UniProtXMLHandler.h

Go to the documentation of this file.

// Copyright (c) 2002-present, OpenMS Inc. -- EKU Tuebingen, ETH Zurich, and FU Berlin
// SPDX-License-Identifier: BSD-3-Clause
//
// --------------------------------------------------------------------------
// $Maintainer: Timo Sachsenberg $
// $Authors: Timo Sachsenberg $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/FORMAT/HANDLERS/XMLHandler.h>
#include "UniProtXMLFile.h"
 
#include <functional>
#include <string>
 
namespace OpenMS::Internal
{
  class UniProtXMLHandler :
    public XMLHandler
  {
  public:
    using EntryCallback = std::function<void(UniProtEntry&&)>;
 
    enum class CaptureTarget
    {
      None,
      Accession,
      EntryName,
      FullName,
      PrimaryGene,
      TaxName,
      Sequence,
      FeatureOriginal,
      FeatureVariation,
      IsoformId,
      IsoformName
    };
 
    UniProtXMLHandler(const std::string& filename, EntryCallback callback);
 
    ~UniProtXMLHandler() override;
 
    void onStartElement(const char16_t* qname, const XMLAttributes& attrs) override;
    void onEndElement(const char16_t* qname) override;
    void onCharacters(const char16_t* chars, Size length) override;
 
  private:
    EntryCallback callback_;
    UniProtEntry current_entry_;
 
    int depth_{0};
 
    int entry_depth_{0};                
    int recommended_name_depth_{0};     
    int gene_depth_{0};                 
    int organism_depth_{0};             
    int alt_products_depth_{0};         
    int isoform_depth_{0};              
    int feature_depth_{0};              
    int sequence_depth_{0};             
 
    bool full_name_captured_{false};
 
    std::string char_buf_;
 
    CaptureTarget capture_{CaptureTarget::None};
 
    UniProtFeature current_feature_;
 
    UniProtIsoform current_isoform_;
 
    void resetEntry_();
    void resetFeature_();
 
    static int parsePosition_(const std::string& attr);
  };
 
} // namespace OpenMS::Internal