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. All advertising materials mentioning features or use of this software
  17  *    must display the following acknowledgement:
  18  *      This product includes software developed by the University of
  19  *      California, Berkeley and its contributors.
  20  * 4. Neither the name of the University nor the names of its contributors
  21  *    may be used to endorse or promote products derived from this software
  22  *    without specific prior written permission.
  23  *
  24  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  25  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  26  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  27  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  28  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  29  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  30  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  31  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  32  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  33  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  34  * SUCH DAMAGE.
  35  *
  36  * @(#) Copyright (c) 1989, 1993 The Regents of the University of California.  All rights reserved.
  37  * @(#)uniq.c   8.3 (Berkeley) 5/4/95
  38  * $FreeBSD: src/usr.bin/uniq/uniq.c,v 1.11.2.3 2002/06/28 08:02:19 tjr Exp $
  39  * $DragonFly: src/usr.bin/uniq/uniq.c,v 1.5 2008/10/16 01:52:34 swildner Exp $
  40  */
  41
  42 #include <ctype.h>
  43 #include <err.h>
  44 #include <limits.h>
  45 #include <locale.h>
  46 #include <stdio.h>
  47 #include <stdlib.h>
  48 #include <string.h>
  49 #include <unistd.h>
  50
  51 #define MAXLINELEN      (LINE_MAX + 1)
  52
  53 int cflag, dflag, uflag;
  54 int numchars, numfields, repeats;
  55
  56 FILE    *file(const char *, const char *);
  57 char    *getline(char *, size_t, FILE *);
  58 void     show(FILE *, char *);
  59 char    *skip(char *);
  60 void     obsolete(char *[]);
  61 static void      usage(void);
  62 int      stricoll(char *, char*);
  63
  64 int
  65 main(int argc, char **argv)
  66 {
  67         char *t1, *t2;
  68         FILE *ifp, *ofp;
  69         int ch;
  70         char *prevline, *thisline, *p;
  71         int iflag = 0, comp;
  72
  73         (void) setlocale(LC_ALL, "");
  74
  75         obsolete(argv);
  76         while ((ch = getopt(argc, argv, "cdif:s:u")) != -1)
  77                 switch (ch) {
  78                 case 'c':
  79                         cflag = 1;
  80                         break;
  81                 case 'd':
  82                         dflag = 1;
  83                         break;
  84                 case 'i':
  85                         iflag = 1;
  86                         break;
  87                 case 'f':
  88                         numfields = strtol(optarg, &p, 10);
  89                         if (numfields < 0 || *p)
  90                                 errx(1, "illegal field skip value: %s", optarg);
  91                         break;
  92                 case 's':
  93                         numchars = strtol(optarg, &p, 10);
  94                         if (numchars < 0 || *p)
  95                                 errx(1, "illegal character skip value: %s", optarg);
  96                         break;
  97                 case 'u':
  98                         uflag = 1;
  99                         break;
 100                 case '?':
 101                 default:
 102                         usage();
 103         }
 104
 105         argc -= optind;
 106         argv +=optind;
 107
 108         /* If no flags are set, default is -d -u. */
 109         if (cflag) {
 110                 if (dflag || uflag)
 111                         usage();
 112         } else if (!dflag && !uflag)
 113                 dflag = uflag = 1;
 114
 115         if (argc > 2)
 116                 usage();
 117
 118         ifp = stdin;
 119         ofp = stdout;
 120         if (argc > 0 && strcmp(argv[0], "-") != 0)
 121                 ifp = file(argv[0], "r");
 122         if (argc > 1)
 123                 ofp = file(argv[1], "w");
 124
 125         prevline = malloc(MAXLINELEN);
 126         thisline = malloc(MAXLINELEN);
 127         if (prevline == NULL || thisline == NULL)
 128                 errx(1, "malloc");
 129
 130         if (getline(prevline, MAXLINELEN, ifp) == NULL)
 131                 exit(0);
 132
 133         while (getline(thisline, MAXLINELEN, ifp)) {
 134                 /* If requested get the chosen fields + character offsets. */
 135                 if (numfields || numchars) {
 136                         t1 = skip(thisline);
 137                         t2 = skip(prevline);
 138                 } else {
 139                         t1 = thisline;
 140                         t2 = prevline;
 141                 }
 142
 143                 /* If different, print; set previous to new value. */
 144                 if (iflag)
 145                         comp = stricoll(t1, t2);
 146                 else
 147                         comp = strcoll(t1, t2);
 148
 149                 if (comp) {
 150                         show(ofp, prevline);
 151                         t1 = prevline;
 152                         prevline = thisline;
 153                         thisline = t1;
 154                         repeats = 0;
 155                 } else
 156                         ++repeats;
 157         }
 158         show(ofp, prevline);
 159         exit(0);
 160 }
 161
 162 char *
 163 getline(char *buf, size_t buflen, FILE *fp)
 164 {
 165         size_t bufpos;
 166         int ch = EOF;
 167
 168         bufpos = 0;
 169         while (bufpos + 2 != buflen && (ch = getc(fp)) != EOF && ch != '\n')
 170                 buf[bufpos++] = ch;
 171         if (bufpos + 1 != buflen)
 172                 buf[bufpos] = '\0';
 173         while (ch != EOF && ch != '\n')
 174                 ch = getc(fp);
 175
 176         return (bufpos != 0 || ch == '\n' ? buf : NULL);
 177 }
 178
 179 /*
 180  * show --
 181  *      Output a line depending on the flags and number of repetitions
 182  *      of the line.
 183  */
 184 void
 185 show(FILE *ofp, char *str)
 186 {
 187
 188         if (cflag && *str)
 189                 (void)fprintf(ofp, "%4d %s\n", repeats + 1, str);
 190         if ((dflag && repeats) || (uflag && !repeats))
 191                 (void)fprintf(ofp, "%s\n", str);
 192 }
 193
 194 char *
 195 skip(char *str)
 196 {
 197         int nchars, nfields;
 198
 199         for (nfields = 0; *str != '\0' && nfields++ != numfields; ) {
 200                 while (isblank((unsigned char)*str))
 201                         str++;
 202                 while (*str != '\0' && !isblank((unsigned char)*str))
 203                         str++;
 204         }
 205         for (nchars = numchars; nchars-- && *str; ++str);
 206         return(str);
 207 }
 208
 209 FILE *
 210 file(const char *name, const char *mode)
 211 {
 212         FILE *fp;
 213
 214         if ((fp = fopen(name, mode)) == NULL)
 215                 err(1, "%s", name);
 216         return(fp);
 217 }
 218
 219 void
 220 obsolete(char **argv)
 221 {
 222         int len;
 223         char *ap, *p, *start;
 224
 225         while ((ap = *++argv)) {
 226                 /* Return if "--" or not an option of any form. */
 227                 if (ap[0] != '-') {
 228                         if (ap[0] != '+')
 229                                 return;
 230                 } else if (ap[1] == '-')
 231                         return;
 232                 if (!isdigit((unsigned char)ap[1]))
 233                         continue;
 234                 /*
 235                  * Digit signifies an old-style option.  Malloc space for dash,
 236                  * new option and argument.
 237                  */
 238                 len = strlen(ap);
 239                 if ((start = p = malloc(len + 3)) == NULL)
 240                         errx(1, "malloc");
 241                 *p++ = '-';
 242                 *p++ = ap[0] == '+' ? 's' : 'f';
 243                 (void)strcpy(p, ap + 1);
 244                 *argv = start;
 245         }
 246 }
 247
 248 static void
 249 usage(void)
 250 {
 251         (void)fprintf(stderr,
 252 "usage: uniq [-c | -d | -u] [-i] [-f fields] [-s chars] [input [output]]\n");
 253         exit(1);
 254 }
 255
 256 int
 257 stricoll(char *s1, char *s2)
 258 {
 259         char *p, line1[MAXLINELEN], line2[MAXLINELEN];
 260
 261         for (p = line1; *s1; s1++)
 262                 *p++ = tolower((unsigned char)*s1);
 263         *p = '\0';
 264         for (p = line2; *s2; s2++)
 265                 *p++ = tolower((unsigned char)*s2);
 266         *p = '\0';
 267         return strcoll(line1, line2);
 268 }