usr.bin/fold/fold.c

   1 /*      $NetBSD: fold.c,v 1.15 2008/10/29 01:31:09 ahoka 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 1.15 2008/10/29 01:31:09 ahoka 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         int     main(int, char **);
  59 static  void    fold(int);
  60 static  int     new_column_position(int, wint_t);
  61 static  void    usage(void);
  62
  63 int count_bytes = 0;
  64 int split_words = 0;
  65
  66 int
  67 main(int argc, char **argv)
  68 {
  69         int ch;
  70         int width;
  71         char *p;
  72
  73         setlocale(LC_CTYPE, "");
  74         setprogname(argv[0]);
  75
  76         width = -1;
  77         while ((ch = getopt(argc, argv, "0123456789bsw:")) != -1)
  78                 switch (ch) {
  79                 case 'b':
  80                         count_bytes = 1;
  81                         break;
  82                 case 's':
  83                         split_words = 1;
  84                         break;
  85                 case 'w':
  86                         if ((width = atoi(optarg)) <= 0)
  87                                 errx(1, "illegal width value");
  88                         break;
  89                 case '0': case '1': case '2': case '3': case '4':
  90                 case '5': case '6': case '7': case '8': case '9':
  91                         if (width == -1) {
  92                                 p = argv[optind - 1];
  93                                 if (p[0] == '-' && p[1] == ch && !p[2])
  94                                         width = atoi(++p);
  95                                 else
  96                                         width = atoi(argv[optind] + 1);
  97                         }
  98                         break;
  99                 default:
 100                         usage();
 101                 }
 102         argv += optind;
 103         argc -= optind;
 104
 105         if (width == -1)
 106                 width = DEFLINEWIDTH;
 107
 108         if (!*argv)
 109                 fold(width);
 110         else for (; *argv; ++argv)
 111                 if (!freopen(*argv, "r", stdin)) {
 112                         err (1, "%s", *argv);
 113                         /* NOTREACHED */
 114                 } else
 115                         fold(width);
 116         exit(0);
 117 }
 118
 119 /*
 120  * Fold the contents of standard input to fit within WIDTH columns
 121  * (or bytes) and write to standard output.
 122  *
 123  * If split_words is set, split the line at the last space character
 124  * on the line.  This flag necessitates storing the line in a buffer
 125  * until the current column > width, or a newline or EOF is read.
 126  *
 127  * The buffer can grow larger than WIDTH due to backspaces and carriage
 128  * returns embedded in the input stream.
 129  */
 130 static void
 131 fold(int width)
 132 {
 133         static wchar_t *buf = NULL;
 134         wchar_t *nbuf;
 135         static int   buf_max = 0;
 136         wint_t ch;
 137         int col, indx, i;
 138
 139         col = indx = 0;
 140         while ((ch = getwchar()) != WEOF) {
 141                 if (ch == L'\n') {
 142                         if (indx != 0) {
 143                                 for (i = 0; i < indx; i++)
 144                                         putwchar(buf[i]);
 145                         }
 146                         putwchar(L'\n');
 147                         col = indx = 0;
 148                         continue;
 149                 }
 150
 151                 col = new_column_position (col, ch);
 152                 if (col > width) {
 153                         int last_space;
 154
 155 #ifdef __GNUC__
 156                         last_space = 0; /* XXX gcc */
 157 #endif
 158                         if (split_words) {
 159                                 for (i = 0, last_space = -1; i < indx; i++)
 160                                         if (buf[i] == L' ')
 161                                                 last_space = i;
 162                         }
 163
 164                         if (split_words && last_space != -1) {
 165                                 for (i = 0; i < last_space; i++)
 166                                         putwchar(buf[i]);
 167
 168                                 /* increase last_space here, so we skip trailing whitespace */
 169                                 last_space++;
 170                                 wmemmove (buf, buf+last_space, indx-last_space);
 171
 172                                 indx -= last_space;
 173                                 col = 0;
 174                                 for (i = 0; i < indx; i++) {
 175                                         col = new_column_position (col, buf[i]);
 176                                 }
 177                         } else {
 178                                 for (i = 0; i < indx; i++)
 179                                         putwchar(buf[i]);
 180                                 col = indx = 0;
 181                         }
 182                         putwchar('\n');
 183
 184                         /* calculate the column position for the next line. */
 185                         col = new_column_position (col, ch);
 186                 }
 187
 188                 if (indx + 1 > buf_max) {
 189                         /* Allocate buffer in LINE_MAX increments */
 190                         if ((nbuf = realloc (buf, buf_max + 2048)) == NULL) {
 191                                 err (1, "realloc");
 192                                 /* NOTREACHED */
 193                         }
 194                         buf = nbuf;
 195                         buf_max += 2048;
 196                 }
 197                 buf[indx++] = ch;
 198         }
 199
 200         if (indx != 0) {
 201                 for (i = 0; i < indx; i++)
 202                         putwchar(buf[i]);
 203         }
 204 }
 205
 206 /*
 207  * calculate the column position
 208  */
 209 static int
 210 new_column_position (int col, wint_t ch)
 211 {
 212         int w;
 213
 214         if (!count_bytes) {
 215                 switch (ch) {
 216                 case L'\b':
 217                         if (col > 0)
 218                                 --col;
 219                         break;
 220                 case L'\r':
 221                         col = 0;
 222                         break;
 223                 case L'\t':
 224                         col = (col + 8) & ~7;
 225                         break;
 226                 default:
 227                         w = wcwidth(ch);
 228                         if (w > 0)
 229                                 col += w;
 230                         break;
 231                 }
 232         } else {
 233                 char dummy[MB_LEN_MAX];
 234
 235                 /* XXX: we assume stateless encoding */
 236                 col += wcrtomb(dummy, ch, NULL);
 237         }
 238
 239         return col;
 240 }
 241
 242 static void
 243 usage(void)
 244 {
 245         (void)fprintf(stderr,
 246             "usage: %s [-bs] [-w width] [file ...]\n", getprogname());
 247         exit(1);
 248 }
 249