Line data    Source code

       1             : // -*- C++ -*-
       2             : /* Copyright (C) 1989-2020 Free Software Foundation, Inc.
       3             :      Written by James Clark (jjc@jclark.com)
       4             : 
       5             : This file is part of groff, the GNU roff typesetting system.
       6             : 
       7             : groff is free software; you can redistribute it and/or modify it under
       8             : the terms of the GNU General Public License as published by the Free
       9             : Software Foundation, either version 3 of the License, or
      10             : (at your option) any later version.
      11             : 
      12             : groff is distributed in the hope that it will be useful, but WITHOUT ANY
      13             : WARRANTY; without even the implied warranty of MERCHANTABILITY or
      14             : FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
      15             : for more details.
      16             : 
      17             : You should have received a copy of the GNU General Public License
      18             : along with this program.  If not, see <http://www.gnu.org/licenses/>. */
      19             : 
      20             : enum token_type {
      21             :   TOKEN_OTHER,
      22             :   TOKEN_UPPER,
      23             :   TOKEN_LOWER,
      24             :   TOKEN_ACCENT,
      25             :   TOKEN_PUNCT,
      26             :   TOKEN_HYPHEN,
      27             :   TOKEN_RANGE_SEP
      28             : };
      29             : 
      30             : class token_info {
      31             : private:
      32             :   token_type type;
      33             :   const char *sort_key;
      34             :   const char *other_case;
      35             : public:
      36             :   token_info();
      37             :   void set(token_type, const char *sk = 0, const char *oc = 0);
      38             :   void lower_case(const char *start, const char *end, string &result) const;
      39             :   void upper_case(const char *start, const char *end, string &result) const;
      40             :   void sortify(const char *start, const char *end, string &result) const;
      41             :   int sortify_non_empty(const char *start, const char *end) const;
      42             :   int is_upper() const;
      43             :   int is_lower() const;
      44             :   int is_accent() const;
      45             :   int is_other() const;
      46             :   int is_punct() const;
      47             :   int is_hyphen() const;
      48             :   int is_range_sep() const;
      49             : };
      50             : 
      51           0 : inline int token_info::is_upper() const
      52             : {
      53           0 :   return type == TOKEN_UPPER;
      54             : }
      55             : 
      56           0 : inline int token_info::is_lower() const
      57             : {
      58           0 :   return type == TOKEN_LOWER;
      59             : }
      60             : 
      61           0 : inline int token_info::is_accent() const
      62             : {
      63           0 :   return type == TOKEN_ACCENT;
      64             : }
      65             : 
      66             : inline int token_info::is_other() const
      67             : {
      68             :   return type == TOKEN_OTHER;
      69             : }
      70             : 
      71           0 : inline int token_info::is_punct() const
      72             : {
      73           0 :   return type == TOKEN_PUNCT;
      74             : }
      75             : 
      76           0 : inline int token_info::is_hyphen() const
      77             : {
      78           0 :   return type == TOKEN_HYPHEN;
      79             : }
      80             : 
      81           0 : inline int token_info::is_range_sep() const
      82             : {
      83           0 :   return type == TOKEN_RANGE_SEP;
      84             : }
      85             : 
      86             : bool get_token(const char **ptr, const char *end);
      87             : const token_info *lookup_token(const char *start, const char *end);