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. All advertising materials mentioning features or use of this software
  14  *    must display the following acknowledgement:
  15  *      This product includes software developed by the University of
  16  *      California, Berkeley and its contributors.
  17  * 4. Neither the name of the University nor the names of its contributors
  18  *    may be used to endorse or promote products derived from this software
  19  *    without specific prior written permission.
  20  *
  21  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  22  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  23  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  24  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  25  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  26  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  27  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  28  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  29  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  30  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  31  * SUCH DAMAGE.
  32  *
  33  * $FreeBSD: src/lib/libc/gen/unvis.c,v 1.4.8.1 2000/08/17 08:25:54 jhb Exp $
  34  * $DragonFly: src/lib/libc/gen/unvis.c,v 1.5 2005/11/19 22:32:53 swildner Exp $
  35  *
  36  * @(#)unvis.c  8.1 (Berkeley) 6/4/93
  37  */
  38
  39 #include <sys/types.h>
  40 #include <ctype.h>
  41 #include <vis.h>
  42
  43 /*
  44  * decode driven by state machine
  45  */
  46 #define S_GROUND        0       /* haven't seen escape char */
  47 #define S_START         1       /* start decoding special sequence */
  48 #define S_META          2       /* metachar started (M) */
  49 #define S_META1         3       /* metachar more, regular char (-) */
  50 #define S_CTRL          4       /* control char started (^) */
  51 #define S_OCTAL2        5       /* octal digit 2 */
  52 #define S_OCTAL3        6       /* octal digit 3 */
  53 #define S_HEX2          7       /* hex digit 2 */
  54
  55 #define S_HTTP          0x080   /* %HEXHEX escape */
  56
  57 #define isoctal(c)      (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
  58 #define ishex(c)        ((((u_char)(c)) >= '0' && ((u_char)(c)) <= '9') || (((u_char)(c)) >= 'a' && ((u_char)(c)) <= 'f'))
  59
  60 /*
  61  * unvis - decode characters previously encoded by vis
  62  */
  63 int
  64 unvis(char *cp, int c, int *astate, int flag)
  65 {
  66
  67         if (flag & UNVIS_END) {
  68                 if (*astate == S_OCTAL2 || *astate == S_OCTAL3) {
  69                         *astate = S_GROUND;
  70                         return (UNVIS_VALID);
  71                 }
  72                 return (*astate == S_GROUND ? UNVIS_NOCHAR : UNVIS_SYNBAD);
  73         }
  74
  75         switch (*astate & ~S_HTTP) {
  76
  77         case S_GROUND:
  78                 *cp = 0;
  79                 if (c == '\\') {
  80                         *astate = S_START;
  81                         return (0);
  82                 }
  83                 if (flag & VIS_HTTPSTYLE && c == '%') {
  84                         *astate = S_START | S_HTTP;
  85                         return (0);
  86                 }
  87                 *cp = c;
  88                 return (UNVIS_VALID);
  89
  90         case S_START:
  91                 if (*astate & S_HTTP) {
  92                     if (ishex(tolower(c))) {
  93                         *cp = isdigit(c) ? (c - '0') : (tolower(c) - 'a');
  94                         *astate = S_HEX2;
  95                         return (0);
  96                     }
  97                 }
  98                 switch(c) {
  99                 case '\\':
 100                         *cp = c;
 101                         *astate = S_GROUND;
 102                         return (UNVIS_VALID);
 103                 case '0': case '1': case '2': case '3':
 104                 case '4': case '5': case '6': case '7':
 105                         *cp = (c - '0');
 106                         *astate = S_OCTAL2;
 107                         return (0);
 108                 case 'M':
 109                         *cp = (char)0200;
 110                         *astate = S_META;
 111                         return (0);
 112                 case '^':
 113                         *astate = S_CTRL;
 114                         return (0);
 115                 case 'n':
 116                         *cp = '\n';
 117                         *astate = S_GROUND;
 118                         return (UNVIS_VALID);
 119                 case 'r':
 120                         *cp = '\r';
 121                         *astate = S_GROUND;
 122                         return (UNVIS_VALID);
 123                 case 'b':
 124                         *cp = '\b';
 125                         *astate = S_GROUND;
 126                         return (UNVIS_VALID);
 127                 case 'a':
 128                         *cp = '\007';
 129                         *astate = S_GROUND;
 130                         return (UNVIS_VALID);
 131                 case 'v':
 132                         *cp = '\v';
 133                         *astate = S_GROUND;
 134                         return (UNVIS_VALID);
 135                 case 't':
 136                         *cp = '\t';
 137                         *astate = S_GROUND;
 138                         return (UNVIS_VALID);
 139                 case 'f':
 140                         *cp = '\f';
 141                         *astate = S_GROUND;
 142                         return (UNVIS_VALID);
 143                 case 's':
 144                         *cp = ' ';
 145                         *astate = S_GROUND;
 146                         return (UNVIS_VALID);
 147                 case 'E':
 148                         *cp = '\033';
 149                         *astate = S_GROUND;
 150                         return (UNVIS_VALID);
 151                 case '\n':
 152                         /*
 153                          * hidden newline
 154                          */
 155                         *astate = S_GROUND;
 156                         return (UNVIS_NOCHAR);
 157                 case '$':
 158                         /*
 159                          * hidden marker
 160                          */
 161                         *astate = S_GROUND;
 162                         return (UNVIS_NOCHAR);
 163                 }
 164                 *astate = S_GROUND;
 165                 return (UNVIS_SYNBAD);
 166
 167         case S_META:
 168                 if (c == '-')
 169                         *astate = S_META1;
 170                 else if (c == '^')
 171                         *astate = S_CTRL;
 172                 else {
 173                         *astate = S_GROUND;
 174                         return (UNVIS_SYNBAD);
 175                 }
 176                 return (0);
 177
 178         case S_META1:
 179                 *astate = S_GROUND;
 180                 *cp |= c;
 181                 return (UNVIS_VALID);
 182
 183         case S_CTRL:
 184                 if (c == '?')
 185                         *cp |= 0177;
 186                 else
 187                         *cp |= c & 037;
 188                 *astate = S_GROUND;
 189                 return (UNVIS_VALID);
 190
 191         case S_OCTAL2:  /* second possible octal digit */
 192                 if (isoctal(c)) {
 193                         /*
 194                          * yes - and maybe a third
 195                          */
 196                         *cp = (*cp << 3) + (c - '0');
 197                         *astate = S_OCTAL3;
 198                         return (0);
 199                 }
 200                 /*
 201                  * no - done with current sequence, push back passed char
 202                  */
 203                 *astate = S_GROUND;
 204                 return (UNVIS_VALIDPUSH);
 205
 206         case S_OCTAL3:  /* third possible octal digit */
 207                 *astate = S_GROUND;
 208                 if (isoctal(c)) {
 209                         *cp = (*cp << 3) + (c - '0');
 210                         return (UNVIS_VALID);
 211                 }
 212                 /*
 213                  * we were done, push back passed char
 214                  */
 215                 return (UNVIS_VALIDPUSH);
 216
 217         case S_HEX2:    /* second mandatory hex digit */
 218                 if (ishex(tolower(c))) {
 219                         *cp = (isdigit(c) ? (*cp << 4) + (c - '0') : (*cp << 4) + (tolower(c) - 'a' + 10));
 220                 }
 221                 *astate = S_GROUND;
 222                 return (UNVIS_VALID);
 223
 224         default:
 225                 /*
 226                  * decoder in unknown state - (probably uninitialized)
 227                  */
 228                 *astate = S_GROUND;
 229                 return (UNVIS_SYNBAD);
 230         }
 231 }
 232
 233 /*
 234  * strunvis - decode src into dst
 235  *
 236  *      Number of chars decoded into dst is returned, -1 on error.
 237  *      Dst is null terminated.
 238  */
 239
 240 int
 241 strunvis(char *dst, const char *src)
 242 {
 243         char c;
 244         char *start = dst;
 245         int state = 0;
 246
 247         while ( (c = *src++) ) {
 248         again:
 249                 switch (unvis(dst, c, &state, 0)) {
 250                 case UNVIS_VALID:
 251                         dst++;
 252                         break;
 253                 case UNVIS_VALIDPUSH:
 254                         dst++;
 255                         goto again;
 256                 case 0:
 257                 case UNVIS_NOCHAR:
 258                         break;
 259                 default:
 260                         return (-1);
 261                 }
 262         }
 263         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 264                 dst++;
 265         *dst = '\0';
 266         return (dst - start);
 267 }
 268
 269 int
 270 strunvisx(char *dst, const char *src, int flag)
 271 {
 272         char c;
 273         char *start = dst;
 274         int state = 0;
 275
 276         while ( (c = *src++) ) {
 277         again:
 278                 switch (unvis(dst, c, &state, flag)) {
 279                 case UNVIS_VALID:
 280                         dst++;
 281                         break;
 282                 case UNVIS_VALIDPUSH:
 283                         dst++;
 284                         goto again;
 285                 case 0:
 286                 case UNVIS_NOCHAR:
 287                         break;
 288                 default:
 289                         return (-1);
 290                 }
 291         }
 292         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 293                 dst++;
 294         *dst = '\0';
 295         return (dst - start);
 296 }