1 /* Commandline diff utility to test diff implementations. */
2 /*
3  * Copyright (c) 2018 Martin Pieuchot
4  * Copyright (c) 2020 Neels Hofmeyr <neels@hofmeyr.de>
5  *
6  * Permission to use, copy, modify, and distribute this software for any
7  * purpose with or without fee is hereby granted, provided that the above
8  * copyright notice and this permission notice appear in all copies.
9  *
10  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
11  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
12  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
13  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
14  * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
15  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
16  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
17  */
18 
19 #include <sys/mman.h>
20 #include <sys/stat.h>
21 
22 #include <err.h>
23 #include <fcntl.h>
24 #include <inttypes.h>
25 #include <stdio.h>
26 #include <stdlib.h>
27 #include <unistd.h>
28 
29 #include <diff/diff_main.h>
30 #include <diff/diff_output.h>
31 
32 #ifdef __linux__
33 /* stupid shims to compile and test on linux */
34 #define __dead
35 
36 static const char *getprogname()
37 {
38 	return "diff";
39 }
40 #endif
41 
42 __dead void	 usage(void);
43 int		 diffreg(char *, char *, int);
44 char		*mmapfile(const char *, struct stat *);
45 
46 __dead void
47 usage(void)
48 {
49 	fprintf(stderr,
50 		"usage: %s [-p] file1 file2\n"
51 		"\n"
52 		"  -p   Use Patience Diff (slower but often nicer)\n"
53 		, getprogname());
54 	exit(1);
55 }
56 
57 static bool do_patience = false;
58 
59 int
60 main(int argc, char *argv[])
61 {
62 	int ch;
63 
64 	while ((ch = getopt(argc, argv, "p")) != -1) {
65 		switch (ch) {
66 		case 'p':
67 			do_patience = true;
68 			break;
69 		default:
70 			usage();
71 		}
72 	}
73 
74 	argc -= optind;
75 	argv += optind;
76 
77 	if (argc != 2)
78 		usage();
79 
80 	return diffreg(argv[0], argv[1], 0);
81 }
82 
83 const struct diff_algo_config myers_then_patience, myers_then_myers_divide, patience, myers_divide;
84 
85 const struct diff_algo_config myers_then_patience = (struct diff_algo_config){
86 	.impl = diff_algo_myers,
87 	.permitted_state_size = 1024 * 1024 * sizeof(int),
88 	.fallback_algo = &patience,
89 };
90 
91 const struct diff_algo_config myers_then_myers_divide = (struct diff_algo_config){
92 	.impl = diff_algo_myers,
93 	.permitted_state_size = 1024 * 1024 * sizeof(int),
94 	.fallback_algo = &myers_divide,
95 };
96 
97 const struct diff_algo_config patience = (struct diff_algo_config){
98 	.impl = diff_algo_patience,
99 	.inner_algo = &patience,	// After subdivision, do Patience again.
100 	.fallback_algo = &myers_then_myers_divide, // If subdivision failed, do Myers Divide et Impera.
101 };
102 
103 const struct diff_algo_config myers_divide = (struct diff_algo_config){
104 	.impl = diff_algo_myers_divide,
105 	.inner_algo = &myers_then_myers_divide,	// When division succeeded, start from the top.
106 	// (fallback_algo = NULL implies diff_algo_none).
107 };
108 
109 const struct diff_config diff_config = {
110 	.atomize_func = diff_atomize_text_by_line,
111 	.algo = &myers_then_myers_divide,
112 };
113 
114 const struct diff_config diff_config_patience = {
115 	.atomize_func = diff_atomize_text_by_line,
116 	.algo = &myers_then_patience,
117 };
118 
119 int
120 diffreg(char *file1, char *file2, int flags)
121 {
122 	char *str1, *str2;
123 	struct stat st1, st2;
124 	struct diff_input_info info = {
125 		.left_path = file1,
126 		.right_path = file2,
127 	};
128 	struct diff_result *result;
129 	enum diff_rc rc;
130 	const struct diff_config *cfg = do_patience ? &diff_config_patience : &diff_config;
131 
132 	str1 = mmapfile(file1, &st1);
133 	str2 = mmapfile(file2, &st2);
134 
135 	result = diff_main(cfg, str1, st1.st_size, str2, st2.st_size);
136 #if 0
137 	rc = diff_output_plain(stdout, &info, result);
138 #else
139 	rc = diff_output_unidiff(stdout, &info, result, 3);
140 #endif
141 	diff_result_free(result);
142 
143 	munmap(str1, st1.st_size);
144 	munmap(str2, st2.st_size);
145 
146 	return rc;
147 }
148 
149 char *
150 mmapfile(const char *path, struct stat *st)
151 {
152 	int			 fd;
153 	char			*p;
154 
155 	fd = open(path, O_RDONLY);
156 	if (fd == -1)
157 		err(2, "%s", path);
158 
159 	if (fstat(fd, st) == -1)
160 		err(2, "%s", path);
161 
162 	if ((uintmax_t)st->st_size > SIZE_MAX)
163 		errx(2, "%s: file too big to fit memory", path);
164 
165 	p = mmap(NULL, st->st_size, PROT_READ, MAP_PRIVATE, fd, 0);
166 	if (p == MAP_FAILED)
167 		err(2, "mmap");
168 
169 	close(fd);
170 
171 	return p;
172 }