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 <ctype.h> 52 #include <err.h> 53 #include <errno.h> 54 #include <getopt.h> 55 #include <limits.h> 56 #include <locale.h> 57 #include <nl_types.h> 58 #include <stdint.h> 59 #include <stdio.h> 60 #include <stdlib.h> 61 #include <string.h> 62 #include <termios.h> 63 #include <unistd.h> 64 #include <wchar.h> 65 #include <wctype.h> 66 67 static int cflag, dflag, uflag, iflag; 68 static int numchars, numfields, repeats; 69 70 static const struct option long_opts[] = 71 { 72 {"count", no_argument, NULL, 'c'}, 73 {"repeated", no_argument, NULL, 'd'}, 74 {"skip-fields", required_argument, NULL, 'f'}, 75 {"ignore-case", no_argument, NULL, 'i'}, 76 {"skip-chars", required_argument, NULL, 's'}, 77 {"unique", no_argument, NULL, 'u'}, 78 {NULL, no_argument, NULL, 0} 79 }; 80 81 static FILE *file(const char *, const char *); 82 static wchar_t *convert(const char *); 83 static int inlcmp(const char *, const char *); 84 static void show(FILE *, const char *); 85 static wchar_t *skip(wchar_t *); 86 static void obsolete(char *[]); 87 static void usage(void); 88 89 static void 90 strerror_init(void) 91 { 92 93 /* 94 * Cache NLS data before entering capability mode. 95 * XXXPJD: There should be strerror_init() and strsignal_init() in libc. 96 */ 97 (void)catopen("libc", NL_CAT_LOCALE); 98 } 99 100 int 101 main (int argc, char *argv[]) 102 { 103 wchar_t *tprev, *tthis; 104 FILE *ifp, *ofp; 105 int ch, comp; 106 size_t prevbuflen, thisbuflen, b1; 107 char *prevline, *thisline, *p; 108 const char *ifn; 109 cap_rights_t rights; 110 111 (void) setlocale(LC_ALL, ""); 112 113 obsolete(argv); 114 while ((ch = getopt_long(argc, argv, "+cdif:s:u", long_opts, 115 NULL)) != -1) 116 switch (ch) { 117 case 'c': 118 cflag = 1; 119 break; 120 case 'd': 121 dflag = 1; 122 break; 123 case 'i': 124 iflag = 1; 125 break; 126 case 'f': 127 numfields = strtol(optarg, &p, 10); 128 if (numfields < 0 || *p) 129 errx(1, "illegal field skip value: %s", optarg); 130 break; 131 case 's': 132 numchars = strtol(optarg, &p, 10); 133 if (numchars < 0 || *p) 134 errx(1, "illegal character skip value: %s", optarg); 135 break; 136 case 'u': 137 uflag = 1; 138 break; 139 case '?': 140 default: 141 usage(); 142 } 143 144 argc -= optind; 145 argv += optind; 146 147 if (argc > 2) 148 usage(); 149 150 ifp = stdin; 151 ifn = "stdin"; 152 ofp = stdout; 153 if (argc > 0 && strcmp(argv[0], "-") != 0) 154 ifp = file(ifn = argv[0], "r"); 155 cap_rights_init(&rights, CAP_FSTAT, CAP_READ); 156 if (cap_rights_limit(fileno(ifp), &rights) < 0 && errno != ENOSYS) 157 err(1, "unable to limit rights for %s", ifn); 158 cap_rights_init(&rights, CAP_FSTAT, CAP_WRITE); 159 if (argc > 1) 160 ofp = file(argv[1], "w"); 161 else 162 cap_rights_set(&rights, CAP_IOCTL); 163 if (cap_rights_limit(fileno(ofp), &rights) < 0 && errno != ENOSYS) { 164 err(1, "unable to limit rights for %s", 165 argc > 1 ? argv[1] : "stdout"); 166 } 167 if (cap_rights_is_set(&rights, CAP_IOCTL)) { 168 unsigned long cmd; 169 170 cmd = TIOCGETA; /* required by isatty(3) in printf(3) */ 171 172 if (cap_ioctls_limit(fileno(ofp), &cmd, 1) < 0 && 173 errno != ENOSYS) { 174 err(1, "unable to limit ioctls for %s", 175 argc > 1 ? argv[1] : "stdout"); 176 } 177 } 178 179 strerror_init(); 180 if (cap_enter() < 0 && errno != ENOSYS) 181 err(1, "unable to enter capability mode"); 182 183 prevbuflen = thisbuflen = 0; 184 prevline = thisline = NULL; 185 186 if (getline(&prevline, &prevbuflen, ifp) < 0) { 187 if (ferror(ifp)) 188 err(1, "%s", ifn); 189 exit(0); 190 } 191 tprev = convert(prevline); 192 193 tthis = NULL; 194 while (getline(&thisline, &thisbuflen, ifp) >= 0) { 195 if (tthis != NULL) 196 free(tthis); 197 tthis = convert(thisline); 198 199 if (tthis == NULL && tprev == NULL) 200 comp = inlcmp(thisline, prevline); 201 else if (tthis == NULL || tprev == NULL) 202 comp = 1; 203 else 204 comp = wcscoll(tthis, tprev); 205 206 if (comp) { 207 /* If different, print; set previous to new value. */ 208 show(ofp, prevline); 209 p = prevline; 210 b1 = prevbuflen; 211 prevline = thisline; 212 prevbuflen = thisbuflen; 213 if (tprev != NULL) 214 free(tprev); 215 tprev = tthis; 216 thisline = p; 217 thisbuflen = b1; 218 tthis = NULL; 219 repeats = 0; 220 } else 221 ++repeats; 222 } 223 if (ferror(ifp)) 224 err(1, "%s", ifn); 225 show(ofp, prevline); 226 exit(0); 227 } 228 229 static wchar_t * 230 convert(const char *str) 231 { 232 size_t n; 233 wchar_t *buf, *ret, *p; 234 235 if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1) 236 return (NULL); 237 if (SIZE_MAX / sizeof(*buf) < n + 1) 238 errx(1, "conversion buffer length overflow"); 239 if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL) 240 err(1, "malloc"); 241 if (mbstowcs(buf, str, n + 1) != n) 242 errx(1, "internal mbstowcs() error"); 243 /* The last line may not end with \n. */ 244 if (n > 0 && buf[n - 1] == L'\n') 245 buf[n - 1] = L'\0'; 246 247 /* If requested get the chosen fields + character offsets. */ 248 if (numfields || numchars) { 249 if ((ret = wcsdup(skip(buf))) == NULL) 250 err(1, "wcsdup"); 251 free(buf); 252 } else 253 ret = buf; 254 255 if (iflag) { 256 for (p = ret; *p != L'\0'; p++) 257 *p = towlower(*p); 258 } 259 260 return (ret); 261 } 262 263 static int 264 inlcmp(const char *s1, const char *s2) 265 { 266 int c1, c2; 267 268 while (*s1 == *s2++) 269 if (*s1++ == '\0') 270 return (0); 271 c1 = (unsigned char)*s1; 272 c2 = (unsigned char)*(s2 - 1); 273 /* The last line may not end with \n. */ 274 if (c1 == '\n') 275 c1 = '\0'; 276 if (c2 == '\n') 277 c2 = '\0'; 278 return (c1 - c2); 279 } 280 281 /* 282 * show -- 283 * Output a line depending on the flags and number of repetitions 284 * of the line. 285 */ 286 static void 287 show(FILE *ofp, const char *str) 288 { 289 290 if ((dflag && repeats == 0) || (uflag && repeats > 0)) 291 return; 292 if (cflag) 293 (void)fprintf(ofp, "%4d %s", repeats + 1, str); 294 else 295 (void)fprintf(ofp, "%s", str); 296 } 297 298 static wchar_t * 299 skip(wchar_t *str) 300 { 301 int nchars, nfields; 302 303 for (nfields = 0; *str != L'\0' && nfields++ != numfields; ) { 304 while (iswblank(*str)) 305 str++; 306 while (*str != L'\0' && !iswblank(*str)) 307 str++; 308 } 309 for (nchars = numchars; nchars-- && *str != L'\0'; ++str) 310 ; 311 return(str); 312 } 313 314 static FILE * 315 file(const char *name, const char *mode) 316 { 317 FILE *fp; 318 319 if ((fp = fopen(name, mode)) == NULL) 320 err(1, "%s", name); 321 return(fp); 322 } 323 324 static void 325 obsolete(char *argv[]) 326 { 327 int len; 328 char *ap, *p, *start; 329 330 while ((ap = *++argv)) { 331 /* Return if "--" or not an option of any form. */ 332 if (ap[0] != '-') { 333 if (ap[0] != '+') 334 return; 335 } else if (ap[1] == '-') 336 return; 337 if (!isdigit((unsigned char)ap[1])) 338 continue; 339 /* 340 * Digit signifies an old-style option. Malloc space for dash, 341 * new option and argument. 342 */ 343 len = strlen(ap); 344 if ((start = p = malloc(len + 3)) == NULL) 345 err(1, "malloc"); 346 *p++ = '-'; 347 *p++ = ap[0] == '+' ? 's' : 'f'; 348 (void)strcpy(p, ap + 1); 349 *argv = start; 350 } 351 } 352 353 static void 354 usage(void) 355 { 356 (void)fprintf(stderr, 357 "usage: uniq [-c] [-d | -u] [-i] [-f fields] [-s chars] [input [output]]\n"); 358 exit(1); 359 } 360