---

BasicDocStream.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 _BASICFILESTREAM_HPP
#define _BASICFILESTREAM_HPP


#include "common_headers.hpp"
#include <cassert>
#include <cstdio>
#include <cstring>
#include "DocStream.hpp"
#include "Exception.hpp"


#define MAXLINE 65536


class BasicTokenTerm : public TokenTerm {
 public:
  BasicTokenTerm() {}
  virtual ~BasicTokenTerm() {}
  virtual const char *spelling() { return str;}
  friend class BasicTokenDoc;
 private:
  char *str;
};



class BasicTokenDoc : public Document {
 public:
  BasicTokenDoc(ifstream *stream): docStr(stream) {
  }
   void startTermIteration(); 
  
  char *getID() const { return (char *)id;}

  bool hasMore() { return (strcmp(curWord, "</DOC>") != 0);}
    
  TokenTerm * nextTerm();

  friend class BasicDocStream;
 private:
  void readID(); 
  char *curWord;
  char buf1[20000];
  char buf2[20000];
  char id[2000];
  ifstream *docStr;
};


class BasicDocStream : public DocStream
{
public:
  BasicDocStream() {}
  BasicDocStream (const char * inputFile);

  virtual ~BasicDocStream() {  delete ifs;}

public:
        
  bool hasMore(); 

  void startDocIteration();

  Document *nextDoc();

private:
  char file[1024];
  ifstream *ifs;
  char buf[2000];
  bool nextTokenRead;
};




#endif

---