1 /*
2 * Copyright (c) 1989, 1993
3 * The Regents of the University of California. All rights reserved.
4 *
5 * This code is derived from software contributed to Berkeley by
6 * Case Larsen.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
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.
19 *
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
30 * SUCH DAMAGE.
31 *
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 $
35 */
36
37 #include <ctype.h>
38 #include <err.h>
39 #include <errno.h>
40 #include <limits.h>
41 #include <locale.h>
42 #include <nl_types.h>
43 #include <stdint.h>
44 #include <stdio.h>
45 #include <stdlib.h>
46 #include <string.h>
47 #include <termios.h>
48 #include <unistd.h>
49 #include <wchar.h>
50 #include <wctype.h>
51
52 static int cflag, dflag, uflag, iflag;
53 static int numchars, numfields, repeats;
54
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);
62
63 int
main(int argc,char * argv[])64 main(int argc, char *argv[])
65 {
66 wchar_t *tprev, *tthis;
67 FILE *ifp, *ofp;
68 int ch, comp;
69 size_t prevbuflen, thisbuflen, b1;
70 char *prevline, *thisline, *p;
71 const char *ifn;
72
73 (void) setlocale(LC_ALL, "");
74
75 obsolete(argv);
76 while ((ch = getopt(argc, argv, "cdif:s:u")) != -1)
77 switch (ch) {
78 case 'c':
79 cflag = 1;
80 break;
81 case 'd':
82 dflag = 1;
83 break;
84 case 'i':
85 iflag = 1;
86 break;
87 case 'f':
88 numfields = strtol(optarg, &p, 10);
89 if (numfields < 0 || *p)
90 errx(1, "illegal field skip value: %s", optarg);
91 break;
92 case 's':
93 numchars = strtol(optarg, &p, 10);
94 if (numchars < 0 || *p)
95 errx(1, "illegal character skip value: %s", optarg);
96 break;
97 case 'u':
98 uflag = 1;
99 break;
100 case '?':
101 default:
102 usage();
103 }
104
105 argc -= optind;
106 argv += optind;
107
108 /* If no flags are set, default is -d -u. */
109 if (cflag) {
110 if (dflag || uflag)
111 usage();
112 } else if (!dflag && !uflag)
113 dflag = uflag = 1;
114
115 if (argc > 2)
116 usage();
117
118 ifp = stdin;
119 ifn = "stdin";
120 ofp = stdout;
121 if (argc > 0 && strcmp(argv[0], "-") != 0)
122 ifp = file(ifn = argv[0], "r");
123 if (argc > 1)
124 ofp = file(argv[1], "w");
125
126 prevbuflen = thisbuflen = 0;
127 prevline = thisline = NULL;
128
129 if (getline(&prevline, &prevbuflen, ifp) < 0) {
130 if (ferror(ifp))
131 err(1, "%s", ifn);
132 exit(0);
133 }
134 tprev = convert(prevline);
135
136 if (!cflag && uflag && dflag)
137 show(ofp, prevline);
138
139 tthis = NULL;
140 while (getline(&thisline, &thisbuflen, ifp) >= 0) {
141 if (tthis != NULL)
142 free(tthis);
143 tthis = convert(thisline);
144
145 if (tthis == NULL && tprev == NULL)
146 comp = inlcmp(thisline, prevline);
147 else if (tthis == NULL || tprev == NULL)
148 comp = 1;
149 else
150 comp = wcscoll(tthis, tprev);
151
152 if (comp) {
153 /* If different, print; set previous to new value. */
154 if (cflag || !dflag || !uflag)
155 show(ofp, prevline);
156 p = prevline;
157 b1 = prevbuflen;
158 prevline = thisline;
159 prevbuflen = thisbuflen;
160 if (tprev != NULL)
161 free(tprev);
162 tprev = tthis;
163 if (!cflag && uflag && dflag)
164 show(ofp, prevline);
165 thisline = p;
166 thisbuflen = b1;
167 tthis = NULL;
168 repeats = 0;
169 } else
170 ++repeats;
171 }
172 if (ferror(ifp))
173 err(1, "%s", ifn);
174 if (cflag || !dflag || !uflag)
175 show(ofp, prevline);
176 exit(0);
177 }
178
179 static wchar_t *
convert(const char * str)180 convert(const char *str)
181 {
182 size_t n;
183 wchar_t *buf, *ret, *p;
184
185 if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1)
186 return (NULL);
187 if (SIZE_MAX / sizeof(*buf) < n + 1)
188 errx(1, "conversion buffer length overflow");
189 if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL)
190 err(1, "malloc");
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')
195 buf[n - 1] = L'\0';
196
197 /* If requested get the chosen fields + character offsets. */
198 if (numfields || numchars) {
199 if ((ret = wcsdup(skip(buf))) == NULL)
200 err(1, "wcsdup");
201 free(buf);
202 } else
203 ret = buf;
204
205 if (iflag) {
206 for (p = ret; *p != L'\0'; p++)
207 *p = towlower(*p);
208 }
209
210 return (ret);
211 }
212
213 static int
inlcmp(const char * s1,const char * s2)214 inlcmp(const char *s1, const char *s2)
215 {
216 int c1, c2;
217
218 while (*s1 == *s2++)
219 if (*s1++ == '\0')
220 return (0);
221 c1 = (unsigned char)*s1;
222 c2 = (unsigned char)*(s2 - 1);
223 /* The last line may not end with \n. */
224 if (c1 == '\n')
225 c1 = '\0';
226 if (c2 == '\n')
227 c2 = '\0';
228 return (c1 - c2);
229 }
230
231 /*
232 * show --
233 * Output a line depending on the flags and number of repetitions
234 * of the line.
235 */
236 static void
show(FILE * ofp,const char * str)237 show(FILE *ofp, const char *str)
238 {
239
240 if (cflag)
241 (void)fprintf(ofp, "%4d %s", repeats + 1, str);
242 if ((dflag && repeats) || (uflag && !repeats))
243 (void)fprintf(ofp, "%s", str);
244 }
245
246 static wchar_t *
skip(wchar_t * str)247 skip(wchar_t *str)
248 {
249 int nchars, nfields;
250
251 for (nfields = 0; *str != L'\0' && nfields++ != numfields; ) {
252 while (iswblank(*str))
253 str++;
254 while (*str != L'\0' && !iswblank(*str))
255 str++;
256 }
257 for (nchars = numchars; nchars-- && *str != L'\0'; ++str)
258 ;
259 return(str);
260 }
261
262 static FILE *
file(const char * name,const char * mode)263 file(const char *name, const char *mode)
264 {
265 FILE *fp;
266
267 if ((fp = fopen(name, mode)) == NULL)
268 err(1, "%s", name);
269 return(fp);
270 }
271
272 static void
obsolete(char * argv[])273 obsolete(char *argv[])
274 {
275 int len;
276 char *ap, *p, *start;
277
278 while ((ap = *++argv)) {
279 /* Return if "--" or not an option of any form. */
280 if (ap[0] != '-') {
281 if (ap[0] != '+')
282 return;
283 } else if (ap[1] == '-')
284 return;
285 if (!isdigit((unsigned char)ap[1]))
286 continue;
287 /*
288 * Digit signifies an old-style option. Malloc space for dash,
289 * new option and argument.
290 */
291 len = strlen(ap);
292 if ((start = p = malloc(len + 3)) == NULL)
293 err(1, "malloc");
294 *p++ = '-';
295 *p++ = ap[0] == '+' ? 's' : 'f';
296 (void)strcpy(p, ap + 1);
297 *argv = start;
298 }
299 }
300
301 static void
usage(void)302 usage(void)
303 {
304 (void)fprintf(stderr,
305 "usage: uniq [-c | -d | -u] [-i] [-f fields] [-s chars] [input [output]]\n");
306 exit(1);
307 }
308