lib/libc/gen/unvis.c

   1 /*-
   2  * Copyright (c) 1989, 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  * $FreeBSD: src/lib/libc/gen/unvis.c,v 1.4.8.1 2000/08/17 08:25:54 jhb Exp $
  30  * $DragonFly: src/lib/libc/gen/unvis.c,v 1.5 2005/11/19 22:32:53 swildner Exp $
  31  *
  32  * @(#)unvis.c  8.1 (Berkeley) 6/4/93
  33  */
  34
  35 #include <sys/types.h>
  36 #include <ctype.h>
  37 #include <vis.h>
  38
  39 /*
  40  * decode driven by state machine
  41  */
  42 #define S_GROUND        0       /* haven't seen escape char */
  43 #define S_START         1       /* start decoding special sequence */
  44 #define S_META          2       /* metachar started (M) */
  45 #define S_META1         3       /* metachar more, regular char (-) */
  46 #define S_CTRL          4       /* control char started (^) */
  47 #define S_OCTAL2        5       /* octal digit 2 */
  48 #define S_OCTAL3        6       /* octal digit 3 */
  49 #define S_HEX2          7       /* hex digit 2 */
  50
  51 #define S_HTTP          0x080   /* %HEXHEX escape */
  52
  53 #define isoctal(c)      (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
  54 #define ishex(c)        ((((u_char)(c)) >= '0' && ((u_char)(c)) <= '9') || (((u_char)(c)) >= 'a' && ((u_char)(c)) <= 'f'))
  55
  56 /*
  57  * unvis - decode characters previously encoded by vis
  58  */
  59 int
  60 unvis(char *cp, int c, int *astate, int flag)
  61 {
  62
  63         if (flag & UNVIS_END) {
  64                 if (*astate == S_OCTAL2 || *astate == S_OCTAL3) {
  65                         *astate = S_GROUND;
  66                         return (UNVIS_VALID);
  67                 }
  68                 return (*astate == S_GROUND ? UNVIS_NOCHAR : UNVIS_SYNBAD);
  69         }
  70
  71         switch (*astate & ~S_HTTP) {
  72
  73         case S_GROUND:
  74                 *cp = 0;
  75                 if (c == '\\') {
  76                         *astate = S_START;
  77                         return (0);
  78                 }
  79                 if (flag & VIS_HTTPSTYLE && c == '%') {
  80                         *astate = S_START | S_HTTP;
  81                         return (0);
  82                 }
  83                 *cp = c;
  84                 return (UNVIS_VALID);
  85
  86         case S_START:
  87                 if (*astate & S_HTTP) {
  88                     if (ishex(tolower(c))) {
  89                         *cp = isdigit(c) ? (c - '0') : (tolower(c) - 'a');
  90                         *astate = S_HEX2;
  91                         return (0);
  92                     }
  93                 }
  94                 switch(c) {
  95                 case '\\':
  96                         *cp = c;
  97                         *astate = S_GROUND;
  98                         return (UNVIS_VALID);
  99                 case '0': case '1': case '2': case '3':
 100                 case '4': case '5': case '6': case '7':
 101                         *cp = (c - '0');
 102                         *astate = S_OCTAL2;
 103                         return (0);
 104                 case 'M':
 105                         *cp = (char)0200;
 106                         *astate = S_META;
 107                         return (0);
 108                 case '^':
 109                         *astate = S_CTRL;
 110                         return (0);
 111                 case 'n':
 112                         *cp = '\n';
 113                         *astate = S_GROUND;
 114                         return (UNVIS_VALID);
 115                 case 'r':
 116                         *cp = '\r';
 117                         *astate = S_GROUND;
 118                         return (UNVIS_VALID);
 119                 case 'b':
 120                         *cp = '\b';
 121                         *astate = S_GROUND;
 122                         return (UNVIS_VALID);
 123                 case 'a':
 124                         *cp = '\007';
 125                         *astate = S_GROUND;
 126                         return (UNVIS_VALID);
 127                 case 'v':
 128                         *cp = '\v';
 129                         *astate = S_GROUND;
 130                         return (UNVIS_VALID);
 131                 case 't':
 132                         *cp = '\t';
 133                         *astate = S_GROUND;
 134                         return (UNVIS_VALID);
 135                 case 'f':
 136                         *cp = '\f';
 137                         *astate = S_GROUND;
 138                         return (UNVIS_VALID);
 139                 case 's':
 140                         *cp = ' ';
 141                         *astate = S_GROUND;
 142                         return (UNVIS_VALID);
 143                 case 'E':
 144                         *cp = '\033';
 145                         *astate = S_GROUND;
 146                         return (UNVIS_VALID);
 147                 case '\n':
 148                         /*
 149                          * hidden newline
 150                          */
 151                         *astate = S_GROUND;
 152                         return (UNVIS_NOCHAR);
 153                 case '$':
 154                         /*
 155                          * hidden marker
 156                          */
 157                         *astate = S_GROUND;
 158                         return (UNVIS_NOCHAR);
 159                 }
 160                 *astate = S_GROUND;
 161                 return (UNVIS_SYNBAD);
 162
 163         case S_META:
 164                 if (c == '-')
 165                         *astate = S_META1;
 166                 else if (c == '^')
 167                         *astate = S_CTRL;
 168                 else {
 169                         *astate = S_GROUND;
 170                         return (UNVIS_SYNBAD);
 171                 }
 172                 return (0);
 173
 174         case S_META1:
 175                 *astate = S_GROUND;
 176                 *cp |= c;
 177                 return (UNVIS_VALID);
 178
 179         case S_CTRL:
 180                 if (c == '?')
 181                         *cp |= 0177;
 182                 else
 183                         *cp |= c & 037;
 184                 *astate = S_GROUND;
 185                 return (UNVIS_VALID);
 186
 187         case S_OCTAL2:  /* second possible octal digit */
 188                 if (isoctal(c)) {
 189                         /*
 190                          * yes - and maybe a third
 191                          */
 192                         *cp = (*cp << 3) + (c - '0');
 193                         *astate = S_OCTAL3;
 194                         return (0);
 195                 }
 196                 /*
 197                  * no - done with current sequence, push back passed char
 198                  */
 199                 *astate = S_GROUND;
 200                 return (UNVIS_VALIDPUSH);
 201
 202         case S_OCTAL3:  /* third possible octal digit */
 203                 *astate = S_GROUND;
 204                 if (isoctal(c)) {
 205                         *cp = (*cp << 3) + (c - '0');
 206                         return (UNVIS_VALID);
 207                 }
 208                 /*
 209                  * we were done, push back passed char
 210                  */
 211                 return (UNVIS_VALIDPUSH);
 212
 213         case S_HEX2:    /* second mandatory hex digit */
 214                 if (ishex(tolower(c))) {
 215                         *cp = (isdigit(c) ? (*cp << 4) + (c - '0') : (*cp << 4) + (tolower(c) - 'a' + 10));
 216                 }
 217                 *astate = S_GROUND;
 218                 return (UNVIS_VALID);
 219
 220         default:
 221                 /*
 222                  * decoder in unknown state - (probably uninitialized)
 223                  */
 224                 *astate = S_GROUND;
 225                 return (UNVIS_SYNBAD);
 226         }
 227 }
 228
 229 /*
 230  * strunvis - decode src into dst
 231  *
 232  *      Number of chars decoded into dst is returned, -1 on error.
 233  *      Dst is null terminated.
 234  */
 235
 236 int
 237 strunvis(char *dst, const char *src)
 238 {
 239         char c;
 240         char *start = dst;
 241         int state = 0;
 242
 243         while ( (c = *src++) ) {
 244         again:
 245                 switch (unvis(dst, c, &state, 0)) {
 246                 case UNVIS_VALID:
 247                         dst++;
 248                         break;
 249                 case UNVIS_VALIDPUSH:
 250                         dst++;
 251                         goto again;
 252                 case 0:
 253                 case UNVIS_NOCHAR:
 254                         break;
 255                 default:
 256                         return (-1);
 257                 }
 258         }
 259         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 260                 dst++;
 261         *dst = '\0';
 262         return (dst - start);
 263 }
 264
 265 int
 266 strunvisx(char *dst, const char *src, int flag)
 267 {
 268         char c;
 269         char *start = dst;
 270         int state = 0;
 271
 272         while ( (c = *src++) ) {
 273         again:
 274                 switch (unvis(dst, c, &state, flag)) {
 275                 case UNVIS_VALID:
 276                         dst++;
 277                         break;
 278                 case UNVIS_VALIDPUSH:
 279                         dst++;
 280                         goto again;
 281                 case 0:
 282                 case UNVIS_NOCHAR:
 283                         break;
 284                 default:
 285                         return (-1);
 286                 }
 287         }
 288         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 289                 dst++;
 290         *dst = '\0';
 291         return (dst - start);
 292 }