usr.bin/tr/tr.c

   1 /*
   2  * Copyright (c) 1988, 1993
   3  *      The Regents of the University of California.  All rights reserved.
   4  *
   5  * Redistribution and use in source and binary forms, with or without
   6  * modification, are permitted provided that the following conditions
   7  * are met:
   8  * 1. Redistributions of source code must retain the above copyright
   9  *    notice, this list of conditions and the following disclaimer.
  10  * 2. Redistributions in binary form must reproduce the above copyright
  11  *    notice, this list of conditions and the following disclaimer in the
  12  *    documentation and/or other materials provided with the distribution.
  13  * 3. Neither the name of the University nor the names of its contributors
  14  *    may be used to endorse or promote products derived from this software
  15  *    without specific prior written permission.
  16  *
  17  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  18  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  19  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  20  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  21  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  22  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  23  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  24  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  25  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  26  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  27  * SUCH DAMAGE.
  28  *
  29  * @(#) Copyright (c) 1988, 1993 The Regents of the University of California.  All rights reserved.
  30  * @(#)tr.c     8.2 (Berkeley) 5/4/95
  31  * $FreeBSD: src/usr.bin/tr/tr.c,v 1.8.2.2 2002/07/29 12:59:33 tjr Exp $
  32  */
  33
  34 #include <sys/types.h>
  35
  36 #include <ctype.h>
  37 #include <err.h>
  38 #include <locale.h>
  39 #include <stdio.h>
  40 #include <stdlib.h>
  41 #include <string.h>
  42 #include <unistd.h>
  43
  44 #include "extern.h"
  45
  46 /*
  47  * For -C option: determine whether a byte is a valid character in the
  48  * current character set (as defined by LC_CTYPE).
  49  */
  50 #define ISCHAR(c) (iscntrl(c) || isprint(c))
  51
  52 static int string1[NCHARS] = {
  53         0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,         /* ASCII */
  54         0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
  55         0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
  56         0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
  57         0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
  58         0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
  59         0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
  60         0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
  61         0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
  62         0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
  63         0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
  64         0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
  65         0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
  66         0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
  67         0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
  68         0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
  69         0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
  70         0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
  71         0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
  72         0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
  73         0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
  74         0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
  75         0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
  76         0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
  77         0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
  78         0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
  79         0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,
  80         0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
  81         0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
  82         0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
  83         0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7,
  84         0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
  85 }, string2[NCHARS];
  86
  87 STR s1 = { STRING1, NORMAL, 0, OOBCH, { 0, OOBCH }, NULL, NULL };
  88 STR s2 = { STRING2, NORMAL, 0, OOBCH, { 0, OOBCH }, NULL, NULL };
  89
  90 static void setup(int *, char *, STR *, int, int);
  91 static void usage(void);
  92
  93 int
  94 main(int argc, char **argv)
  95 {
  96         int ch, cnt, lastch, *p;
  97         int Cflag, cflag, dflag, sflag, isstring2;
  98
  99         (void)setlocale(LC_ALL, "");
 100
 101         Cflag = cflag = dflag = sflag = 0;
 102         while ((ch = getopt(argc, argv, "Ccdsu")) != -1)
 103                 switch((char)ch) {
 104                 case 'C':
 105                         Cflag = 1;
 106                         cflag = 0;
 107                         break;
 108                 case 'c':
 109                         cflag = 1;
 110                         Cflag = 0;
 111                         break;
 112                 case 'd':
 113                         dflag = 1;
 114                         break;
 115                 case 's':
 116                         sflag = 1;
 117                         break;
 118                 case 'u':
 119                         setbuf(stdout, NULL);
 120                         break;
 121                 case '?':
 122                 default:
 123                         usage();
 124                 }
 125         argc -= optind;
 126         argv += optind;
 127
 128         switch(argc) {
 129         case 0:
 130         default:
 131                 usage();
 132                 /* NOTREACHED */
 133         case 1:
 134                 isstring2 = 0;
 135                 break;
 136         case 2:
 137                 isstring2 = 1;
 138                 break;
 139         }
 140
 141         /*
 142          * tr -ds [-Cc] string1 string2
 143          * Delete all characters (or complemented characters) in string1.
 144          * Squeeze all characters in string2.
 145          */
 146         if (dflag && sflag) {
 147                 if (!isstring2)
 148                         usage();
 149
 150                 setup(string1, argv[0], &s1, cflag, Cflag);
 151                 setup(string2, argv[1], &s2, 0, 0);
 152
 153                 for (lastch = OOBCH; (ch = getchar()) != EOF;)
 154                         if (!string1[ch] && (!string2[ch] || lastch != ch)) {
 155                                 lastch = ch;
 156                                 (void)putchar(ch);
 157                         }
 158                 exit(0);
 159         }
 160
 161         /*
 162          * tr -d [-Cc] string1
 163          * Delete all characters (or complemented characters) in string1.
 164          */
 165         if (dflag) {
 166                 if (isstring2)
 167                         usage();
 168
 169                 setup(string1, argv[0], &s1, cflag, Cflag);
 170
 171                 while ((ch = getchar()) != EOF)
 172                         if (!string1[ch])
 173                                 (void)putchar(ch);
 174                 exit(0);
 175         }
 176
 177         /*
 178          * tr -s [-Cc] string1
 179          * Squeeze all characters (or complemented characters) in string1.
 180          */
 181         if (sflag && !isstring2) {
 182                 setup(string1, argv[0], &s1, cflag, Cflag);
 183
 184                 for (lastch = OOBCH; (ch = getchar()) != EOF;)
 185                         if (!string1[ch] || lastch != ch) {
 186                                 lastch = ch;
 187                                 (void)putchar(ch);
 188                         }
 189                 exit(0);
 190         }
 191
 192         /*
 193          * tr [-Ccs] string1 string2
 194          * Replace all characters (or complemented characters) in string1 with
 195          * the character in the same position in string2.  If the -s option is
 196          * specified, squeeze all the characters in string2.
 197          */
 198         if (!isstring2)
 199                 usage();
 200
 201         s1.str = argv[0];
 202         s2.str = argv[1];
 203
 204         if (cflag || Cflag)
 205                 for (cnt = NCHARS, p = string1; cnt--;)
 206                         *p++ = OOBCH;
 207
 208         if (!next(&s2))
 209                 errx(1, "empty string2");
 210
 211         ch = s2.lastch;
 212         /* If string2 runs out of characters, use the last one specified. */
 213         if (sflag)
 214                 while (next(&s1)) {
 215                         string1[s1.lastch] = ch = s2.lastch;
 216                         string2[ch] = 1;
 217                         (void)next(&s2);
 218                 }
 219         else
 220                 while (next(&s1)) {
 221                         string1[s1.lastch] = ch = s2.lastch;
 222                         (void)next(&s2);
 223                 }
 224
 225         if (cflag)
 226                 for (cnt = 0, p = string1; cnt < NCHARS; ++p, ++cnt)
 227                         *p = *p == OOBCH ? ch : cnt;
 228         else if (Cflag)
 229                 for (cnt = 0, p = string1; cnt < NCHARS; ++p, ++cnt)
 230                         *p = *p == OOBCH && ISCHAR(cnt) ? ch : cnt;
 231
 232         if (sflag)
 233                 for (lastch = OOBCH; (ch = getchar()) != EOF;) {
 234                         ch = string1[ch];
 235                         if (!string2[ch] || lastch != ch) {
 236                                 lastch = ch;
 237                                 (void)putchar(ch);
 238                         }
 239                 }
 240         else
 241                 while ((ch = getchar()) != EOF)
 242                         (void)putchar(string1[ch]);
 243         exit (0);
 244 }
 245
 246 static void
 247 setup(int *string, char *arg, STR *str, int cflag, int Cflag)
 248 {
 249         int cnt, *p;
 250
 251         str->str = arg;
 252         bzero(string, NCHARS * sizeof(int));
 253         while (next(str))
 254                 string[str->lastch] = 1;
 255         if (cflag)
 256                 for (p = string, cnt = NCHARS; cnt--; ++p)
 257                         *p = !*p;
 258         else if (Cflag)
 259                 for (cnt = 0; cnt < NCHARS; cnt++)
 260                         string[cnt] = !string[cnt] && ISCHAR(cnt);
 261 }
 262
 263 static void
 264 usage(void)
 265 {
 266         (void)fprintf(stderr, "%s\n%s\n%s\n%s\n",
 267                 "usage: tr [-Ccsu] string1 string2",
 268                 "       tr [-Ccu] -d string1",
 269                 "       tr [-Ccu] -s string1",
 270                 "       tr [-Ccu] -ds string1 string2");
 271         exit(1);
 272 }