1 /* Split source by line breaks, and calculate a simplistic checksum. */
2 /*
3  * Copyright (c) 2020 Neels Hofmeyr <neels@hofmeyr.de>
4  *
5  * Permission to use, copy, modify, and distribute this software for any
6  * purpose with or without fee is hereby granted, provided that the above
7  * copyright notice and this permission notice appear in all copies.
8  *
9  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
10  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
11  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
12  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
13  * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
14  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
15  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
16  */
17 
18 #include <diff/diff_main.h>
19 
20 static int diff_data_atomize_text_lines(struct diff_data *d)
21 {
22 	const uint8_t *pos = d->data;
23 	const uint8_t *end = pos + d->len;
24 
25 	unsigned int array_size_estimate = d->len / 50;
26 	unsigned int pow2 = 1;
27 	while (array_size_estimate >>= 1)
28 		pow2++;
29 
30 	ARRAYLIST_INIT(d->atoms, 1 << pow2);
31 
32 	while (pos < end) {
33 		const uint8_t *line_end = pos;
34 		unsigned int hash = 0;
35 
36 		while (line_end < end && *line_end != '\r' && *line_end != '\n') {
37 			hash = hash * 23 + *line_end;
38 			line_end++;
39 		}
40 
41 		/* When not at the end of data, the line ending char ('\r' or '\n') must follow */
42 		if (line_end < end)
43 			line_end++;
44 		/* If that was an '\r', also pull in any following '\n' */
45 		if (line_end[0] == '\r' && line_end < end && line_end[1] == '\n')
46 			line_end++;
47 
48 		/* Record the found line as diff atom */
49 		struct diff_atom *atom;
50 		ARRAYLIST_ADD(atom, d->atoms);
51 		if (!atom)
52 			return DIFF_RC_ENOMEM;
53 
54 		*atom = (struct diff_atom){
55 			.at = pos,
56 			.len = line_end - pos,
57 			.hash = hash,
58 		};
59 
60 		/* Starting point for next line: */
61 		pos = line_end;
62 	}
63 
64 	return DIFF_RC_OK;
65 }
66 
67 enum diff_rc diff_atomize_text_by_line(void *func_data, struct diff_data *left, struct diff_data *right)
68 {
69 	enum diff_rc rc;
70 	rc = diff_data_atomize_text_lines(left);
71 	if (rc != DIFF_RC_OK)
72 		return rc;
73 	return diff_data_atomize_text_lines(right);
74 }