flat_text_formatter.cpp

来自「ncbi源码」· C++ 代码 · 共 489 行 · 第 1/2 页

/*
 * ===========================================================================
 * PRODUCTION $Log: flat_text_formatter.cpp,v $
 * PRODUCTION Revision 1000.1  2004/06/01 19:43:34  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.6
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: flat_text_formatter.cpp,v 1000.1 2004/06/01 19:43:34 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:  Aaron Ucko, NCBI
*
* File Description:
*   new (early 2003) flat-file generator -- base class for traditional
*   line-oriented formats (GenBank, EMBL, DDBJ but not GBSeq)
*
* ===========================================================================
*/

#include <ncbi_pch.hpp>
#include <objtools/flat/flat_ddbj_formatter.hpp>
#include <objtools/flat/flat_embl_formatter.hpp>
#include <objtools/flat/flat_ncbi_formatter.hpp>
#include <objtools/flat/flat_items.hpp>

#include <objects/seq/Seq_ext.hpp>
#include <objects/seq/Seq_hist.hpp>
#include <objects/seqloc/Textseq_id.hpp>

#include <objmgr/seq_vector.hpp>

BEGIN_NCBI_SCOPE
BEGIN_SCOPE(objects)

// Some of the code here may need to be split out to account for
// GenBank/DDBJ differences.

CFlatTextOStream::CFlatTextOStream(CNcbiOstream& stream, bool trace_topics)
    : m_Stream(stream)
{
    if (trace_topics) {
        m_TraceStream.reset(CObjectOStream::Open(eSerial_AsnText, stream));
    }
}


void CFlatTextOStream::AddParagraph(const list<string>&  lines,
                                    const IFlatItem*     item,
                                    const CSerialObject* topic)
{
    if (topic  &&  m_TraceStream.get()) {
        m_TraceStream->Write(topic, topic->GetThisTypeInfo());
        m_TraceStream->FlushBuffer();
    }
    ITERATE (list<string>, it, lines) {
        m_Stream << *it << '\n';
    }
    m_Stream << flush;
}


CFlatTextFormatter* CFlatTextFormatter::New(IFlatTextOStream& stream,
                                            CScope& scope,
                                            IFlatFormatter::EMode mode,
                                            IFlatFormatter::EDatabase db,
                                            IFlatFormatter::EStyle style,
                                            IFlatFormatter::TFlags flags)
{
    switch (db) {
    case eDB_DDBJ:
        return new CFlatDDBJFormatter(stream, scope, mode, style, flags);
    case eDB_EMBL:
        return new CFlatEMBLFormatter(stream, scope, mode, style, flags);
    case eDB_NCBI:
        return new CFlatNCBIFormatter(stream, scope, mode, style, flags);
    default:
        return 0; // shouldn't happen
    }
}


void CFlatTextFormatter::BeginSequence(CFlatContext& context)
{
    IFlatFormatter::BeginSequence(context);
    m_Stream->NewSequence();
}


void CFlatTextFormatter::FormatHead(const CFlatHead& head)
{
    list<string> l;

    {{
        CNcbiOstrstream locus_line;
        string tmp;
        locus_line << Pad(head.GetLocus(), tmp, 16) << ' ' << setw(11)
                   << m_Context->GetLength() << ' ' << m_Context->GetUnits();
        if (m_Context->IsProt()) {
            locus_line << string(12, ' ');
        } else {
            locus_line << ' ';
            switch (head.GetStrandedness()) {
            case CSeq_inst::eStrand_ss:    locus_line << "ss-"; break;
            case CSeq_inst::eStrand_ds:    locus_line << "ds-"; break;
            case CSeq_inst::eStrand_mixed: locus_line << "ms-"; break;
            default:                       locus_line << "   "; break;
            }
            locus_line << Pad(head.GetMolString(), tmp, 6) << "  ";
        }
        locus_line << (head.GetTopology() == CSeq_inst::eTopology_circular
                       ? "circular " : "linear   ")
                   << Upcase(head.GetDivision()) << ' ';
        tmp.erase();
        FormatDate(head.GetUpdateDate(), tmp);
        locus_line << tmp;
        Wrap(l, "LOCUS", CNcbiOstrstreamToString(locus_line));
        m_Stream->AddParagraph(l, &head);
        l.clear();
    }}

    // XXX - quote HTML if needed
    Wrap(l, "DEFINITION", head.GetDefinition());
    // hunt down appropriate descriptor, if any?
    m_Stream->AddParagraph(l, &head);
    l.clear();

    {{
        string acc = m_Context->GetPrimaryID().GetSeqIdString(false);
        ITERATE (list<string>, it, head.GetSecondaryIDs()) {
            acc += ' ' + *it;
        }
        Wrap(l, "ACCESSION", acc);
        Wrap(l, "VERSION",
             m_Context->GetAccession()
             + "  GI:" + NStr::IntToString(m_Context->GetGI()));
        m_Stream->AddParagraph(l, &head, &m_Context->GetPrimaryID());
    }}

    if ( !head.GetDBSource().empty() ) {
        l.clear();
        string tag = "DBSOURCE";
        ITERATE (list<string>, it, head.GetDBSource()) {
            Wrap(l, tag, *it);
            tag.erase();
        }
        if ( !l.empty() ) {
            m_Stream->AddParagraph(l, &head, head.GetProteinBlock());
        }
    }
}


void CFlatTextFormatter::FormatKeywords(const CFlatKeywords& keys)
{
    list<string> l, kw;
    ITERATE (list<string>, it, keys.GetKeywords()) {
        kw.push_back(*it + (&*it == &keys.GetKeywords().back() ? '.' : ';'));
    }
    if (kw.empty()) {
        kw.push_back(".");
    }
    string tag;
    NStr::WrapList(kw, m_Stream->GetWidth(), " ", l, 0, m_Indent,
                   Pad("KEYWORDS", tag, ePara));
    m_Stream->AddParagraph(l, &keys);
}


void CFlatTextFormatter::FormatSegment(const CFlatSegment& seg)
{
    list<string> l;
    Wrap(l, "SEGMENT",
         NStr::IntToString(seg.GetNum()) + " of "
         + NStr::IntToString(seg.GetCount()));
    m_Stream->AddParagraph(l, &seg);
}


void CFlatTextFormatter::FormatSource(const CFlatSource& source)
{
    list<string> l;
    {{
        string name = source.GetFormalName();
        if ( !source.GetCommonName().empty() ) {
            name += " (" + source.GetCommonName() + ')';
        }
        Wrap(l, "SOURCE", name);
    }}
    if (DoHTML()  &&  source.GetTaxID()) {
        Wrap(l, "ORGANISM",
             "<a href=\"" + source.GetTaxonomyURL() + "\">"
             + source.GetFormalName() + "</a>",
             eSubp);
    } else {
        Wrap(l, "ORGANISM", source.GetFormalName(), eSubp);
    }
    Wrap(l, kEmptyStr, source.GetLineage() + '.');
    m_Stream->AddParagraph(l, &source, &source.GetDescriptor());
}


void CFlatTextFormatter::FormatReference(const CFlatReference& ref)
{
    list<string> l;
    Wrap(l, "REFERENCE",
         NStr::IntToString(ref.GetSerial()) + ref.GetRange(*m_Context));
    
    {{
        string authors;
        ITERATE (list<string>, it, ref.GetAuthors()) {
            if (it != ref.GetAuthors().begin()) {
                authors += (&*it == &ref.GetAuthors().back()) ? " and " : ", ";
            }
            authors += *it;
        }
        Wrap(l, "AUTHORS", authors, eSubp);
    }}
    Wrap(l, "CONSRTM", ref.GetConsortium(), eSubp);

    {{
        string title, journal;