gen/FreeBSD/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
  34 #if defined(LIBC_SCCS) && !defined(lint)
  35 static char sccsid[] = "@(#)unvis.c     8.1 (Berkeley) 6/4/93";
  36 #endif /* LIBC_SCCS and not lint */
  37 #include <sys/cdefs.h>
  38 __FBSDID("$FreeBSD: src/lib/libc/gen/unvis.c,v 1.8 2003/02/16 17:29:09 nectar Exp $");
  39
  40 #include <sys/types.h>
  41 #include <ctype.h>
  42 #include <vis.h>
  43
  44 /*
  45  * decode driven by state machine
  46  */
  47 #define S_GROUND        0       /* haven't seen escape char */
  48 #define S_START         1       /* start decoding special sequence */
  49 #define S_META          2       /* metachar started (M) */
  50 #define S_META1         3       /* metachar more, regular char (-) */
  51 #define S_CTRL          4       /* control char started (^) */
  52 #define S_OCTAL2        5       /* octal digit 2 */
  53 #define S_OCTAL3        6       /* octal digit 3 */
  54 #define S_HEX2          7       /* hex digit 2 */
  55
  56 #define S_HTTP          0x080   /* %HEXHEX escape */
  57
  58 #define isoctal(c)      (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
  59 #define ishex(c)        ((((u_char)(c)) >= '0' && ((u_char)(c)) <= '9') || (((u_char)(c)) >= 'a' && ((u_char)(c)) <= 'f'))
  60
  61 /*
  62  * unvis - decode characters previously encoded by vis
  63  */
  64 int
  65 unvis(cp, c, astate, flag)
  66         char *cp;
  67         int c, *astate, flag;
  68 {
  69
  70         if (flag & UNVIS_END) {
  71                 if (*astate == S_OCTAL2 || *astate == S_OCTAL3) {
  72                         *astate = S_GROUND;
  73                         return (UNVIS_VALID);
  74                 }
  75                 return (*astate == S_GROUND ? UNVIS_NOCHAR : UNVIS_SYNBAD);
  76         }
  77
  78         switch (*astate & ~S_HTTP) {
  79
  80         case S_GROUND:
  81                 *cp = 0;
  82                 if (c == '\\') {
  83                         *astate = S_START;
  84                         return (0);
  85                 }
  86                 if (flag & VIS_HTTPSTYLE && c == '%') {
  87                         *astate = S_START | S_HTTP;
  88                         return (0);
  89                 }
  90                 *cp = c;
  91                 return (UNVIS_VALID);
  92
  93         case S_START:
  94                 if (*astate & S_HTTP) {
  95                     if (ishex(tolower(c))) {
  96                         *cp = isdigit(c) ? (c - '0') : (tolower(c) - 'a');
  97                         *astate = S_HEX2;
  98                         return (0);
  99                     }
 100                 }
 101                 switch(c) {
 102                 case '\\':
 103                         *cp = c;
 104                         *astate = S_GROUND;
 105                         return (UNVIS_VALID);
 106                 case '0': case '1': case '2': case '3':
 107                 case '4': case '5': case '6': case '7':
 108                         *cp = (c - '0');
 109                         *astate = S_OCTAL2;
 110                         return (0);
 111                 case 'M':
 112                         *cp = 0200;
 113                         *astate = S_META;
 114                         return (0);
 115                 case '^':
 116                         *astate = S_CTRL;
 117                         return (0);
 118                 case 'n':
 119                         *cp = '\n';
 120                         *astate = S_GROUND;
 121                         return (UNVIS_VALID);
 122                 case 'r':
 123                         *cp = '\r';
 124                         *astate = S_GROUND;
 125                         return (UNVIS_VALID);
 126                 case 'b':
 127                         *cp = '\b';
 128                         *astate = S_GROUND;
 129                         return (UNVIS_VALID);
 130                 case 'a':
 131                         *cp = '\007';
 132                         *astate = S_GROUND;
 133                         return (UNVIS_VALID);
 134                 case 'v':
 135                         *cp = '\v';
 136                         *astate = S_GROUND;
 137                         return (UNVIS_VALID);
 138                 case 't':
 139                         *cp = '\t';
 140                         *astate = S_GROUND;
 141                         return (UNVIS_VALID);
 142                 case 'f':
 143                         *cp = '\f';
 144                         *astate = S_GROUND;
 145                         return (UNVIS_VALID);
 146                 case 's':
 147                         *cp = ' ';
 148                         *astate = S_GROUND;
 149                         return (UNVIS_VALID);
 150                 case 'E':
 151                         *cp = '\033';
 152                         *astate = S_GROUND;
 153                         return (UNVIS_VALID);
 154                 case '\n':
 155                         /*
 156                          * hidden newline
 157                          */
 158                         *astate = S_GROUND;
 159                         return (UNVIS_NOCHAR);
 160                 case '$':
 161                         /*
 162                          * hidden marker
 163                          */
 164                         *astate = S_GROUND;
 165                         return (UNVIS_NOCHAR);
 166                 }
 167                 *astate = S_GROUND;
 168                 return (UNVIS_SYNBAD);
 169
 170         case S_META:
 171                 if (c == '-')
 172                         *astate = S_META1;
 173                 else if (c == '^')
 174                         *astate = S_CTRL;
 175                 else {
 176                         *astate = S_GROUND;
 177                         return (UNVIS_SYNBAD);
 178                 }
 179                 return (0);
 180
 181         case S_META1:
 182                 *astate = S_GROUND;
 183                 *cp |= c;
 184                 return (UNVIS_VALID);
 185
 186         case S_CTRL:
 187                 if (c == '?')
 188                         *cp |= 0177;
 189                 else
 190                         *cp |= c & 037;
 191                 *astate = S_GROUND;
 192                 return (UNVIS_VALID);
 193
 194         case S_OCTAL2:  /* second possible octal digit */
 195                 if (isoctal(c)) {
 196                         /*
 197                          * yes - and maybe a third
 198                          */
 199                         *cp = (*cp << 3) + (c - '0');
 200                         *astate = S_OCTAL3;
 201                         return (0);
 202                 }
 203                 /*
 204                  * no - done with current sequence, push back passed char
 205                  */
 206                 *astate = S_GROUND;
 207                 return (UNVIS_VALIDPUSH);
 208
 209         case S_OCTAL3:  /* third possible octal digit */
 210                 *astate = S_GROUND;
 211                 if (isoctal(c)) {
 212                         *cp = (*cp << 3) + (c - '0');
 213                         return (UNVIS_VALID);
 214                 }
 215                 /*
 216                  * we were done, push back passed char
 217                  */
 218                 return (UNVIS_VALIDPUSH);
 219
 220         case S_HEX2:    /* second mandatory hex digit */
 221                 if (ishex(tolower(c))) {
 222                         *cp = (isdigit(c) ? (*cp << 4) + (c - '0') : (*cp << 4) + (tolower(c) - 'a' + 10));
 223                 }
 224                 *astate = S_GROUND;
 225                 return (UNVIS_VALID);
 226
 227         default:
 228                 /*
 229                  * decoder in unknown state - (probably uninitialized)
 230                  */
 231                 *astate = S_GROUND;
 232                 return (UNVIS_SYNBAD);
 233         }
 234 }
 235
 236 /*
 237  * strunvis - decode src into dst
 238  *
 239  *      Number of chars decoded into dst is returned, -1 on error.
 240  *      Dst is null terminated.
 241  */
 242
 243 int
 244 strunvis(dst, src)
 245         char *dst;
 246         const char *src;
 247 {
 248         char c;
 249         char *start = dst;
 250         int state = 0;
 251
 252         while ( (c = *src++) ) {
 253         again:
 254                 switch (unvis(dst, c, &state, 0)) {
 255                 case UNVIS_VALID:
 256                         dst++;
 257                         break;
 258                 case UNVIS_VALIDPUSH:
 259                         dst++;
 260                         goto again;
 261                 case 0:
 262                 case UNVIS_NOCHAR:
 263                         break;
 264                 default:
 265                         return (-1);
 266                 }
 267         }
 268         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 269                 dst++;
 270         *dst = '\0';
 271         return (dst - start);
 272 }
 273
 274 int
 275 strunvisx(dst, src, flag)
 276         char *dst;
 277         const char *src;
 278 {
 279         char c;
 280         char *start = dst;
 281         int state = 0;
 282
 283         while ( (c = *src++) ) {
 284         again:
 285                 switch (unvis(dst, c, &state, flag)) {
 286                 case UNVIS_VALID:
 287                         dst++;
 288                         break;
 289                 case UNVIS_VALIDPUSH:
 290                         dst++;
 291                         goto again;
 292                 case 0:
 293                 case UNVIS_NOCHAR:
 294                         break;
 295                 default:
 296                         return (-1);
 297                 }
 298         }
 299         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 300                 dst++;
 301         *dst = '\0';
 302         return (dst - start);
 303 }