sagereader.h

Go to the documentation of this file.

/**
 * \file input/sage/sagereader.h
 * \date 21/08/2024
 * \author Olivier Langella
 * \brief read data files from Sage output
 */
 
/*******************************************************************************
 * Copyright (c) 2024 Olivier Langella
 *<Olivier.Langella@universite-paris-saclay.fr>.
 *
 * This file is part of i2MassChroQ.
 *
 *     i2MassChroQ 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.
 *
 *     i2MassChroQ 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 i2MassChroQ.  If not, see <http://www.gnu.org/licenses/>.
 *
 ******************************************************************************/
 
#pragma once
#include "../../../../fasta/fastahandlerinterface.h"
#include "../../../../amino_acid/aamodification.h"
#include "pappsomspp/core/types.h"
#include "sagefilereader.h"
#include "../psmproteinmap.h"
 
 
namespace pappso::cbor::psm
{
/**
 * @todo write docs
 */
class SageReader
{
  public:
  /**
   * Default constructor
   */
  SageReader(pappso::UiMonitorInterface *p_monitor,
             pappso::cbor::CborStreamWriter *p_output,
             const SageFileReader &sage_file_reader,
             const QString &sage_json_file);
 
  void read();
  /**
   * Destructor
   */
  virtual ~SageReader();
 
 
  struct SageModification
  {
    SageModification()
    {
      modification    = nullptr;
      residue         = (Enums::AminoAcidChar)' ';
      position        = ' ';
      strModification = "";
    };
    SageModification(const SageModification &other)
    {
      modification    = other.modification;
      position        = other.position;
      residue         = other.residue;
      strModification = other.strModification;
    };
    pappso::AaModificationP modification;
    QChar position; //^, [,], $
    Enums::AminoAcidChar residue;
    QString strModification;
  };
 
  std::vector<SageModification> getStaticModificationList() const;
  std::vector<SageModification> getVariableModificationList() const;
  QString getDecoyTag() const;
 
  const SageFileReader &getSageFileReader() const;
 
  pappso::cbor::CborStreamWriter &getCborStreamWriter() const;
 
  const QString &getmJsonAbsoluteFilePath() const;
 
  const QString &getMzmlPath(const QString &file_msrun) const;
 
  private:
  void readTsvFile();
  void extractMzmlPathList(const QJsonDocument &json_doc);
  QString getTsvFilePath(const QJsonDocument &json_doc);
  QString getFastaFilePath(const QJsonDocument &json_doc);
  QString convertToLocalFileOrDie(const QString &file_str) const;
 
 
  class FastaSeq : public pappso::FastaHandlerInterface
  {
    public:
    FastaSeq(SageReader *self);
    void setSequence(const QString &description_in, const QString &sequence_in) override;
 
    private:
    SageReader *mp_self;
    QString m_decoyTag;
  };
 
  private:
  const SageFileReader &m_sageFileReader;
  pappso::UiMonitorInterface *mp_monitor;
  pappso::cbor::CborStreamWriter *mp_cborWriter;
  PsmProteinMap m_psmProteinMap;
  QString m_jsonAbsoluteFilePath;
  QStringList m_mzmlPathList;
};
} // namespace pappso::cbor::psm