOTE(selenocysteine);
    DO_NOTE(prot_names);
    DO_NOTE(bond);
    DO_NOTE(site);
    DO_NOTE(rrna_its);
    x_FormatNoteQual(eFQ_xtra_prod_quals, "xtra_products");
    x_FormatNoteQual(eFQ_modelev,         "model_evidence");

    DO_NOTE(go_component);
    DO_NOTE(go_function);
    DO_NOTE(go_process);
#undef DO_NOTE
        
    DO_QUAL(citation);

    DO_QUAL(number);

    DO_QUAL(pseudo);

    DO_QUAL(codon_start);

    DO_QUAL(anticodon);
    DO_QUAL(bound_moiety);
    DO_QUAL(clone);
    DO_QUAL(cons_splice);
    DO_QUAL(direction);
    DO_QUAL(function);
    DO_QUAL(evidence);
    DO_QUAL(exception);
    DO_QUAL(frequency);
    DO_QUAL(EC_number);
    x_FormatQual(eFQ_gene_map,    "map");
    x_FormatQual(eFQ_gene_allele, "allele");
    DO_QUAL(allele);
    DO_QUAL(map);
    DO_QUAL(mod_base);
    DO_QUAL(PCR_conditions);
    DO_QUAL(phenotype);
    DO_QUAL(rpt_family);
    DO_QUAL(rpt_type);
    DO_QUAL(rpt_unit);
    DO_QUAL(insertion_seq);
    DO_QUAL(transposon);
    DO_QUAL(usedin);

    // extra imports, actually...
    x_FormatQual(eFQ_illegal_qual, "illegal");

    DO_QUAL(replace);

    DO_QUAL(transl_except);
    DO_QUAL(transl_table);
    DO_QUAL(codon);
    DO_QUAL(organism);
    DO_QUAL(label);
    x_FormatQual(eFQ_cds_product, "product");
    DO_QUAL(protein_id);
    DO_QUAL(transcript_id);
    DO_QUAL(db_xref);
    x_FormatQual(eFQ_gene_xref, "db_xref");
    DO_QUAL(translation);
    DO_QUAL(transcription);
    DO_QUAL(peptide);
#undef DO_QUAL
}


void CFlattishSourceFeature::x_AddQuals(void) const
{
    const CSeqFeatData& data = m_Feat->GetData();
    _ASSERT(data.IsOrg()  ||  data.IsBiosrc());
    // add various generic qualifiers...
    x_AddQual(eSQ_mol_type,
              new CFlatMolTypeQV(m_Context->GetBiomol(), m_Context->GetMol()));
    if (m_Feat->IsSetComment()) {
        x_AddQual(eSQ_seqfeat_note, new CFlatStringQV(m_Feat->GetComment()));
    }
    if (m_Feat->IsSetTitle()) {
        x_AddQual(eSQ_label, new CFlatLabelQV(m_Feat->GetTitle()));
    }
    if (m_Feat->IsSetCit()) {
        x_AddQual(eSQ_citation, new CFlatPubSetQV(m_Feat->GetCit()));
    }
    if (m_Feat->IsSetDbxref()) {
        x_AddQual(eSQ_org_xref, new CFlatXrefQV(m_Feat->GetDbxref()));
    }
    switch (data.Which()) {
    case CSeqFeatData::e_Org:     x_AddQuals(data.GetOrg());     break;
    case CSeqFeatData::e_Biosrc:  x_AddQuals(data.GetBiosrc());  break;
    default: break; // can't happen, but some compilers warn anyway
    }
}


static ESourceQualifier s_OrgModToSlot(const COrgMod& om)
{
    switch (om.GetSubtype()) {
#define DO_ORGMOD(x) case COrgMod::eSubtype_##x:  return eSQ_##x;
        DO_ORGMOD(strain);
        DO_ORGMOD(substrain);
        DO_ORGMOD(type);
        DO_ORGMOD(subtype);
        DO_ORGMOD(variety);
        DO_ORGMOD(serotype);
        DO_ORGMOD(serogroup);
        DO_ORGMOD(serovar);
        DO_ORGMOD(cultivar);
        DO_ORGMOD(pathovar);
        DO_ORGMOD(chemovar);
        DO_ORGMOD(biovar);
        DO_ORGMOD(biotype);
        DO_ORGMOD(group);
        DO_ORGMOD(subgroup);
        DO_ORGMOD(isolate);
        DO_ORGMOD(common);
        DO_ORGMOD(acronym);
        DO_ORGMOD(dosage);
    case COrgMod::eSubtype_nat_host:  return eSQ_spec_or_nat_host;
        DO_ORGMOD(sub_species);
        DO_ORGMOD(specimen_voucher);
        DO_ORGMOD(authority);
        DO_ORGMOD(forma);
        DO_ORGMOD(forma_specialis);
        DO_ORGMOD(ecotype);
        DO_ORGMOD(synonym);
        DO_ORGMOD(anamorph);
        DO_ORGMOD(teleomorph);
        DO_ORGMOD(breed);
        DO_ORGMOD(gb_acronym);
        DO_ORGMOD(gb_anamorph);
        DO_ORGMOD(gb_synonym);
        DO_ORGMOD(old_lineage);
        DO_ORGMOD(old_name);
#undef DO_ORGMOD
    case COrgMod::eSubtype_other:  return eSQ_orgmod_note;
    default:                       return eSQ_none;
    }
}


void CFlattishSourceFeature::x_AddQuals(const COrg_ref& org) const
{
    {{
        string name;
        if (org.IsSetTaxname()) {
            name = org.GetTaxname();
        }
        if (name.empty()  &&  org.IsSetOrgname()) {
            org.GetOrgname().GetFlatName(name);
        }
        if (org.IsSetCommon()) {
            if (name.empty()) {
                name = org.GetCommon();
            }
            x_AddQual(eSQ_common_name, new CFlatStringQV(org.GetCommon()));
        }
        if ( !name.empty() ) {
            x_AddQual(eSQ_organism, new CFlatStringQV(name));
        }
    }}
    if (org.IsSetDb()) {
        x_AddQual(eSQ_db_xref, new CFlatXrefQV(org.GetDb()));
    }
    for (CTypeConstIterator<COrgMod> it(org);  it;  ++it) {
        ESourceQualifier slot = s_OrgModToSlot(*it);
        if (slot != eSQ_none) {
            x_AddQual(slot, new CFlatOrgModQV(*it));
        }
    }
}


static ESourceQualifier s_SubSourceToSlot(const CSubSource& ss)
{
    switch (ss.GetSubtype()) {
#define DO_SS(x) case CSubSource::eSubtype_##x:  return eSQ_##x;
        DO_SS(chromosome);
        DO_SS(map);
        DO_SS(clone);
        DO_SS(subclone);
        DO_SS(haplotype);
        DO_SS(genotype);
        DO_SS(sex);
        DO_SS(cell_line);
        DO_SS(cell_type);
        DO_SS(tissue_type);
        DO_SS(clone_lib);
        DO_SS(dev_stage);
        DO_SS(frequency);
        DO_SS(germline);
        DO_SS(rearranged);
        DO_SS(lab_host);
        DO_SS(pop_variant);
        DO_SS(tissue_lib);
        DO_SS(plasmid_name);
        DO_SS(transposon_name);
        DO_SS(insertion_seq_name);
        DO_SS(plastid_name);
        DO_SS(country);
        DO_SS(segment);
        DO_SS(endogenous_virus_name);
        DO_SS(transgenic);
        DO_SS(environmental_sample);
        DO_SS(isolation_source);
#undef DO_SS
    case CSubSource::eSubtype_other:  return eSQ_subsource_note;
    default:                          return eSQ_none;
    }
}


void CFlattishSourceFeature::x_AddQuals(const CBioSource& src) const
{
    x_AddQual(eSQ_organelle, new CFlatOrganelleQV(src.GetGenome()));
    x_AddQuals(src.GetOrg());
    ITERATE (CBioSource::TSubtype, it, src.GetSubtype()) {
        ESourceQualifier slot = s_SubSourceToSlot(**it);
        if (slot != eSQ_none) {
            x_AddQual(slot, new CFlatSubSourceQV(**it));
        }
    }
    x_AddQual(eSQ_focus, new CFlatBoolQV(src.IsSetIs_focus()));
}


void CFlattishSourceFeature::x_FormatQuals(void) const
{
    m_FF->SetQuals().reserve(m_Quals.size());

#define DO_QUAL(x) x_FormatQual(eSQ_##x, #x)
    DO_QUAL(organism);

    DO_QUAL(organelle);

    DO_QUAL(mol_type);

    DO_QUAL(strain);
    x_FormatQual(eSQ_substrain, "sub_strain");
    DO_QUAL(variety);
    DO_QUAL(serotype);
    DO_QUAL(serovar);
    DO_QUAL(cultivar);
    DO_QUAL(isolate);
    DO_QUAL(isolation_source);
    x_FormatQual(eSQ_spec_or_nat_host, "specific_host");
    DO_QUAL(sub_species);
    DO_QUAL(specimen_voucher);

    DO_QUAL(db_xref);
    x_FormatQual(eSQ_org_xref, "db_xref");

    DO_QUAL(chromosome);

    DO_QUAL(segment);

    DO_QUAL(map);
    DO_QUAL(clone);
    x_FormatQual(eSQ_subclone, "sub_clone");
    DO_QUAL(haplotype);
    DO_QUAL(sex);
    DO_QUAL(cell_line);
    DO_QUAL(cell_type);
    DO_QUAL(tissue_type);
    DO_QUAL(clone_lib);
    DO_QUAL(dev_stage);
    DO_QUAL(frequency);

    DO_QUAL(germline);
    DO_QUAL(rearranged);
    DO_QUAL(transgenic);
    DO_QUAL(environmental_sample);

    DO_QUAL(lab_host);
    DO_QUAL(pop_variant);
    DO_QUAL(tissue_lib);

    x_FormatQual(eSQ_plasmid_name,       "plasmid");
    x_FormatQual(eSQ_transposon_name,    "transposon");
    x_FormatQual(eSQ_insertion_seq_name, "insertion_seq");

    DO_QUAL(country);

    DO_QUAL(focus);

#define DO_NOTE(x) x_FormatNoteQual(eSQ_##x, #x)
    if (m_WasDesc) {
        DO_NOTE(seqfeat_note);
        DO_NOTE(orgmod_note);
        DO_NOTE(subsource_note);
    } else {
        DO_NOTE(unstructured);
    }

    DO_NOTE(type);
    DO_NOTE(subtype);
    DO_NOTE(serogroup);
    DO_NOTE(pathovar);
    DO_NOTE(chemovar);
    DO_NOTE(biovar);
    DO_NOTE(biotype);
    DO_NOTE(group);
    DO_NOTE(subgroup);
    DO_NOTE(common);
    DO_NOTE(acronym);
    DO_NOTE(dosage);

    DO_NOTE(authority);
    DO_NOTE(forma);
    DO_NOTE(forma_specialis);
    DO_NOTE(ecotype);
    DO_NOTE(synonym);
    DO_NOTE(anamorph);
    DO_NOTE(teleomorph);
    DO_NOTE(breed);

    DO_NOTE(genotype);
    x_FormatNoteQual(eSQ_plastid_name, "plastid");

    x_FormatNoteQual(eSQ_endogenous_virus_name, "endogenous_virus");

    if ( !m_WasDesc ) {
        DO_NOTE(seqfeat_note);
        DO_NOTE(orgmod_note);
        DO_NOTE(subsource_note);
    }

    x_FormatNoteQual(eSQ_common_name, "common");

    x_FormatNoteQual(eSQ_zero_orgmod, "?");
    x_FormatNoteQual(eSQ_one_orgmod,  "?");
    x_FormatNoteQual(eSQ_zero_subsrc, "?");
#undef DO_NOTE

    DO_QUAL(sequenced_mol);
    DO_QUAL(label);
    DO_QUAL(usedin);
    DO_QUAL(citation);
#undef DO_QUAL
}

END_SCOPE(objects)
END_NCBI_SCOPE

/*
* ===========================================================================
*
* $Log: flat_feature.cpp,v $
* Revision 1000.1  2004/06/01 19:43:05  gouriano
* PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.11
*
* Revision 1.11  2004/05/21 21:42:53  gorelenk
* Added PCH ncbi_pch.hpp
*
* Revision 1.10  2003/10/17 20:58:41  ucko
* Don't assume coding-region features have their "product" fields set.
*
* Revision 1.9  2003/10/16 20:21:53  ucko
* Fix a copy-and-paste error in CFlattishFeature::x_AddQuals
*
* Revision 1.8  2003/10/08 21:11:12  ucko
* Add a couple of accessors to IFlattishFeature for the GFF/GTF formatter.
*
* Revision 1.7  2003/07/22 18:04:13  dicuccio
* Fixed access of unset optional variables
*
* Revision 1.6  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 1.5  2003/04/24 16:15:58  vasilche
* Added missing includes and forward class declarations.
*
* 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  2003/03/11 15:37:51  kuznets
* iterate -> ITERATE
*
* Revision 1.2  2003/03/10 22:01:36  ucko
* Change SLegalImport::m_Name from string to const char* (needed by MSVC).
*
* Revision 1.1  2003/03/10 16:39:09  ucko
* Initial check-in of new flat-file generator
*
*
* ===========================================================================
*/