bin/uniq/uniq.c

   1 /*      $OpenBSD: uniq.c,v 1.26 2017/12/24 00:11:43 tb Exp $    */
   2 /*      $NetBSD: uniq.c,v 1.7 1995/08/31 22:03:48 jtc Exp $     */
   3
   4 /*
   5  * Copyright (c) 1989, 1993
   6  *      The Regents of the University of California.  All rights reserved.
   7  *
   8  * This code is derived from software contributed to Berkeley by
   9  * Case Larsen.
  10  *
  11  * Redistribution and use in source and binary forms, with or without
  12  * modification, are permitted provided that the following conditions
  13  * are met:
  14  * 1. Redistributions of source code must retain the above copyright
  15  *    notice, this list of conditions and the following disclaimer.
  16  * 2. Redistributions in binary form must reproduce the above copyright
  17  *    notice, this list of conditions and the following disclaimer in the
  18  *    documentation and/or other materials provided with the distribution.
  19  * 3. Neither the name of the University nor the names of its contributors
  20  *    may be used to endorse or promote products derived from this software
  21  *    without specific prior written permission.
  22  *
  23  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  24  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  25  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  26  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  27  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  28  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  29  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  30  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  31  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  32  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  33  * SUCH DAMAGE.
  34  */
  35
  36 #include <ctype.h>
  37 #include <err.h>
  38 #include <errno.h>
  39 #include <limits.h>
  40 #include <locale.h>
  41 #include <stdio.h>
  42 #include <stdlib.h>
  43 #include <string.h>
  44 #include <unistd.h>
  45 #include <wchar.h>
  46 #include <wctype.h>
  47
  48 #define MAXLINELEN      (8 * 1024)
  49
  50 int cflag, dflag, iflag, uflag;
  51 int numchars, numfields, repeats;
  52
  53 FILE    *file(char *, char *);
  54 void     show(FILE *, char *);
  55 char    *skip(char *);
  56 void     obsolete(char *[]);
  57 __dead void     usage(void);
  58
  59 int
  60 main(int argc, char *argv[])
  61 {
  62         char *t1, *t2;
  63         FILE *ifp = NULL, *ofp = NULL;
  64         int ch;
  65         char *prevline, *thisline;
  66
  67         setlocale(LC_CTYPE, "");
  68
  69         if (pledge("stdio rpath wpath cpath", NULL) == -1)
  70                 err(1, "pledge");
  71
  72         obsolete(argv);
  73         while ((ch = getopt(argc, argv, "cdf:is:u")) != -1) {
  74                 const char *errstr;
  75
  76                 switch (ch) {
  77                 case 'c':
  78                         cflag = 1;
  79                         break;
  80                 case 'd':
  81                         dflag = 1;
  82                         break;
  83                 case 'f':
  84                         numfields = (int)strtonum(optarg, 0, INT_MAX,
  85                             &errstr);
  86                         if (errstr)
  87                                 errx(1, "field skip value is %s: %s",
  88                                     errstr, optarg);
  89                         break;
  90                 case 'i':
  91                         iflag = 1;
  92                         break;
  93                 case 's':
  94                         numchars = (int)strtonum(optarg, 0, INT_MAX,
  95                             &errstr);
  96                         if (errstr)
  97                                 errx(1,
  98                                     "character skip value is %s: %s",
  99                                     errstr, optarg);
 100                         break;
 101                 case 'u':
 102                         uflag = 1;
 103                         break;
 104                 default:
 105                         usage();
 106                 }
 107         }
 108
 109         argc -= optind;
 110         argv += optind;
 111
 112         /* If neither -d nor -u are set, default is -d -u. */
 113         if (!dflag && !uflag)
 114                 dflag = uflag = 1;
 115
 116         switch(argc) {
 117         case 0:
 118                 ifp = stdin;
 119                 ofp = stdout;
 120                 break;
 121         case 1:
 122                 ifp = file(argv[0], "r");
 123                 ofp = stdout;
 124                 break;
 125         case 2:
 126                 ifp = file(argv[0], "r");
 127                 ofp = file(argv[1], "w");
 128                 break;
 129         default:
 130                 usage();
 131         }
 132
 133         if (pledge("stdio", NULL) == -1)
 134                 err(1, "pledge");
 135
 136         prevline = malloc(MAXLINELEN);
 137         thisline = malloc(MAXLINELEN);
 138         if (prevline == NULL || thisline == NULL)
 139                 err(1, "malloc");
 140
 141         if (fgets(prevline, MAXLINELEN, ifp) == NULL)
 142                 exit(0);
 143
 144         while (fgets(thisline, MAXLINELEN, ifp)) {
 145                 /* If requested get the chosen fields + character offsets. */
 146                 if (numfields || numchars) {
 147                         t1 = skip(thisline);
 148                         t2 = skip(prevline);
 149                 } else {
 150                         t1 = thisline;
 151                         t2 = prevline;
 152                 }
 153
 154                 /* If different, print; set previous to new value. */
 155                 if ((iflag ? strcasecmp : strcmp)(t1, t2)) {
 156                         show(ofp, prevline);
 157                         t1 = prevline;
 158                         prevline = thisline;
 159                         thisline = t1;
 160                         repeats = 0;
 161                 } else
 162                         ++repeats;
 163         }
 164         show(ofp, prevline);
 165         exit(0);
 166 }
 167
 168 /*
 169  * show --
 170  *      Output a line depending on the flags and number of repetitions
 171  *      of the line.
 172  */
 173 void
 174 show(FILE *ofp, char *str)
 175 {
 176         if ((dflag && repeats) || (uflag && !repeats)) {
 177                 if (cflag)
 178                         (void)fprintf(ofp, "%4d %s", repeats + 1, str);
 179                 else
 180                         (void)fprintf(ofp, "%s", str);
 181         }
 182 }
 183
 184 char *
 185 skip(char *str)
 186 {
 187         wchar_t wc;
 188         int nchars, nfields;
 189         int len;
 190         int field_started;
 191
 192         for (nfields = numfields; nfields && *str; nfields--) {
 193                 /* Skip one field, including preceding blanks. */
 194                 for (field_started = 0; *str != '\0'; str += len) {
 195                         if ((len = mbtowc(&wc, str, MB_CUR_MAX)) == -1) {
 196                                 (void)mbtowc(NULL, NULL, MB_CUR_MAX);
 197                                 wc = L'?';
 198                                 len = 1;
 199                         }
 200                         if (iswblank(wc)) {
 201                                 if (field_started)
 202                                         break;
 203                         } else
 204                                 field_started = 1;
 205                 }
 206         }
 207
 208         /* Skip some additional characters. */
 209         for (nchars = numchars; nchars-- && *str != '\0'; str += len)
 210                 if ((len = mblen(str, MB_CUR_MAX)) == -1)
 211                         len = 1;
 212
 213         return (str);
 214 }
 215
 216 FILE *
 217 file(char *name, char *mode)
 218 {
 219         FILE *fp;
 220
 221         if (strcmp(name, "-") == 0)
 222                 return(*mode == 'r' ? stdin : stdout);
 223         if ((fp = fopen(name, mode)) == NULL)
 224                 err(1, "%s", name);
 225         return (fp);
 226 }
 227
 228 void
 229 obsolete(char *argv[])
 230 {
 231         size_t len;
 232         char *ap, *p, *start;
 233
 234         while ((ap = *++argv)) {
 235                 /* Return if "--" or not an option of any form. */
 236                 if (ap[0] != '-') {
 237                         if (ap[0] != '+')
 238                                 return;
 239                 } else if (ap[1] == '-')
 240                         return;
 241                 if (!isdigit((unsigned char)ap[1]))
 242                         continue;
 243                 /*
 244                  * Digit signifies an old-style option.  Malloc space for dash,
 245                  * new option and argument.
 246                  */
 247                 len = strlen(ap) + 3;
 248                 if ((start = p = malloc(len)) == NULL)
 249                         err(1, "malloc");
 250                 *p++ = '-';
 251                 *p++ = ap[0] == '+' ? 's' : 'f';
 252                 (void)strlcpy(p, ap + 1, len - 2);
 253                 *argv = start;
 254         }
 255 }
 256
 257 __dead void
 258 usage(void)
 259 {
 260         extern char *__progname;
 261
 262         (void)fprintf(stderr,
 263             "usage: %s [-ci] [-d | -u] [-f fields] [-s chars] [input_file [output_file]]\n",
 264             __progname);
 265         exit(1);
 266 }