contextreader.h

Go to the documentation of this file.

// -*- C++ -*-
/*
  Phrasehunter - index and query text corpora
  Copyright (C) 2006  Torsten Marek (shlomme@gmx.de) &
  Armin Schmidt (armin.sch@gmail.com)
  
  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; either version 2
  of the License, or (at your option) any later version.
  
  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.
  
  You should have received a copy of the GNU General Public License
  along with this program; if not, write to the Free Software
  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
*/

#ifndef CONTEXTREADER_H
#define CONTEXTREADER_H CONTEXTREADER_H

#include <boost/shared_ptr.hpp>
#include <boost/filesystem/path.hpp>
#include <boost/lexical_cast.hpp>

#include "ph_types.h"
#include "phexception.h"

namespace PhraseHunter {

//! Class for reading the left and right context of a token.
class ContextReader 
{
public:
    /**
       \brief Constructor. Should not be called directly. Instead, use CorpusManager::contextReader().
       \param Textdirectory The directory containing the plain source text files.
    */
    ContextReader(const boost::filesystem::path& textdirectory);
    ~ContextReader() {}

    /**
       \brief Get the context for one particular position in a particular document.
       \param doc The ID of the document.
       \param pos The offset of the token, i.e. the byte position in the document.
       \param tokenLength Byte length of word.
       \param width The width of each left and right context.
    */
    TokenContextPtr getContextFromPosition(DocID doc, IdxPos pos, 
                                           size_t tokenLength, unsigned int width) const
      throw(Exceptions::FileError);
    /**
       \brief Fill a TokenContext object with a particular context.
       \param context TokenContext object to fill.
       \param width the width of each left and right context.
    */
    void fillContext(TokenContextPtr context, unsigned int width) const
        throw(Exceptions::FileError);

    /**
       \brief Get the context of a token.
       \param token The token in question.
       \param width The width of each left and right context.
    */
    std::vector<TokenContextPtr> context(TokenPtr token, unsigned int width) const
        throw(Exceptions::FileError);
    //! Overloaded convenience function.
    std::vector<TokenContextPtr> context(const TokenVector& tokens, unsigned int width) const
        throw(Exceptions::FileError);

private:
    static const int BufferSize = 5120;
    void readBlock(std::ifstream& file, TokenContextPtr) const;

    unsigned int removeNewlines(char* buffer, unsigned int length) const;

    inline boost::filesystem::path documentFile(DocID docId) const
    {
        return m_textDirectory / boost::lexical_cast<std::string>(docId);    
    }
    
    boost::filesystem::path m_textDirectory;
};

} // PhraseHunter

#endif // CONTEXTREADER_H

---