1 /*
2  * Copyright (c) 2022 Omar Polo <op@openbsd.org>
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 #include <stdio.h>
18 #include <stdlib.h>
19 
20 #include "db.h"
21 #include "fts.h"
22 #include "tokenize.h"
23 
24 struct doclist {
25 	uint32_t	*ids;
26 	size_t		 len;
27 };
28 
29 int
30 fts(struct db *db, const char *query, db_hit_cb cb, void *data)
31 {
32 	struct doclist *xs = NULL;
33 	size_t i, len;
34 	char **toks, **t;
35 	int ret = 0;
36 
37 	if ((toks = tokenize(query)) == NULL)
38 		return -1;
39 
40 	len = 0;
41 	for (t = toks; *t != NULL; ++t)
42 		len++;
43 
44 	if (len == 0)
45 		goto done;
46 
47 	if ((xs = calloc(len, sizeof(*xs))) == NULL) {
48 		freetoks(toks);
49 		return -1;
50 	}
51 
52 	for (i = 0; i < len; ++i) {
53 		xs[i].ids = db_word_docs(db, toks[i], &xs[i].len);
54 		if (xs[i].ids == NULL || xs[i].len == 0)
55 			goto done;
56 	}
57 
58 	for (;;) {
59 		struct db_entry e;
60 		uint32_t mdoc;
61 
62 		mdoc = xs[0].ids[0];
63 		for (i = 1; i < len; ++i) {
64 			if (xs[i].ids[0] > mdoc)
65 				goto next;
66 			while (xs[i].ids[0] < mdoc) {
67 				if (--xs[i].len == 0)
68 					goto done;
69 				xs[i].ids++;
70 			}
71 
72 			if (xs[i].ids[0] != mdoc)
73 				goto next;
74 		}
75 
76 		if (db_doc_by_id(db, mdoc, &e) == -1) {
77 			ret = -1;
78 			goto done;
79 		}
80 
81 		if (cb(db, &e, data) == -1) {
82 			ret = -1;
83 			goto done;
84 		}
85 
86 	next:
87 		if (--xs[0].len == 0)
88 			goto done;
89 		xs[0].ids++;
90 	}
91 
92 done:
93 	free(xs);
94 	freetoks(toks);
95 
96 	return ret;
97 }