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. All advertising materials mentioning features or use of this software
17 * must display the following acknowledgement:
18 * This product includes software developed by the University of
19 * California, Berkeley and its contributors.
20 * 4. Neither the name of the University nor the names of its contributors
21 * may be used to endorse or promote products derived from this software
22 * without specific prior written permission.
24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
38 static const char copyright[] =
39 "@(#) Copyright (c) 1989, 1993\n\
40 The Regents of the University of California. All rights reserved.\n";
45 static char sccsid[] = "@(#)uniq.c 8.3 (Berkeley) 5/4/95";
47 static const char rcsid[] =
64 int cflag, dflag, uflag, iflag;
65 int numchars, numfields, repeats;
67 FILE *file(const char *, const char *);
68 wchar_t *convert(const char *);
69 int inlcmp(const char *, const char *);
70 void show(FILE *, const char *);
71 wchar_t *skip(wchar_t *);
72 void obsolete(char *[]);
73 static void usage(void);
76 main (int argc, char *argv[])
78 wchar_t *tprev, *tthis;
81 size_t prevbuflen, thisbuflen, b1;
82 char *prevline, *thisline, *p;
85 (void) setlocale(LC_ALL, "");
88 while ((ch = getopt(argc, argv, "cdif:s:u")) != -1)
100 numfields = strtol(optarg, &p, 10);
101 if (numfields < 0 || *p)
102 errx(1, "illegal field skip value: %s", optarg);
105 numchars = strtol(optarg, &p, 10);
106 if (numchars < 0 || *p)
107 errx(1, "illegal character skip value: %s", optarg);
120 /* If no flags are set, default is -d -u. */
124 } else if (!dflag && !uflag)
133 if (argc > 0 && strcmp(argv[0], "-") != 0)
134 ifp = file(ifn = argv[0], "r");
136 ofp = file(argv[1], "w");
138 prevbuflen = thisbuflen = 0;
139 prevline = thisline = NULL;
141 if (getline(&prevline, &prevbuflen, ifp) < 0) {
146 tprev = convert(prevline);
148 if (!cflag && uflag && dflag)
152 while (getline(&thisline, &thisbuflen, ifp) >= 0) {
155 tthis = convert(thisline);
157 if (tthis == NULL && tprev == NULL)
158 comp = inlcmp(thisline, prevline);
159 else if (tthis == NULL || tprev == NULL)
162 comp = wcscoll(tthis, tprev);
165 /* If different, print; set previous to new value. */
166 if (cflag || !dflag || !uflag)
171 prevbuflen = thisbuflen;
175 if (!cflag && uflag && dflag)
186 if (cflag || !dflag || !uflag)
192 convert(const char *str)
195 wchar_t *buf, *ret, *p;
197 if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1)
199 if (SIZE_MAX / sizeof(*buf) < n + 1)
200 errx(1, "conversion buffer length overflow");
201 if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL)
203 if (mbstowcs(buf, str, n + 1) != n)
204 errx(1, "internal mbstowcs() error");
205 /* The last line may not end with \n. */
206 if (n > 0 && buf[n - 1] == L'\n')
209 /* If requested get the chosen fields + character offsets. */
210 if (numfields || numchars) {
211 if ((ret = wcsdup(skip(buf))) == NULL)
218 for (p = ret; *p != L'\0'; p++)
226 inlcmp(const char *s1, const char *s2)
233 c1 = (unsigned char)*s1;
234 c2 = (unsigned char)*(s2 - 1);
235 /* The last line may not end with \n. */
245 * Output a line depending on the flags and number of repetitions
249 show(FILE *ofp, const char *str)
253 (void)fprintf(ofp, "%4d %s", repeats + 1, str);
254 if ((dflag && repeats) || (uflag && !repeats))
255 (void)fprintf(ofp, "%s", str);
263 for (nfields = 0; *str != L'\0' && nfields++ != numfields; ) {
264 while (iswblank(*str))
266 while (*str != L'\0' && !iswblank(*str))
269 for (nchars = numchars; nchars-- && *str != L'\0'; ++str)
275 file(const char *name, const char *mode)
279 if ((fp = fopen(name, mode)) == NULL)
285 obsolete(char *argv[])
288 char *ap, *p, *start;
290 while ((ap = *++argv)) {
291 /* Return if "--" or not an option of any form. */
295 } else if (ap[1] == '-')
297 if (!isdigit((unsigned char)ap[1]))
300 * Digit signifies an old-style option. Malloc space for dash,
301 * new option and argument.
304 if ((start = p = malloc(len + 3)) == NULL)
307 *p++ = ap[0] == '+' ? 's' : 'f';
308 (void)strcpy(p, ap + 1);
316 (void)fprintf(stderr,
317 "usage: uniq [-c | -d | -u] [-i] [-f fields] [-s chars] [input [output]]\n");