2 * Copyright (c) 1989, 1993
3 * The Regents of the University of California. All rights reserved.
5 * This code is derived from software contributed to Berkeley by
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
11 * 1. Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in the
15 * documentation and/or other materials provided with the distribution.
16 * 3. Neither the name of the University nor the names of its contributors
17 * may be used to endorse or promote products derived from this software
18 * without specific prior written permission.
20 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
21 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
23 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
24 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
26 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
28 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
29 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
32 * @(#) Copyright (c) 1989, 1993 The Regents of the University of California. All rights reserved.
33 * @(#)uniq.c 8.3 (Berkeley) 5/4/95
34 * $FreeBSD: head/usr.bin/uniq/uniq.c 303526 2016-07-30 01:07:47Z bapt $
52 static int cflag
, dflag
, uflag
, iflag
;
53 static int numchars
, numfields
, repeats
;
55 static FILE *file(const char *, const char *);
56 static wchar_t *convert(const char *);
57 static int inlcmp(const char *, const char *);
58 static void show(FILE *, const char *);
59 static wchar_t *skip(wchar_t *);
60 static void obsolete(char *[]);
61 static void usage(void);
64 main(int argc
, char *argv
[])
66 wchar_t *tprev
, *tthis
;
69 size_t prevbuflen
, thisbuflen
, b1
;
70 char *prevline
, *thisline
, *p
;
73 (void) setlocale(LC_ALL
, "");
76 while ((ch
= getopt(argc
, argv
, "cdif:s:u")) != -1)
88 numfields
= strtol(optarg
, &p
, 10);
89 if (numfields
< 0 || *p
)
90 errx(1, "illegal field skip value: %s", optarg
);
93 numchars
= strtol(optarg
, &p
, 10);
94 if (numchars
< 0 || *p
)
95 errx(1, "illegal character skip value: %s", optarg
);
108 /* If no flags are set, default is -d -u. */
112 } else if (!dflag
&& !uflag
)
121 if (argc
> 0 && strcmp(argv
[0], "-") != 0)
122 ifp
= file(ifn
= argv
[0], "r");
124 ofp
= file(argv
[1], "w");
126 prevbuflen
= thisbuflen
= 0;
127 prevline
= thisline
= NULL
;
129 if (getline(&prevline
, &prevbuflen
, ifp
) < 0) {
134 tprev
= convert(prevline
);
136 if (!cflag
&& uflag
&& dflag
)
140 while (getline(&thisline
, &thisbuflen
, ifp
) >= 0) {
143 tthis
= convert(thisline
);
145 if (tthis
== NULL
&& tprev
== NULL
)
146 comp
= inlcmp(thisline
, prevline
);
147 else if (tthis
== NULL
|| tprev
== NULL
)
150 comp
= wcscoll(tthis
, tprev
);
153 /* If different, print; set previous to new value. */
154 if (cflag
|| !dflag
|| !uflag
)
159 prevbuflen
= thisbuflen
;
163 if (!cflag
&& uflag
&& dflag
)
174 if (cflag
|| !dflag
|| !uflag
)
180 convert(const char *str
)
183 wchar_t *buf
, *ret
, *p
;
185 if ((n
= mbstowcs(NULL
, str
, 0)) == (size_t)-1)
187 if (SIZE_MAX
/ sizeof(*buf
) < n
+ 1)
188 errx(1, "conversion buffer length overflow");
189 if ((buf
= malloc((n
+ 1) * sizeof(*buf
))) == NULL
)
191 if (mbstowcs(buf
, str
, n
+ 1) != n
)
192 errx(1, "internal mbstowcs() error");
193 /* The last line may not end with \n. */
194 if (n
> 0 && buf
[n
- 1] == L
'\n')
197 /* If requested get the chosen fields + character offsets. */
198 if (numfields
|| numchars
) {
199 if ((ret
= wcsdup(skip(buf
))) == NULL
)
206 for (p
= ret
; *p
!= L
'\0'; p
++)
214 inlcmp(const char *s1
, const char *s2
)
221 c1
= (unsigned char)*s1
;
222 c2
= (unsigned char)*(s2
- 1);
223 /* The last line may not end with \n. */
233 * Output a line depending on the flags and number of repetitions
237 show(FILE *ofp
, const char *str
)
241 (void)fprintf(ofp
, "%4d %s", repeats
+ 1, str
);
242 if ((dflag
&& repeats
) || (uflag
&& !repeats
))
243 (void)fprintf(ofp
, "%s", str
);
251 for (nfields
= 0; *str
!= L
'\0' && nfields
++ != numfields
; ) {
252 while (iswblank(*str
))
254 while (*str
!= L
'\0' && !iswblank(*str
))
257 for (nchars
= numchars
; nchars
-- && *str
!= L
'\0'; ++str
)
263 file(const char *name
, const char *mode
)
267 if ((fp
= fopen(name
, mode
)) == NULL
)
273 obsolete(char *argv
[])
276 char *ap
, *p
, *start
;
278 while ((ap
= *++argv
)) {
279 /* Return if "--" or not an option of any form. */
283 } else if (ap
[1] == '-')
285 if (!isdigit((unsigned char)ap
[1]))
288 * Digit signifies an old-style option. Malloc space for dash,
289 * new option and argument.
292 if ((start
= p
= malloc(len
+ 3)) == NULL
)
295 *p
++ = ap
[0] == '+' ? 's' : 'f';
296 (void)strcpy(p
, ap
+ 1);
304 (void)fprintf(stderr
,
305 "usage: uniq [-c | -d | -u] [-i] [-f fields] [-s chars] [input [output]]\n");