usr.bin/fold/fold.c

   1 /*      $NetBSD: fold.c,v 1.17 2011/09/04 20:24:59 joerg Exp $  */
   2
   3 /*-
   4  * Copyright (c) 1990, 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  * Kevin Ruddy.
   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 #include <sys/cdefs.h>
  36 #ifndef lint
  37 __COPYRIGHT("@(#) Copyright (c) 1990, 1993\
  38  The Regents of the University of California.  All rights reserved.");
  39 #endif /* not lint */
  40
  41 #ifndef lint
  42 #if 0
  43 static char sccsid[] = "@(#)fold.c      8.1 (Berkeley) 6/6/93";
  44 #endif
  45 __RCSID("$NetBSD: fold.c,v 1.17 2011/09/04 20:24:59 joerg Exp $");
  46 #endif /* not lint */
  47
  48 #include <limits.h>
  49 #include <locale.h>
  50 #include <stdio.h>
  51 #include <stdlib.h>
  52 #include <unistd.h>
  53 #include <wchar.h>
  54 #include <err.h>
  55
  56 #define DEFLINEWIDTH    80
  57
  58 static  void    fold(int);
  59 static  int     new_column_position(int, wint_t);
  60 __dead static   void    usage(void);
  61
  62 static int count_bytes = 0;
  63 static int split_words = 0;
  64
  65 int
  66 main(int argc, char **argv)
  67 {
  68         int ch;
  69         int width;
  70         char *p;
  71
  72         setlocale(LC_CTYPE, "");
  73         setprogname(argv[0]);
  74
  75         width = -1;
  76         while ((ch = getopt(argc, argv, "0123456789bsw:")) != -1)
  77                 switch (ch) {
  78                 case 'b':
  79                         count_bytes = 1;
  80                         break;
  81                 case 's':
  82                         split_words = 1;
  83                         break;
  84                 case 'w':
  85                         if ((width = atoi(optarg)) <= 0)
  86                                 errx(1, "illegal width value");
  87                         break;
  88                 case '0': case '1': case '2': case '3': case '4':
  89                 case '5': case '6': case '7': case '8': case '9':
  90                         if (width == -1) {
  91                                 p = argv[optind - 1];
  92                                 if (p[0] == '-' && p[1] == ch && !p[2])
  93                                         width = atoi(++p);
  94                                 else
  95                                         width = atoi(argv[optind] + 1);
  96                         }
  97                         break;
  98                 default:
  99                         usage();
 100                 }
 101         argv += optind;
 102         argc -= optind;
 103
 104         if (width == -1)
 105                 width = DEFLINEWIDTH;
 106
 107         if (!*argv)
 108                 fold(width);
 109         else for (; *argv; ++argv)
 110                 if (!freopen(*argv, "r", stdin)) {
 111                         err (1, "%s", *argv);
 112                         /* NOTREACHED */
 113                 } else
 114                         fold(width);
 115         exit(0);
 116 }
 117
 118 /*
 119  * Fold the contents of standard input to fit within WIDTH columns
 120  * (or bytes) and write to standard output.
 121  *
 122  * If split_words is set, split the line at the last space character
 123  * on the line.  This flag necessitates storing the line in a buffer
 124  * until the current column > width, or a newline or EOF is read.
 125  *
 126  * The buffer can grow larger than WIDTH due to backspaces and carriage
 127  * returns embedded in the input stream.
 128  */
 129 static void
 130 fold(int width)
 131 {
 132         static wchar_t *buf = NULL;
 133         wchar_t *nbuf;
 134         static int   buf_max = 0;
 135         wint_t ch;
 136         int col, indx, i;
 137
 138         col = indx = 0;
 139         while ((ch = getwchar()) != WEOF) {
 140                 if (ch == L'\n') {
 141                         if (indx != 0) {
 142                                 for (i = 0; i < indx; i++)
 143                                         putwchar(buf[i]);
 144                         }
 145                         putwchar(L'\n');
 146                         col = indx = 0;
 147                         continue;
 148                 }
 149
 150                 col = new_column_position (col, ch);
 151                 if (col > width) {
 152                         int last_space;
 153
 154 #ifdef __GNUC__
 155                         last_space = 0; /* XXX gcc */
 156 #endif
 157                         if (split_words) {
 158                                 for (i = 0, last_space = -1; i < indx; i++)
 159                                         if (buf[i] == L' ')
 160                                                 last_space = i;
 161                         }
 162
 163                         if (split_words && last_space != -1) {
 164                                 for (i = 0; i < last_space; i++)
 165                                         putwchar(buf[i]);
 166
 167                                 /* increase last_space here, so we skip trailing whitespace */
 168                                 last_space++;
 169                                 wmemmove (buf, buf+last_space, indx-last_space);
 170
 171                                 indx -= last_space;
 172                                 col = 0;
 173                                 for (i = 0; i < indx; i++) {
 174                                         col = new_column_position (col, buf[i]);
 175                                 }
 176                         } else {
 177                                 for (i = 0; i < indx; i++)
 178                                         putwchar(buf[i]);
 179                                 col = indx = 0;
 180                         }
 181                         putwchar('\n');
 182
 183                         /* calculate the column position for the next line. */
 184                         col = new_column_position (col, ch);
 185                 }
 186
 187                 if (indx + 1 > buf_max) {
 188                         /* Allocate buffer in LINE_MAX increments */
 189                         if ((nbuf = realloc (buf, buf_max + 2048)) == NULL) {
 190                                 err (1, "realloc");
 191                                 /* NOTREACHED */
 192                         }
 193                         buf = nbuf;
 194                         buf_max += 2048;
 195                 }
 196                 buf[indx++] = ch;
 197         }
 198
 199         if (indx != 0) {
 200                 for (i = 0; i < indx; i++)
 201                         putwchar(buf[i]);
 202         }
 203 }
 204
 205 /*
 206  * calculate the column position
 207  */
 208 static int
 209 new_column_position (int col, wint_t ch)
 210 {
 211         int w;
 212
 213         if (!count_bytes) {
 214                 switch (ch) {
 215                 case L'\b':
 216                         if (col > 0)
 217                                 --col;
 218                         break;
 219                 case L'\r':
 220                         col = 0;
 221                         break;
 222                 case L'\t':
 223                         col = (col + 8) & ~7;
 224                         break;
 225                 default:
 226                         w = wcwidth(ch);
 227                         if (w > 0)
 228                                 col += w;
 229                         break;
 230                 }
 231         } else {
 232                 char dummy[MB_LEN_MAX];
 233
 234                 /* XXX: we assume stateless encoding */
 235                 col += wcrtomb(dummy, ch, NULL);
 236         }
 237
 238         return col;
 239 }
 240
 241 static void
 242 usage(void)
 243 {
 244         (void)fprintf(stderr,
 245             "usage: %s [-bs] [-w width] [file ...]\n", getprogname());
 246         exit(1);
 247 }
 248