wasteTypes.h

Go to the documentation of this file.

/* -*- Mode: C++; coding: utf-8; c-basic-offset: 2; -*- */
/*
   libmoot : moocow's part-of-speech tagging library
   Copyright (C) 2013-2017 by Bryan Jurish <moocow@cpan.org> and Kay-Michael Würzner

   This library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 3 of the License, or (at your option) any later version.
   
   This library 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
   Lesser General Public License for more details.
   
   You should have received a copy of the GNU Lesser General Public
   License along with this library; if not, write to the Free Software
   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/

/*--------------------------------------------------------------------------
 * File: wasteTypes.h
 * Author: Bryan Jurish <moocow@cpan.org>, Kay-Michael Würzner
 * Description:
 *   + moot PoS tagger : WASTE HMM tokenizer: common definitions
 *--------------------------------------------------------------------------*/

#ifndef _WASTE_TYPES_H
#define _WASTE_TYPES_H

#include <string>
#include <stdexcept>

namespace moot {

enum wasteScannerTypeE {
  wScanTypeEOF,         
  wScanTypeWB,          
  wScanTypeSB,          
  wScanTypeLatin,       
  wScanTypeGreek,       
  wScanTypeAlpha,       
  wScanTypeNewline,     
  wScanTypeSpace,       
  wScanTypeNumber,      
  wScanTypeRoman,       
  wScanTypeHyphen,      
  wScanTypePunct,       
  wScanTypeLink,        
  wScanTypeXML,         
  wScanTypeComment,     
  wScanTypePercent,     
  wScanTypeOther,       
  NwScanTypes           
};
typedef wasteScannerTypeE wasteScannerType;

extern const char *wasteScannerTypeNames[NwScanTypes];


enum wasteLexerTypeE {
  wLexerTypeDot,        
  wLexerTypeComma,      
  wLexerTypeHyph,       
  wLexerTypeApostrophe, 
  wLexerTypeQuote,      
  wLexerTypeMonetary,   
  wLexerTypePercent,    
  wLexerTypePlus,       
  wLexerTypeLBR,        
  wLexerTypeRBR,        
  wLexerTypeSlash,      
  wLexerTypeColon,      
  wLexerTypeSemicolon,  
  wLexerTypeEOS,        
  wLexerTypePunct,      
  wLexerTypeSpace,      
  wLexerTypeNewline,    
  wLexerTypeNumber,     
  wLexerTypeRomanCaps,  
  wLexerTypeRomanLower, 
  wLexerTypeAlphaLower, 
  wLexerTypeAlphaUpper, 
  wLexerTypeAlphaCaps,  
  wLexerTypeAlphaTrunc, 
  wLexerTypeOther,      
  NwLexerTypes          
};
typedef wasteLexerTypeE wasteLexerType;

extern const char *wasteLexerTypeNames[NwLexerTypes];

//--------------------------------------------------------------------------


enum wasteTagAttrPosE {
  wtap_w = 1, //-- 'w': beginning-of-word
  wtap_S = 4, //-- 'S': end-of-sentence
  wtap_s = 7  //-- 's': beginning-of-sentence
};
typedef wasteTagAttrPosE wasteTagAttrPos;

inline bool waste_tag_attr_get(const std::string &tagstr, size_t rpos, bool mydefault=false)
{
  return tagstr.size() > rpos ? (tagstr[tagstr.size()-rpos]!='0') : mydefault;
};

inline void waste_tag_attr_set(std::string &tagstr, size_t rpos, bool val)
{
  if (tagstr.size() <= rpos) throw std::overflow_error("waste_tag_attr_set(): tag string too short");
  tagstr[tagstr.size()-rpos] = (val ? '1' : '0');
};


//--------------------------------------------------------------------------


wasteLexerTypeE waste_casetype(const std::string &tok_text);

wasteLexerTypeE waste_lexertype(const std::string &tok_text);

}; /*--/namespace moot --*/

#endif /* _WASTE_TYPES_H */