fastq.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_FASTQ_HPP__
#define SHORE_IO_FASTQ_HPP__

#include <string>

#include "shore/fmtio/read.hpp"
#include "shore/fmtio/flatread.hpp"
#include "shore/fmtio/text.hpp"
#include "shore/datatype/datatypes.hpp"
#include "shore/stream/streams.hpp"
#include "shore/processing/pipeline.hpp"

namespace shore {

enum FastqQualType
{
        FQ_QUAL_SANGER,FQ_QUAL_ILLUMINA,FQ_QUAL_SOLEXA
};

class basic_fastq_reader
:public shore::flatread_tags_parser
{
 private:

        shore::basic_line_reader m_reader;

        FastqQualType m_qualtype;

        std::string m_idbuf;
        std::string m_plusbuf;
        std::vector<std::string> m_tokbuf1;
        std::vector<std::string> m_tokbuf2;
        std::string m_seqbuf;
        std::string m_qualbuf;


        bool read_entry();
        void parse(shore::read &read);

 public:

        basic_fastq_reader(const std::string &fn);
        basic_fastq_reader(std::istream *const is);

        void set_quality_type(const FastqQualType t);

        bool next(shore::read &r);

        std::string get_name() const;
};

typedef shore::monolithic<basic_fastq_reader,shore::read,shore::read::compare_type> fastq_reader;

typedef shore::source<fastq_reader> fastq_source;

class fastq_writer
{
 public:

        enum HeaderType
        {
                FQH_SHORE,
                FQH_SHORE_PE,
                FQH_ILLUMINA
                //FQH_SANGER
                //FQH_SRA
        };

 private:

        shore::ostreams m_os;

        HeaderType m_htype;

        std::string m_machine;
        std::string m_barcode;

        // report qualities with illumina offset, not sanger
        bool m_illuminaqual;
        bool m_writetags;

        shore::read_reader::rltxy m_rltxybuf;
        
 public:

        typedef shore::read append_type;

        fastq_writer(const std::string& fn,const HeaderType ht);

        void set_flowcell(const std::string& machine);
        void set_barcode(const std::string& bc);

        void set_writetags(const bool b);

        void set_illumina_qualities(const bool q);

        void append(const shore::read& f);

        void flush();
};

typedef shore::sink<fastq_writer> fastq_sink;

class qual_writer
{
 private:

        static const int SANGER_TRF=33;

        shore::ostreams m_os;

 public:

        typedef shore::read append_type;

        qual_writer(const std::string &fn);

        void append(const shore::read &f);

        void flush();
};

typedef shore::sink<qual_writer> qual_sink;

} // namespace

#endif // SHORE_IO_FASTQ_HPP__