compat/unvis.c

   1 /*      $OpenBSD: unvis.c,v 1.12 2005/08/08 08:05:34 espie Exp $ */
   2 /*-
   3  * Copyright (c) 1989, 1993
   4  *      The Regents of the University of California.  All rights reserved.
   5  *
   6  * Redistribution and use in source and binary forms, with or without
   7  * modification, are permitted provided that the following conditions
   8  * are met:
   9  * 1. Redistributions of source code must retain the above copyright
  10  *    notice, this list of conditions and the following disclaimer.
  11  * 2. Redistributions in binary form must reproduce the above copyright
  12  *    notice, this list of conditions and the following disclaimer in the
  13  *    documentation and/or other materials provided with the distribution.
  14  * 3. Neither the name of the University nor the names of its contributors
  15  *    may be used to endorse or promote products derived from this software
  16  *    without specific prior written permission.
  17  *
  18  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  19  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  20  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  21  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  22  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  23  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  24  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  25  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  26  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  27  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  28  * SUCH DAMAGE.
  29  */
  30
  31 #include <sys/types.h>
  32 #include <ctype.h>
  33
  34 #include "compat.h"
  35
  36 /*
  37  * decode driven by state machine
  38  */
  39 #define S_GROUND        0       /* haven't seen escape char */
  40 #define S_START         1       /* start decoding special sequence */
  41 #define S_META          2       /* metachar started (M) */
  42 #define S_META1         3       /* metachar more, regular char (-) */
  43 #define S_CTRL          4       /* control char started (^) */
  44 #define S_OCTAL2        5       /* octal digit 2 */
  45 #define S_OCTAL3        6       /* octal digit 3 */
  46
  47 #define isoctal(c)      (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
  48
  49 /*
  50  * unvis - decode characters previously encoded by vis
  51  */
  52 int
  53 unvis(char *cp, char c, int *astate, int flag)
  54 {
  55
  56         if (flag & UNVIS_END) {
  57                 if (*astate == S_OCTAL2 || *astate == S_OCTAL3) {
  58                         *astate = S_GROUND;
  59                         return (UNVIS_VALID);
  60                 }
  61                 return (*astate == S_GROUND ? UNVIS_NOCHAR : UNVIS_SYNBAD);
  62         }
  63
  64         switch (*astate) {
  65
  66         case S_GROUND:
  67                 *cp = 0;
  68                 if (c == '\\') {
  69                         *astate = S_START;
  70                         return (0);
  71                 }
  72                 *cp = c;
  73                 return (UNVIS_VALID);
  74
  75         case S_START:
  76                 switch(c) {
  77                 case '\\':
  78                         *cp = c;
  79                         *astate = S_GROUND;
  80                         return (UNVIS_VALID);
  81                 case '0': case '1': case '2': case '3':
  82                 case '4': case '5': case '6': case '7':
  83                         *cp = (c - '0');
  84                         *astate = S_OCTAL2;
  85                         return (0);
  86                 case 'M':
  87                         *cp = (char) 0200;
  88                         *astate = S_META;
  89                         return (0);
  90                 case '^':
  91                         *astate = S_CTRL;
  92                         return (0);
  93                 case 'n':
  94                         *cp = '\n';
  95                         *astate = S_GROUND;
  96                         return (UNVIS_VALID);
  97                 case 'r':
  98                         *cp = '\r';
  99                         *astate = S_GROUND;
 100                         return (UNVIS_VALID);
 101                 case 'b':
 102                         *cp = '\b';
 103                         *astate = S_GROUND;
 104                         return (UNVIS_VALID);
 105                 case 'a':
 106                         *cp = '\007';
 107                         *astate = S_GROUND;
 108                         return (UNVIS_VALID);
 109                 case 'v':
 110                         *cp = '\v';
 111                         *astate = S_GROUND;
 112                         return (UNVIS_VALID);
 113                 case 't':
 114                         *cp = '\t';
 115                         *astate = S_GROUND;
 116                         return (UNVIS_VALID);
 117                 case 'f':
 118                         *cp = '\f';
 119                         *astate = S_GROUND;
 120                         return (UNVIS_VALID);
 121                 case 's':
 122                         *cp = ' ';
 123                         *astate = S_GROUND;
 124                         return (UNVIS_VALID);
 125                 case 'E':
 126                         *cp = '\033';
 127                         *astate = S_GROUND;
 128                         return (UNVIS_VALID);
 129                 case '\n':
 130                         /*
 131                          * hidden newline
 132                          */
 133                         *astate = S_GROUND;
 134                         return (UNVIS_NOCHAR);
 135                 case '$':
 136                         /*
 137                          * hidden marker
 138                          */
 139                         *astate = S_GROUND;
 140                         return (UNVIS_NOCHAR);
 141                 }
 142                 *astate = S_GROUND;
 143                 return (UNVIS_SYNBAD);
 144
 145         case S_META:
 146                 if (c == '-')
 147                         *astate = S_META1;
 148                 else if (c == '^')
 149                         *astate = S_CTRL;
 150                 else {
 151                         *astate = S_GROUND;
 152                         return (UNVIS_SYNBAD);
 153                 }
 154                 return (0);
 155
 156         case S_META1:
 157                 *astate = S_GROUND;
 158                 *cp |= c;
 159                 return (UNVIS_VALID);
 160
 161         case S_CTRL:
 162                 if (c == '?')
 163                         *cp |= 0177;
 164                 else
 165                         *cp |= c & 037;
 166                 *astate = S_GROUND;
 167                 return (UNVIS_VALID);
 168
 169         case S_OCTAL2:  /* second possible octal digit */
 170                 if (isoctal(c)) {
 171                         /*
 172                          * yes - and maybe a third
 173                          */
 174                         *cp = (*cp << 3) + (c - '0');
 175                         *astate = S_OCTAL3;
 176                         return (0);
 177                 }
 178                 /*
 179                  * no - done with current sequence, push back passed char
 180                  */
 181                 *astate = S_GROUND;
 182                 return (UNVIS_VALIDPUSH);
 183
 184         case S_OCTAL3:  /* third possible octal digit */
 185                 *astate = S_GROUND;
 186                 if (isoctal(c)) {
 187                         *cp = (*cp << 3) + (c - '0');
 188                         return (UNVIS_VALID);
 189                 }
 190                 /*
 191                  * we were done, push back passed char
 192                  */
 193                 return (UNVIS_VALIDPUSH);
 194
 195         default:
 196                 /*
 197                  * decoder in unknown state - (probably uninitialized)
 198                  */
 199                 *astate = S_GROUND;
 200                 return (UNVIS_SYNBAD);
 201         }
 202 }
 203
 204 /*
 205  * strunvis - decode src into dst
 206  *
 207  *      Number of chars decoded into dst is returned, -1 on error.
 208  *      Dst is null terminated.
 209  */
 210
 211 int
 212 strunvis(char *dst, const char *src)
 213 {
 214         char c;
 215         char *start = dst;
 216         int state = 0;
 217
 218         while ((c = *src++)) {
 219         again:
 220                 switch (unvis(dst, c, &state, 0)) {
 221                 case UNVIS_VALID:
 222                         dst++;
 223                         break;
 224                 case UNVIS_VALIDPUSH:
 225                         dst++;
 226                         goto again;
 227                 case 0:
 228                 case UNVIS_NOCHAR:
 229                         break;
 230                 default:
 231                         *dst = '\0';
 232                         return (-1);
 233                 }
 234         }
 235         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 236                 dst++;
 237         *dst = '\0';
 238         return (dst - start);
 239 }
 240
 241 ssize_t
 242 strnunvis(char *dst, const char *src, size_t sz)
 243 {
 244         char c, p;
 245         char *start = dst, *end = dst + sz - 1;
 246         int state = 0;
 247
 248         if (sz > 0)
 249                 *end = '\0';
 250         while ((c = *src++)) {
 251         again:
 252                 switch (unvis(&p, c, &state, 0)) {
 253                 case UNVIS_VALID:
 254                         if (dst < end)
 255                                 *dst = p;
 256                         dst++;
 257                         break;
 258                 case UNVIS_VALIDPUSH:
 259                         if (dst < end)
 260                                 *dst = p;
 261                         dst++;
 262                         goto again;
 263                 case 0:
 264                 case UNVIS_NOCHAR:
 265                         break;
 266                 default:
 267                         if (dst <= end)
 268                                 *dst = '\0';
 269                         return (-1);
 270                 }
 271         }
 272         if (unvis(&p, c, &state, UNVIS_END) == UNVIS_VALID) {
 273                 if (dst < end)
 274                         *dst = p;
 275                 dst++;
 276         }
 277         if (dst <= end)
 278                 *dst = '\0';
 279         return (dst - start);
 280 }
 281