shi_reader.cpp

来自「ncbi源码」· C++ 代码 · 共 286 行

/*
 * ===========================================================================
 * PRODUCTION $Log: shi_reader.cpp,v $
 * PRODUCTION Revision 1000.1  2004/06/01 21:01:49  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.9
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: shi_reader.cpp,v 1000.1 2004/06/01 21:01:49 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.
 *
 * ===========================================================================
 *
 * Authors:  Vladimir Tereshkov
 *
 * File Description:
 *    CShiReader - taxplot file format loader
 */

#include <ncbi_pch.hpp>
#include "shi_reader.hpp"

#include <gui/core/doc_exception.hpp>
#include <gui/core/doc_manager.hpp>
#include <gui/core/idocument.hpp>
#include <gui/core/plugin_utils.hpp>
#include <gui/core/version.hpp>
#include <gui/plugin/PluginCommandSet.hpp>
#include <gui/plugin/PluginInfo.hpp>
#include <gui/plugin/PluginValue.hpp>
#include <gui/utils/message_box.hpp>
#include <gui/objutils/utils.hpp>
#include <gui/dialogs/file_browser.hpp>

#include <objects/general/Object_id.hpp>
#include <objects/seq/Seqdesc.hpp>
#include <objects/seq/Seq_descr.hpp>

#define BIT32			0x80000000
#define BIT31			0x40000000
#define THREE			0x7
#define THIRTEEN		0x1FFF
#define EIGHTEEN		0x3FFFF
#define TWENTYSEVEN		0x7FFFFFF
#define THIRTYONE		0x7FFFFFFF


BEGIN_NCBI_SCOPE
USING_SCOPE(objects);



//
// factory implementations
//

void CShiReader::GetInfo(CPluginInfo& info)
{
    info.Reset();

    // version info macro
    info.SetInfo(CPluginVersion::eMajor, CPluginVersion::eMinor, 0,
                 string(__DATE__) + " " + string(__TIME__),
                 "CShiReader",
                 "Taxplot File", "Read a Taxplot file format",
                 "http://graceland.ncbi.nlm.nih.gov:6224"
                 "/staff/tereshko/plugin_help/shi.html");

    // command info
    CPluginCommandSet& cmds     = info.SetCommands();
    CPluginCommand& load_args   = cmds.AddDataCommand(eDataCommand_load);    
    load_args.AddArgument("file", "File name", CPluginArg::eFile);
}


//
// Default ctor
//
CShiReader::CShiReader()
{
}


//
// One and only dtor
//
CShiReader::~CShiReader()
{
}


//
// Load()
// This is a pure virtual requirement and is the main plugin hook.
//
void CShiReader::Load(CPluginMessage& msg)
{
    const CPluginCommand& args = msg.GetRequest().GetCommand();
    CPluginReply& reply = msg.SetReply();
    string fname = args["file"].AsString();

    if ( fname.empty() ) {
        reply.SetStatus(eMessageStatus_ignored);
        return;
    }

    try {            
        CNcbiIfstream istr(fname.c_str(), ios::binary);
        CRef<CShiReaderCache> dataCache(new CShiReaderCache(fname));
        dataCache->CreateCache(istr);

        CRef<CScope> scope(new CScope(CDocManager::GetObjectManager()));            
        scope->AddDefaults();
        IDocument* doc = CDocManager::CreateDocument(*scope, *dataCache);            
        reply.AddObject(*doc);
    }
    catch (exception& e) {
        _TRACE("failed to read shi: " << e.what());
    }
    catch (...) {
        _TRACE("failed to read shi: unknown error");
    }

}

inline Int4 CShiReaderCache::x_GetNextInt(Uchar * buff, CT_OFF_TYPE & pos)
{
    Uchar * ptr =  buff + pos * 4;    
    Int4 ret = (Int4(ptr[3]) << 24) | 
        (Int4(ptr[2]) << 16) | 
        (Int4(ptr[1]) << 8)  | 
        (Int4(ptr[0]));

    pos += 1;
    return ret;
}

void CShiReaderCache::CreateCache(CNcbiIfstream & fileStream)
{
    SOneShiRecord   shiRecord;
    vector<Uchar>   buff;
    Int4            value,no_more,last_gi,nshi;
    const Int4      cutoff = 1000;
    map<Int4, Int4> taxMap;


    fileStream.seekg(0, ios::end);
    CT_POS_TYPE fileSize = fileStream.tellg();
    CT_OFF_TYPE sz = fileSize - CT_POS_TYPE(0);
    fileStream.seekg(0, ios::beg);  

    buff.resize(sz);
    fileStream.read(((char*)&buff[0]), sz);

    no_more = 0; last_gi = 1; 
    shiRecord.m_Gi = 0;
    CT_OFF_TYPE fileCursor = 0;

    m_Cache.clear();

    nshi =  x_GetNextInt(&buff[0], fileCursor);
    value = x_GetNextInt(&buff[0], fileCursor);

    while ((fileCursor * 4) < sz){
        // building rec. structure
        if (last_gi) {	
            shiRecord.m_Nqugi = THIRTYONE & value;		
            fileCursor +=1;
            shiRecord.m_Chromosome = x_GetNextInt(&buff[0], fileCursor);
            shiRecord.m_Pdb        = x_GetNextInt(&buff[0], fileCursor);
            value                  = x_GetNextInt(&buff[0], fileCursor);            
            shiRecord.m_Gi         = 0;
        }
        else {
            // first gi after last_gi
            if (shiRecord.m_Gi == 0) shiRecord.m_Gi = TWENTYSEVEN & value;
        }

        shiRecord.m_Symmet   = BIT31 & value;
        shiRecord.m_Orgclass = THREE & (value>>27);
        shiRecord.m_Dagi     = TWENTYSEVEN & value; 

        value =  x_GetNextInt(&buff[0], fileCursor);
        shiRecord.m_Taxid = (BIT32&value)?((THIRTYONE & value)>>13):value;
        shiRecord.m_Score = (BIT32&value)?(THIRTEEN & value):x_GetNextInt(&buff[0], fileCursor); 

        if ((fileCursor * 4) < sz) {	
            value   = x_GetNextInt(&buff[0], fileCursor);
            last_gi = (BIT32&value);		
        }
        else last_gi = 1;

        // checking and adding        
        if ((shiRecord.m_Score > cutoff) && (taxMap.insert(pair<Int4, Int4>(shiRecord.m_Taxid, shiRecord.m_Score)).second==false)){       
            if (taxMap[shiRecord.m_Taxid] < shiRecord.m_Score) taxMap[shiRecord.m_Taxid] = shiRecord.m_Score;      // already present, updating     
        }         

        // taxMap contains only valuable data right here
        if (last_gi) { 
            taxMap.insert(pair<Int4, Int4>(0, shiRecord.m_Gi)); // adding current gi as 0 position
            m_Cache.push_back(taxMap);              
            taxMap.clear();   
        }    
    } 
}


END_NCBI_SCOPE


/*
 * ===========================================================================
 * $Log: shi_reader.cpp,v $
 * Revision 1000.1  2004/06/01 21:01:49  gouriano
 * PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.9
 *
 * Revision 1.9  2004/06/01 18:10:55  dicuccio
 * Use plugin args instead of internal file browser dialog
 *
 * Revision 1.8  2004/05/21 22:27:49  gorelenk
 * Added PCH ncbi_pch.hpp
 *
 * Revision 1.7  2004/05/20 20:34:39  tereshko
 * Changed initial Gi value to zero
 *
 * Revision 1.6  2004/05/03 13:31:33  dicuccio
 * gui/utils --> gui/objutils where needed
 *
 * Revision 1.5  2004/03/11 17:47:51  dicuccio
 * Code formatting changes.  Use new file open dialog
 *
 * Revision 1.4  2004/02/20 20:03:27  ucko
 * Fix to compile with stricter implementations of CT_POS_TYPE
 *
 * Revision 1.3  2004/01/28 16:00:56  tereshko
 * Added current gi extraction, loosen filter criteria
 *
 * Revision 1.2  2004/01/21 16:33:34  tereshko
 * +Changes for CodeWarrior in this folder
 *
 * Revision 1.4  2004/01/21 16:09:43  rsmith
 * change stream position types for picky compiler (Codewarrior).
 *
 * Revision 1.3  2004/01/21 14:16:28  dicuccio
 * Adjusted API to be more coding standard compliant.
 *
 * Revision 1.2  2004/01/15 18:08:05  tereshko
 * Fixed for GCC_295
 *
 * Revision 1.1  2004/01/14 16:35:59  tereshko
 * CShiReader data plugin
 *
 * Revision 1.3  2003/12/10 15:09:32  dicuccio
 * Changed menu item - capitalize AGP
 *
 * Revision 1.2  2003/12/09 21:33:54  jcherry
 * Added url for help
 *
 * Revision 1.1  2003/12/09 00:20:09  jcherry
 * Initial version
 *
 * ===========================================================================
 */