reader_pubseq.cpp

来自「ncbi源码」· C++ 代码 · 共 772 行 · 第 1/2 页

    bool is_external = is_snp;
    bool load_external = is_external || !TrySNPSplit();
    CDB_Int ext_feat(load_external);

    _TRACE("x_SendRequest: "<<seqref.print()<<", ext_feat="<<load_external);

    cmd->SetParam("@gi", &giIn);
    cmd->SetParam("@sat_key", &satKeyIn);
    cmd->SetParam("@sat", &satIn);
    cmd->SetParam("@ext_feat", &ext_feat);
    cmd->Send();
    return cmd.release();
}


CDB_Result* CPubseqReader::x_ReceiveData(CDB_RPCCmd& cmd)
{
    // new row
    CDB_VarChar descrOut("-");
    CDB_Int classOut(0);
    CDB_Int confidential(0),withdrawn(0);
    
    while( cmd.HasMoreResults() ) {
        _TRACE("next result");
        if ( cmd.HasFailed() && confidential.Value()>0 ||
             withdrawn.Value()>0 ) {
            break;
        }
        
        auto_ptr<CDB_Result> result(cmd.Result());
        if ( !result.get() || result->ResultType() != eDB_RowResult ) {
            continue;
        }
        
        while ( result->Fetch() ) {
            _TRACE("next fetch: " << result->NofItems() << " items");
            for ( unsigned pos = 0; pos < result->NofItems(); ++pos ) {
                const string& name = result->ItemName(pos);
                _TRACE("next item: " << name);
                if ( name == "asn1" ) {
                    return result.release();
                }
                else if ( name == "confidential" ) {
                    result->GetItem(&confidential);
                }
                else if ( name == "override" ) {
                    result->GetItem(&withdrawn);
                }
                else {
                    result->SkipItem();
                }
            }
        }
    }
    if ( confidential.Value()>0 || withdrawn.Value()>0 ) {
        NCBI_THROW(CLoaderException, ePrivateData, "gi is private");
    }
    NCBI_THROW(CLoaderException, eNoData, "no data");
}


CRef<CTSE_Info> CPubseqReader::x_ReceiveMainBlob(CDB_Result& result)
{
    CRef<CSeq_entry> seq_entry(new CSeq_entry);

    CResultBtSrcRdr reader(&result);
    CObjectIStreamAsnBinary in(reader);
    
    CReader::SetSeqEntryReadHooks(in);
    in >> *seq_entry;

    return Ref(new CTSE_Info(*seq_entry));
}


CRef<CSeq_annot_SNP_Info> CPubseqReader::x_ReceiveSNPAnnot(CDB_Result& result)
{
    CRef<CSeq_annot_SNP_Info> snp_annot_info(new CSeq_annot_SNP_Info);
    
    {{
        CResultBtSrcRdr src(&result);
        CNlmZipBtRdr src2(&src);
        
        CObjectIStreamAsnBinary in(src2);
        
        CSeq_annot_SNP_Info_Reader::Parse(in, *snp_annot_info);
    }}
    
    return snp_annot_info;
}


CResultBtSrcRdr::CResultBtSrcRdr(CDB_Result* result)
    : m_Result(result)
{
}


CResultBtSrcRdr::~CResultBtSrcRdr()
{
}


size_t CResultBtSrcRdr::Read(char* buffer, size_t bufferLength)
{
    size_t ret;
    while ( (ret = m_Result->ReadItem(buffer, bufferLength)) == 0 ) {
        if ( !m_Result->Fetch() )
            break;
    }
    return ret;
}


END_SCOPE(objects)


const string kPubseqReaderDriverName("pubseq_reader");


/// Class factory for Pubseq reader
///
/// @internal
///
class CPubseqReaderCF : 
    public CSimpleClassFactoryImpl<objects::CReader, objects::CPubseqReader>
{
public:
    typedef CSimpleClassFactoryImpl<objects::CReader, 
                                    objects::CPubseqReader> TParent;
public:

    CPubseqReaderCF() : TParent(kPubseqReaderDriverName, 0)
    {
    }

    ~CPubseqReaderCF()
    {
    }
};

void NCBI_EntryPoint_ReaderPubseqos(
     CPluginManager<objects::CReader>::TDriverInfoList&   info_list,
     CPluginManager<objects::CReader>::EEntryPointRequest method)
{
    CHostEntryPointImpl<CPubseqReaderCF>::NCBI_EntryPointImpl(info_list, method);
}


END_NCBI_SCOPE


/*
* $Log: reader_pubseq.cpp,v $
* Revision 1000.1  2004/06/01 19:42:05  gouriano
* PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.52
*
* Revision 1.52  2004/05/21 21:42:52  gorelenk
* Added PCH ncbi_pch.hpp
*
* Revision 1.51  2004/02/18 14:01:26  dicuccio
* Added new satellites for TRACE_ASSM, TR_ASSM_CH.  Added support for overloading
* the ID1 named service
*
* Revision 1.50  2004/02/04 17:47:42  kuznets
* Fixed naming of entry points
*
* Revision 1.49  2004/01/22 20:10:38  vasilche
* 1. Splitted ID2 specs to two parts.
* ID2 now specifies only protocol.
* Specification of ID2 split data is moved to seqsplit ASN module.
* For now they are still reside in one resulting library as before - libid2.
* As the result split specific headers are now in objects/seqsplit.
* 2. Moved ID2 and ID1 specific code out of object manager.
* Protocol is processed by corresponding readers.
* ID2 split parsing is processed by ncbi_xreader library - used by all readers.
* 3. Updated OBJMGR_LIBS correspondingly.
*
* Revision 1.48  2004/01/20 16:55:28  vasilche
* Do more common check first.
*
* Revision 1.47  2004/01/13 21:54:50  vasilche
* Requrrected new version
*
* Revision 1.4  2004/01/13 16:55:57  vasilche
* CReader, CSeqref and some more classes moved from xobjmgr to separate lib.
* Headers moved from include/objmgr to include/objtools/data_loaders/genbank.
*
* Revision 1.3  2003/12/30 22:14:43  vasilche
* Updated genbank loader and readers plugins.
*
* Revision 1.45  2003/12/19 19:47:45  vasilche
* Added support for TRACE data, Seq-id ::= general { db "ti", tag id NNN }.
*
* Revision 1.44  2003/12/03 16:15:29  ucko
* Correct spelling of NCBI_Pubseq_ReaderEntryPoint.
*
* Revision 1.43  2003/12/03 14:30:03  kuznets
* Code clean up.
* Made use of driver name constant instead of immediate in-place string.
*
* Revision 1.42  2003/12/02 16:18:17  kuznets
* Added plugin manager support for CReader interface and implementaions
* (id1 reader, pubseq reader)
*
* Revision 1.41  2003/11/26 17:55:59  vasilche
* Implemented ID2 split in ID1 cache.
* Fixed loading of splitted annotations.
*
* Revision 1.40  2003/11/04 14:43:26  vasilche
* Load SNP only when bit 1 in ext_feat is set.
*
* Revision 1.39  2003/10/22 16:12:38  vasilche
* Added CLoaderException::eNoConnection.
* Added check for 'fail' state of ID1 connection stream.
* CLoaderException::eNoConnection will be rethrown from CGBLoader.
*
* Revision 1.38  2003/10/21 14:27:35  vasilche
* Added caching of gi -> sat,satkey,version resolution.
* SNP blobs are stored in cache in preprocessed format (platform dependent).
* Limit number of connections to GenBank servers.
* Added collection of ID1 loader statistics.
*
* Revision 1.37  2003/10/14 21:06:25  vasilche
* Fixed compression statistics.
* Disabled caching of SNP blobs.
*
* Revision 1.36  2003/09/30 16:22:02  vasilche
* Updated internal object manager classes to be able to load ID2 data.
* SNP blobs are loaded as ID2 split blobs - readers convert them automatically.
* Scope caches results of requests for data to data loaders.
* Optimized CSeq_id_Handle for gis.
* Optimized bioseq lookup in scope.
* Reduced object allocations in annotation iterators.
* CScope is allowed to be destroyed before other objects using this scope are
* deleted (feature iterators, bioseq handles etc).
* Optimized lookup for matching Seq-ids in CSeq_id_Mapper.
* Added 'adaptive' option to objmgr_demo application.
*
* Revision 1.35  2003/08/27 14:25:22  vasilche
* Simplified CCmpTSE class.
*
* Revision 1.34  2003/08/14 20:05:19  vasilche
* Simple SNP features are stored as table internally.
* They are recreated when needed using CFeat_CI.
*
* Revision 1.33  2003/07/24 20:35:16  vasilche
* Fix includes.
*
* Revision 1.32  2003/07/24 19:28:09  vasilche
* Implemented SNP split for ID1 loader.
*
* Revision 1.31  2003/07/18 20:27:54  vasilche
* Check if reference counting is working before trying ot use it.
*
* Revision 1.30  2003/07/17 22:23:27  vasilche
* Fixed unsigned <-> size_t argument.
*
* Revision 1.29  2003/07/17 20:07:56  vasilche
* Reduced memory usage by feature indexes.
* SNP data is loaded separately through PUBSEQ_OS.
* String compression for SNP data.
*
* Revision 1.28  2003/06/02 16:06:38  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 1.27  2003/05/13 20:14:40  vasilche
* Catching exceptions and reconnection were moved from readers to genbank loader.
*
* Revision 1.26  2003/04/24 16:12:38  vasilche
* Object manager internal structures are splitted more straightforward.
* Removed excessive header dependencies.
*
* Revision 1.25  2003/04/15 16:33:29  dicuccio
* Minor logic reorganization to appease MSVC - wasn't dealing well with a verbose
* cast
*
* Revision 1.24  2003/04/15 15:30:15  vasilche
* Added include <memory> when needed.
* Removed buggy buffer in printing methods.
* Removed unnecessary include of stream_util.hpp.
*
* Revision 1.23  2003/04/15 14:24:08  vasilche
* Changed CReader interface to not to use fake streams.
*
* Revision 1.22  2003/04/02 03:57:09  kimelman
* packet size tuning
*
* Revision 1.21  2003/03/03 20:34:51  vasilche
* Added NCBI_THREADS macro - it's opposite to NCBI_NO_THREADS.
* Avoid using _REENTRANT macro - use NCBI_THREADS instead.
*
* Revision 1.20  2003/03/01 22:26:56  kimelman
* performance fixes
*
* Revision 1.19  2003/01/18 08:42:25  kimelman
* 1.added SNP retrieval per M.DiCuccio request; 2.avoid gi relookup
*
* Revision 1.18  2002/12/30 23:36:22  vakatov
* CPubseqStreamBuf::underflow() -- strstream::freeze(false) to avoid mem.leak
*
* Revision 1.17  2002/12/26 20:53:41  dicuccio
* Minor tweaks to relieve compiler warnings in MSVC
*
* Revision 1.16  2002/09/19 20:05:44  vasilche
* Safe initialization of static mutexes
*
* Revision 1.15  2002/07/22 22:55:55  kimelman
* bugfixes: a) null termination added for text seqid strstream.
*           b) processing of failed request.
*
* Revision 1.14  2002/07/10 16:49:59  grichenk
* Removed CRef<CSeq_entry>, use pointer instead
*
* Revision 1.13  2002/06/04 17:18:33  kimelman
* memory cleanup :  new/delete/Cref rearrangements
*
* Revision 1.12  2002/05/09 21:40:59  kimelman
* MT tuning
*
* Revision 1.11  2002/05/06 03:28:47  vakatov
* OM/OM1 renaming
*
* Revision 1.10  2002/05/03 21:28:10  ucko
* Introduce T(Signed)SeqPos.
*
* Revision 1.9  2002/04/25 20:54:07  kimelman
* noise off
*
* Revision 1.8  2002/04/12 22:56:23  kimelman
* processing of ctlib fail
*
* Revision 1.7  2002/04/12 14:52:34  butanaev
* Typos fixed, code cleanup.
*
* Revision 1.6  2002/04/11 20:03:26  kimelman
* switch to pubseq
*
* Revision 1.5  2002/04/11 17:59:36  butanaev
* Typo fixed.
*
* Revision 1.4  2002/04/11 17:47:17  butanaev
* Switched to using dbapi driver manager.
*
* Revision 1.3  2002/04/10 22:47:56  kimelman
* added pubseq_reader as default one
*
* Revision 1.2  2002/04/09 16:10:57  ucko
* Split CStrStreamBuf out into a common location.
*
* Revision 1.1  2002/04/08 20:52:27  butanaev
* Added PUBSEQ reader.
*
* Revision 1.8  2002/04/03 18:37:33  butanaev
* Replaced DBLink with dbapi.
*
* Revision 1.7  2002/01/10 16:24:26  butanaev
* Fixed possible memory leaks.
*
* Revision 1.6  2001/12/21 15:01:49  butanaev
* Removed debug code, bug fixes.
*
* Revision 1.5  2001/12/19 19:42:13  butanaev
* Implemented construction of PUBSEQ blob stream, CPubseqReader family  interfaces.
*
* Revision 1.4  2001/12/14 20:48:07  butanaev
* Implemented fetching Seqrefs from PUBSEQ.
*
* Revision 1.3  2001/12/13 17:50:34  butanaev
* Adjusted for new interface changes.
*
* Revision 1.2  2001/12/12 22:08:58  butanaev
* Removed duplicate code, created frame for CPubseq* implementation.
*
*/