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 #endif /* not lint */ 46 47 #include <sys/capsicum.h> 48 49 #include <capsicum_helpers.h> 50 #include <ctype.h> 51 #include <err.h> 52 #include <errno.h> 53 #include <getopt.h> 54 #include <limits.h> 55 #include <locale.h> 56 #include <nl_types.h> 57 #include <stdint.h> 58 #include <stdio.h> 59 #include <stdlib.h> 60 #include <string.h> 61 #include <termios.h> 62 #include <unistd.h> 63 #include <wchar.h> 64 #include <wctype.h> 65 66 static int Dflag, cflag, dflag, uflag, iflag; 67 static int numchars, numfields, repeats; 68 69 /* Dflag values */ 70 #define DF_NONE 0 71 #define DF_NOSEP 1 72 #define DF_PRESEP 2 73 #define DF_POSTSEP 3 74 75 static const struct option long_opts[] = 76 { 77 {"all-repeated",optional_argument, NULL, 'D'}, 78 {"count", no_argument, NULL, 'c'}, 79 {"repeated", no_argument, NULL, 'd'}, 80 {"skip-fields", required_argument, NULL, 'f'}, 81 {"ignore-case", no_argument, NULL, 'i'}, 82 {"skip-chars", required_argument, NULL, 's'}, 83 {"unique", no_argument, NULL, 'u'}, 84 {NULL, no_argument, NULL, 0} 85 }; 86 87 static FILE *file(const char *, const char *); 88 static wchar_t *convert(const char *); 89 static int inlcmp(const char *, const char *); 90 static void show(FILE *, const char *); 91 static wchar_t *skip(wchar_t *); 92 static void obsolete(char *[]); 93 static void usage(void); 94 95 int 96 main (int argc, char *argv[]) 97 { 98 wchar_t *tprev, *tthis; 99 FILE *ifp, *ofp; 100 int ch, comp; 101 size_t prevbuflen, thisbuflen, b1; 102 char *prevline, *thisline, *p; 103 const char *ifn, *errstr;; 104 cap_rights_t rights; 105 106 (void) setlocale(LC_ALL, ""); 107 108 obsolete(argv); 109 while ((ch = getopt_long(argc, argv, "+D::cdif:s:u", long_opts, 110 NULL)) != -1) 111 switch (ch) { 112 case 'D': 113 if (optarg == NULL || strcasecmp(optarg, "none") == 0) 114 Dflag = DF_NOSEP; 115 else if (strcasecmp(optarg, "prepend") == 0) 116 Dflag = DF_PRESEP; 117 else if (strcasecmp(optarg, "separate") == 0) 118 Dflag = DF_POSTSEP; 119 else 120 usage(); 121 break; 122 case 'c': 123 cflag = 1; 124 break; 125 case 'd': 126 dflag = 1; 127 break; 128 case 'i': 129 iflag = 1; 130 break; 131 case 'f': 132 numfields = strtonum(optarg, 0, INT_MAX, &errstr); 133 if (errstr) 134 errx(1, "field skip value is %s: %s", errstr, optarg); 135 break; 136 case 's': 137 numchars = strtonum(optarg, 0, INT_MAX, &errstr); 138 if (errstr != NULL) 139 errx(1, "character skip value is %s: %s", errstr, optarg); 140 break; 141 case 'u': 142 uflag = 1; 143 break; 144 case '?': 145 default: 146 usage(); 147 } 148 149 argc -= optind; 150 argv += optind; 151 152 if (argc > 2) 153 usage(); 154 155 ifp = stdin; 156 ifn = "stdin"; 157 ofp = stdout; 158 if (argc > 0 && strcmp(argv[0], "-") != 0) 159 ifp = file(ifn = argv[0], "r"); 160 cap_rights_init(&rights, CAP_FSTAT, CAP_READ); 161 if (caph_rights_limit(fileno(ifp), &rights) < 0) 162 err(1, "unable to limit rights for %s", ifn); 163 cap_rights_init(&rights, CAP_FSTAT, CAP_WRITE); 164 if (argc > 1) 165 ofp = file(argv[1], "w"); 166 else 167 cap_rights_set(&rights, CAP_IOCTL); 168 if (caph_rights_limit(fileno(ofp), &rights) < 0) { 169 err(1, "unable to limit rights for %s", 170 argc > 1 ? argv[1] : "stdout"); 171 } 172 if (cap_rights_is_set(&rights, CAP_IOCTL)) { 173 unsigned long cmd; 174 175 cmd = TIOCGETA; /* required by isatty(3) in printf(3) */ 176 177 if (caph_ioctls_limit(fileno(ofp), &cmd, 1) < 0) { 178 err(1, "unable to limit ioctls for %s", 179 argc > 1 ? argv[1] : "stdout"); 180 } 181 } 182 183 caph_cache_catpages(); 184 if (caph_enter() < 0) 185 err(1, "unable to enter capability mode"); 186 187 prevbuflen = thisbuflen = 0; 188 prevline = thisline = NULL; 189 190 if (getline(&prevline, &prevbuflen, ifp) < 0) { 191 if (ferror(ifp)) 192 err(1, "%s", ifn); 193 exit(0); 194 } 195 tprev = convert(prevline); 196 197 tthis = NULL; 198 while (getline(&thisline, &thisbuflen, ifp) >= 0) { 199 if (tthis != NULL) 200 free(tthis); 201 tthis = convert(thisline); 202 203 if (tthis == NULL && tprev == NULL) 204 comp = inlcmp(thisline, prevline); 205 else if (tthis == NULL || tprev == NULL) 206 comp = 1; 207 else 208 comp = wcscoll(tthis, tprev); 209 210 if (comp) { 211 /* If different, print; set previous to new value. */ 212 if (Dflag == DF_POSTSEP && repeats > 0) 213 fputc('\n', ofp); 214 if (!Dflag) 215 show(ofp, prevline); 216 p = prevline; 217 b1 = prevbuflen; 218 prevline = thisline; 219 prevbuflen = thisbuflen; 220 if (tprev != NULL) 221 free(tprev); 222 tprev = tthis; 223 thisline = p; 224 thisbuflen = b1; 225 tthis = NULL; 226 repeats = 0; 227 } else { 228 if (Dflag) { 229 if (repeats == 0) { 230 if (Dflag == DF_PRESEP) 231 fputc('\n', ofp); 232 show(ofp, prevline); 233 } 234 show(ofp, thisline); 235 } 236 ++repeats; 237 } 238 } 239 if (ferror(ifp)) 240 err(1, "%s", ifn); 241 if (!Dflag) 242 show(ofp, prevline); 243 exit(0); 244 } 245 246 static wchar_t * 247 convert(const char *str) 248 { 249 size_t n; 250 wchar_t *buf, *ret, *p; 251 252 if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1) 253 return (NULL); 254 if (SIZE_MAX / sizeof(*buf) < n + 1) 255 errx(1, "conversion buffer length overflow"); 256 if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL) 257 err(1, "malloc"); 258 if (mbstowcs(buf, str, n + 1) != n) 259 errx(1, "internal mbstowcs() error"); 260 /* The last line may not end with \n. */ 261 if (n > 0 && buf[n - 1] == L'\n') 262 buf[n - 1] = L'\0'; 263 264 /* If requested get the chosen fields + character offsets. */ 265 if (numfields || numchars) { 266 if ((ret = wcsdup(skip(buf))) == NULL) 267 err(1, "wcsdup"); 268 free(buf); 269 } else 270 ret = buf; 271 272 if (iflag) { 273 for (p = ret; *p != L'\0'; p++) 274 *p = towlower(*p); 275 } 276 277 return (ret); 278 } 279 280 static int 281 inlcmp(const char *s1, const char *s2) 282 { 283 int c1, c2; 284 285 while (*s1 == *s2++) 286 if (*s1++ == '\0') 287 return (0); 288 c1 = (unsigned char)*s1; 289 c2 = (unsigned char)*(s2 - 1); 290 /* The last line may not end with \n. */ 291 if (c1 == '\n') 292 c1 = '\0'; 293 if (c2 == '\n') 294 c2 = '\0'; 295 return (c1 - c2); 296 } 297 298 /* 299 * show -- 300 * Output a line depending on the flags and number of repetitions 301 * of the line. 302 */ 303 static void 304 show(FILE *ofp, const char *str) 305 { 306 307 if ((!Dflag && dflag && repeats == 0) || (uflag && repeats > 0)) 308 return; 309 if (cflag) 310 (void)fprintf(ofp, "%4d %s", repeats + 1, str); 311 else 312 (void)fprintf(ofp, "%s", str); 313 } 314 315 static wchar_t * 316 skip(wchar_t *str) 317 { 318 int nchars, nfields; 319 320 for (nfields = 0; *str != L'\0' && nfields++ != numfields; ) { 321 while (iswblank(*str)) 322 str++; 323 while (*str != L'\0' && !iswblank(*str)) 324 str++; 325 } 326 for (nchars = numchars; nchars-- && *str != L'\0'; ++str) 327 ; 328 return(str); 329 } 330 331 static FILE * 332 file(const char *name, const char *mode) 333 { 334 FILE *fp; 335 336 if ((fp = fopen(name, mode)) == NULL) 337 err(1, "%s", name); 338 return(fp); 339 } 340 341 static void 342 obsolete(char *argv[]) 343 { 344 int len; 345 char *ap, *p, *start; 346 347 while ((ap = *++argv)) { 348 /* Return if "--" or not an option of any form. */ 349 if (ap[0] != '-') { 350 if (ap[0] != '+') 351 return; 352 } else if (ap[1] == '-') 353 return; 354 if (!isdigit((unsigned char)ap[1])) 355 continue; 356 /* 357 * Digit signifies an old-style option. Malloc space for dash, 358 * new option and argument. 359 */ 360 len = strlen(ap); 361 if ((start = p = malloc(len + 3)) == NULL) 362 err(1, "malloc"); 363 *p++ = '-'; 364 *p++ = ap[0] == '+' ? 's' : 'f'; 365 (void)strcpy(p, ap + 1); 366 *argv = start; 367 } 368 } 369 370 static void 371 usage(void) 372 { 373 (void)fprintf(stderr, 374 "usage: uniq [-c | -d | -D | -u] [-i] [-f fields] [-s chars] [input [output]]\n"); 375 exit(1); 376 } 377