validatorp.hpp

来自「ncbi源码」· HPP 代码 · 共 1,149 行 · 第 1/3 页

/*
 * ===========================================================================
 * PRODUCTION $Log: validatorp.hpp,v $
 * PRODUCTION Revision 1000.3  2004/06/01 19:47:42  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.64
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: validatorp.hpp,v 1000.3 2004/06/01 19:47:42 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:  Jonathan Kans, Clifford Clausen, Aaron Ucko......
 *
 * File Description:
 *   Privae classes and definition for the validator
 *   .......
 *
 */

#ifndef VALIDATOR___VALIDATORP__HPP
#define VALIDATOR___VALIDATORP__HPP

#include <corelib/ncbistd.hpp>

#include <objmgr/scope.hpp>
#include <objmgr/feat_ci.hpp>  // for CMappedFeat
#include <objects/seqset/Bioseq_set.hpp>
#include <objects/seq/GIBB_mol.hpp>
#include <util/strsearch.hpp>
#include <objects/seqfeat/Seq_feat.hpp>
#include <objects/seqalign/Seq_align.hpp>
#include <objects/seqalign/Std_seg.hpp>
#include <objects/seqalign/Packed_seg.hpp>

#include <objtools/validator/validator.hpp>

BEGIN_NCBI_SCOPE
BEGIN_SCOPE(objects)

class CSeq_entry;
class CCit_sub;
class CCit_art;
class CCit_gen;
class CSeq_feat;
class CBioseq;
class CSeqdesc;
class CSeq_annot;
class CTrna_ext;
class CProt_ref;
class CSeq_loc;
class CFeat_CI;
class CPub_set;
class CAuthor;
class CTitle;
class CDesc_CI;
class CMolInfo;
class CUser_object;
class CSeqdesc_CI;
class CSeq_graph;
class CMappedGraph;
class CDense_diag;
class CDense_seg;
class CSeq_align_set;
class CPubdesc;
class CBioSource;
class COrg_ref;
class CByte_graph;
class CDelta_seq;
class CSeqFeatData;
class CGene_ref;
class CCdregion;
class CRNA_ref;
class CImp_feat;
class CSeq_literal;
class CBioseq_Handle;


BEGIN_SCOPE(validator)


// ===========================  Internal error types  ==========================

enum EErrType {
    eErr_ALL = 0,

    eErr_SEQ_INST_ExtNotAllowed,
    eErr_SEQ_INST_ExtBadOrMissing,
    eErr_SEQ_INST_SeqDataNotFound,
    eErr_SEQ_INST_SeqDataNotAllowed,
    eErr_SEQ_INST_ReprInvalid,
    eErr_SEQ_INST_CircularProtein,
    eErr_SEQ_INST_DSProtein,
    eErr_SEQ_INST_MolNotSet,
    eErr_SEQ_INST_MolOther,
    eErr_SEQ_INST_FuzzyLen,
    eErr_SEQ_INST_InvalidLen,
    eErr_SEQ_INST_InvalidAlphabet,
    eErr_SEQ_INST_SeqDataLenWrong,
    eErr_SEQ_INST_SeqPortFail,
    eErr_SEQ_INST_InvalidResidue,
    eErr_SEQ_INST_StopInProtein,
    eErr_SEQ_INST_PartialInconsistent,
    eErr_SEQ_INST_ShortSeq,
    eErr_SEQ_INST_NoIdOnBioseq,
    eErr_SEQ_INST_BadDeltaSeq,
    eErr_SEQ_INST_LongHtgsSequence,
    eErr_SEQ_INST_LongLiteralSequence,
    eErr_SEQ_INST_SequenceExceeds350kbp,
    eErr_SEQ_INST_ConflictingIdsOnBioseq,
    eErr_SEQ_INST_MolNuclAcid,
    eErr_SEQ_INST_ConflictingBiomolTech,
    eErr_SEQ_INST_SeqIdNameHasSpace,
    eErr_SEQ_INST_IdOnMultipleBioseqs,
    eErr_SEQ_INST_DuplicateSegmentReferences,
    eErr_SEQ_INST_TrailingX,
    eErr_SEQ_INST_BadSeqIdFormat,
    eErr_SEQ_INST_PartsOutOfOrder,
    eErr_SEQ_INST_BadSecondaryAccn,
    eErr_SEQ_INST_ZeroGiNumber,
    eErr_SEQ_INST_RnaDnaConflict,
    eErr_SEQ_INST_HistoryGiCollision,
    eErr_SEQ_INST_GiWithoutAccession,
    eErr_SEQ_INST_MultipleAccessions,
    eErr_SEQ_INST_HistAssemblyMissing,
    eErr_SEQ_INST_TerminalNs,
    eErr_SEQ_INST_UnexpectedIdentifierChange,
    eErr_SEQ_INST_InternalNsInSeqLit,
    eErr_SEQ_INST_SeqLitGapLength0,
    eErr_SEQ_INST_TpaAssmeblyProblem,
    eErr_SEQ_INST_SeqLocLength,

    eErr_SEQ_DESCR_BioSourceMissing,
    eErr_SEQ_DESCR_InvalidForType,
    eErr_SEQ_DESCR_FileOpenCollision,
    eErr_SEQ_DESCR_Unknown,
    eErr_SEQ_DESCR_NoPubFound,
    eErr_SEQ_DESCR_NoOrgFound,
    eErr_SEQ_DESCR_MultipleBioSources,
    eErr_SEQ_DESCR_NoMolInfoFound,
    eErr_SEQ_DESCR_BadCountryCode,
    eErr_SEQ_DESCR_NoTaxonID,
    eErr_SEQ_DESCR_InconsistentBioSources,
    eErr_SEQ_DESCR_MissingLineage,
    eErr_SEQ_DESCR_SerialInComment,
    eErr_SEQ_DESCR_BioSourceNeedsFocus,
    eErr_SEQ_DESCR_BadOrganelle,
    eErr_SEQ_DESCR_MultipleChromosomes,
    eErr_SEQ_DESCR_BadSubSource,
    eErr_SEQ_DESCR_BadOrgMod,
    eErr_SEQ_DESCR_InconsistentProteinTitle,
    eErr_SEQ_DESCR_Inconsistent,
    eErr_SEQ_DESCR_ObsoleteSourceLocation,
    eErr_SEQ_DESCR_ObsoleteSourceQual,
    eErr_SEQ_DESCR_StructuredSourceNote,
    eErr_SEQ_DESCR_MultipleTitles,
    eErr_SEQ_DESCR_Obsolete,
    eErr_SEQ_DESCR_UnnecessaryBioSourceFocus,
    eErr_SEQ_DESCR_RefGeneTrackingWithoutStatus,
    eErr_SEQ_DESCR_UnwantedCompleteFlag,

    eErr_GENERIC_NonAsciiAsn,
    eErr_GENERIC_Spell,
    eErr_GENERIC_AuthorListHasEtAl,
    eErr_GENERIC_MissingPubInfo,
    eErr_GENERIC_UnnecessaryPubEquiv,
    eErr_GENERIC_BadPageNumbering,

    eErr_SEQ_PKG_NoCdRegionPtr,
    eErr_SEQ_PKG_NucProtProblem,
    eErr_SEQ_PKG_SegSetProblem,
    eErr_SEQ_PKG_EmptySet,
    eErr_SEQ_PKG_NucProtNotSegSet,
    eErr_SEQ_PKG_SegSetNotParts,
    eErr_SEQ_PKG_SegSetMixedBioseqs,
    eErr_SEQ_PKG_PartsSetMixedBioseqs,
    eErr_SEQ_PKG_PartsSetHasSets,
    eErr_SEQ_PKG_FeaturePackagingProblem,
    eErr_SEQ_PKG_GenomicProductPackagingProblem,
    eErr_SEQ_PKG_InconsistentMolInfoBiomols,
    eErr_SEQ_PKG_GraphPackagingProblem,

    eErr_SEQ_FEAT_InvalidForType,
    eErr_SEQ_FEAT_PartialProblem,
    eErr_SEQ_FEAT_PartialsInconsistent,
    eErr_SEQ_FEAT_InvalidType,
    eErr_SEQ_FEAT_Range,
    eErr_SEQ_FEAT_MixedStrand,
    eErr_SEQ_FEAT_SeqLocOrder,
    eErr_SEQ_FEAT_CdTransFail,
    eErr_SEQ_FEAT_StartCodon,
    eErr_SEQ_FEAT_InternalStop,
    eErr_SEQ_FEAT_NoProtein,
    eErr_SEQ_FEAT_MisMatchAA,
    eErr_SEQ_FEAT_TransLen,
    eErr_SEQ_FEAT_NoStop,
    eErr_SEQ_FEAT_TranslExcept,
    eErr_SEQ_FEAT_NoProtRefFound,
    eErr_SEQ_FEAT_NotSpliceConsensus,
    eErr_SEQ_FEAT_OrfCdsHasProduct,
    eErr_SEQ_FEAT_GeneRefHasNoData,
    eErr_SEQ_FEAT_ExceptInconsistent,
    eErr_SEQ_FEAT_ProtRefHasNoData,
    eErr_SEQ_FEAT_GenCodeMismatch,
    eErr_SEQ_FEAT_RNAtype0,
    eErr_SEQ_FEAT_UnknownImpFeatKey,
    eErr_SEQ_FEAT_UnknownImpFeatQual,
    eErr_SEQ_FEAT_WrongQualOnImpFeat,
    eErr_SEQ_FEAT_MissingQualOnImpFeat,
    eErr_SEQ_FEAT_PsuedoCdsHasProduct,
    eErr_SEQ_FEAT_IllegalDbXref,
    eErr_SEQ_FEAT_FarLocation,
    eErr_SEQ_FEAT_DuplicateFeat,
    eErr_SEQ_FEAT_UnnecessaryGeneXref,
    eErr_SEQ_FEAT_TranslExceptPhase,
    eErr_SEQ_FEAT_TrnaCodonWrong,
    eErr_SEQ_FEAT_BadTrnaAA,
    eErr_SEQ_FEAT_BothStrands,
    eErr_SEQ_FEAT_CDSgeneRange,
    eErr_SEQ_FEAT_CDSmRNArange,
    eErr_SEQ_FEAT_OverlappingPeptideFeat,
    eErr_SEQ_FEAT_SerialInComment,
    eErr_SEQ_FEAT_MultipleCDSproducts,
    eErr_SEQ_FEAT_FocusOnBioSourceFeature,
    eErr_SEQ_FEAT_PeptideFeatOutOfFrame,
    eErr_SEQ_FEAT_InvalidQualifierValue,
    eErr_SEQ_FEAT_MultipleMRNAproducts,
    eErr_SEQ_FEAT_mRNAgeneRange,
    eErr_SEQ_FEAT_TranscriptLen,
    eErr_SEQ_FEAT_TranscriptMismatches,
    eErr_SEQ_FEAT_CDSproductPackagingProblem,
    eErr_SEQ_FEAT_DuplicateInterval,
    eErr_SEQ_FEAT_PolyAsiteNotPoint,
    eErr_SEQ_FEAT_ImpFeatBadLoc,
    eErr_SEQ_FEAT_LocOnSegmentedBioseq,
    eErr_SEQ_FEAT_UnnecessaryCitPubEquiv,
    eErr_SEQ_FEAT_ImpCDShasTranslation,
    eErr_SEQ_FEAT_ImpCDSnotPseudo,
    eErr_SEQ_FEAT_MissingMRNAproduct,
    eErr_SEQ_FEAT_AbuttingIntervals,
    eErr_SEQ_FEAT_CollidingGeneNames,
    eErr_SEQ_FEAT_CollidingLocusTags,
    eErr_SEQ_FEAT_MultiIntervalGene,
    eErr_SEQ_FEAT_FeatContentDup,
    eErr_SEQ_FEAT_BadProductSeqId,
    eErr_SEQ_FEAT_RnaProductMismatch,
    eErr_SEQ_FEAT_DifferntIdTypesInSeqLoc,
    eErr_SEQ_FEAT_MissingCDSproduct,
    eErr_SEQ_FEAT_MissingLocation,
    eErr_SEQ_FEAT_OnlyGeneXrefs,
    eErr_SEQ_FEAT_UTRdoesNotAbutCDS,
    eErr_SEQ_FEAT_MultipleCdsOnMrna,
    eErr_SEQ_FEAT_BadConflictFlag,
    eErr_SEQ_FEAT_ConflictFlagSet,
    eErr_SEQ_FEAT_LocusTagProblem,
    eErr_SEQ_FEAT_AltStartCodon,
    eErr_SEQ_FEAT_GenesInconsistent,

    eErr_SEQ_ALIGN_SeqIdProblem,
    eErr_SEQ_ALIGN_StrandRev,
    eErr_SEQ_ALIGN_DensegLenStart,
    eErr_SEQ_ALIGN_StartMorethanBiolen,
    eErr_SEQ_ALIGN_EndMorethanBiolen,
    eErr_SEQ_ALIGN_LenMorethanBiolen,
    eErr_SEQ_ALIGN_SumLenStart,
    eErr_SEQ_ALIGN_SegsDimMismatch,
    eErr_SEQ_ALIGN_SegsNumsegMismatch,
    eErr_SEQ_ALIGN_SegsStartsMismatch,
    eErr_SEQ_ALIGN_SegsPresentMismatch,
    eErr_SEQ_ALIGN_SegsPresentStartsMismatch,
    eErr_SEQ_ALIGN_SegsPresentStrandsMismatch,
    eErr_SEQ_ALIGN_FastaLike,
    eErr_SEQ_ALIGN_SegmentGap,
    eErr_SEQ_ALIGN_SegsInvalidDim,
    eErr_SEQ_ALIGN_Segtype,
    eErr_SEQ_ALIGN_BlastAligns,

    eErr_SEQ_GRAPH_GraphMin,
    eErr_SEQ_GRAPH_GraphMax,
    eErr_SEQ_GRAPH_GraphBelow,
    eErr_SEQ_GRAPH_GraphAbove,
    eErr_SEQ_GRAPH_GraphByteLen,
    eErr_SEQ_GRAPH_GraphOutOfOrder,
    eErr_SEQ_GRAPH_GraphBioseqLen,
    eErr_SEQ_GRAPH_GraphSeqLitLen,
    eErr_SEQ_GRAPH_GraphSeqLocLen,
    eErr_SEQ_GRAPH_GraphStartPhase,
    eErr_SEQ_GRAPH_GraphStopPhase,
    eErr_SEQ_GRAPH_GraphDiffNumber,
    eErr_SEQ_GRAPH_GraphACGTScore,
    eErr_SEQ_GRAPH_GraphNScore,
    eErr_SEQ_GRAPH_GraphGapScore,
    eErr_SEQ_GRAPH_GraphOverlap,

    eErr_Internal_Exception,

    eErr_UNKNOWN
};


// =============================================================================
//                            Validation classes                          
// =============================================================================

// ===========================  Central Validation  ==========================

// CValidError_imp provides the entry point to the validation process.
// It calls upon the various validation classes to perform validation of
// each part.
// The class holds all the data for the validation process. 
class CValidError_imp
{
public:
    // Interface to be used by the CValidError class

    // Constructor & Destructor
    CValidError_imp(CObjectManager& objmgr, CValidError* errors, 
        Uint4 options = 0);
    virtual ~CValidError_imp(void);

    // Validation methods
    bool Validate(const CSeq_entry& se, const CCit_sub* cs = 0,
        CScope* scope = 0);
    void Validate(const CSeq_submit& ss, CScope* scope = 0);
    void Validate(const CSeq_annot& sa, CScope* scope = 0);

    void SetProgressCallback(CValidator::TProgressCallback callback,
        void* user_data);
public:
    // interface to be used by the various validation classes

    // typedefs:
    typedef const CSeq_feat& TFeat;
    typedef const CBioseq& TBioseq;
    typedef const CBioseq_set& TSet;
    typedef const CSeqdesc& TDesc;
    typedef const CSeq_annot& TAnnot;
    typedef const CSeq_graph& TGraph;
    typedef const CSeq_align& TAlign;
    typedef const CSeq_entry& TEntry;
    typedef const CSeq_feat::TDbxref TDbtags;
    typedef map < const CSeq_feat*, const CSeq_annot* >& TFeatAnnotMap;

    // Posts errors.
    void PostErr(EDiagSev sv, EErrType et, const string& msg,
        const CSerialObject& obj);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TDesc ds);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TFeat ft);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TBioseq sq);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TBioseq sq,
        TDesc ds);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TSet set);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TSet set, 
        TDesc ds);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TAnnot annot);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TGraph graph);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TBioseq sq,
        TGraph graph);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TAlign align);
    void PostErr(EDiagSev sv, EErrType et, const string& msg, TEntry entry);