1 /*
2  * Copyright (c) 2022 Omar Polo <op@omarpolo.com>
3  *
4  * Permission to use, copy, modify, and distribute this software for any
5  * purpose with or without fee is hereby granted, provided that the above
6  * copyright notice and this permission notice appear in all copies.
7  *
8  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
9  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
10  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
11  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
12  * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
13  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
14  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
15  */
16 
17 #define DB_VERSION	 0
18 #define DB_WORDLEN	32
19 
20 struct db {
21 	uint8_t	*m;
22 	off_t	 len;
23 	uint32_t version;
24 	uint32_t nwords;
25 
26 	uint8_t	*idx_start;
27 	uint8_t	*idx_end;
28 	uint8_t	*list_start;
29 	uint8_t	*list_end;
30 	uint8_t	*docs_start;
31 	uint8_t	*docs_end;
32 };
33 
34 struct db_stats {
35 	size_t		 nwords;
36 	size_t		 ndocs;
37 	const char	*longest_word;
38 	const char	*most_popular;
39 	size_t		 most_popular_ndocs;
40 };
41 
42 struct db_entry {
43 	char	*name;
44 	char	*descr;
45 };
46 
47 typedef int (*db_hit_cb)(struct db *, struct db_entry *, void *);
48 
49 struct dictionary;
50 
51 int		 db_create(FILE *, struct dictionary *, struct db_entry *, size_t);
52 int		 db_open(struct db *, int);
53 uint32_t	*db_word_docs(struct db *, const char *, size_t *);
54 int		 db_stats(struct db *, struct db_stats *);
55 int		 db_listall(struct db *, db_hit_cb, void *);
56 int		 db_doc_by_id(struct db *, int, struct db_entry *);
57 void		 db_close(struct db *);