usr.bin/uniq/uniq.c

   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: src/usr.bin/uniq/uniq.c,v 1.11.2.3 2002/06/28 08:02:19 tjr Exp $
  35  * $DragonFly: src/usr.bin/uniq/uniq.c,v 1.5 2008/10/16 01:52:34 swildner Exp $
  36  */
  37
  38 #include <ctype.h>
  39 #include <err.h>
  40 #include <limits.h>
  41 #include <locale.h>
  42 #include <stdio.h>
  43 #include <stdlib.h>
  44 #include <string.h>
  45 #include <unistd.h>
  46
  47 #define MAXLINELEN      (LINE_MAX + 1)
  48
  49 int cflag, dflag, uflag;
  50 int numchars, numfields, repeats;
  51
  52 FILE    *file(const char *, const char *);
  53 char    *getline(char *, size_t, FILE *);
  54 void     show(FILE *, char *);
  55 char    *skip(char *);
  56 void     obsolete(char *[]);
  57 static void      usage(void);
  58 int      stricoll(char *, char*);
  59
  60 int
  61 main(int argc, char **argv)
  62 {
  63         char *t1, *t2;
  64         FILE *ifp, *ofp;
  65         int ch;
  66         char *prevline, *thisline, *p;
  67         int iflag = 0, comp;
  68
  69         (void) setlocale(LC_ALL, "");
  70
  71         obsolete(argv);
  72         while ((ch = getopt(argc, argv, "cdif:s:u")) != -1)
  73                 switch (ch) {
  74                 case 'c':
  75                         cflag = 1;
  76                         break;
  77                 case 'd':
  78                         dflag = 1;
  79                         break;
  80                 case 'i':
  81                         iflag = 1;
  82                         break;
  83                 case 'f':
  84                         numfields = strtol(optarg, &p, 10);
  85                         if (numfields < 0 || *p)
  86                                 errx(1, "illegal field skip value: %s", optarg);
  87                         break;
  88                 case 's':
  89                         numchars = strtol(optarg, &p, 10);
  90                         if (numchars < 0 || *p)
  91                                 errx(1, "illegal character skip value: %s", optarg);
  92                         break;
  93                 case 'u':
  94                         uflag = 1;
  95                         break;
  96                 case '?':
  97                 default:
  98                         usage();
  99         }
 100
 101         argc -= optind;
 102         argv +=optind;
 103
 104         /* If no flags are set, default is -d -u. */
 105         if (cflag) {
 106                 if (dflag || uflag)
 107                         usage();
 108         } else if (!dflag && !uflag)
 109                 dflag = uflag = 1;
 110
 111         if (argc > 2)
 112                 usage();
 113
 114         ifp = stdin;
 115         ofp = stdout;
 116         if (argc > 0 && strcmp(argv[0], "-") != 0)
 117                 ifp = file(argv[0], "r");
 118         if (argc > 1)
 119                 ofp = file(argv[1], "w");
 120
 121         prevline = malloc(MAXLINELEN);
 122         thisline = malloc(MAXLINELEN);
 123         if (prevline == NULL || thisline == NULL)
 124                 errx(1, "malloc");
 125
 126         if (getline(prevline, MAXLINELEN, ifp) == NULL)
 127                 exit(0);
 128
 129         while (getline(thisline, MAXLINELEN, ifp)) {
 130                 /* If requested get the chosen fields + character offsets. */
 131                 if (numfields || numchars) {
 132                         t1 = skip(thisline);
 133                         t2 = skip(prevline);
 134                 } else {
 135                         t1 = thisline;
 136                         t2 = prevline;
 137                 }
 138
 139                 /* If different, print; set previous to new value. */
 140                 if (iflag)
 141                         comp = stricoll(t1, t2);
 142                 else
 143                         comp = strcoll(t1, t2);
 144
 145                 if (comp) {
 146                         show(ofp, prevline);
 147                         t1 = prevline;
 148                         prevline = thisline;
 149                         thisline = t1;
 150                         repeats = 0;
 151                 } else
 152                         ++repeats;
 153         }
 154         show(ofp, prevline);
 155         exit(0);
 156 }
 157
 158 char *
 159 getline(char *buf, size_t buflen, FILE *fp)
 160 {
 161         size_t bufpos;
 162         int ch = EOF;
 163
 164         bufpos = 0;
 165         while (bufpos + 2 != buflen && (ch = getc(fp)) != EOF && ch != '\n')
 166                 buf[bufpos++] = ch;
 167         if (bufpos + 1 != buflen)
 168                 buf[bufpos] = '\0';
 169         while (ch != EOF && ch != '\n')
 170                 ch = getc(fp);
 171
 172         return (bufpos != 0 || ch == '\n' ? buf : NULL);
 173 }
 174
 175 /*
 176  * show --
 177  *      Output a line depending on the flags and number of repetitions
 178  *      of the line.
 179  */
 180 void
 181 show(FILE *ofp, char *str)
 182 {
 183
 184         if (cflag && *str)
 185                 (void)fprintf(ofp, "%4d %s\n", repeats + 1, str);
 186         if ((dflag && repeats) || (uflag && !repeats))
 187                 (void)fprintf(ofp, "%s\n", str);
 188 }
 189
 190 char *
 191 skip(char *str)
 192 {
 193         int nchars, nfields;
 194
 195         for (nfields = 0; *str != '\0' && nfields++ != numfields; ) {
 196                 while (isblank((unsigned char)*str))
 197                         str++;
 198                 while (*str != '\0' && !isblank((unsigned char)*str))
 199                         str++;
 200         }
 201         for (nchars = numchars; nchars-- && *str; ++str);
 202         return(str);
 203 }
 204
 205 FILE *
 206 file(const char *name, const char *mode)
 207 {
 208         FILE *fp;
 209
 210         if ((fp = fopen(name, mode)) == NULL)
 211                 err(1, "%s", name);
 212         return(fp);
 213 }
 214
 215 void
 216 obsolete(char **argv)
 217 {
 218         int len;
 219         char *ap, *p, *start;
 220
 221         while ((ap = *++argv)) {
 222                 /* Return if "--" or not an option of any form. */
 223                 if (ap[0] != '-') {
 224                         if (ap[0] != '+')
 225                                 return;
 226                 } else if (ap[1] == '-')
 227                         return;
 228                 if (!isdigit((unsigned char)ap[1]))
 229                         continue;
 230                 /*
 231                  * Digit signifies an old-style option.  Malloc space for dash,
 232                  * new option and argument.
 233                  */
 234                 len = strlen(ap);
 235                 if ((start = p = malloc(len + 3)) == NULL)
 236                         errx(1, "malloc");
 237                 *p++ = '-';
 238                 *p++ = ap[0] == '+' ? 's' : 'f';
 239                 (void)strcpy(p, ap + 1);
 240                 *argv = start;
 241         }
 242 }
 243
 244 static void
 245 usage(void)
 246 {
 247         (void)fprintf(stderr,
 248 "usage: uniq [-c | -d | -u] [-i] [-f fields] [-s chars] [input [output]]\n");
 249         exit(1);
 250 }
 251
 252 int
 253 stricoll(char *s1, char *s2)
 254 {
 255         char *p, line1[MAXLINELEN], line2[MAXLINELEN];
 256
 257         for (p = line1; *s1; s1++)
 258                 *p++ = tolower((unsigned char)*s1);
 259         *p = '\0';
 260         for (p = line2; *s2; s2++)
 261                 *p++ = tolower((unsigned char)*s2);
 262         *p = '\0';
 263         return strcoll(line1, line2);
 264 }