prosite.cpp

来自「ncbi源码」· C++ 代码 · 共 160 行

/*
 * ===========================================================================
 * PRODUCTION $Log: prosite.cpp,v $
 * PRODUCTION Revision 1000.2  2004/06/01 20:55:35  gouriano
 * PRODUCTION PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.4
 * PRODUCTION
 * ===========================================================================
 */

/*  $Id: prosite.cpp,v 1000.2 2004/06/01 20:55:35 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:  Josh Cherry
 *
 * File Description:  Class for handling prosite-format pattern databases
 *
 */


#include <ncbi_pch.hpp>
#include "prosite_entry.hpp"
#include "prosite.hpp"

BEGIN_NCBI_SCOPE

// this function reads a stream in the format of prosite.dat and
// APPENDS prosite entries to the vector of entries it's handed
void CProsite::ReadEntries(istream& input, vector<CPrositeEntry>& entries)
{
    string line;
    CPrositeEntry entry;

    char buffer[4096];
    while (input.getline(buffer, 4096)) {
        line = buffer;
        string ltype = line.substr(0, 2);
        if (ltype == "ID") {
            entry.SetId(line.substr(5));
        } else if (ltype == "DE") {
            entry.SetDesc(line.substr(5));
        } else if (ltype == "DO") {
            entry.SetDoc(line.substr(5));
        } else if (ltype == "AC") {
            entry.SetAccession(line.substr(5));
        } else if (ltype == "PA") {
            entry.SetPattern() += line.substr(5);
        } else if (ltype == "CC") {
            if (line.length() >= 5) {
                if (line.substr(5) == "/SKIP-FLAG=TRUE;") {
                    entry.SetSkipFlag(1);
                }
            }
        } else if (ltype == "//") {
            if (!entry.GetPattern().empty()) {
                // get rid of the ending '.' in pattern
                string& pa = entry.SetPattern();
                pa.erase(pa.length() - 1);
                // save the entry
                entries.push_back(entry);
            }
            entry.Reset();
        }
    }
}


string CProsite::PSPatternToPCRE(const string& pat)
{

    list<string> l;
    string re;
    // get elements between the -'s
    NStr::Split(pat, "-", l);
    ITERATE (list<string>, iter, l) {
        re += x_ElementConvert(*iter);
    }
    return re;
}


string CProsite::x_ElementConvert(const string& el)
{
    string rv;
    for(unsigned int i = 0;  i < el.length();  i++) {
        switch (char ch = el[i]) {
        case '{':
            rv += "[^";
            break;
        case '}':
            rv += ']';
            break;
        case '(':
            rv += '{';
            break;
        case ')':
            rv += '}';
            break;
        case 'x': case 'X':
            rv += '.';
            break;
        case '<':
            rv += '^';
            break;
        case '>':
            rv += '$';
            break;
        default:
            rv += ch;
        }
    }
    return rv;
}


END_NCBI_SCOPE


/*
 * ===========================================================================
 * $Log: prosite.cpp,v $
 * Revision 1000.2  2004/06/01 20:55:35  gouriano
 * PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.4
 *
 * Revision 1.4  2004/05/21 22:27:47  gorelenk
 * Added PCH ncbi_pch.hpp
 *
 * Revision 1.3  2004/01/27 18:38:07  dicuccio
 * Code clean-up.  Use standard names for plugins.  Removed unnecessary #includes
 *
 * Revision 1.2  2003/08/15 20:24:47  jcherry
 * Sped up reading of prosite data file
 *
 * Revision 1.1  2003/08/04 20:05:45  jcherry
 * Initial version
 *
 * ===========================================================================
 */