diff options
Diffstat (limited to 'busybox/coreutils/uniq.c')
-rw-r--r-- | busybox/coreutils/uniq.c | 112 |
1 files changed, 112 insertions, 0 deletions
diff --git a/busybox/coreutils/uniq.c b/busybox/coreutils/uniq.c new file mode 100644 index 000000000..6caab5dae --- /dev/null +++ b/busybox/coreutils/uniq.c | |||
@@ -0,0 +1,112 @@ | |||
1 | /* vi: set sw=4 ts=4: */ | ||
2 | /* | ||
3 | * uniq implementation for busybox | ||
4 | * | ||
5 | * Copyright (C) 2003 Manuel Novoa III <mjn3@codepoet.org> | ||
6 | * | ||
7 | * This program is free software; you can redistribute it and/or modify | ||
8 | * it under the terms of the GNU General Public License as published by | ||
9 | * the Free Software Foundation; either version 2 of the License, or | ||
10 | * (at your option) any later version. | ||
11 | * | ||
12 | * This program is distributed in the hope that it will be useful, | ||
13 | * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
14 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | ||
15 | * General Public License for more details. | ||
16 | * | ||
17 | * You should have received a copy of the GNU General Public License | ||
18 | * along with this program; if not, write to the Free Software | ||
19 | * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA | ||
20 | * | ||
21 | */ | ||
22 | |||
23 | /* BB_AUDIT SUSv3 compliant */ | ||
24 | /* http://www.opengroup.org/onlinepubs/007904975/utilities/uniq.html */ | ||
25 | |||
26 | #include <stdio.h> | ||
27 | #include <stdlib.h> | ||
28 | #include <string.h> | ||
29 | #include <ctype.h> | ||
30 | #include <unistd.h> | ||
31 | #include "busybox.h" | ||
32 | #include "libcoreutils/coreutils.h" | ||
33 | |||
34 | static const char uniq_opts[] = "f:s:cdu\0\7\3\5\1\2\4"; | ||
35 | |||
36 | int uniq_main(int argc, char **argv) | ||
37 | { | ||
38 | FILE *in, *out; | ||
39 | /* Note: Ignore the warning about dups and e0 being used uninitialized. | ||
40 | * They will be initialized on the fist pass of the loop (since s0 is NULL). */ | ||
41 | unsigned long dups, skip_fields, skip_chars, i; | ||
42 | const char *s0, *e0, *s1, *e1, *input_filename; | ||
43 | int opt; | ||
44 | int uniq_flags = 6; /* -u */ | ||
45 | |||
46 | skip_fields = skip_chars = 0; | ||
47 | |||
48 | while ((opt = getopt(argc, argv, uniq_opts)) > 0) { | ||
49 | if (opt == 'f') { | ||
50 | skip_fields = bb_xgetularg10(optarg); | ||
51 | } else if (opt == 's') { | ||
52 | skip_chars = bb_xgetularg10(optarg); | ||
53 | } else if ((s0 = strchr(uniq_opts, opt)) != NULL) { | ||
54 | uniq_flags &= s0[4]; | ||
55 | uniq_flags |= s0[7]; | ||
56 | } else { | ||
57 | bb_show_usage(); | ||
58 | } | ||
59 | } | ||
60 | |||
61 | input_filename = *(argv += optind); | ||
62 | |||
63 | in = xgetoptfile_sort_uniq(argv, "r"); | ||
64 | if (*argv) { | ||
65 | ++argv; | ||
66 | } | ||
67 | out = xgetoptfile_sort_uniq(argv, "w"); | ||
68 | if (*argv && argv[1]) { | ||
69 | bb_show_usage(); | ||
70 | } | ||
71 | |||
72 | s0 = NULL; | ||
73 | |||
74 | /* gnu uniq ignores newlines */ | ||
75 | while ((s1 = bb_get_chomped_line_from_file(in)) != NULL) { | ||
76 | e1 = s1; | ||
77 | for (i=skip_fields ; i ; i--) { | ||
78 | e1 = bb_skip_whitespace(e1); | ||
79 | while (*e1 && !isspace(*e1)) { | ||
80 | ++e1; | ||
81 | } | ||
82 | } | ||
83 | for (i = skip_chars ; *e1 && i ; i--) { | ||
84 | ++e1; | ||
85 | } | ||
86 | if (s0) { | ||
87 | if (strcmp(e0, e1) == 0) { | ||
88 | ++dups; /* Note: Testing for overflow seems excessive. */ | ||
89 | continue; | ||
90 | } | ||
91 | DO_LAST: | ||
92 | if ((dups && (uniq_flags & 2)) || (!dups && (uniq_flags & 4))) { | ||
93 | bb_fprintf(out, "\0%7d\t" + (uniq_flags & 1), dups + 1); | ||
94 | bb_fprintf(out, "%s\n", s0); | ||
95 | } | ||
96 | free((void *)s0); | ||
97 | } | ||
98 | |||
99 | s0 = s1; | ||
100 | e0 = e1; | ||
101 | dups = 0; | ||
102 | } | ||
103 | |||
104 | if (s0) { | ||
105 | e1 = NULL; | ||
106 | goto DO_LAST; | ||
107 | } | ||
108 | |||
109 | bb_xferror(in, input_filename); | ||
110 | |||
111 | bb_fflush_stdout_and_exit(EXIT_SUCCESS); | ||
112 | } | ||