1 // -*- C++ -*-
2 /* Copyright (C) 1989, 1990, 1991, 1992 Free Software Foundation, Inc.
3 Written by James Clark (jjc@jclark.com)
4
5 This file is part of groff.
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 2, or (at your option) any later
10 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 along
18 with groff; see the file COPYING. If not, write to the Free Software
19 Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */
20
21 enum token_type {
22 TOKEN_OTHER,
23 TOKEN_UPPER,
24 TOKEN_LOWER,
25 TOKEN_ACCENT,
26 TOKEN_PUNCT,
27 TOKEN_HYPHEN
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 };
49
is_upper()50 inline int token_info::is_upper() const
51 {
52 return type == TOKEN_UPPER;
53 }
54
is_lower()55 inline int token_info::is_lower() const
56 {
57 return type == TOKEN_LOWER;
58 }
59
is_accent()60 inline int token_info::is_accent() const
61 {
62 return type == TOKEN_ACCENT;
63 }
64
is_other()65 inline int token_info::is_other() const
66 {
67 return type == TOKEN_OTHER;
68 }
69
is_punct()70 inline int token_info::is_punct() const
71 {
72 return type == TOKEN_PUNCT;
73 }
74
is_hyphen()75 inline int token_info::is_hyphen() const
76 {
77 return type == TOKEN_HYPHEN;
78 }
79
80 int get_token(const char **ptr, const char *end);
81 const token_info *lookup_token(const char *start, const char *end);
82