usr.bin/cut/cut.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  * Adam S. Moskowitz of Menlo Consulting and Marciano Pitargue.
   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  * @(#)cut.c    8.3 (Berkeley) 5/4/95
  38  * $FreeBSD: src/usr.bin/cut/cut.c,v 1.9.2.3 2001/07/30 09:59:16 dd Exp $
  39  * $DragonFly: src/usr.bin/cut/cut.c,v 1.3 2003/10/02 17:42:27 hmp 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 int     cflag;
  52 char    dchar;
  53 int     dflag;
  54 int     fflag;
  55 int     sflag;
  56
  57 void    c_cut (FILE *, const char *);
  58 void    f_cut (FILE *, const char *);
  59 void    get_list (char *);
  60 int     main (int, char **);
  61 static  void usage (void);
  62
  63 int
  64 main(int argc, char **argv)
  65 {
  66         FILE *fp;
  67         void (*fcn) (FILE *, const char *) = NULL;
  68         int ch;
  69
  70         fcn = NULL;
  71         setlocale (LC_ALL, "");
  72
  73         dchar = '\t';                   /* default delimiter is \t */
  74
  75         /* Since we don't support multi-byte characters, the -c and -b
  76            options are equivalent, and the -n option is meaningless. */
  77         while ((ch = getopt(argc, argv, "b:c:d:f:sn")) != -1)
  78                 switch(ch) {
  79                 case 'b':
  80                 case 'c':
  81                         fcn = c_cut;
  82                         get_list(optarg);
  83                         cflag = 1;
  84                         break;
  85                 case 'd':
  86                         dchar = *optarg;
  87                         dflag = 1;
  88                         break;
  89                 case 'f':
  90                         get_list(optarg);
  91                         fcn = f_cut;
  92                         fflag = 1;
  93                         break;
  94                 case 's':
  95                         sflag = 1;
  96                         break;
  97                 case 'n':
  98                         break;
  99                 case '?':
 100                 default:
 101                         usage();
 102                 }
 103         argc -= optind;
 104         argv += optind;
 105
 106         if (fflag) {
 107                 if (cflag)
 108                         usage();
 109         } else if (!cflag || dflag || sflag)
 110                 usage();
 111
 112         if (*argv)
 113                 for (; *argv; ++argv) {
 114                         if (!(fp = fopen(*argv, "r")))
 115                                 err(1, "%s", *argv);
 116                         fcn(fp, *argv);
 117                         (void)fclose(fp);
 118                 }
 119         else
 120                 fcn(stdin, "stdin");
 121         exit(0);
 122 }
 123
 124 size_t autostart, autostop, maxval;
 125
 126 char positions[_POSIX2_LINE_MAX + 1];
 127
 128 void
 129 get_list(char *list)
 130 {
 131         size_t setautostart, start, stop;
 132         char *pos;
 133         char *p;
 134
 135         /*
 136          * set a byte in the positions array to indicate if a field or
 137          * column is to be selected; use +1, it's 1-based, not 0-based.
 138          * This parser is less restrictive than the Draft 9 POSIX spec.
 139          * POSIX doesn't allow lists that aren't in increasing order or
 140          * overlapping lists.  We also handle "-3-5" although there's no
 141          * real reason too.
 142          */
 143         for (; (p = strsep(&list, ", \t")) != NULL;) {
 144                 setautostart = start = stop = 0;
 145                 if (*p == '-') {
 146                         ++p;
 147                         setautostart = 1;
 148                 }
 149                 if (isdigit((unsigned char)*p)) {
 150                         start = stop = strtol(p, &p, 10);
 151                         if (setautostart && start > autostart)
 152                                 autostart = start;
 153                 }
 154                 if (*p == '-') {
 155                         if (isdigit((unsigned char)p[1]))
 156                                 stop = strtol(p + 1, &p, 10);
 157                         if (*p == '-') {
 158                                 ++p;
 159                                 if (!autostop || autostop > stop)
 160                                         autostop = stop;
 161                         }
 162                 }
 163                 if (*p)
 164                         errx(1, "[-cf] list: illegal list value");
 165                 if (!stop || !start)
 166                         errx(1, "[-cf] list: values may not include zero");
 167                 if (stop > _POSIX2_LINE_MAX)
 168                         errx(1, "[-cf] list: %ld too large (max %d)",
 169                             (long)stop, _POSIX2_LINE_MAX);
 170                 if (maxval < stop)
 171                         maxval = stop;
 172                 for (pos = positions + start; start++ <= stop; *pos++ = 1);
 173         }
 174
 175         /* overlapping ranges */
 176         if (autostop && maxval > autostop)
 177                 maxval = autostop;
 178
 179         /* set autostart */
 180         if (autostart)
 181                 memset(positions + 1, '1', autostart);
 182 }
 183
 184 /* ARGSUSED */
 185 void
 186 c_cut(FILE *fp, const char *fname)
 187 {
 188         int ch, col;
 189         char *pos;
 190         fname = NULL;
 191
 192         ch = 0;
 193         for (;;) {
 194                 pos = positions + 1;
 195                 for (col = maxval; col; --col) {
 196                         if ((ch = getc(fp)) == EOF)
 197                                 return;
 198                         if (ch == '\n')
 199                                 break;
 200                         if (*pos++)
 201                                 (void)putchar(ch);
 202                 }
 203                 if (ch != '\n') {
 204                         if (autostop)
 205                                 while ((ch = getc(fp)) != EOF && ch != '\n')
 206                                         (void)putchar(ch);
 207                         else
 208                                 while ((ch = getc(fp)) != EOF && ch != '\n');
 209                 }
 210                 (void)putchar('\n');
 211         }
 212 }
 213
 214 void
 215 f_cut(FILE *fp, const char *fname __unused)
 216 {
 217         int ch, field, isdelim;
 218         char *pos, *p, sep;
 219         int output;
 220         char *lbuf, *mlbuf = NULL;
 221         size_t lbuflen;
 222
 223         for (sep = dchar; (lbuf = fgetln(fp, &lbuflen)) != NULL;) {
 224                 /* Assert EOL has a newline. */
 225                 if (*(lbuf + lbuflen - 1) != '\n') {
 226                         /* Can't have > 1 line with no trailing newline. */
 227                         mlbuf = malloc(lbuflen + 1);
 228                         if (mlbuf == NULL)
 229                                 err(1, "malloc");
 230                         memcpy(mlbuf, lbuf, lbuflen);
 231                         *(mlbuf + lbuflen) = '\n';
 232                         lbuf = mlbuf;
 233                 }
 234                 output = 0;
 235                 for (isdelim = 0, p = lbuf;; ++p) {
 236                         ch = *p;
 237                         /* this should work if newline is delimiter */
 238                         if (ch == sep)
 239                                 isdelim = 1;
 240                         if (ch == '\n') {
 241                                 if (!isdelim && !sflag)
 242                                         (void)fwrite(lbuf, lbuflen, 1, stdout);
 243                                 break;
 244                         }
 245                 }
 246                 if (!isdelim)
 247                         continue;
 248
 249                 pos = positions + 1;
 250                 for (field = maxval, p = lbuf; field; --field, ++pos) {
 251                         if (*pos) {
 252                                 if (output++)
 253                                         (void)putchar(sep);
 254                                 while ((ch = *p++) != '\n' && ch != sep)
 255                                         (void)putchar(ch);
 256                         } else {
 257                                 while ((ch = *p++) != '\n' && ch != sep)
 258                                         continue;
 259                         }
 260                         if (ch == '\n')
 261                                 break;
 262                 }
 263                 if (ch != '\n') {
 264                         if (autostop) {
 265                                 if (output)
 266                                         (void)putchar(sep);
 267                                 for (; (ch = *p) != '\n'; ++p)
 268                                         (void)putchar(ch);
 269                         } else
 270                                 for (; (ch = *p) != '\n'; ++p);
 271                 }
 272                 (void)putchar('\n');
 273         }
 274         if (mlbuf != NULL)
 275                 free(mlbuf);
 276 }
 277
 278 static void
 279 usage(void)
 280 {
 281         (void)fprintf(stderr, "%s\n%s\n%s\n",
 282                 "usage: cut -b list [-n] [file ...]",
 283                 "       cut -c list [file ...]",
 284                 "       cut -f list [-s] [-d delim] [file ...]");
 285         exit(1);
 286 }