include/marks.h

   1 /*
   2  * Copyright (C) 2004 Jesus Gimenez, Lluis Marquez and Senen Moya
   3  *
   4  * This library is free software; you can redistribute it and/or
   5  * modify it under the terms of the GNU Lesser General Public
   6  * License as published by the Free Software Foundation; either
   7  * version 2.1 of the License, or (at your option) any later version.
   8  *
   9  * This library is distributed in the hope that it will be useful,
  10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12  * Lesser General Public License for more details.
  13  *
  14  * You should have received a copy of the GNU Lesser General Public
  15  * License along with this library; if not, write to the Free Software
  16  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  17  */
  18
  19 #ifndef MARKS_H
  20
  21 #define SLASTW "Swn" //Last Word
  22 #define WMARK  "w"   //Words
  23 #define PMARK  "p"   //POS
  24 #define KMARK  "k"   //Ambiguity Classes
  25 #define MMARK  "m"   //Maybe
  26 #define MFTMARK "f"   //Most Frequent Tag --> f(-1) --> f-1:NN
  27 #define PREFIX_MARK  "a"   //prefixes
  28 #define SUFFIX_MARK  "z"   //Suffixes
  29 #define CHAR_A_MARK "ca"  //Character, counting from the beggining of the begining of the token (starting at 1)
  30 #define CHAR_Z_MARK "cz"  //Character, counting from the end of the begining of the token (starting at 1)
  31 #define LENGTH_MARK "L"  //token length
  32 #define START_CAPITAL_MARK "SA" //start with upper case
  33 #define START_LOWER_MARK   "sa" //start with lower case
  34 #define START_NUMBER_MARK  "SN" //start with number
  35 #define ALL_UPPER_MARK "AA" //all upper case
  36 #define ALL_LOWER_MARK "aa" //all lower case
  37 #define CONTAIN_CAP_MARK "CA" //contains a capital letter
  38 #define CONTAIN_CAPS_MARK "CAA" //contains several capital letters
  39 #define CONTAIN_PERIOD_MARK "CP" //contains period
  40 #define CONTAIN_COMMA_MARK "CC" //contains comma
  41 #define CONTAIN_NUMBER_MARK "CN" //contains number
  42 #define MULTIWORD_MARK "MW" //contains underscores (multiword)
  43
  44 #define MARKS_H
  45 #endif