1 /*- 2 * SPDX-License-Identifier: BSD-3-Clause 3 * 4 * Copyright (c) 1989, 1993 5 * The Regents of the University of California. All rights reserved. 6 * 7 * This code is derived from software contributed to Berkeley by 8 * Case Larsen. 9 * 10 * Redistribution and use in source and binary forms, with or without 11 * modification, are permitted provided that the following conditions 12 * are met: 13 * 1. Redistributions of source code must retain the above copyright 14 * notice, this list of conditions and the following disclaimer. 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in the 17 * documentation and/or other materials provided with the distribution. 18 * 3. Neither the name of the University nor the names of its contributors 19 * may be used to endorse or promote products derived from this software 20 * without specific prior written permission. 21 * 22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32 * SUCH DAMAGE. 33 */ 34 35 #ifndef lint 36 static const char copyright[] = 37 "@(#) Copyright (c) 1989, 1993\n\ 38 The Regents of the University of California. All rights reserved.\n"; 39 #endif /* not lint */ 40 41 #ifndef lint 42 #if 0 43 static char sccsid[] = "@(#)uniq.c 8.3 (Berkeley) 5/4/95"; 44 #endif 45 static const char rcsid[] = 46 "$FreeBSD$"; 47 #endif /* not lint */ 48 49 #include <sys/capsicum.h> 50 51 #include <capsicum_helpers.h> 52 #include <ctype.h> 53 #include <err.h> 54 #include <errno.h> 55 #include <getopt.h> 56 #include <limits.h> 57 #include <locale.h> 58 #include <nl_types.h> 59 #include <stdint.h> 60 #include <stdio.h> 61 #include <stdlib.h> 62 #include <string.h> 63 #include <termios.h> 64 #include <unistd.h> 65 #include <wchar.h> 66 #include <wctype.h> 67 68 static int cflag, dflag, uflag, iflag; 69 static int numchars, numfields, repeats; 70 71 static const struct option long_opts[] = 72 { 73 {"count", no_argument, NULL, 'c'}, 74 {"repeated", no_argument, NULL, 'd'}, 75 {"skip-fields", required_argument, NULL, 'f'}, 76 {"ignore-case", no_argument, NULL, 'i'}, 77 {"skip-chars", required_argument, NULL, 's'}, 78 {"unique", no_argument, NULL, 'u'}, 79 {NULL, no_argument, NULL, 0} 80 }; 81 82 static FILE *file(const char *, const char *); 83 static wchar_t *convert(const char *); 84 static int inlcmp(const char *, const char *); 85 static void show(FILE *, const char *); 86 static wchar_t *skip(wchar_t *); 87 static void obsolete(char *[]); 88 static void usage(void); 89 90 int 91 main (int argc, char *argv[]) 92 { 93 wchar_t *tprev, *tthis; 94 FILE *ifp, *ofp; 95 int ch, comp; 96 size_t prevbuflen, thisbuflen, b1; 97 char *prevline, *thisline, *p; 98 const char *ifn; 99 cap_rights_t rights; 100 101 (void) setlocale(LC_ALL, ""); 102 103 obsolete(argv); 104 while ((ch = getopt_long(argc, argv, "+cdif:s:u", long_opts, 105 NULL)) != -1) 106 switch (ch) { 107 case 'c': 108 cflag = 1; 109 break; 110 case 'd': 111 dflag = 1; 112 break; 113 case 'i': 114 iflag = 1; 115 break; 116 case 'f': 117 numfields = strtol(optarg, &p, 10); 118 if (numfields < 0 || *p) 119 errx(1, "illegal field skip value: %s", optarg); 120 break; 121 case 's': 122 numchars = strtol(optarg, &p, 10); 123 if (numchars < 0 || *p) 124 errx(1, "illegal character skip value: %s", optarg); 125 break; 126 case 'u': 127 uflag = 1; 128 break; 129 case '?': 130 default: 131 usage(); 132 } 133 134 argc -= optind; 135 argv += optind; 136 137 if (argc > 2) 138 usage(); 139 140 ifp = stdin; 141 ifn = "stdin"; 142 ofp = stdout; 143 if (argc > 0 && strcmp(argv[0], "-") != 0) 144 ifp = file(ifn = argv[0], "r"); 145 cap_rights_init(&rights, CAP_FSTAT, CAP_READ); 146 if (cap_rights_limit(fileno(ifp), &rights) < 0 && errno != ENOSYS) 147 err(1, "unable to limit rights for %s", ifn); 148 cap_rights_init(&rights, CAP_FSTAT, CAP_WRITE); 149 if (argc > 1) 150 ofp = file(argv[1], "w"); 151 else 152 cap_rights_set(&rights, CAP_IOCTL); 153 if (cap_rights_limit(fileno(ofp), &rights) < 0 && errno != ENOSYS) { 154 err(1, "unable to limit rights for %s", 155 argc > 1 ? argv[1] : "stdout"); 156 } 157 if (cap_rights_is_set(&rights, CAP_IOCTL)) { 158 unsigned long cmd; 159 160 cmd = TIOCGETA; /* required by isatty(3) in printf(3) */ 161 162 if (cap_ioctls_limit(fileno(ofp), &cmd, 1) < 0 && 163 errno != ENOSYS) { 164 err(1, "unable to limit ioctls for %s", 165 argc > 1 ? argv[1] : "stdout"); 166 } 167 } 168 169 caph_cache_catpages(); 170 if (caph_enter() < 0) 171 err(1, "unable to enter capability mode"); 172 173 prevbuflen = thisbuflen = 0; 174 prevline = thisline = NULL; 175 176 if (getline(&prevline, &prevbuflen, ifp) < 0) { 177 if (ferror(ifp)) 178 err(1, "%s", ifn); 179 exit(0); 180 } 181 tprev = convert(prevline); 182 183 tthis = NULL; 184 while (getline(&thisline, &thisbuflen, ifp) >= 0) { 185 if (tthis != NULL) 186 free(tthis); 187 tthis = convert(thisline); 188 189 if (tthis == NULL && tprev == NULL) 190 comp = inlcmp(thisline, prevline); 191 else if (tthis == NULL || tprev == NULL) 192 comp = 1; 193 else 194 comp = wcscoll(tthis, tprev); 195 196 if (comp) { 197 /* If different, print; set previous to new value. */ 198 show(ofp, prevline); 199 p = prevline; 200 b1 = prevbuflen; 201 prevline = thisline; 202 prevbuflen = thisbuflen; 203 if (tprev != NULL) 204 free(tprev); 205 tprev = tthis; 206 thisline = p; 207 thisbuflen = b1; 208 tthis = NULL; 209 repeats = 0; 210 } else 211 ++repeats; 212 } 213 if (ferror(ifp)) 214 err(1, "%s", ifn); 215 show(ofp, prevline); 216 exit(0); 217 } 218 219 static wchar_t * 220 convert(const char *str) 221 { 222 size_t n; 223 wchar_t *buf, *ret, *p; 224 225 if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1) 226 return (NULL); 227 if (SIZE_MAX / sizeof(*buf) < n + 1) 228 errx(1, "conversion buffer length overflow"); 229 if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL) 230 err(1, "malloc"); 231 if (mbstowcs(buf, str, n + 1) != n) 232 errx(1, "internal mbstowcs() error"); 233 /* The last line may not end with \n. */ 234 if (n > 0 && buf[n - 1] == L'\n') 235 buf[n - 1] = L'\0'; 236 237 /* If requested get the chosen fields + character offsets. */ 238 if (numfields || numchars) { 239 if ((ret = wcsdup(skip(buf))) == NULL) 240 err(1, "wcsdup"); 241 free(buf); 242 } else 243 ret = buf; 244 245 if (iflag) { 246 for (p = ret; *p != L'\0'; p++) 247 *p = towlower(*p); 248 } 249 250 return (ret); 251 } 252 253 static int 254 inlcmp(const char *s1, const char *s2) 255 { 256 int c1, c2; 257 258 while (*s1 == *s2++) 259 if (*s1++ == '\0') 260 return (0); 261 c1 = (unsigned char)*s1; 262 c2 = (unsigned char)*(s2 - 1); 263 /* The last line may not end with \n. */ 264 if (c1 == '\n') 265 c1 = '\0'; 266 if (c2 == '\n') 267 c2 = '\0'; 268 return (c1 - c2); 269 } 270 271 /* 272 * show -- 273 * Output a line depending on the flags and number of repetitions 274 * of the line. 275 */ 276 static void 277 show(FILE *ofp, const char *str) 278 { 279 280 if ((dflag && repeats == 0) || (uflag && repeats > 0)) 281 return; 282 if (cflag) 283 (void)fprintf(ofp, "%4d %s", repeats + 1, str); 284 else 285 (void)fprintf(ofp, "%s", str); 286 } 287 288 static wchar_t * 289 skip(wchar_t *str) 290 { 291 int nchars, nfields; 292 293 for (nfields = 0; *str != L'\0' && nfields++ != numfields; ) { 294 while (iswblank(*str)) 295 str++; 296 while (*str != L'\0' && !iswblank(*str)) 297 str++; 298 } 299 for (nchars = numchars; nchars-- && *str != L'\0'; ++str) 300 ; 301 return(str); 302 } 303 304 static FILE * 305 file(const char *name, const char *mode) 306 { 307 FILE *fp; 308 309 if ((fp = fopen(name, mode)) == NULL) 310 err(1, "%s", name); 311 return(fp); 312 } 313 314 static void 315 obsolete(char *argv[]) 316 { 317 int len; 318 char *ap, *p, *start; 319 320 while ((ap = *++argv)) { 321 /* Return if "--" or not an option of any form. */ 322 if (ap[0] != '-') { 323 if (ap[0] != '+') 324 return; 325 } else if (ap[1] == '-') 326 return; 327 if (!isdigit((unsigned char)ap[1])) 328 continue; 329 /* 330 * Digit signifies an old-style option. Malloc space for dash, 331 * new option and argument. 332 */ 333 len = strlen(ap); 334 if ((start = p = malloc(len + 3)) == NULL) 335 err(1, "malloc"); 336 *p++ = '-'; 337 *p++ = ap[0] == '+' ? 's' : 'f'; 338 (void)strcpy(p, ap + 1); 339 *argv = start; 340 } 341 } 342 343 static void 344 usage(void) 345 { 346 (void)fprintf(stderr, 347 "usage: uniq [-c] [-d | -u] [-i] [-f fields] [-s chars] [input [output]]\n"); 348 exit(1); 349 } 350