utilities.cpp

来自「ncbi源码」· C++ 代码 · 共 1,229 行 · 第 1/4 页

/*
 * ===========================================================================
 * PRODUCTION $Log: utilities.cpp,v $
 * PRODUCTION Revision 1000.2  2004/06/01 19:47:34  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.20
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: utilities.cpp,v 1000.2 2004/06/01 19:47:34 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
 *
 * File Description:
 *      Implementation of utility classes and functions.
 *
 */
#include <ncbi_pch.hpp>
#include <corelib/ncbistd.hpp>
#include <corelib/ncbistr.hpp>

#include <serial/enumvalues.hpp>
#include <serial/serialimpl.hpp>

#include <objects/seqloc/Seq_id.hpp>
#include <objects/seqfeat/SeqFeatData.hpp>
#include <objects/seqfeat/Gb_qual.hpp>
#include <objects/seqset/Seq_entry.hpp>
#include <objects/seqset/Bioseq_set.hpp>
#include <objects/seq/Bioseq.hpp>
#include <objmgr/bioseq_handle.hpp>
#include <objmgr/scope.hpp>
#include <objmgr/seq_vector.hpp>
#include <objmgr/util/sequence.hpp>

#include <vector>
#include <algorithm>
#include <list>

#include "utilities.hpp"

BEGIN_NCBI_SCOPE
BEGIN_SCOPE(objects)
BEGIN_SCOPE(validator)

// =============================================================================
//                           Enumeration of GBQual types
// =============================================================================


CGbqualType::EType CGbqualType::GetType(const string& qual)
{
    EType type;
    try {
        type = static_cast<EType>(GetTypeInfo_enum_EType()->FindValue(qual));
    } catch (runtime_error rt) {
        type = CGbqualType::e_Bad;
    }

    return type;
}


CGbqualType::EType CGbqualType::GetType(const CGb_qual& qual)
{
    return GetType(qual.GetQual());
}


const string& CGbqualType::GetString(CGbqualType::EType gbqual)
{
    return GetTypeInfo_enum_EType()->FindName(gbqual, true);
}

        
BEGIN_NAMED_ENUM_IN_INFO("", CGbqualType::, EType, false)
{
    ADD_ENUM_VALUE("bad",               e_Bad);
    ADD_ENUM_VALUE("allele",            e_Allele);
    ADD_ENUM_VALUE("anticodon",         e_Anticodon);
    ADD_ENUM_VALUE("bound_moiety",      e_Bound_moiety);
    ADD_ENUM_VALUE("citation",          e_Citation);
    ADD_ENUM_VALUE("clone",             e_Clone);
    ADD_ENUM_VALUE("codon",             e_Codon);
    ADD_ENUM_VALUE("codon_start",       e_Codon_start);
    ADD_ENUM_VALUE("cons_splice",       e_Cons_splice);
    ADD_ENUM_VALUE("direction",         e_Direction);
    ADD_ENUM_VALUE("EC_number",         e_EC_number);
    ADD_ENUM_VALUE("evidence",          e_Evidence);
    ADD_ENUM_VALUE("exception",         e_Exception);
    ADD_ENUM_VALUE("frequency",         e_Frequency);
    ADD_ENUM_VALUE("function",          e_Function);
    ADD_ENUM_VALUE("gene",              e_Gene);
    ADD_ENUM_VALUE("insertion_seq",     e_Insertion_seq);
    ADD_ENUM_VALUE("label",             e_Label);
    ADD_ENUM_VALUE("locus_tag",         e_Locus_tag);
    ADD_ENUM_VALUE("map",               e_Map);
    ADD_ENUM_VALUE("mod_base",          e_Mod_base);
    ADD_ENUM_VALUE("note",              e_Note);
    ADD_ENUM_VALUE("number",            e_Number);
    ADD_ENUM_VALUE("organism",          e_Organism);
    ADD_ENUM_VALUE("partial",           e_Partial);
    ADD_ENUM_VALUE("PCR_conditions",    e_PCR_conditions);
    ADD_ENUM_VALUE("phenotype",         e_Phenotype);
    ADD_ENUM_VALUE("product",           e_Product);
    ADD_ENUM_VALUE("replace",           e_Replace);
    ADD_ENUM_VALUE("rpt_family",        e_Rpt_family);
    ADD_ENUM_VALUE("rpt_type",          e_Rpt_type);
    ADD_ENUM_VALUE("rpt_unit",          e_Rpt_unit);
    ADD_ENUM_VALUE("site",              e_Site);
    ADD_ENUM_VALUE("site_type",         e_Site_type);
    ADD_ENUM_VALUE("standard_name",     e_Standard_name);
    ADD_ENUM_VALUE("transl_except",     e_Transl_except);
    ADD_ENUM_VALUE("transl_table",      e_Transl_table);
    ADD_ENUM_VALUE("translation",       e_Translation);
    ADD_ENUM_VALUE("transposon",        e_Transposon);
    ADD_ENUM_VALUE("usedin",            e_Usedin);
}
END_ENUM_INFO


// =============================================================================
//                        Associating Features and GBQuals
// =============================================================================


bool CFeatQualAssoc::IsLegalGbqual
(CSeqFeatData::ESubtype ftype,
 CGbqualType::EType gbqual) 
{
    return Instance()->IsLegal(ftype, gbqual);
}


const CFeatQualAssoc::TGBQualTypeVec& CFeatQualAssoc::GetMandatoryGbquals
(CSeqFeatData::ESubtype ftype)
{
    return Instance()->GetMandatoryQuals(ftype);
}


auto_ptr<CFeatQualAssoc> CFeatQualAssoc::sm_Instance;

bool CFeatQualAssoc::IsLegal
(CSeqFeatData::ESubtype ftype, 
 CGbqualType::EType gbqual)
{
    if ( m_LegalGbquals.find(ftype) != m_LegalGbquals.end() ) {
        if ( find( m_LegalGbquals[ftype].begin(), 
                   m_LegalGbquals[ftype].end(), 
                   gbqual) != m_LegalGbquals[ftype].end() ) {
            return true;
        }
    }
    return false;
}


const CFeatQualAssoc::TGBQualTypeVec& CFeatQualAssoc::GetMandatoryQuals
(CSeqFeatData::ESubtype ftype)
{
    static TGBQualTypeVec empty;

    if ( m_MandatoryGbquals.find(ftype) != m_MandatoryGbquals.end() ) {
        return m_MandatoryGbquals[ftype];
    }

    return empty;
}


CFeatQualAssoc* CFeatQualAssoc::Instance(void)
{
    if ( !sm_Instance.get() ) {
        sm_Instance.reset(new CFeatQualAssoc);
    }
    return sm_Instance.get();
}


CFeatQualAssoc::CFeatQualAssoc(void)
{
    PoplulateLegalGbquals();
    PopulateMandatoryGbquals();
}


void CFeatQualAssoc::Associate
(CSeqFeatData::ESubtype feat_subtype,
 CGbqualType::EType gbqual_type)
{
    // IMPORTANT: Bug in GCC compile prevent the code to be written as:
    //    m_LegalGbqual[feat_subtype].push_back(gbqual_type);
    TGBQualTypeVec& vec = m_LegalGbquals[feat_subtype];
    vec.push_back(gbqual_type);
}


void CFeatQualAssoc::PoplulateLegalGbquals(void)
{
    // gene
    Associate( CSeqFeatData::eSubtype_gene, CGbqualType::e_Allele );
    Associate( CSeqFeatData::eSubtype_gene, CGbqualType::e_Function );
    Associate( CSeqFeatData::eSubtype_gene, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_gene, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_gene, CGbqualType::e_Phenotype );
    Associate( CSeqFeatData::eSubtype_gene, CGbqualType::e_Product );
    Associate( CSeqFeatData::eSubtype_gene, CGbqualType::e_Standard_name );
    Associate( CSeqFeatData::eSubtype_gene, CGbqualType::e_Usedin );
    
 
    // CDS
    Associate( CSeqFeatData::eSubtype_cdregion, CGbqualType::e_Allele );
    Associate( CSeqFeatData::eSubtype_cdregion, CGbqualType::e_Codon );
    Associate( CSeqFeatData::eSubtype_cdregion, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_cdregion, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_cdregion, CGbqualType::e_Number );
    Associate( CSeqFeatData::eSubtype_cdregion, CGbqualType::e_Standard_name );
    Associate( CSeqFeatData::eSubtype_cdregion, CGbqualType::e_Usedin );

    // prot
    Associate( CSeqFeatData::eSubtype_prot, CGbqualType::e_Product );

    // preRNA
    Associate( CSeqFeatData::eSubtype_preRNA, CGbqualType::e_Allele );
    Associate( CSeqFeatData::eSubtype_preRNA, CGbqualType::e_Function );
    Associate( CSeqFeatData::eSubtype_preRNA, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_preRNA, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_preRNA, CGbqualType::e_Product );
    Associate( CSeqFeatData::eSubtype_preRNA, CGbqualType::e_Standard_name );
    Associate( CSeqFeatData::eSubtype_preRNA, CGbqualType::e_Usedin );

    // mRNA
    Associate( CSeqFeatData::eSubtype_mRNA, CGbqualType::e_Allele );
    Associate( CSeqFeatData::eSubtype_mRNA, CGbqualType::e_Function );
    Associate( CSeqFeatData::eSubtype_mRNA, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_mRNA, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_mRNA, CGbqualType::e_Product );
    Associate( CSeqFeatData::eSubtype_mRNA, CGbqualType::e_Standard_name );
    Associate( CSeqFeatData::eSubtype_mRNA, CGbqualType::e_Usedin );

    // tRNA
    Associate( CSeqFeatData::eSubtype_tRNA, CGbqualType::e_Function );
    Associate( CSeqFeatData::eSubtype_tRNA, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_tRNA, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_tRNA, CGbqualType::e_Product );
    Associate( CSeqFeatData::eSubtype_tRNA, CGbqualType::e_Standard_name );
    Associate( CSeqFeatData::eSubtype_tRNA, CGbqualType::e_Usedin );

    // rRNA
    Associate( CSeqFeatData::eSubtype_rRNA, CGbqualType::e_Function );
    Associate( CSeqFeatData::eSubtype_rRNA, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_rRNA, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_rRNA, CGbqualType::e_Product );
    Associate( CSeqFeatData::eSubtype_rRNA, CGbqualType::e_Standard_name );
    Associate( CSeqFeatData::eSubtype_rRNA, CGbqualType::e_Usedin );

    // snRNA
    Associate( CSeqFeatData::eSubtype_snRNA, CGbqualType::e_Function );
    Associate( CSeqFeatData::eSubtype_snRNA, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_snRNA, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_snRNA, CGbqualType::e_Product );
    Associate( CSeqFeatData::eSubtype_snRNA, CGbqualType::e_Standard_name );
    Associate( CSeqFeatData::eSubtype_snRNA, CGbqualType::e_Usedin );

    // scRNA
    Associate( CSeqFeatData::eSubtype_scRNA, CGbqualType::e_Function );
    Associate( CSeqFeatData::eSubtype_scRNA, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_scRNA, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_scRNA, CGbqualType::e_Product );
    Associate( CSeqFeatData::eSubtype_scRNA, CGbqualType::e_Standard_name );
    Associate( CSeqFeatData::eSubtype_scRNA, CGbqualType::e_Usedin );

    // otherRNA
    Associate( CSeqFeatData::eSubtype_otherRNA, CGbqualType::e_Function );
    Associate( CSeqFeatData::eSubtype_otherRNA, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_otherRNA, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_otherRNA, CGbqualType::e_Product );
    Associate( CSeqFeatData::eSubtype_otherRNA, CGbqualType::e_Standard_name );
    Associate( CSeqFeatData::eSubtype_otherRNA, CGbqualType::e_Usedin );

    // attenuator
    Associate( CSeqFeatData::eSubtype_attenuator, CGbqualType::e_Label );
    Associate( CSeqFeatData::eSubtype_attenuator, CGbqualType::e_Map );
    Associate( CSeqFeatData::eSubtype_attenuator, CGbqualType::e_Phenotype );