Seq_id.hpp

Go to the documentation of this file.

Go to the SVN repository for this file.

/* $Id: Seq_id.hpp 102244 2024-04-10 18:51:00Z ucko $
 * ===========================================================================
 *
 *                            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:  .......
 *
 * File Description:
 *   .......
 *
 * Remark:
 *   This code was originally generated by application DATATOOL
 *   using specifications from the ASN data definition file
 *   'seqloc.asn'.
 */
 
#ifndef OBJECTS_SEQLOC_SEQ_ID_HPP
#define OBJECTS_SEQLOC_SEQ_ID_HPP
 
 
// generated includes
#include <objects/seqloc/Seq_id_.hpp>
#include <corelib/ncbi_limits.hpp>
#include <serial/serializable.hpp>
 
#include <objects/seq/Bioseq.hpp>
#include <objects/seqloc/Textseq_id.hpp>
 
#include <set>
 
// generated classes
 
BEGIN_NCBI_SCOPE
 
class ILineReader;
 
BEGIN_objects_SCOPE // namespace ncbi::objects::
 
/** @addtogroup OBJECTS_Seqid
 *
 * @{
 */
 
 
class CBioseq;
class CSeq_id_Handle;
 
 
class NCBI_SEQLOC_EXPORT CSeq_id : public CSeq_id_Base,
                                   public CSerializable
{
    typedef CSeq_id_Base Tparent;
 
public:
    enum EParseFlags {
        /// Warn rather than throwing an exception when a FASTA-style ID set
        /// contains unparsable portions, either from unsupported syntax or
        /// because it is only possible to accept a single ID anyway (in the
        /// string-based constructor and corresponding Set() variant).
        fParse_PartialOK  = 0x01,
        fParse_RawText    = 0x02, ///< Try to ID raw non-numeric accessions
        fParse_RawGI      = 0x04, ///< Treat raw numbers as GIs, not local IDs
        fParse_AnyRaw     = fParse_RawText | fParse_RawGI,
        /// Treat otherwise unidentified strings as raw accessions,
        /// provided that they pass rudimentary validation.  Also,
        /// accept PDB accessions with chains but no delimiters.
        fParse_ValidLocal = 0x08,
        /// Treat otherwise unidentified strings as local accessions as long
        /// as they don't resemble FASTA-style IDs (or ID sets).
        fParse_AnyLocal   = 0x18,
        fParse_NoFASTA    = 0x20, ///< Don't bother checking for a tag
        /// For IdentifyAccession, don't warn about falling back to a
        /// different specific type because broad identification is
        /// sufficient.  (Automatically on when calling IdentifyAccession
        /// internally.)
        fParse_FallbackOK = 0x40,
 
        /// By default in ParseIDs and IsValid, allow raw parsable
        /// non-numeric accessions and plausible local accessions.
        /// (The string-based constructor and Set method have a
        /// stricter default: fParse_AnyRaw.)
        fParse_Default    = fParse_RawText | fParse_ValidLocal
    };
    typedef int TParseFlags; // binary OR of EParseFlags
 
 
    enum EErrorFlags {
        fNoError            = 0,
        fEmptyId            = 1, // Id may consists of empty string(s)
        fInvalidChar        = 1 << 1,
        fExceedsMaxLength   = 1 << 2
    };
    using TErrorFlags = int;
 
    /// Tag for method variants that would otherwise be ambiguous.
    enum EFastaAsTypeAndContent {
        eFasta_AsTypeAndContent
    };
 
    ///
    /// See also CSeq_id related functions in "util/sequence.hpp":
    ///
    ///   TSeqPos GetLength(const CSeq_id&, CScope*);
    ///   bool IsSameBioseq(const CSeq_id&, const CSeq_id&, CScope*);
    ///
 
    /// Default constructor
    CSeq_id(void);
 
    /// Construct a Seq-id from a flat string.
    /// @param the_id
    ///   Input ID, preferably FASTA-style.
    /// @param flags
    ///   How to interpret anything other than a single FASTA-style ID.
    explicit CSeq_id(const CTempString& the_id,
                     TParseFlags flags = fParse_AnyRaw);
 
    /// Construct a seq-id from a dbtag.
    /// @param tag
    ///   Input dbtag.
    /// @param set_as_general
    ///   Whether to store tags from unrecognized databases as is in
    ///   Seq-ids of type general rather than rejecting them altogether.
    explicit CSeq_id(const CDbtag& tag, bool set_as_general = true);
 
    /// Construct a numeric Seq-id.
    /// @param the_type
    ///   Type of Seq-id (normally e_Gi)
    /// @param int_seq_id
    ///   Numeric value.
    CSeq_id(E_Choice the_type,
            TIntId   int_seq_id);
#ifdef NCBI_STRICT_GI
    CSeq_id(E_Choice the_type,
            TGi      gi);
#endif
 
    /// Construct a Seq-id from a flat representation.
    /// @param the_type
    ///   Type of Seq_id to construct
    /// @param acc_in
    ///   Primary string value -- normally accession, overridden as
    ///   country for patents, database for "general" IDs, molecule ID
    ///   for PDB IDs.
    /// @param name_in
    ///   Additional string value -- normally name/locus, overridden as
    ///   (application) number for patents, tag for "general" IDs,
    ///   chain ID for PDB.
    /// @param version
    ///   Numeric value -- normally version number, overriden as sequence
    ///   number for patents.
    /// @param release_in
    ///   Historically used to convey release identifiers; for patents,
    ///   may be set to "pgp" (case-insensitive) to indicate a
    ///   Pre-Grant Patent [application].
    CSeq_id(E_Choice           the_type,
            const CTempString& acc_in,
            const CTempString& name_in    = kEmptyStr,
            int                version    = 0,
            const CTempString& release_in = kEmptyStr);
 
    /// Construct a Seq-id from a FASTA string with the leading (type)
    /// component already parsed out.
    /// @param the_type
    ///   Type of Seq_id to construct
    /// @param the_content
    ///   FASTA-style content, with embedded vertical bars as appropriate.
    CSeq_id(EFastaAsTypeAndContent, E_Choice the_type,
            const CTempString& the_content);
 
    /// Reassign based on flat specifications; arguments interpreted
    /// as with constructors.  (Returns a reference to self.)
 
    CSeq_id& Set(const CTempString& the_id, TParseFlags flags = fParse_AnyRaw);
 
    CSeq_id& Set(const CDbtag& tag, bool set_as_general = true);
 
    CSeq_id& Set(E_Choice the_type,
                 TIntId   int_seq_id);
 
    CSeq_id& Set(E_Choice           the_type,
                 const CTempString& acc_in,
                 const CTempString& name_in    = kEmptyStr,
                 int                version    = 0,
                 const CTempString& release_in = kEmptyStr);
 
    CSeq_id& Set(EFastaAsTypeAndContent, E_Choice the_type,
                 const CTempString& the_content);
 
    /// Destructor
    virtual ~CSeq_id(void);
 
    /// Converts a string to a choice, no need to require a member.
    static E_Choice WhichInverseSeqId(const CTempString& SeqIdCode);
 
    /// Converts a choice to a FASTA tag, with no trailing vertical bar.
    static const char* WhichFastaTag(E_Choice choice);
 
    /// For IdentifyAccession (below)
    enum EAccessionInfo {
        // E_Choice values, explicitly pulled in to help avoid warnings
        // elsewhere about bitwise operations between different enum types.
        eSeqId_not_set           = e_not_set,
        eSeqId_local             = e_Local,
        eSeqId_gibbsq            = e_Gibbsq,
        eSeqId_gibbmt            = e_Gibbmt,
        eSeqId_giim              = e_Giim,
        eSeqId_genbank           = e_Genbank,
        eSeqId_embl              = e_Embl,
        eSeqId_pir               = e_Pir,
        eSeqId_swissprot         = e_Swissprot,
        eSeqId_patent            = e_Patent,
        eSeqId_other             = e_Other,
        eSeqId_refseq            = eSeqId_other,
        eSeqId_general           = e_General,
        eSeqId_gi                = e_Gi,
        eSeqId_ddbj              = e_Ddbj,
        eSeqId_prf               = e_Prf,
        eSeqId_pdb               = e_Pdb,
        eSeqId_tpg               = e_Tpg,
        eSeqId_tpe               = e_Tpe,
        eSeqId_tpd               = e_Tpd,
        eSeqId_gpipe             = e_Gpipe,
        eSeqId_named_annot_track = e_Named_annot_track,
        
        // Mask for Seq_id type; allow 8 bits to be safe
        eAcc_type_mask = 0xff,
 
        // Useful general flags (not inherent in choice of division,
        // albeit not necessarily applicable to all divisions).
        fAcc_nuc       = 0x80000000,
        fAcc_prot      = 0x40000000,
        fAcc_seq       = 0,
        fAcc_predicted = 0x20000000, // only for refseq
        fAcc_specials  = 0x10000000, // has special cases; only used internally
        fAcc_master    = 0x08000000,
        fAcc_ncbo      = 0x04000000, // for refseq pathogen detection pipeline
        fAcc_fallback  = 0x02000000, // is a fallback; only used internally
        fAcc_vdb_only  = 0x01000000,
        eAcc_flag_mask = 0xff000000,
 
        // Divisions and categories (multiples of 1 << 8; always
        // globally unique nowadays, no matter how specialized)
        eAcc_other         =   0 << 8, // no further classification
        eAcc_est           =   1 << 8, // expressed sequence tag (mRNA)
        eAcc_dirsub        =   2 << 8, // direct submission of anything
        eAcc_div_patent    =   3 << 8, // patented sequence
        eAcc_mrna          =   4 << 8, // non-EST mRNA or cDNA
        eAcc_ncrna         =   5 << 8, // non-coding RNA
        eAcc_gsdb_ds       =   6 << 8, // Genome Sequence DB direct submission
        eAcc_gsdb          =   7 << 8, // other GSDB record
        eAcc_backbone      =   8 << 8, // from journal scanning
        eAcc_tsa           =   9 << 8, // transcriptome shotgun assembly
        eAcc_segset        =  10 << 8, // seg-set header; might not be genomic
        eAcc_gss           =  11 << 8, // genome survey sequence (may be mRNA)
        eAcc_unique        =  12 << 8, // sequence data shared across records
        eAcc_ambig         = 112 << 8, // multiply assigned (!)
        eAcc_ambig_g       = 113 << 8, // assigned in GenBank
        eAcc_ambig_e       = 114 << 8, // assigned in EMBL
        eAcc_ambig_ge      = 115 << 8, // assigned in both GenBank and EMBL
        eAcc_ambig_d       = 116 << 8, // assigned in DDBJ
        eAcc_ambig_gd      = 117 << 8, // GenBank and DDBJ
        eAcc_ambig_ed      = 118 << 8, // EMBL and DDBJ
        eAcc_ambig_ged     = 119 << 8, // all three
        eAcc_unreserved    = 127 << 8, // not yet formally assigned
        fAcc_genomic       = 128 << 8, // genomic (flag; any of the below)
        eAcc_genome        = 128 << 8, // complete genome
        eAcc_htgs          = 129 << 8, // high-throughput genome sequence
        eAcc_con           = 130 << 8, // intermediate genomic assembly; contig
        eAcc_wgs           = 131 << 8, // whole-genome shotgun collection
        // 132 was GSS, which isn't necessarily genomic after all. :-/
        eAcc_chromosome    = 133 << 8, // whole chromosome
        eAcc_genomic_rgn   = 134 << 8, // incomplete genomic region
        eAcc_wgs_intermed  = 135 << 8, // WGS intermediate assembly
        eAcc_sts           = 136 << 8, // sequence tagged site
        eAcc_mga           = 137 << 8, // Mass sequence for Genome Annotation
        eAcc_optical_map   = 138 << 8, // optical map
        eAcc_targeted      = 139 << 8, // targeted genomic project
        eAcc_division_mask = 0xff00,
 
        // Internal values combinining a division and a flag for convenience.
        eAcc_wgs_master          = eAcc_wgs          | fAcc_master,
        eAcc_wgs_intermed_master = eAcc_wgs_intermed | fAcc_master,
        eAcc_tsa_master          = eAcc_tsa          | fAcc_master,
        eAcc_targeted_master     = eAcc_targeted     | fAcc_master,
        eAcc_wgs_vdb_only        = eAcc_wgs          | fAcc_vdb_only,
        eAcc_wgs_intermed_vdb_only = eAcc_wgs_intermed | fAcc_vdb_only,
        eAcc_tsa_vdb_only        = eAcc_tsa          | fAcc_vdb_only,
        eAcc_targeted_vdb_only   = eAcc_targeted     | fAcc_vdb_only,
        eAcc_wgs_vdb_master      = eAcc_wgs | fAcc_master | fAcc_vdb_only,
        eAcc_wgs_intermed_vdb_master
                             = eAcc_wgs_intermed | fAcc_master | fAcc_vdb_only,
        eAcc_tsa_vdb_master      = eAcc_tsa | fAcc_master | fAcc_vdb_only,
        eAcc_targeted_vdb_master = eAcc_targeted | fAcc_master | fAcc_vdb_only,
 
        // Internal macro, left defined only temporarily
#define NCBI_ACC(type, div, mol) eSeqId_##type | eAcc_##div | fAcc_##mol
        // Actual return values with EXAMPLE prefixes (to be followed
        // by digits) or IDs, grouped by Seq-id type.  In most cases,
        // there are other prefixes with the same classification, and
        // if not there could be in principle.
        eAcc_unknown         = NCBI_ACC(not_set, other, seq),
        // Most N accessions are GenBank ESTs, but some low-numbered
        // ones (now only used as secondary accessions) were assigned
        // haphazardly, and some are therefore ambiguous.
        eAcc_ambiguous_nuc   = NCBI_ACC(not_set, ambig,      nuc),  // N0-N1
        eAcc_maybe_gb        = NCBI_ACC(not_set, ambig_g,    nuc),
        eAcc_maybe_embl      = NCBI_ACC(not_set, ambig_e,    nuc),
        eAcc_maybe_ddbj      = NCBI_ACC(not_set, ambig_d,    nuc),
        eAcc_gb_embl         = NCBI_ACC(not_set, ambig_ge,   nuc),  // N00001
        eAcc_gb_ddbj         = NCBI_ACC(not_set, ambig_gd,   nuc),  // N00006
        eAcc_embl_ddbj       = NCBI_ACC(not_set, ambig_ed,   nuc),  // N00070
        eAcc_gb_embl_ddbj    = NCBI_ACC(not_set, ambig_ged,  nuc),  // N00005
        eAcc_unreserved_nuc  = NCBI_ACC(not_set, unreserved, nuc),  // XY
        eAcc_unreserved_prot = NCBI_ACC(not_set, unreserved, prot), // XYZ
 
        eAcc_local  = NCBI_ACC(local,  other, seq),
        eAcc_gibbsq = NCBI_ACC(gibbsq, other, seq),
        eAcc_gibbmt = NCBI_ACC(gibbmt, other, seq),
        eAcc_giim   = NCBI_ACC(giim,   other, seq),
 
        // NB: eAcc_gb_patent and eAcc_gb_segset are only *mostly* nucleotide,
        // and eAcc_gb_mga is so far unused.
        eAcc_gb_other        = NCBI_ACC(genbank, other,          seq),
        eAcc_gb_prot         = NCBI_ACC(genbank, other,          prot), // AAA
        eAcc_gb_other_nuc    = NCBI_ACC(genbank, other,          nuc),  // AS
        eAcc_gb_est          = NCBI_ACC(genbank, est,            nuc),  // H
        eAcc_gb_dirsub       = NCBI_ACC(genbank, dirsub,         nuc),  // U
        eAcc_gb_patent       = NCBI_ACC(genbank, div_patent,     seq),  // I
        eAcc_gb_patent_prot  = NCBI_ACC(genbank, div_patent,     prot), // AAE
        eAcc_gb_cdna         = NCBI_ACC(genbank, mrna,           nuc),  // BC
        eAcc_gsdb_dirsub     = NCBI_ACC(genbank, gsdb_ds,        nuc),  // J
        eAcc_gb_gsdb         = NCBI_ACC(genbank, gsdb,           nuc),  // AD
        eAcc_gb_backbone     = NCBI_ACC(genbank, backbone,       nuc),  // S
        eAcc_gb_tsa_nuc      = NCBI_ACC(genbank, tsa,            nuc),  // EZ
        eAcc_gb_tsa_prot     = NCBI_ACC(genbank, tsa,            prot), // JAA
        eAcc_gb_tsam_nuc     = NCBI_ACC(genbank, tsa_master,     nuc),
        eAcc_gb_tsam_prot    = NCBI_ACC(genbank, tsa_master,     prot),
        eAcc_gb_tsav_nuc     = NCBI_ACC(genbank, tsa_vdb_only,   nuc),
        eAcc_gb_tsav_prot    = NCBI_ACC(genbank, tsa_vdb_only,   prot),
        eAcc_gb_tsavm_nuc    = NCBI_ACC(genbank, tsa_vdb_master, nuc),
        eAcc_gb_tsavm_prot   = NCBI_ACC(genbank, tsa_vdb_master, prot),
        eAcc_gb_segset       = NCBI_ACC(genbank, segset,         seq),  // AH
        eAcc_gb_gss          = NCBI_ACC(genbank, gss,            nuc),  // B
        eAcc_gb_genome       = NCBI_ACC(genbank, genome,         nuc),  // AE
        eAcc_gb_htgs         = NCBI_ACC(genbank, htgs,           nuc),  // AC
        eAcc_gb_con          = NCBI_ACC(genbank, con,            nuc),  // CH
        eAcc_gb_wgs_nuc      = NCBI_ACC(genbank, wgs,            nuc),  // AAAA
        eAcc_gb_wgs_prot     = NCBI_ACC(genbank, wgs,            prot), // EAA
        eAcc_gb_wgsm_nuc     = NCBI_ACC(genbank, wgs_master,     nuc),
        eAcc_gb_wgsm_prot    = NCBI_ACC(genbank, wgs_master,     prot),
        eAcc_gb_wgsv_nuc     = NCBI_ACC(genbank, wgs_vdb_only,   nuc),
        eAcc_gb_wgsv_prot    = NCBI_ACC(genbank, wgs_vdb_only,   prot),
        eAcc_gb_wgsvm_nuc    = NCBI_ACC(genbank, wgs_vdb_master, nuc),
        eAcc_gb_wgsvm_prot   = NCBI_ACC(genbank, wgs_vdb_master, prot),
        eAcc_gb_chromosome   = NCBI_ACC(genbank, chromosome,     nuc), // CM
        eAcc_gb_sts          = NCBI_ACC(genbank, sts,            nuc), // G
        eAcc_gb_mga          = NCBI_ACC(genbank, mga,            nuc),
        eAcc_gb_optical_map  = NCBI_ACC(genbank, optical_map,    nuc), // MAP_
        eAcc_gb_targeted_nuc = NCBI_ACC(genbank, targeted,       nuc), // KAAA
 
        eAcc_embl_other      = NCBI_ACC(embl, other,          seq),
        eAcc_embl_prot       = NCBI_ACC(embl, other,          prot), // CAA
        eAcc_embl_other_nuc  = NCBI_ACC(embl, other,          nuc),  // AL
        eAcc_embl_est        = NCBI_ACC(embl, est,            nuc),  // F
        eAcc_embl_dirsub     = NCBI_ACC(embl, dirsub,         nuc),  // V
        eAcc_embl_patent     = NCBI_ACC(embl, div_patent,     nuc),  // A
        eAcc_embl_tsa_nuc    = NCBI_ACC(embl, tsa,            nuc),  // HAAA
        eAcc_embl_tsa_prot   = NCBI_ACC(embl, tsa,            prot), // unused
        eAcc_embl_tsam_nuc   = NCBI_ACC(embl, tsa_master,     nuc),
        eAcc_embl_tsam_prot  = NCBI_ACC(embl, tsa_master,     prot),
        eAcc_embl_tsav_nuc   = NCBI_ACC(embl, tsa_vdb_only,   nuc),
        eAcc_embl_tsav_prot  = NCBI_ACC(embl, tsa_vdb_only,   prot),
        eAcc_embl_tsavm_nuc  = NCBI_ACC(embl, tsa_vdb_master, nuc),
        eAcc_embl_tsavm_prot = NCBI_ACC(embl, tsa_vdb_master, prot),
        eAcc_embl_gss        = NCBI_ACC(embl, gss,            nuc), // AJ864682
        eAcc_embl_genome     = NCBI_ACC(embl, genome,         nuc),  // unused
        eAcc_embl_htgs       = NCBI_ACC(embl, htgs,           nuc),  // unused
        eAcc_embl_con        = NCBI_ACC(embl, con,            nuc),  // AN
        eAcc_embl_wgs_nuc    = NCBI_ACC(embl, wgs,            nuc),  // CAAA
        eAcc_embl_wgs_prot   = NCBI_ACC(embl, wgs,            prot), // unused
        eAcc_embl_wgsm_nuc   = NCBI_ACC(embl, wgs_master,     nuc), 
        eAcc_embl_wgsm_prot  = NCBI_ACC(embl, wgs_master,     prot),
        eAcc_embl_wgsv_nuc   = NCBI_ACC(embl, wgs_vdb_only,   nuc),
        eAcc_embl_wgsv_prot  = NCBI_ACC(embl, wgs_vdb_only,   prot),
        eAcc_embl_wgsvm_nuc  = NCBI_ACC(embl, wgs_vdb_master, nuc), 
        eAcc_embl_wgsvm_prot = NCBI_ACC(embl, wgs_vdb_master, prot),
        eAcc_embl_mga        = NCBI_ACC(embl, mga,            nuc),  // unused
 
        eAcc_pir       = NCBI_ACC(pir,       other,      prot),
        eAcc_swissprot = NCBI_ACC(swissprot, other,      prot), // P
        eAcc_patent    = NCBI_ACC(patent,    div_patent, seq),
 
        eAcc_refseq_prot         = NCBI_ACC(refseq, other,          prot),//NP_
        eAcc_refseq_mrna         = NCBI_ACC(refseq, mrna,           nuc), //NM_
        eAcc_refseq_ncrna        = NCBI_ACC(refseq, ncrna,          nuc), //NR_
        eAcc_refseq_unique_prot  = NCBI_ACC(refseq, unique,         prot),//WP_
        eAcc_refseq_unreserved   = NCBI_ACC(refseq, unreserved,     seq), //AA_
        eAcc_refseq_genome       = NCBI_ACC(refseq, genome,         nuc), //NS_
        eAcc_refseq_contig       = NCBI_ACC(refseq, con,            nuc), //NT_
        eAcc_refseq_wgs_nuc      = NCBI_ACC(refseq, wgs,            nuc), //NZ_
        eAcc_refseq_wgs_prot     = NCBI_ACC(refseq, wgs,            prot),//ZP_
        eAcc_refseq_wgsm_nuc     = NCBI_ACC(refseq, wgs_master,     nuc),
        eAcc_refseq_wgsm_prot    = NCBI_ACC(refseq, wgs_master,     prot),
        eAcc_refseq_wgsv_nuc     = NCBI_ACC(refseq, wgs_vdb_only,   nuc),
        eAcc_refseq_wgsv_prot    = NCBI_ACC(refseq, wgs_vdb_only,   prot),
        eAcc_refseq_wgsvm_nuc    = NCBI_ACC(refseq, wgs_vdb_master, nuc),
        eAcc_refseq_wgsvm_prot   = NCBI_ACC(refseq, wgs_vdb_master, prot),
        eAcc_refseq_chromosome   = NCBI_ACC(refseq, chromosome,     nuc), //NC_
        eAcc_refseq_genomic      = NCBI_ACC(refseq, genomic_rgn,    nuc), //NG_
        eAcc_refseq_wgs_intermed = NCBI_ACC(refseq, wgs_intermed,   nuc), //NW_
        eAcc_refseq_wgsm_intermed   = NCBI_ACC(refseq, wgs_intermed_master,
                                               nuc),
        eAcc_refseq_wgsv_intermed   = NCBI_ACC(refseq, wgs_intermed_vdb_only,
                                               nuc),
        eAcc_refseq_wgsvm_intermed  = NCBI_ACC(refseq, wgs_intermed_vdb_master,
                                               nuc),
        eAcc_refseq_prot_predicted  = eAcc_refseq_prot  | fAcc_predicted, //XP_
        eAcc_refseq_mrna_predicted  = eAcc_refseq_mrna  | fAcc_predicted, //XM_
        eAcc_refseq_ncrna_predicted = eAcc_refseq_ncrna | fAcc_predicted, //XR_
        eAcc_refseq_chromosome_ncbo = eAcc_refseq_chromosome | fAcc_ncbo, //WC_
        eAcc_refseq_contig_ncbo     = eAcc_refseq_contig     | fAcc_ncbo, //WT_
 
        eAcc_general      = NCBI_ACC(general, other, seq),
        eAcc_general_nuc  = NCBI_ACC(general, other, nuc),  // TRACE_ASSM
        eAcc_general_prot = NCBI_ACC(general, other, prot),
 
        eAcc_gi = NCBI_ACC(gi, other, seq),
 
        eAcc_ddbj_other          = NCBI_ACC(ddbj, other,          seq),
        eAcc_ddbj_prot           = NCBI_ACC(ddbj, other,          prot), // BAA
        eAcc_ddbj_other_nuc      = NCBI_ACC(ddbj, other,          nuc),//N00028
        eAcc_ddbj_est            = NCBI_ACC(ddbj, est,            nuc),  // C
        eAcc_ddbj_dirsub         = NCBI_ACC(ddbj, dirsub,         nuc),  // D
        eAcc_ddbj_patent         = NCBI_ACC(ddbj, div_patent,     nuc),  // E
        eAcc_ddbj_mrna           = NCBI_ACC(ddbj, mrna,           nuc),  // AK
        eAcc_ddbj_tsa_nuc        = NCBI_ACC(ddbj, tsa,            nuc),  // FX
        eAcc_ddbj_tsa_prot       = NCBI_ACC(ddbj, tsa,            prot), // LAA
        eAcc_ddbj_tsam_nuc       = NCBI_ACC(ddbj, tsa_master,     nuc),
        eAcc_ddbj_tsam_prot      = NCBI_ACC(ddbj, tsa_master,     prot),
        eAcc_ddbj_tsav_nuc       = NCBI_ACC(ddbj, tsa_vdb_only,   nuc),
        eAcc_ddbj_tsav_prot      = NCBI_ACC(ddbj, tsa_vdb_only,   prot),
        eAcc_ddbj_tsavm_nuc      = NCBI_ACC(ddbj, tsa_vdb_master, nuc),
        eAcc_ddbj_tsavm_prot     = NCBI_ACC(ddbj, tsa_vdb_master, prot),
        eAcc_ddbj_gss            = NCBI_ACC(ddbj, gss,            nuc),  // AG
        eAcc_ddbj_genome         = NCBI_ACC(ddbj, genome,         nuc),  // AP
        eAcc_ddbj_htgs           = NCBI_ACC(ddbj, htgs,           nuc),  // {}
        eAcc_ddbj_con            = NCBI_ACC(ddbj, con,            nuc),  // BA
        eAcc_ddbj_wgs_nuc        = NCBI_ACC(ddbj, wgs,            nuc),  // BAAA
        eAcc_ddbj_wgs_prot       = NCBI_ACC(ddbj, wgs,            prot), // GAA
        eAcc_ddbj_wgsm_nuc       = NCBI_ACC(ddbj, wgs_master,     nuc),
        eAcc_ddbj_wgsm_prot      = NCBI_ACC(ddbj, wgs_master,     prot),
        eAcc_ddbj_wgsv_nuc       = NCBI_ACC(ddbj, wgs_vdb_only,   nuc),
        eAcc_ddbj_wgsv_prot      = NCBI_ACC(ddbj, wgs_vdb_only,   prot),
        eAcc_ddbj_wgsvm_nuc      = NCBI_ACC(ddbj, wgs_vdb_master, nuc),
        eAcc_ddbj_wgsvm_prot     = NCBI_ACC(ddbj, wgs_vdb_master, prot),
        eAcc_ddbj_mga            = NCBI_ACC(ddbj, mga,            nuc), //AAAAA
        eAcc_ddbj_targeted_nuc   = NCBI_ACC(ddbj, targeted,       nuc), // TAAA
        eAcc_ddbj_targetedm_nuc  = NCBI_ACC(ddbj, targeted_master,     nuc),
        eAcc_ddbj_targetedv_nuc  = NCBI_ACC(ddbj, targeted_vdb_only,   nuc),
        eAcc_ddbj_targetedvm_nuc = NCBI_ACC(ddbj, targeted_vdb_master, nuc),
 
        eAcc_prf = NCBI_ACC(prf, other, prot),
        eAcc_pdb = NCBI_ACC(pdb, other, seq),  // not necessarily protein!
 
        eAcc_gb_tpa_other      = NCBI_ACC(tpg, other,          seq),
        eAcc_gb_tpa_nuc        = NCBI_ACC(tpg, other,          nuc),  // BK
        eAcc_gb_tpa_prot       = NCBI_ACC(tpg, other,          prot), // DAA
        eAcc_gb_tpa_segset     = NCBI_ACC(tpg, segset,         nuc),  // BL
        eAcc_gb_tpa_con        = NCBI_ACC(tpg, con,            nuc),  // GJ
        eAcc_gb_tpa_wgs_nuc    = NCBI_ACC(tpg, wgs,            nuc),  // DAAA
        eAcc_gb_tpa_wgs_prot   = NCBI_ACC(tpg, wgs,            prot),
        eAcc_gb_tpa_wgsm_nuc   = NCBI_ACC(tpg, wgs_master,     nuc),
        eAcc_gb_tpa_wgsm_prot  = NCBI_ACC(tpg, wgs_master,     prot),
        eAcc_gb_tpa_wgsv_nuc   = NCBI_ACC(tpg, wgs_vdb_only,   nuc),
        eAcc_gb_tpa_wgsv_prot  = NCBI_ACC(tpg, wgs_vdb_only,   prot), // HAA
        eAcc_gb_tpa_wgsvm_nuc  = NCBI_ACC(tpg, wgs_vdb_master, nuc),
        eAcc_gb_tpa_wgsvm_prot = NCBI_ACC(tpg, wgs_vdb_master, prot),
        eAcc_gb_tpa_chromosome = NCBI_ACC(tpg, chromosome,     nuc),  // GK
 
        eAcc_embl_tpa_other      = NCBI_ACC(tpe, other,          seq),
        eAcc_embl_tpa_nuc        = NCBI_ACC(tpe, other,          nuc), // BN
        eAcc_embl_tpa_prot       = NCBI_ACC(tpe, other,      prot), // CAD29848
        eAcc_embl_tpa_tsa_nuc    = NCBI_ACC(tpe, tsa,            nuc),
        eAcc_embl_tpa_tsa_prot   = NCBI_ACC(tpe, tsa,            prot),
        eAcc_embl_tpa_tsam_nuc   = NCBI_ACC(tpe, tsa_master,     nuc),
        eAcc_embl_tpa_tsam_prot  = NCBI_ACC(tpe, tsa_master,     prot),
        eAcc_embl_tpa_tsav_nuc   = NCBI_ACC(tpe, tsa_vdb_only,   nuc),
        eAcc_embl_tpa_tsav_prot  = NCBI_ACC(tpe, tsa_vdb_only,   prot),
        eAcc_embl_tpa_tsavm_nuc  = NCBI_ACC(tpe, tsa_vdb_master, nuc),
        eAcc_embl_tpa_tsavm_prot = NCBI_ACC(tpe, tsa_vdb_master, prot),
        eAcc_embl_tpa_wgs_nuc    = NCBI_ACC(tpe, wgs,            nuc),  // {}
        eAcc_embl_tpa_wgs_prot   = NCBI_ACC(tpe, wgs,            prot), // {}
        eAcc_embl_tpa_wgsm_nuc   = NCBI_ACC(tpe, wgs_master,     nuc),
        eAcc_embl_tpa_wgsm_prot  = NCBI_ACC(tpe, wgs_master,     prot),
        eAcc_embl_tpa_wgsv_nuc   = NCBI_ACC(tpe, wgs_vdb_only,   nuc),
        eAcc_embl_tpa_wgsv_prot  = NCBI_ACC(tpe, wgs_vdb_only,   prot),
        eAcc_embl_tpa_wgsvm_nuc  = NCBI_ACC(tpe, wgs_vdb_master, nuc),
        eAcc_embl_tpa_wgsvm_prot = NCBI_ACC(tpe, wgs_vdb_master, prot),
 
        eAcc_ddbj_tpa_other        = NCBI_ACC(tpd, other,          seq),
        eAcc_ddbj_tpa_nuc          = NCBI_ACC(tpd, other,          nuc), //BR
        eAcc_ddbj_tpa_prot         = NCBI_ACC(tpd, other,          prot),//FAA
        eAcc_ddbj_tpa_tsa_nuc      = NCBI_ACC(tpd, tsa,            nuc), //YAAA
        eAcc_ddbj_tpa_tsa_prot     = NCBI_ACC(tpd, tsa,            prot),//{}
        eAcc_ddbj_tpa_tsam_nuc     = NCBI_ACC(tpd, tsa_master,     nuc),
        eAcc_ddbj_tpa_tsam_prot    = NCBI_ACC(tpd, tsa_master,     prot),
        eAcc_ddbj_tpa_tsav_nuc     = NCBI_ACC(tpd, tsa_vdb_only,   nuc),
        eAcc_ddbj_tpa_tsav_prot    = NCBI_ACC(tpd, tsa_vdb_only,   prot),
        eAcc_ddbj_tpa_tsavm_nuc    = NCBI_ACC(tpd, tsa_vdb_master, nuc),
        eAcc_ddbj_tpa_tsavm_prot   = NCBI_ACC(tpd, tsa_vdb_master, prot),
        eAcc_ddbj_tpa_con          = NCBI_ACC(tpd, con,            nuc), //HT
        eAcc_ddbj_tpa_wgs_nuc      = NCBI_ACC(tpd, wgs,            nuc), //EAAA
        eAcc_ddbj_tpa_wgs_prot     = NCBI_ACC(tpd, wgs,            prot),//IAA
        eAcc_ddbj_tpa_wgsm_nuc     = NCBI_ACC(tpd, wgs_master,     nuc),
        eAcc_ddbj_tpa_wgsm_prot    = NCBI_ACC(tpd, wgs_master,     prot),
        eAcc_ddbj_tpa_wgsv_nuc     = NCBI_ACC(tpd, wgs_vdb_only,   nuc),
        eAcc_ddbj_tpa_wgsv_prot    = NCBI_ACC(tpd, wgs_vdb_only,   prot),
        eAcc_ddbj_tpa_wgsvm_nuc    = NCBI_ACC(tpd, wgs_vdb_master, nuc),
        eAcc_ddbj_tpa_wgsvm_prot   = NCBI_ACC(tpd, wgs_vdb_master, prot),
        eAcc_ddbj_tpa_chromosome   = NCBI_ACC(tpd, chromosome,     nuc), //HU
        eAcc_ddbj_tpa_targeted_nuc = NCBI_ACC(tpd, targeted,       nuc), //ZAAA
        eAcc_ddbj_tpa_targetedm_nuc  = NCBI_ACC(tpd, targeted_master,     nuc),
        eAcc_ddbj_tpa_targetedv_nuc  = NCBI_ACC(tpd, targeted_vdb_only,   nuc),
        eAcc_ddbj_tpa_targetedvm_nuc = NCBI_ACC(tpd, targeted_vdb_master, nuc),
 
        // genome pipeline, modeled after RefSeq
        eAcc_gpipe_other_nuc  = NCBI_ACC(gpipe, other,       nuc),  // GPN_
        eAcc_gpipe_prot       = NCBI_ACC(gpipe, other,       prot), // GPP_
        eAcc_gpipe_scaffold   = NCBI_ACC(gpipe, con,         nuc),  // GPS_
        eAcc_gpipe_mrna       = NCBI_ACC(gpipe, mrna,        nuc),  // GPM_
        eAcc_gpipe_chromosome = NCBI_ACC(gpipe, chromosome,  nuc),  // GPC_
        eAcc_gpipe_genomic    = NCBI_ACC(gpipe, genomic_rgn, nuc),  // GPG_
        eAcc_gpipe_ncrna      = NCBI_ACC(gpipe, ncrna,       nuc),  // GPR_
        eAcc_gpipe_unreserved = NCBI_ACC(gpipe, unreserved,  seq),  // GPX_
 
        // named annotation track; mixed nucleotides and proteins
        eAcc_named_annot_track = NCBI_ACC(named_annot_track, other, seq) // AT_
#undef NCBI_ACC
    };
 
    static E_Choice GetAccType(EAccessionInfo info)
        { return static_cast<E_Choice>(info & eAcc_type_mask); }
 
    /// Deduces information from a bare accession a la WHICH_db_accession;
    /// may report false negatives on properties.
    static EAccessionInfo IdentifyAccession(const CTempString& accession,
                                            TParseFlags flags = fParse_AnyRaw);
    EAccessionInfo IdentifyAccession(TParseFlags flags
                                     = fParse_AnyRaw | fParse_AnyLocal) const;
 
    static void LoadAccessionGuide(const string& filename);
    static void LoadAccessionGuide(ILineReader& in);
 
    /// Match() - TRUE if SeqIds are equivalent
    bool Match(const CSeq_id& sid2) const;
 
    /// Compare return values
    enum E_SIC {
        e_error = 0,  /// some problem
        e_DIFF,       /// different SeqId types-can't compare
        e_NO,         /// SeqIds compared, but are different
        e_YES         /// SeqIds compared, are equivalent
    };
 
    /// Compare() - more general
    E_SIC Compare(const CSeq_id& sid2) const;
    int CompareOrdered(const CSeq_id& sid2) const;
    bool operator<(const CSeq_id& sid2) const
        {
            return CompareOrdered(sid2) < 0;
        }
 
    /// Return embedded CTextseq_id, if any
    const CTextseq_id* GetTextseq_Id(void) const;
 
    /// Implement serializable interface
    virtual void WriteAsFasta(ostream& out) const;
    CProxy DumpAsFasta(void) const { return Dump(eAsFasta); }
    const string AsFastaString(void) const;
 
    /// return the label for a given string
    enum ELabelType {
        eType, ///< FASTA-style type, or database in GeneralDbIsContent mode.
        eContent, ///< Untagged human-readable accession or the like.
        eBoth, ///< Type and content, delimited by a vertical bar.
        eFasta, ///< Tagged ID in NCBI's traditional FASTA style.
        eFastaContent, ///< Like eFasta, but without any tag.
 
        /// default is to show type + content
        eDefault = eBoth
    };
 
    enum ELabelFlags {
        fLabel_Version            = 0x10, ///< Show the version
        /// For type general, use the database name as the tag
        /// and the (text or numeric) key as the content.
        fLabel_GeneralDbIsContent = 0x20,
        fLabel_Trimmed            = 0x40, ///< Trim trailing FASTA delimeters.
        fLabel_UpperCase          = 0x80, ///< Upper case label, with special encoding for PDB chain-ids
 
        /// default options - always show the version
        fLabel_Default = fLabel_Version
    };
    typedef int TLabelFlags;
    /// Append a label for this Seq-id to the supplied string.
    /// @param label
    ///   String to append to.
    /// @param type
    ///   Type of label (human-readable type-tagged content, by default).
    /// @param flags
    ///   Flags fine-tuning behavior for human-readable output (ignored
    ///   in eFasta and eFastaContent mode).
    /// @sa ELabelType, ELabelFlags
    void GetLabel(string*     label,
                  ELabelType  type  = eDefault,
                  TLabelFlags flags = fLabel_Default) const;
    /// Append a label for this Seq-id to the supplied string, splitting
    /// out the version to a separate output parameter.
    /// @note In eFasta and eFastaContent mode, this method includes the
    /// version (if any) in the label and does not touch *version.
    /// @param label
    ///   String to append to.
    /// @param version
    ///   Pointer to hold the returned version.
    /// @param type
    ///   Type of label (human-readable type-tagged content, by default).
    /// @sa ELabelType
    void GetLabel(string*     label,
                  int*        version,
                  ELabelType  type  = eDefault) const;
 
    ///Return seqid string with optional version for text seqid type
    string GetSeqIdString(bool with_version = false) const;
 
    ///Return seqid string for text seqid type with separate integer version
    string GetSeqIdString(int* version) const;
 
    /// Get a string representation of the sequence IDs of a given bioseq.  This
    /// function produces strings in a number of possible formats.
    enum EStringFormat {
        eFormat_FastA,              // FastA format
        eFormat_ForceGI,            // GI only, in FastA format
        eFormat_BestWithoutVersion, // 'Best' accession, without the version
        eFormat_BestWithVersion     // 'Best' accession, with version
    };
    static string GetStringDescr(const CBioseq& bioseq, EStringFormat fmt);
 
    /// Write a bioseq's IDs in FASTA format
    /// @param ostr
    ///    Stream to write to
    /// @param bioseq
    ///    Bioseq to get IDs from
    /// @return
    ///    The stream that was passed in, after all writes occurred
    static CNcbiOstream& WriteAsFasta(CNcbiOstream& ostr,
                                      const CBioseq& bioseq);
 
    /// Perform rudimentary validation on potential local IDs, whose
    /// contents should be pure ASCII and limited to letters, digits,
    /// and certain punctuation characters (-_.:*# as of August 2010).
    static bool IsValidLocalID(const CTempString& s);
 
    /// Perform rudimentary validation on potential local IDs, whose 
    /// contents should not exceed fifty characters and are limited 
    /// to ASCII characters excluding >[]|\""
    static TErrorFlags CheckLocalID(const CTempString& s);
 
    /// Parse a string representing one or more Seq-ids, appending the
    /// results to IDS.  Multiple IDs must appear in FASTA style.
    /// @param ids
    ///   Destination ID set.  Existing contents will be preserved and
    ///   appended to.
    /// @param s
    ///   Input string to parse.
    /// @param flags
    ///   How to interpret anything other than well-formed FASTA IDs.
    /// @return
    ///   The number of IDs successfully parsed.
    static SIZE_TYPE ParseIDs(CBioseq::TId& ids, const CTempString& s,
                              TParseFlags flags = fParse_Default);
 
    static bool IsValid(const CBioseq::TId& ids, TParseFlags flags = fParse_Default);
    static bool IsValid(const CSeq_id& id, TParseFlags flags = fParse_Default);
 
    /// Parse an entire set of |-delimited FASTA-style IDs, appending
    /// the results to IDS.
    /// @param ids
    ///   Destination ID set.  Existing contents will be preserved and
    ///   appended to.
    /// @param s
    ///   Input string to parse.
    /// @param allow_partial_failure
    ///   If s contains invalid IDs, warn about them and try to
    ///   process the remainder of the string, rather than throwing
    ///   any exceptions.
    /// @return
    ///   The number of IDs successfully parsed.
    static SIZE_TYPE ParseFastaIds(CBioseq::TId& ids, const CTempString& s,
                                   bool allow_partial_failure = false);
 
    /// Numerical quality ranking; lower is better.  (Text)Score, aka
    /// WorstRank, corresponds to the C Toolkit's SeqIdFindWorst,
    /// which favors textual accessions, whereas BestRank corresponds
    /// to the C Toolkit's SeqIdFindBest and favors GIs.  In addition,
    /// there is a pair of methods corresponding to the C Toolkit's
    /// GetOrderBySeqId, used when generating FASTA deflines.
    ///
    /// All rankings give a slight bonus to accessions that carry
    /// versions.
 
    enum EMaxScore {
        kMaxScore = 99999
    };
 
    enum EAdjustScoreFlags {
        fRequireAccessions = 1 << 0
    };
    DECLARE_SAFE_FLAGS_TYPE(EAdjustScoreFlags, TAdjustScoreFlags);
 
    int AdjustScore       (int base_score,
                           TAdjustScoreFlags flags = TAdjustScoreFlags())
        const;
    int StrictAdjustScore (int base_score) const
        { return AdjustScore(base_score, fRequireAccessions); }
    int BaseTextScore     (void)           const;
    int BaseBestRankScore (void)           const;
    int BaseWorstRankScore(void)           const { return BaseTextScore(); }
    int BaseFastaAAScore  (void)           const;
    int BaseFastaNAScore  (void)           const;
    int BaseBlastScore    (void)           const;
 
    int TextScore     (void) const { return AdjustScore(BaseTextScore()); }
    int BestRankScore (void) const { return AdjustScore(BaseBestRankScore()); }
    int WorstRankScore(void) const { return TextScore(); }
    int FastaAAScore  (void) const { return AdjustScore(BaseFastaAAScore()); }
    int FastaNAScore  (void) const { return AdjustScore(BaseFastaNAScore()); }
    int BlastScore    (void) const { return AdjustScore(BaseBlastScore()); }
 
    int StrictTextScore     (void) const
        { return StrictAdjustScore(BaseTextScore()); }
    int StrictBestRankScore (void) const
        { return StrictAdjustScore(BaseBestRankScore()); }
    int StrictFastaAAScore  (void) const
        { return StrictAdjustScore(BaseFastaAAScore()); }
    int StrictFastaNAScore  (void) const
        { return StrictAdjustScore(BaseFastaNAScore()); }
    int StrictBlastScore    (void) const
        { return StrictAdjustScore(BaseBlastScore()); }
 
    /// Wrappers for use with FindBestChoice from <corelib/ncbiutil.hpp>
    static int Score(const CRef<CSeq_id>& id)
        { return id ? id->TextScore() : kMax_Int; }
    static int BestRank(const CRef<CSeq_id>& id)
        { return id ? id->BestRankScore() : kMax_Int; }
    static int WorstRank(const CRef<CSeq_id>& id)
        { return Score(id); }
    static int FastaAARank(const CRef<CSeq_id>& id)
        { return id ? id->FastaAAScore() : kMax_Int; }
    static int FastaNARank(const CRef<CSeq_id>& id)
        { return id ? id->FastaNAScore() : kMax_Int; }
    static int BlastRank(const CRef<CSeq_id>& id)
        { return id ? id->BlastScore() : kMax_Int; }
 
    static int StrictScore(const CRef<CSeq_id>& id)
        { return id ? id->StrictTextScore() : kMax_Int; }
    static int StrictBestRank(const CRef<CSeq_id>& id)
        { return id ? id->StrictBestRankScore() : kMax_Int; }
    static int StrictFastaAARank(const CRef<CSeq_id>& id)
        { return id ? id->StrictFastaAAScore() : kMax_Int; }
    static int StrictFastaNARank(const CRef<CSeq_id>& id)
        { return id ? id->StrictFastaNAScore() : kMax_Int; }
    static int StrictBlastRank(const CRef<CSeq_id>& id)
        { return id ? id->StrictBlastScore() : kMax_Int; }
 
    /// Optimized implementation of CSerialObject::Assign, which is
    /// not so efficient.
    virtual void Assign(const CSerialObject& source,
                        ESerialRecursionMode how = eRecursive);
 
    typedef set<CSeq_id_Handle> TSeqIdHandles;
    /// Collect partially matching seq-ids: no-version, no-name etc.
    /// The original id is not added to the set.
    void GetMatchingIds(TSeqIdHandles& matches) const;
    /// Collect partially matching textseq-ids.
    /// @sa GetMatchingIds
    void GetMatchingTextseqIds(TSeqIdHandles& matches) const;
 
    /// Check if the option to prefer accession.version over GI is enabled
    /// (SeqId/PreferAccessionOverGi or SEQ_ID_PREFER_ACCESSION_OVER_GI).
    static bool PreferAccessionOverGi(void);
    /// Check if the option to avoid GI ids is enabled
    /// (SeqId/AvoidGi or SEQ_ID_AVOID_GI).
    static bool AvoidGi(void);
 
    /// Flags specifying special treatment for certain types of Seq-ids in
    /// ComposeOSLT().
    /// @sa ComposeOSLT
    enum EComposeOSLTFlags {
        fAllowLocalId      = (1 << 0),  ///< 
        fGpipeAddSecondary = (1 << 1)   ///< Add "ACC.VER(=1)" for a 2ndary id
    };
    typedef int TComposeOSLTFlags;
 
    /// JIRA ID-5188 : Compose OSLT string for the primary id, as well as OSLT
    /// strings for the secondary ids, if any.
    /// NB: given a single Seq-id, it is not always possible to determine
    /// whether it should be treated as primary or secondary if it were part of
    /// a list of Seq-ids in a Bioseq. In that case, this function returns it as
    /// primary, and the final judgement needs to be made by the caller.
    /// @param secondary_ids
    ///  OSLT strings for the secondary ids
    /// @param parse_flags
    ///  Flags specifying special treatment for certain types of Seq-ids.
    /// @return
    ///  OSLT string for the primary id
    string ComposeOSLT(list<string>* secondary_ids = nullptr,
                       TComposeOSLTFlags parse_flags = 0) const;
 
    /// ID length restrictions
    const static size_t kMaxLocalIDLength    = 50;
    const static size_t kMaxGeneralDBLength  = 20;
    const static size_t kMaxGeneralTagLength = 50;
    const static size_t kMaxAccessionLength  = 30;
 
    /// SNP annotation scale limits
    enum ESNPScaleLimit {
        eSNPScaleLimit_Default, // Use server defaults
        eSNPScaleLimit_Unit,
        eSNPScaleLimit_Contig,
        eSNPScaleLimit_Supercontig,
        eSNPScaleLimit_Chromosome
    };
 
    static const char* GetSNPScaleLimit_Name(ESNPScaleLimit value);
    static ESNPScaleLimit GetSNPScaleLimit_Value(const string& name);
    bool IsAllowedSNPScaleLimit(ESNPScaleLimit scale_limit) const;
 
private:
    enum ETypeVariant {
        eTV_plain,
        eTV_tr, // variant of sp
        eTV_pgp // variant of pat
    };
 
    static ETypeVariant x_IdentifyTypeVariant(E_Choice type,
                                              const CTempString& str);
 
    // returns next type if determined along the way
    E_Choice x_Init(list<CTempString>& fasta_pieces, E_Choice type,
                    ETypeVariant tv);
 
    // Prohibit copy constructor & assignment operator
    CSeq_id(const CSeq_id&);
    CSeq_id& operator= (const CSeq_id&);
 
    static EAccessionInfo x_IdentifyAccession(const CTempString& main_acc,
                                              TParseFlags flags,
                                              bool has_version);
 
    void x_WriteContentAsFasta(ostream& out) const;
 
    //CRef<CAbstractObjectManager> m_ObjectManager;
 
};
 
 
/////////////////////////////////////////////////////////////////////////////
///
/// SSeqIdRange --
///
/// Represent a range of contiguous INSD-style accessions.
 
struct NCBI_SEQLOC_EXPORT SSeqIdRange
{
    enum EFlags {
        fAllowUnderscores = 0x1 ///< Allow prefixes to contain underscores.
    };
    typedef int TFlags; ///< binary OR of EFlags
 
    explicit SSeqIdRange(const CTempString& s, TFlags flags = 0);
 
#ifndef NCBI_SWIG
    class NCBI_SEQLOC_EXPORT const_iterator
    {
    public:
        typedef random_access_iterator_tag iterator_category;
        typedef string                     value_type;
        typedef ptrdiff_t                  difference_type;
        typedef const string*              pointer;
        typedef string&                    reference;
 
        const_iterator(const SSeqIdRange& range)
            : m_Range(&range), m_Number(range.start)
            { }
 
        const_iterator(const SSeqIdRange& range, int number)
            : m_Range(&range), m_Number(number)
            { _ASSERT(number >= range.start  &&  number <= range.stop + 1); }
 
        const_iterator(const const_iterator& it)
            : m_Range(it.m_Range), m_Number(it.m_Number)
            { }
 
        const_iterator& operator=(const const_iterator& it)
            { m_Range = it.m_Range;  m_Number = it.m_Number;  return *this; }
 
        string  operator* (void) const
            { return m_Accession.empty() ? x_SetAccession() : m_Accession; }
        const string* operator->(void) const
            { return m_Accession.empty() ? &x_SetAccession() : &m_Accession; }
        string  operator[](int n) const
            { return *(*this + n); }
 
        CRef<CSeq_id> GetID(void) const;
 
        const_iterator& operator++(void)
            { m_Accession.erase();  ++m_Number;  return *this; }
        const_iterator  operator++(int)
            { const_iterator orig = *this;  ++*this;  return orig; }
        const_iterator& operator--(void)
            { m_Accession.erase();  --m_Number;  return *this; }
        const_iterator  operator--(int)
            { const_iterator orig = *this;  --*this;  return orig; }
        const_iterator  operator+(int n) const
            { return const_iterator(*m_Range, m_Number + n); }
        const_iterator  operator-(int n) const
            { return const_iterator(*m_Range, m_Number - n); }
        const_iterator& operator+=(int n)
            { m_Accession.erase();  m_Number += n;  return *this; }
        const_iterator& operator-=(int n)
            { m_Accession.erase();  m_Number -= n;  return *this; }
 
        bool operator==(const const_iterator& it) const
            { return m_Number == it.m_Number; }
        bool operator!=(const const_iterator& it) const
            { return m_Number != it.m_Number; }
        bool operator< (const const_iterator& it) const
            { return m_Number < it.m_Number; }
        bool operator> (const const_iterator& it) const
            { return m_Number > it.m_Number; }
        bool operator<=(const const_iterator& it) const
            { return m_Number <= it.m_Number; }
        bool operator>=(const const_iterator& it) const
            { return m_Number >= it.m_Number; }
        int operator-(const const_iterator& it) const
            { return m_Number - it.m_Number; }
 
    private:
        const string& x_SetAccession(void) const;
 
        const SSeqIdRange* m_Range;
        int                m_Number;
        mutable string     m_Accession;
    };
 
    const_iterator begin(void) const
        { return const_iterator(*this); }
    const_iterator end(void) const
        { return const_iterator(*this, stop + 1); }
#endif
 
    size_t size(void) const
        { return stop - start + 1; }
 
    string prefix;
    int    start;
    int    stop;
    int    digits;
    mutable CSeq_id::EAccessionInfo acc_info;
};
 
 
/////////////////////////////////////////////////////////////////////////////
///
/// CSeqIdException --
///
/// Define exceptions generated by CSeq_id.
 
class NCBI_SEQLOC_EXPORT CSeqIdException : public CException
{
public:
    /// Error types that CSeq_id can generate.
    enum EErrCode {
        eUnknownType,   ///< Unrecognized Seq-id type
        eFormat         ///< Contents not parsable as expected
    };
 
    /// Translate from the error code value to its string representation.
    virtual const char* GetErrCodeString(void) const override;
 
    // Standard exception boilerplate code.
    NCBI_EXCEPTION_DEFAULT(CSeqIdException, CException);
};
 
 
/// Dummy convertor for container search functions
template<class TId>
CConstRef<CSeq_id> Get_ConstRef_Seq_id(TId& id)
{
    return CConstRef<CSeq_id>(id);
}
 
 
/// Search the container of CRef<CSeq_id> for the id of given type.
/// Return the id of requested type, or null CRef.
template<class container>
CConstRef<CSeq_id> GetSeq_idByType(const container& ids,
                                   CSeq_id::E_Choice choice)
{
    ITERATE (typename container, iter, ids) {
        if ( *iter  &&  Get_ConstRef_Seq_id(*iter)->Which() == choice ) {
            return Get_ConstRef_Seq_id(*iter);
        }
    }
    return CConstRef<CSeq_id>(0);
}
 
/// Return gi from id list if exists, return 0 otherwise
template<class container>
TGi FindGi(const container& ids)
{
    CConstRef<CSeq_id> id = GetSeq_idByType(ids, CSeq_id::e_Gi);
    return id ? id->GetGi() : ZERO_GI;
}
 
 
/// Return text seq-id from id list if exists, return 0 otherwise
template<class container>
CConstRef<CSeq_id> FindTextseq_id(const container& ids)
{
    ITERATE (typename container, iter, ids) {
        if ( *iter  &&  Get_ConstRef_Seq_id(*iter)->GetTextseq_Id() ) {
            return Get_ConstRef_Seq_id(*iter);
        }
    }
    return CConstRef<CSeq_id>(0);
}
 
 
/////////////////// CSeq_id inline methods
 
// Match - just uses Compare
inline
bool CSeq_id::Match (const CSeq_id& sid2) const
{
    return Compare(sid2) == e_YES;
}
 
 
/////////////////// end of CSeq_id inline methods
 
/* @} */
 
 
END_objects_SCOPE // namespace ncbi::objects::
END_NCBI_SCOPE
 
#endif // OBJECTS_SEQ