annot_object.cpp

来自「ncbi源码」· C++ 代码 · 共 606 行 · 第 1/2 页

                ERR_POST(Warning << "Invalid 'scores' size in denseg");
                numseg = min(numseg, (int)denseg.GetScores().size());
            }
            if (dim != (int)denseg.GetIds().size()) {
                ERR_POST(Warning << "Invalid 'ids' size in denseg");
                dim = min(dim, (int)denseg.GetIds().size());
            }
            if (dim*numseg != (int)denseg.GetStarts().size()) {
                ERR_POST(Warning << "Invalid 'starts' size in denseg");
                dim = min(dim*numseg, (int)denseg.GetStarts().size()) / numseg;
            }
            if (denseg.IsSetStrands()
                && dim*numseg != (int)denseg.GetStrands().size()) {
                ERR_POST(Warning << "Invalid 'strands' size in denseg");
                dim = min(dim*numseg, (int)denseg.GetStrands().size()) / numseg;
            }
            if (hrmaps.size() < loc_index_shift + dim) {
                hrmaps.resize(loc_index_shift + dim);
            }
            for (int seg = 0;  seg < numseg;  seg++) {
                for (int row = 0;  row < dim;  row++) {
                    if (denseg.GetStarts()[seg*dim + row] < 0 ) {
                        continue;
                    }
                    CSeq_loc loc;
                    loc.SetInt().SetId().Assign(*denseg.GetIds()[row]);
                    loc.SetInt().SetFrom(denseg.GetStarts()[seg*dim + row]);
                    loc.SetInt().SetTo(denseg.GetStarts()[seg*dim + row]
                        + denseg.GetLens()[seg] - 1);
                    if ( denseg.IsSetStrands() ) {
                        loc.SetInt().SetStrand(denseg.GetStrands()[seg*dim + row]);
                    }
                    hrmaps[loc_index_shift + row].AddLocation(loc);
                }
            }
            break;
        }
    case CSeq_align::C_Segs::e_Std:
        {
            const CSeq_align::C_Segs::TStd& std =
                align.GetSegs().GetStd();
            ITERATE ( CSeq_align::C_Segs::TStd, it, std ) {
                if (hrmaps.size() < loc_index_shift + (*it)->GetDim()) {
                    hrmaps.resize(loc_index_shift + (*it)->GetDim());
                }
                ITERATE ( CStd_seg::TLoc, it_loc, (*it)->GetLoc() ) {
                    CSeq_loc_CI row_it(**it_loc);
                    for (int row = 0; row_it; ++row_it, ++row) {
                        if (loc_index_shift + row >= hrmaps.size()) {
                            hrmaps.resize(loc_index_shift + row + 1);
                        }
                        CSeq_loc loc;
                        loc.SetInt().SetId().Assign(row_it.GetSeq_id());
                        loc.SetInt().SetFrom(row_it.GetRange().GetFrom());
                        loc.SetInt().SetTo(row_it.GetRange().GetTo());
                        if ( row_it.GetStrand() != eNa_strand_unknown ) {
                            loc.SetInt().SetStrand(row_it.GetStrand());
                        }
                        hrmaps[loc_index_shift + row].AddLocation(loc);
                    }
                }
            }
            break;
        }
    case CSeq_align::C_Segs::e_Packed:
        {
            const CSeq_align::C_Segs::TPacked& packed =
                align.GetSegs().GetPacked();
            int dim    = packed.GetDim();
            int numseg = packed.GetNumseg();
            // claimed dimension may not be accurate :-/
            if (dim * numseg > (int)packed.GetStarts().size()) {
                dim = packed.GetStarts().size() / numseg;
            }
            if (dim * numseg > (int)packed.GetPresent().size()) {
                dim = packed.GetPresent().size() / numseg;
            }
            if (dim > (int)packed.GetLens().size()) {
                dim = packed.GetLens().size();
            }
            if (hrmaps.size() < loc_index_shift + dim) {
                hrmaps.resize(loc_index_shift + dim);
            }
            for (int seg = 0;  seg < numseg;  seg++) {
                for (int row = 0;  row < dim;  row++) {
                    if ( packed.GetPresent()[seg*dim + row] ) {
                        CSeq_loc loc;
                        loc.SetInt().SetId().Assign(*packed.GetIds()[row]);
                        loc.SetInt().SetFrom(packed.GetStarts()[seg*dim + row]);
                        loc.SetInt().SetTo(packed.GetStarts()[seg*dim + row]
                            + packed.GetLens()[seg] - 1);
                        if ( packed.IsSetStrands() ) {
                            loc.SetInt().SetStrand(packed.GetStrands()[seg*dim + row]);
                        }
                        hrmaps[loc_index_shift + row].AddLocation(loc);
                    }
                }
            }
            break;
        }
    case CSeq_align::C_Segs::e_Disc:
        {
            const CSeq_align::C_Segs::TDisc& disc =
                align.GetSegs().GetDisc();
            ITERATE ( CSeq_align_set::Tdata, it, disc.Get() ) {
                x_ProcessAlign(hrmaps, **it, hrmaps.size());
            }
            break;
        }
    }
}


END_SCOPE(objects)
END_NCBI_SCOPE

/*
* ---------------------------------------------------------------------------
* $Log: annot_object.cpp,v $
* Revision 1000.3  2004/06/01 19:22:36  gouriano
* PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.39
*
* Revision 1.39  2004/05/26 14:29:20  grichenk
* Redesigned CSeq_align_Mapper: preserve non-mapping intervals,
* fixed strands handling, improved performance.
*
* Revision 1.38  2004/05/21 21:42:12  gorelenk
* Added PCH ncbi_pch.hpp
*
* Revision 1.37  2004/04/01 20:33:58  grichenk
* One more m_MultiId initialization
*
* Revision 1.36  2004/04/01 20:18:12  grichenk
* Added initialization of m_MultiId member.
*
* Revision 1.35  2004/03/31 20:43:29  grichenk
* Fixed mapping of seq-locs containing both master sequence
* and its segments.
*
* Revision 1.34  2004/03/26 19:42:04  vasilche
* Fixed premature deletion of SNP annot info object.
* Removed obsolete references to chunk info.
*
* Revision 1.33  2004/03/16 15:47:27  vasilche
* Added CBioseq_set_Handle and set of EditHandles
*
* Revision 1.32  2004/02/04 18:05:38  grichenk
* Added annotation filtering by set of types/subtypes.
* Renamed *Choice to *Type in SAnnotSelector.
*
* Revision 1.31  2004/01/23 16:14:47  grichenk
* Implemented alignment mapping
*
* Revision 1.30  2004/01/22 20:10:40  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 1.29  2003/11/26 17:55:56  vasilche
* Implemented ID2 split in ID1 cache.
* Fixed loading of splitted annotations.
*
* Revision 1.28  2003/10/07 13:43:23  vasilche
* Added proper handling of named Seq-annots.
* Added feature search from named Seq-annots.
* Added configurable adaptive annotation search (default: gene, cds, mrna).
* Fixed selection of blobs for loading from GenBank.
* Added debug checks to CSeq_id_Mapper for easier finding lost CSeq_id_Handles.
* Fixed leaked split chunks annotation stubs.
* Moved some classes definitions in separate *.cpp files.
*
* Revision 1.27  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 1.26  2003/08/27 21:24:51  vasilche
* Reordered member initializers.
*
* Revision 1.25  2003/08/27 14:29:52  vasilche
* Reduce object allocations in feature iterator.
*
* Revision 1.24  2003/08/26 21:28:47  grichenk
* Added seq-align verification
*
* Revision 1.23  2003/07/18 16:58:23  grichenk
* Fixed alignment coordinates
*
* Revision 1.22  2003/07/17 20:07:55  vasilche
* Reduced memory usage by feature indexes.
* SNP data is loaded separately through PUBSEQ_OS.
* String compression for SNP data.
*
* Revision 1.21  2003/06/02 16:06:37  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 1.20  2003/04/24 16:12:38  vasilche
* Object manager internal structures are splitted more straightforward.
* Removed excessive header dependencies.
*
* Revision 1.19  2003/03/11 15:51:06  kuznets
* iterate -> ITERATE
*
* Revision 1.18  2003/02/24 18:57:22  vasilche
* Make feature gathering in one linear pass using CSeqMap iterator.
* Do not use feture index by sub locations.
* Sort features at the end of gathering in one vector.
* Extracted some internal structures and classes in separate header.
* Delay creation of mapped features.
*
* Revision 1.17  2003/02/13 14:34:34  grichenk
* Renamed CAnnotObject -> CAnnotObject_Info
* + CSeq_annot_Info and CAnnotObject_Ref
* Moved some members of CAnnotObject to CSeq_annot_Info
* and CAnnotObject_Ref.
* Added feat/align/graph to CAnnotObject_Info map
* to CDataSource.
*
* Revision 1.16  2003/02/04 18:53:36  dicuccio
* Include file clean-up
*
* Revision 1.15  2003/01/22 20:11:54  vasilche
* Merged functionality of CSeqMapResolved_CI to CSeqMap_CI.
* CSeqMap_CI now supports resolution and iteration over sequence range.
* Added several caches to CScope.
* Optimized CSeqVector().
* Added serveral variants of CBioseqHandle::GetSeqVector().
* Tried to optimize annotations iterator (not much success).
* Rewritten CHandleRange and CHandleRangeMap classes to avoid sorting of list.
*
* Revision 1.14  2002/09/13 15:20:30  dicuccio
* Fix memory leak (static deleted before termination).
*
* Revision 1.13  2002/09/11 16:08:26  dicuccio
* Fixed memory leak in x_PrepareAlign().
*
* Revision 1.12  2002/09/03 17:45:45  ucko
* Avoid overrunning alignment data when the claimed dimensions are too high.
*
* Revision 1.11  2002/07/25 15:01:51  grichenk
* Replaced non-const GetXXX() with SetXXX()
*
* Revision 1.10  2002/07/08 20:51:00  grichenk
* Moved log to the end of file
* Replaced static mutex (in CScope, CDataSource) with the mutex
* pool. Redesigned CDataSource data locking.
*
* Revision 1.9  2002/07/01 15:31:57  grichenk
* Fixed 'enumeration value e_not_set...' warning
*
* Revision 1.8  2002/05/29 21:21:13  gouriano
* added debug dump
*
* Revision 1.7  2002/05/24 14:57:12  grichenk
* SerialAssign<>() -> CSerialObject::Assign()
*
* Revision 1.6  2002/05/03 21:28:08  ucko
* Introduce T(Signed)SeqPos.
*
* Revision 1.5  2002/04/05 21:26:19  grichenk
* Enabled iteration over annotations defined on segments of a
* delta-sequence.
*
* Revision 1.4  2002/02/21 19:27:04  grichenk
* Rearranged includes. Added scope history. Added searching for the
* best seq-id match in data sources and scopes. Updated tests.
*
* Revision 1.3  2002/01/23 21:59:31  grichenk
* Redesigned seq-id handles and mapper
*
* Revision 1.2  2002/01/16 16:25:56  gouriano
* restructured objmgr
*
* Revision 1.1  2002/01/11 19:06:16  gouriano
* restructured objmgr
*
*
* ===========================================================================
*/