1 /* $OpenBSD: uniq.c,v 1.26 2017/12/24 00:11:43 tb Exp $ */
2 /* $NetBSD: uniq.c,v 1.7 1995/08/31 22:03:48 jtc Exp $ */
5 * Copyright (c) 1989, 1993
6 * The Regents of the University of California. All rights reserved.
8 * This code is derived from software contributed to Berkeley by
11 * Redistribution and use in source and binary forms, with or without
12 * modification, are permitted provided that the following conditions
14 * 1. Redistributions of source code must retain the above copyright
15 * notice, this list of conditions and the following disclaimer.
16 * 2. Redistributions in binary form must reproduce the above copyright
17 * notice, this list of conditions and the following disclaimer in the
18 * documentation and/or other materials provided with the distribution.
19 * 3. Neither the name of the University nor the names of its contributors
20 * may be used to endorse or promote products derived from this software
21 * without specific prior written permission.
23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
48 #define MAXLINELEN (8 * 1024)
50 int cflag
, dflag
, iflag
, uflag
;
51 int numchars
, numfields
, repeats
;
53 FILE *file(char *, char *);
54 void show(FILE *, char *);
56 void obsolete(char *[]);
57 __dead
void usage(void);
60 main(int argc
, char *argv
[])
63 FILE *ifp
= NULL
, *ofp
= NULL
;
65 char *prevline
, *thisline
;
67 setlocale(LC_CTYPE
, "");
69 if (pledge("stdio rpath wpath cpath", NULL
) == -1)
73 while ((ch
= getopt(argc
, argv
, "cdf:is:u")) != -1) {
84 numfields
= (int)strtonum(optarg
, 0, INT_MAX
,
87 errx(1, "field skip value is %s: %s",
94 numchars
= (int)strtonum(optarg
, 0, INT_MAX
,
98 "character skip value is %s: %s",
112 /* If neither -d nor -u are set, default is -d -u. */
113 if (!dflag
&& !uflag
)
122 ifp
= file(argv
[0], "r");
126 ifp
= file(argv
[0], "r");
127 ofp
= file(argv
[1], "w");
133 if (pledge("stdio", NULL
) == -1)
136 prevline
= malloc(MAXLINELEN
);
137 thisline
= malloc(MAXLINELEN
);
138 if (prevline
== NULL
|| thisline
== NULL
)
141 if (fgets(prevline
, MAXLINELEN
, ifp
) == NULL
)
144 while (fgets(thisline
, MAXLINELEN
, ifp
)) {
145 /* If requested get the chosen fields + character offsets. */
146 if (numfields
|| numchars
) {
154 /* If different, print; set previous to new value. */
155 if ((iflag
? strcasecmp
: strcmp
)(t1
, t2
)) {
170 * Output a line depending on the flags and number of repetitions
174 show(FILE *ofp
, char *str
)
176 if ((dflag
&& repeats
) || (uflag
&& !repeats
)) {
178 (void)fprintf(ofp
, "%4d %s", repeats
+ 1, str
);
180 (void)fprintf(ofp
, "%s", str
);
192 for (nfields
= numfields
; nfields
&& *str
; nfields
--) {
193 /* Skip one field, including preceding blanks. */
194 for (field_started
= 0; *str
!= '\0'; str
+= len
) {
195 if ((len
= mbtowc(&wc
, str
, MB_CUR_MAX
)) == -1) {
196 (void)mbtowc(NULL
, NULL
, MB_CUR_MAX
);
208 /* Skip some additional characters. */
209 for (nchars
= numchars
; nchars
-- && *str
!= '\0'; str
+= len
)
210 if ((len
= mblen(str
, MB_CUR_MAX
)) == -1)
217 file(char *name
, char *mode
)
221 if (strcmp(name
, "-") == 0)
222 return(*mode
== 'r' ? stdin
: stdout
);
223 if ((fp
= fopen(name
, mode
)) == NULL
)
229 obsolete(char *argv
[])
232 char *ap
, *p
, *start
;
234 while ((ap
= *++argv
)) {
235 /* Return if "--" or not an option of any form. */
239 } else if (ap
[1] == '-')
241 if (!isdigit((unsigned char)ap
[1]))
244 * Digit signifies an old-style option. Malloc space for dash,
245 * new option and argument.
247 len
= strlen(ap
) + 3;
248 if ((start
= p
= malloc(len
)) == NULL
)
251 *p
++ = ap
[0] == '+' ? 's' : 'f';
252 (void)strlcpy(p
, ap
+ 1, len
- 2);
260 extern char *__progname
;
262 (void)fprintf(stderr
,
263 "usage: %s [-ci] [-d | -u] [-f fields] [-s chars] [input_file [output_file]]\n",