---

Parser.hpp

Go to the documentation of this file.

/*==========================================================================
 * Copyright (c) 2001 Carnegie Mellon University.  All Rights Reserved.
 *
 * Use of the Lemur Toolkit for Language Modeling and Information Retrieval
 * is subject to the terms of the software license set forth in the LICENSE
 * file included with this software, and also available at
 * http://www.cs.cmu.edu/~lemur/license.html
 *
 *==========================================================================
*/

#ifndef _PARSER_HPP
#define _PARSER_HPP

#include "TextHandler.hpp"
#include "WordSet.hpp"


class Parser : public TextHandler {

public:

  Parser() {
    acros = NULL;
  }

  virtual void parse(char * filename) { parseFile(filename); } ;
  
  virtual void parseFile(char* filename) = 0;

  virtual void parseBuffer(char * buf, int len) = 0;

  virtual void setAcroList(WordSet * acronyms)  {
    acros = acronyms;
  }

  virtual long fileTell() = 0;

  virtual long getDocBytePos() { return docpos; }

protected: 
  bool isAcronym(char * word) {
    if (acros != NULL) 
      return acros->contains(word);
    return false;
  }

  long docpos; 

private:
  WordSet * acros;

};

#endif

---