1 /* locatedb.h -- declarations for the locate database
2 Copyright (C) 1994-2022 Free Software Foundation, Inc.
3
4 This program is free software: you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation, either version 3 of the License, or
7 (at your option) any later version.
8
9 This program 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
12 GNU General Public License for more details.
13
14 You should have received a copy of the GNU General Public License
15 along with this program. If not, see <https://www.gnu.org/licenses/>.
16 */
17
18 #ifndef INC_LOCATEDB_H
19 # define INC_LOCATEDB_H 1
20
21 /* The magic string at the start of a locate database, to make sure
22 it's in the right format. The 02 is the database format version number.
23 This string has the same format as a database entry, but you can't
24 concatenate databases even if you remove it, since the differential count
25 in the first entry of the second database will be wrong. */
26 # define LOCATEDB_MAGIC "\0LOCATE02"
27
28 /* Common-prefix length differences in the ranges
29 0..127, -127..-1 (0x00..0x7f, 0x81..0xff) fit into one byte.
30 This value (which is -128) indicates that the difference is
31 too large to fit into one byte, and a two-byte integer follows. */
32 # define LOCATEDB_ESCAPE 0x80
33 # define LOCATEDB_ONEBYTE_MAX (127)
34 # define LOCATEDB_ONEBYTE_MIN (-127)
35
36
37 /* If it is ever possible to try to encode LOCATEDB_MAGIC as a
38 * single-byte offset, then an unfortunate length of common prefix
39 * will produce a spurious escape character, desynchronising the data
40 * stream. We use a compile-time check in the preprocessor to prevent
41 * this.
42 */
43 # if LOCATEDB_ESCAPE <= LOCATEDB_ONEBYTE_MAX
44 # error "You have a bad combination of LOCATEDB_ESCAPE and LOCATEDB_ONEBYTE_MAX, see above"
45 # endif
46
47 /* These are used for old, bigram-encoded databases: */
48
49 /* Means the differential count follows in a 2-byte int instead. */
50 # define LOCATEDB_OLD_ESCAPE 30
51
52 /* Offset added to differential counts to encode them as positive numbers. */
53 # define LOCATEDB_OLD_OFFSET 14
54
55 typedef enum
56 {
57 GetwordEndianStateInitial = 0,
58 GetwordEndianStateNative = 1,
59 GetwordEndianStateSwab = 2
60 } GetwordEndianState;
61
62 int getword (FILE *fp, const char *filename,
63 size_t maxvalue,
64 GetwordEndianState *endian_state_flag);
65
66 # define SLOCATE_DB_MAGIC_LEN 2
67
68 #endif /* !INC_LOCATEDB_H */