lib/roken/unvis.c

   1 /*      $NetBSD: unvis.c,v 1.19 2000/01/22 22:19:13 mycroft Exp $       */
   2
   3 /*-
   4  * Copyright (c) 1989, 1993
   5  *      The Regents of the University of California.  All rights reserved.
   6  *
   7  * Redistribution and use in source and binary forms, with or without
   8  * modification, are permitted provided that the following conditions
   9  * are met:
  10  * 1. Redistributions of source code must retain the above copyright
  11  *    notice, this list of conditions and the following disclaimer.
  12  * 2. Redistributions in binary form must reproduce the above copyright
  13  *    notice, this list of conditions and the following disclaimer in the
  14  *    documentation and/or other materials provided with the distribution.
  15  * 3. Neither the name of the University nor the names of its contributors
  16  *    may be used to endorse or promote products derived from this software
  17  *    without specific prior written permission.
  18  *
  19  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  20  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  21  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  22  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  23  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  24  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  25  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  26  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  27  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  28  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  29  * SUCH DAMAGE.
  30  */
  31
  32 #if 1
  33 #include <config.h>
  34 #include "roken.h"
  35 #ifndef _DIAGASSERT
  36 #define _DIAGASSERT(X)
  37 #endif
  38 #else
  39 #include <sys/cdefs.h>
  40 #if defined(LIBC_SCCS) && !defined(lint)
  41 #if 0
  42 static char sccsid[] = "@(#)unvis.c     8.1 (Berkeley) 6/4/93";
  43 #else
  44 __RCSID("$NetBSD: unvis.c,v 1.19 2000/01/22 22:19:13 mycroft Exp $");
  45 #endif
  46 #endif /* LIBC_SCCS and not lint */
  47
  48 #define __LIBC12_SOURCE__
  49
  50 #include "namespace.h"
  51 #endif
  52 #include <sys/types.h>
  53
  54 #include <assert.h>
  55 #include <ctype.h>
  56 #include <stdio.h>
  57 #include <vis.h>
  58
  59 #if 0
  60 #ifdef __weak_alias
  61 __weak_alias(strunvis,_strunvis)
  62 __weak_alias(unvis,_unvis)
  63 #endif
  64
  65 __warn_references(unvis,
  66     "warning: reference to compatibility unvis(); include <vis.h> for correct reference")
  67 #endif
  68
  69 /*
  70  * decode driven by state machine
  71  */
  72 #define S_GROUND        0       /* haven't seen escape char */
  73 #define S_START         1       /* start decoding special sequence */
  74 #define S_META          2       /* metachar started (M) */
  75 #define S_META1         3       /* metachar more, regular char (-) */
  76 #define S_CTRL          4       /* control char started (^) */
  77 #define S_OCTAL2        5       /* octal digit 2 */
  78 #define S_OCTAL3        6       /* octal digit 3 */
  79
  80 #define isoctal(c)      (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
  81
  82 int ROKEN_LIB_FUNCTION
  83         rk_strunvis (char *, const char *);
  84 int ROKEN_LIB_FUNCTION
  85         rk_unvis (char *, int, int *, int);
  86
  87 /*
  88  * unvis - decode characters previously encoded by vis
  89  */
  90
  91 int ROKEN_LIB_FUNCTION
  92 rk_unvis(char *cp, int c, int *astate, int flag)
  93 {
  94
  95         _DIAGASSERT(cp != NULL);
  96         _DIAGASSERT(astate != NULL);
  97
  98         if (flag & UNVIS_END) {
  99                 if (*astate == S_OCTAL2 || *astate == S_OCTAL3) {
 100                         *astate = S_GROUND;
 101                         return (UNVIS_VALID);
 102                 }
 103                 return (*astate == S_GROUND ? UNVIS_NOCHAR : UNVIS_SYNBAD);
 104         }
 105
 106         switch (*astate) {
 107
 108         case S_GROUND:
 109                 *cp = 0;
 110                 if (c == '\\') {
 111                         *astate = S_START;
 112                         return (0);
 113                 }
 114                 *cp = c;
 115                 return (UNVIS_VALID);
 116
 117         case S_START:
 118                 switch(c) {
 119                 case '\\':
 120                         *cp = c;
 121                         *astate = S_GROUND;
 122                         return (UNVIS_VALID);
 123                 case '0': case '1': case '2': case '3':
 124                 case '4': case '5': case '6': case '7':
 125                         *cp = (c - '0');
 126                         *astate = S_OCTAL2;
 127                         return (0);
 128                 case 'M':
 129                         *cp = (char)0200;
 130                         *astate = S_META;
 131                         return (0);
 132                 case '^':
 133                         *astate = S_CTRL;
 134                         return (0);
 135                 case 'n':
 136                         *cp = '\n';
 137                         *astate = S_GROUND;
 138                         return (UNVIS_VALID);
 139                 case 'r':
 140                         *cp = '\r';
 141                         *astate = S_GROUND;
 142                         return (UNVIS_VALID);
 143                 case 'b':
 144                         *cp = '\b';
 145                         *astate = S_GROUND;
 146                         return (UNVIS_VALID);
 147                 case 'a':
 148                         *cp = '\007';
 149                         *astate = S_GROUND;
 150                         return (UNVIS_VALID);
 151                 case 'v':
 152                         *cp = '\v';
 153                         *astate = S_GROUND;
 154                         return (UNVIS_VALID);
 155                 case 't':
 156                         *cp = '\t';
 157                         *astate = S_GROUND;
 158                         return (UNVIS_VALID);
 159                 case 'f':
 160                         *cp = '\f';
 161                         *astate = S_GROUND;
 162                         return (UNVIS_VALID);
 163                 case 's':
 164                         *cp = ' ';
 165                         *astate = S_GROUND;
 166                         return (UNVIS_VALID);
 167                 case 'E':
 168                         *cp = '\033';
 169                         *astate = S_GROUND;
 170                         return (UNVIS_VALID);
 171                 case '\n':
 172                         /*
 173                          * hidden newline
 174                          */
 175                         *astate = S_GROUND;
 176                         return (UNVIS_NOCHAR);
 177                 case '$':
 178                         /*
 179                          * hidden marker
 180                          */
 181                         *astate = S_GROUND;
 182                         return (UNVIS_NOCHAR);
 183                 }
 184                 *astate = S_GROUND;
 185                 return (UNVIS_SYNBAD);
 186
 187         case S_META:
 188                 if (c == '-')
 189                         *astate = S_META1;
 190                 else if (c == '^')
 191                         *astate = S_CTRL;
 192                 else {
 193                         *astate = S_GROUND;
 194                         return (UNVIS_SYNBAD);
 195                 }
 196                 return (0);
 197
 198         case S_META1:
 199                 *astate = S_GROUND;
 200                 *cp |= c;
 201                 return (UNVIS_VALID);
 202
 203         case S_CTRL:
 204                 if (c == '?')
 205                         *cp |= 0177;
 206                 else
 207                         *cp |= c & 037;
 208                 *astate = S_GROUND;
 209                 return (UNVIS_VALID);
 210
 211         case S_OCTAL2:  /* second possible octal digit */
 212                 if (isoctal(c)) {
 213                         /*
 214                          * yes - and maybe a third
 215                          */
 216                         *cp = (*cp << 3) + (c - '0');
 217                         *astate = S_OCTAL3;
 218                         return (0);
 219                 }
 220                 /*
 221                  * no - done with current sequence, push back passed char
 222                  */
 223                 *astate = S_GROUND;
 224                 return (UNVIS_VALIDPUSH);
 225
 226         case S_OCTAL3:  /* third possible octal digit */
 227                 *astate = S_GROUND;
 228                 if (isoctal(c)) {
 229                         *cp = (*cp << 3) + (c - '0');
 230                         return (UNVIS_VALID);
 231                 }
 232                 /*
 233                  * we were done, push back passed char
 234                  */
 235                 return (UNVIS_VALIDPUSH);
 236
 237         default:
 238                 /*
 239                  * decoder in unknown state - (probably uninitialized)
 240                  */
 241                 *astate = S_GROUND;
 242                 return (UNVIS_SYNBAD);
 243         }
 244 }
 245
 246 /*
 247  * strunvis - decode src into dst
 248  *
 249  *      Number of chars decoded into dst is returned, -1 on error.
 250  *      Dst is null terminated.
 251  */
 252
 253 int ROKEN_LIB_FUNCTION
 254 rk_strunvis(char *dst, const char *src)
 255 {
 256         char c;
 257         char *start = dst;
 258         int state = 0;
 259
 260         _DIAGASSERT(src != NULL);
 261         _DIAGASSERT(dst != NULL);
 262
 263         while ((c = *src++) != '\0') {
 264         again:
 265                 switch (rk_unvis(dst, (unsigned char)c, &state, 0)) {
 266                 case UNVIS_VALID:
 267                         dst++;
 268                         break;
 269                 case UNVIS_VALIDPUSH:
 270                         dst++;
 271                         goto again;
 272                 case 0:
 273                 case UNVIS_NOCHAR:
 274                         break;
 275                 default:
 276                         return (-1);
 277                 }
 278         }
 279         if (unvis(dst, (unsigned char)c, &state, UNVIS_END) == UNVIS_VALID)
 280                 dst++;
 281         *dst = '\0';
 282         return (dst - start);
 283 }