usr.bin/fold/fold.c

   1 /*-
   2  * Copyright (c) 1990, 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  * Kevin Ruddy.
   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  * 4. 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
  33 #ifndef lint
  34 static const char copyright[] =
  35 "@(#) Copyright (c) 1990, 1993\n\
  36         The Regents of the University of California.  All rights reserved.\n";
  37 #endif /* not lint */
  38
  39 #ifndef lint
  40 #if 0
  41 static char sccsid[] = "@(#)fold.c      8.1 (Berkeley) 6/6/93";
  42 #endif
  43 #endif /* not lint */
  44
  45 #include <sys/cdefs.h>
  46 __FBSDID("$FreeBSD$");
  47
  48 #include <err.h>
  49 #include <limits.h>
  50 #include <locale.h>
  51 #include <stdio.h>
  52 #include <stdlib.h>
  53 #include <string.h>
  54 #include <unistd.h>
  55 #include <wchar.h>
  56 #include <wctype.h>
  57
  58 #define DEFLINEWIDTH    80
  59
  60 void fold(int);
  61 static int newpos(int, wint_t);
  62 static void usage(void);
  63
  64 static int bflag;               /* Count bytes, not columns */
  65 static int sflag;               /* Split on word boundaries */
  66
  67 int
  68 main(int argc, char **argv)
  69 {
  70         int ch, previous_ch;
  71         int rval, width;
  72
  73         (void) setlocale(LC_CTYPE, "");
  74
  75         width = -1;
  76         previous_ch = 0;
  77         while ((ch = getopt(argc, argv, "0123456789bsw:")) != -1) {
  78                 switch (ch) {
  79                 case 'b':
  80                         bflag = 1;
  81                         break;
  82                 case 's':
  83                         sflag = 1;
  84                         break;
  85                 case 'w':
  86                         if ((width = atoi(optarg)) <= 0) {
  87                                 errx(1, "illegal width value");
  88                         }
  89                         break;
  90                 case '0': case '1': case '2': case '3': case '4':
  91                 case '5': case '6': case '7': case '8': case '9':
  92                         /* Accept a width as eg. -30. Note that a width
  93                          * specified using the -w option is always used prior
  94                          * to this undocumented option. */
  95                         switch (previous_ch) {
  96                         case '0': case '1': case '2': case '3': case '4':
  97                         case '5': case '6': case '7': case '8': case '9':
  98                                 /* The width is a number with multiple digits:
  99                                  * add the last one. */
 100                                 width = width * 10 + (ch - '0');
 101                                 break;
 102                         default:
 103                                 /* Set the width, unless it was previously
 104                                  * set. For instance, the following options
 105                                  * would all give a width of 5 and not 10:
 106                                  *   -10 -w5
 107                                  *   -5b10
 108                                  *   -5 -10b */
 109                                 if (width == -1)
 110                                         width = ch - '0';
 111                                 break;
 112                         }
 113                         break;
 114                 default:
 115                         usage();
 116                 }
 117                 previous_ch = ch;
 118         }
 119         argv += optind;
 120         argc -= optind;
 121
 122         if (width == -1)
 123                 width = DEFLINEWIDTH;
 124         rval = 0;
 125         if (!*argv)
 126                 fold(width);
 127         else for (; *argv; ++argv)
 128                 if (!freopen(*argv, "r", stdin)) {
 129                         warn("%s", *argv);
 130                         rval = 1;
 131                 } else
 132                         fold(width);
 133         exit(rval);
 134 }
 135
 136 static void
 137 usage(void)
 138 {
 139         (void)fprintf(stderr, "usage: fold [-bs] [-w width] [file ...]\n");
 140         exit(1);
 141 }
 142
 143 /*
 144  * Fold the contents of standard input to fit within WIDTH columns (or bytes)
 145  * and write to standard output.
 146  *
 147  * If sflag is set, split the line at the last space character on the line.
 148  * This flag necessitates storing the line in a buffer until the current
 149  * column > width, or a newline or EOF is read.
 150  *
 151  * The buffer can grow larger than WIDTH due to backspaces and carriage
 152  * returns embedded in the input stream.
 153  */
 154 void
 155 fold(int width)
 156 {
 157         static wchar_t *buf;
 158         static int buf_max;
 159         int col, i, indx, space;
 160         wint_t ch;
 161
 162         col = indx = 0;
 163         while ((ch = getwchar()) != WEOF) {
 164                 if (ch == '\n') {
 165                         wprintf(L"%.*ls\n", indx, buf);
 166                         col = indx = 0;
 167                         continue;
 168                 }
 169                 if ((col = newpos(col, ch)) > width) {
 170                         if (sflag) {
 171                                 i = indx;
 172                                 while (--i >= 0 && !iswblank(buf[i]))
 173                                         ;
 174                                 space = i;
 175                         }
 176                         if (sflag && space != -1) {
 177                                 space++;
 178                                 wprintf(L"%.*ls\n", space, buf);
 179                                 wmemmove(buf, buf + space, indx - space);
 180                                 indx -= space;
 181                                 col = 0;
 182                                 for (i = 0; i < indx; i++)
 183                                         col = newpos(col, buf[i]);
 184                         } else {
 185                                 wprintf(L"%.*ls\n", indx, buf);
 186                                 col = indx = 0;
 187                         }
 188                         col = newpos(col, ch);
 189                 }
 190                 if (indx + 1 > buf_max) {
 191                         buf_max += LINE_MAX;
 192                         buf = realloc(buf, sizeof(*buf) * buf_max);
 193                         if (buf == NULL)
 194                                 err(1, "realloc()");
 195                 }
 196                 buf[indx++] = ch;
 197         }
 198
 199         if (indx != 0)
 200                 wprintf(L"%.*ls", indx, buf);
 201 }
 202
 203 /*
 204  * Update the current column position for a character.
 205  */
 206 static int
 207 newpos(int col, wint_t ch)
 208 {
 209         char buf[MB_LEN_MAX];
 210         size_t len;
 211         int w;
 212
 213         if (bflag) {
 214                 len = wcrtomb(buf, ch, NULL);
 215                 col += len;
 216         } else
 217                 switch (ch) {
 218                 case '\b':
 219                         if (col > 0)
 220                                 --col;
 221                         break;
 222                 case '\r':
 223                         col = 0;
 224                         break;
 225                 case '\t':
 226                         col = (col + 8) & ~7;
 227                         break;
 228                 default:
 229                         if ((w = wcwidth(ch)) > 0)
 230                                 col += w;
 231                         break;
 232                 }
 233
 234         return (col);
 235 }