fasta.hpp

Go to the documentation of this file.

/*
 * Copyright 2008,2009,2010,2011,2012 Stephan Ossowski, Korbinian Schneeberger,
 * Felix Ott, Joerg Hagmann, Alf Scotland, Sebastian Bender
 * 
 * This file is part of SHORE.
 * 
 * SHORE is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 * 
 * SHORE is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 * 
 * You should have received a copy of the GNU General Public License
 * along with SHORE.  If not, see <http://www.gnu.org/licenses/>.
 */


#ifndef SHORE_IO_FASTA_HPP__
#define SHORE_IO_FASTA_HPP__

#include <vector>
#include <string>

#include "shore/processing/pipeline.hpp"
#include "shore/container/intpack.hpp"
#include "shore/stream/streams.hpp"
#include "shore/datatype/dna_iterator.hpp"

#include "shore/datatype/datatypes.hpp"
#include "shore/fmtio/text.hpp"

namespace shore {

class fasta_reader
{
 private:

        shore::sequence_record m_current;

        std::string m_strbuf;

        std::vector<std::string> m_filenames;
        shore::istreams m_in;

        boost::shared_ptr<shore::mmapping> m_mmapping;

        size_t m_sid;

        bool m_packed;

        bool m_hasdata;

        std::string m_tokbuf[2];

        bool m_shoremode;
        shore::row_reader *m_rtrans;
        shore::row_reader *m_rref;


        void default_load();
        void shore_load();

 public:

        typedef sequence_record current_type;

        fasta_reader(const std::string& filename,const bool packed=false,
                     const bool loadfirst=true);

        fasta_reader(const std::vector<std::string>& fn,const bool packed=false,
                     const bool loadfirst=true);

        ~fasta_reader();

        bool has_data() const;

        const shore::sequence_record& current() const;

        void next();
};

typedef shore::source<fasta_reader> fasta_source;

class fasta_writer
{
 private:

        shore::ostreams m_out;

        bool m_writetags;

 public:

        typedef sequence_record append_type;

        fasta_writer(const std::string& fn);

        void set_writetags(const bool b);

        void append(const shore::sequence_record& r);
        void append(const shore::read& r);
        void flush();
};

typedef shore::sink<fasta_writer> fasta_sink;

typedef shore::sink<fasta_writer,shore::read> fasta_read_sink;

} // namespace shore

#endif // SHORE_IO_FASTA_HPP__