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 * 4. 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
34 static const char copyright[] =
35 "@(#) Copyright (c) 1989, 1993\n\
36 The Regents of the University of California. All rights reserved.\n";
41 static char sccsid[] = "@(#)uniq.c 8.3 (Berkeley) 5/4/95";
43 static const char rcsid[] =
60 int cflag, dflag, uflag, iflag;
61 int numchars, numfields, repeats;
63 FILE *file(const char *, const char *);
64 wchar_t *convert(const char *);
65 int inlcmp(const char *, const char *);
66 void show(FILE *, const char *);
67 wchar_t *skip(wchar_t *);
68 void obsolete(char *[]);
69 static void usage(void);
72 main (int argc, char *argv[])
74 wchar_t *tprev, *tthis;
77 size_t prevbuflen, thisbuflen, b1;
78 char *prevline, *thisline, *p;
81 (void) setlocale(LC_ALL, "");
84 while ((ch = getopt(argc, argv, "cdif:s:u")) != -1)
96 numfields = strtol(optarg, &p, 10);
97 if (numfields < 0 || *p)
98 errx(1, "illegal field skip value: %s", optarg);
101 numchars = strtol(optarg, &p, 10);
102 if (numchars < 0 || *p)
103 errx(1, "illegal character skip value: %s", optarg);
116 /* If no flags are set, default is -d -u. */
120 } else if (!dflag && !uflag)
129 if (argc > 0 && strcmp(argv[0], "-") != 0)
130 ifp = file(ifn = argv[0], "r");
132 ofp = file(argv[1], "w");
134 prevbuflen = thisbuflen = 0;
135 prevline = thisline = NULL;
137 if (getline(&prevline, &prevbuflen, ifp) < 0) {
142 tprev = convert(prevline);
144 if (!cflag && uflag && dflag)
148 while (getline(&thisline, &thisbuflen, ifp) >= 0) {
151 tthis = convert(thisline);
153 if (tthis == NULL && tprev == NULL)
154 comp = inlcmp(thisline, prevline);
155 else if (tthis == NULL || tprev == NULL)
158 comp = wcscoll(tthis, tprev);
161 /* If different, print; set previous to new value. */
162 if (cflag || !dflag || !uflag)
167 prevbuflen = thisbuflen;
171 if (!cflag && uflag && dflag)
182 if (cflag || !dflag || !uflag)
188 convert(const char *str)
191 wchar_t *buf, *ret, *p;
193 if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1)
195 if (SIZE_MAX / sizeof(*buf) < n + 1)
196 errx(1, "conversion buffer length overflow");
197 if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL)
199 if (mbstowcs(buf, str, n + 1) != n)
200 errx(1, "internal mbstowcs() error");
201 /* The last line may not end with \n. */
202 if (n > 0 && buf[n - 1] == L'\n')
205 /* If requested get the chosen fields + character offsets. */
206 if (numfields || numchars) {
207 if ((ret = wcsdup(skip(buf))) == NULL)
214 for (p = ret; *p != L'\0'; p++)
222 inlcmp(const char *s1, const char *s2)
229 c1 = (unsigned char)*s1;
230 c2 = (unsigned char)*(s2 - 1);
231 /* The last line may not end with \n. */
241 * Output a line depending on the flags and number of repetitions
245 show(FILE *ofp, const char *str)
249 (void)fprintf(ofp, "%4d %s", repeats + 1, str);
250 if ((dflag && repeats) || (uflag && !repeats))
251 (void)fprintf(ofp, "%s", str);
259 for (nfields = 0; *str != L'\0' && nfields++ != numfields; ) {
260 while (iswblank(*str))
262 while (*str != L'\0' && !iswblank(*str))
265 for (nchars = numchars; nchars-- && *str != L'\0'; ++str)
271 file(const char *name, const char *mode)
275 if ((fp = fopen(name, mode)) == NULL)
281 obsolete(char *argv[])
284 char *ap, *p, *start;
286 while ((ap = *++argv)) {
287 /* Return if "--" or not an option of any form. */
291 } else if (ap[1] == '-')
293 if (!isdigit((unsigned char)ap[1]))
296 * Digit signifies an old-style option. Malloc space for dash,
297 * new option and argument.
300 if ((start = p = malloc(len + 3)) == NULL)
303 *p++ = ap[0] == '+' ? 's' : 'f';
304 (void)strcpy(p, ap + 1);
312 (void)fprintf(stderr,
313 "usage: uniq [-c | -d | -u] [-i] [-f fields] [-s chars] [input [output]]\n");