obconversion.h

Go to the documentation of this file.

/**********************************************************************
obconversion.h - Handle file conversions. Declaration of OBFormat, OBConversion

Copyright (C) 2004-2009 by Chris Morley

This file is part of the Open Babel project.
For more information, see <http://openbabel.org/>

This program 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 version 2 of the License.

This program 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.
***********************************************************************/

#ifndef OB_CONV_H
#define OB_CONV_H

#include <openbabel/babelconfig.h>

#include <iostream>
#include <fstream>
#include <sstream>
#include <cassert>

#include <string>
#include <vector>
#include <map>
#ifdef HAVE_STRINGS_H
#include <strings.h>
#endif

#include <openbabel/oberror.h>
#include <openbabel/format.h>
#include <openbabel/lineend.h>

// These macros are used in DLL builds. If they have not
// been set in babelconfig.h, define them as nothing.
#ifndef OBCONV
        #define OBCONV
#endif
#ifndef OBDLL
        #define OBDLL
#endif

namespace OpenBabel {

  // Needed to preserve deprecated API
  typedef OBPlugin::PluginIterator Formatpos;

  OBERROR extern  OBMessageHandler obErrorLog;

  //*************************************************
  // Class introduction in obconversion.cpp
  class OBCONV OBConversion
    {
    public:

      OBConversion(std::istream* is=NULL, std::ostream* os=NULL);
      OBConversion(std::string inFilename, std::string outFilename="");
      OBConversion(const OBConversion& o);
      OBConversion& operator=(const OBConversion& rhs);

      virtual     ~OBConversion();

      static int                                RegisterFormat(const char* ID, OBFormat* pFormat, const char* MIME = NULL);
      static OBFormat*  FindFormat(const char* ID);
      static OBFormat*  FindFormat(const std::string ID);
      static OBFormat*  FormatFromExt(const char* filename);
      static OBFormat*  FormatFromExt(const char* filename, bool& isgzip);
      static OBFormat*  FormatFromExt(const std::string filename);
      static OBFormat*  FormatFromExt(const std::string filename, bool& isgzip);
      static OBFormat*        FormatFromMIME(const char* MIME);

#ifndef SWIG
      static bool               GetNextFormat(Formatpos& itr, const char*& str,OBFormat*& pFormat);
#endif



      static const char* Description(); //generic conversion options


      std::istream* GetInStream() const {return pInput;};
      std::ostream* GetOutStream() const {return pOutput;};

      //  if false, then will be treated as gzipped stream only if z/zin is set.
      void          SetInStream(std::istream* pIn, bool takeOwnership=false);
      void          SetOutStream(std::ostream* pOut, bool takeOwnership=false);

      bool        SetInAndOutFormats(const char* inID, const char* outID, bool ingzip=false, bool outgzip=false);
      bool        SetInAndOutFormats(OBFormat* pIn, OBFormat* pOut, bool ingzip=false, bool outgzip=false);
      bool            SetInFormat(const char* inID, bool isgzip=false);
      bool            SetInFormat(OBFormat* pIn, bool isgzip=false);
      bool            SetOutFormat(const char* outID, bool isgzip=false);
      bool            SetOutFormat(OBFormat* pOut, bool isgzip=false);

      OBFormat*   GetInFormat() const{return pInFormat;};
      OBFormat*   GetOutFormat() const{return pOutFormat;};
      bool GetInGzipped() const{return inFormatGzip;};
      bool GetOutGzipped() const{return outFormatGzip;};
      std::string GetInFilename() const{return InFilename;};
      std::string GetOutFilename() const{return OutFilename;};

      std::streampos GetInPos()const{return wInpos;};

      size_t GetInLen()const{return wInlen;};

      const char* GetTitle() const;

      OBConversion* GetAuxConv() const {return pAuxConv;};
      void          SetAuxConv(OBConversion* pConv) {pAuxConv=pConv;};

      enum Option_type { INOPTIONS, OUTOPTIONS, GENOPTIONS, ALL };

      const char* IsOption(const char* opt,Option_type opttyp=OUTOPTIONS);

      const std::map<std::string,std::string>* GetOptions(Option_type opttyp)
        { return &OptionsArray[opttyp];};

      void AddOption(const char* opt, Option_type opttyp=OUTOPTIONS, const char* txt=NULL);

      bool RemoveOption(const char* opt, Option_type optype);

      void SetOptions(const char* options, Option_type opttyp);

      static void RegisterOptionParam(std::string name, OBFormat* pFormat,
                                      int numberParams=0, Option_type typ=OUTOPTIONS);

      static int GetOptionParams(std::string name, Option_type typ);

      void CopyOptions(OBConversion* pSourceConv, Option_type typ=ALL);


      // @brief Set and return the list of supported input format
      std::vector<std::string> GetSupportedInputFormat();
      // @brief Set and return the list of supported output format
      std::vector<std::string> GetSupportedOutputFormat();


      int         Convert(std::istream* is, std::ostream* os);

      int         Convert();

      int                                       FullConvert(std::vector<std::string>& FileList,
                              std::string& OutputFileName, std::vector<std::string>& OutputFileList);


      int     AddChemObject(OBBase* pOb);
      OBBase*  GetChemObject(); 
      bool     IsLast();
      bool     IsFirstInput();
      void     SetFirstInput(bool b=true);
      int      GetOutputIndex() const ;
      void     SetOutputIndex(int indx);
      void     SetMoreFilesToCome();
      void     SetOneObjectOnly(bool b=true);
      void     SetLast(bool b){SetOneObjectOnly(b);}
      bool     IsLastFile(){ return !MoreFilesToCome;}
      int      GetCount()const { return Count; }

      static OBFormat* GetDefaultFormat(){return OBFormat::FindType(NULL);};


      bool                              Write(OBBase* pOb, std::ostream* pout=NULL);


      std::string                     WriteString(OBBase* pOb, bool trimWhitespace = false);


      bool                            WriteFile(OBBase* pOb, std::string filePath);

      void CloseOutFile();


      bool      Read(OBBase* pOb, std::istream* pin=NULL);

//      OBBase* ReadObject(std::istream* pin=NULL);


      bool      ReadString(OBBase* pOb, std::string input);


      bool      ReadFile(OBBase* pOb, std::string filePath);

      bool OpenInAndOutFiles(std::string infilepath, std::string outfilepath);

      void ReportNumberConverted(int count, OBFormat* pFormat=NULL);

      int NumInputObjects();


protected:
      static std::string BatchFileName(std::string& BaseName, std::string& InFile);
      static std::string IncrementedFileName(std::string& BaseName, const int Count);
      static bool CheckForUnintendedBatch(const std::string& infile, const std::string& outfile);

      void ClearInStreams();

    protected:

      //helper class for saving stream state
      struct StreamState
      {
          std::ios *pStream; //active stream
          std::vector<std::ios *> ownedStreams; //streams we own the memory to

          StreamState(): pStream(NULL) {}
          ~StreamState()
          {
            assert(ownedStreams.size() == 0); //should be popped
          }

          void pushInput(OBConversion& conv);
          void popInput(OBConversion& conv);

          void pushOutput(OBConversion& conv);
          void popOutput(OBConversion& conv);

          bool isSet() const { return pStream != NULL; }
      };

      bool             SetStartAndEnd();
//      static FMapType& FormatsMap();///<contains ID and pointer to all OBFormat classes
//      static FMapType& FormatsMIMEMap();///<contains MIME and pointer to all OBFormat classes
      typedef std::map<std::string,int> OPAMapType;
      static OPAMapType& OptionParamArray(Option_type typ);
      bool             OpenAndSetFormat(bool SetFormat, std::ifstream* is, std::stringstream* ss=NULL);

      std::string         InFilename, OutFilename; //OutFileName added v2.4.0

      typedef   FilteringInputStream< LineEndingExtractor > LEInStream;

      std::istream *pInput; //input stream, may be filtered
      std::vector<std::istream *> ownedInStreams; //streams we own the memory to

      std::ostream *pOutput; //output stream, may have filters applied
      std::vector<std::ostream *> ownedOutStreams; //streams we own the memory to


      static OBFormat*  pDefaultFormat;
      OBFormat*           pInFormat;
      OBFormat*   pOutFormat;

      std::map<std::string,std::string> OptionsArray[3];

      int                 Index;
      unsigned int        StartNumber;
      unsigned int        EndNumber;
      int                 Count;
      bool                      m_IsFirstInput;
      bool                m_IsLast;
      bool                MoreFilesToCome;
      bool                OneObjectOnly;
      bool                ReadyToInput;
      bool      SkippedMolecules;    

      //unlike the z and zin options, these are not sticky - setting formats will reset them
      bool inFormatGzip;
      bool outFormatGzip;

      OBBase*             pOb1;
      std::streampos wInpos; 
      std::streampos rInpos; 
      size_t wInlen; 
      size_t rInlen; 

      OBConversion* pAuxConv;

      std::vector<std::string> SupportedInputFormat; 
      std::vector<std::string> SupportedOutputFormat; 

    };

} //namespace OpenBabel
#endif //OB_CONV_H