1 /*
2 * Copyright 2010 Nexenta Systmes, Inc. All rights reserved.
3 * Copyright (c) 1995 Alex Tatmanjants <alex@elvisti.kiev.ua>
4 * at Electronni Visti IA, Kiev, Ukraine.
5 * All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 *
16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND
17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE
20 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
22 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
23 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
24 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26 * SUCH DAMAGE.
27 */
28
29 #ifndef _COLLATE_H_
30 #define _COLLATE_H_
31
32 #include <sys/types.h>
33 #include <limits.h>
34
35 #define COLLATE_STR_LEN 24 /* should be 64-bit multiple */
36 #define COLLATE_VERSION "IllumosCollate2\n"
37
38 #define COLLATE_MAX_PRIORITY (0x7fffffff) /* max signed value */
39 #define COLLATE_SUBST_PRIORITY (0x40000000) /* bit indicates subst table */
40
41 #define DIRECTIVE_UNDEF 0x00
42 #define DIRECTIVE_FORWARD 0x01
43 #define DIRECTIVE_BACKWARD 0x02
44 #define DIRECTIVE_POSITION 0x04
45 #define DIRECTIVE_UNDEFINED 0x08 /* special last weight for UNDEFINED */
46
47 #define DIRECTIVE_DIRECTION_MASK (DIRECTIVE_FORWARD | DIRECTIVE_BACKWARD)
48
49 /*
50 * The collate file format is as follows:
51 *
52 * char version[COLLATE_STR_LEN]; // must be COLLATE_VERSION
53 * collate_info_t info; // see below, includes padding
54 * collate_char_pri_t char_data[256]; // 8 bit char values
55 * collate_subst_t subst[*]; // 0 or more substitutions
56 * collate_chain_pri_t chains[*]; // 0 or more chains
57 * collate_large_pri_t large[*]; // extended char priorities
58 *
59 * Note that all structures must be 32-bit aligned, as each structure
60 * contains 32-bit member fields. The entire file is mmap'd, so its
61 * critical that alignment be observed. It is not generally safe to
62 * use any 64-bit values in the structures.
63 */
64
65 typedef struct collate_info {
66 uint8_t directive_count;
67 uint8_t directive[COLL_WEIGHTS_MAX];
68 int32_t pri_count[COLL_WEIGHTS_MAX];
69 int32_t flags;
70 int32_t chain_count;
71 int32_t large_count;
72 int32_t subst_count[COLL_WEIGHTS_MAX];
73 int32_t undef_pri[COLL_WEIGHTS_MAX];
74 } collate_info_t;
75
76 typedef struct collate_char {
77 int32_t pri[COLL_WEIGHTS_MAX];
78 } collate_char_t;
79
80 typedef struct collate_chain {
81 wchar_t str[COLLATE_STR_LEN];
82 int32_t pri[COLL_WEIGHTS_MAX];
83 } collate_chain_t;
84
85 typedef struct collate_large {
86 int32_t val;
87 collate_char_t pri;
88 } collate_large_t;
89
90 typedef struct collate_subst {
91 int32_t key;
92 int32_t pri[COLLATE_STR_LEN];
93 } collate_subst_t;
94
95 int _collate_load_tables(const char *);
96 void _collate_lookup(const wchar_t *, int *, int *, int, int **);
97 size_t _collate_wxfrm(const wchar_t *, wchar_t *, size_t);
98 size_t _collate_sxfrm(const wchar_t *, char *, size_t);
99 int _collate_range_cmp(wchar_t, wchar_t);
100
101 extern int _collate_load_error;
102 extern int _collate_substitute_nontrivial;
103 extern collate_info_t *_collate_info;
104
105 #endif /* !_COLLATE_H_ */