gen/unvis-fbsd.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 1.9 2004/08/02 08:46:23 stefanf Exp $");
  39
  40 #include "xlocale_private.h"
  41
  42 #include <sys/types.h>
  43 #include <ctype.h>
  44 #include <vis.h>
  45
  46 /*
  47  * decode driven by state machine
  48  */
  49 #define S_GROUND        0       /* haven't seen escape char */
  50 #define S_START         1       /* start decoding special sequence */
  51 #define S_META          2       /* metachar started (M) */
  52 #define S_META1         3       /* metachar more, regular char (-) */
  53 #define S_CTRL          4       /* control char started (^) */
  54 #define S_OCTAL2        5       /* octal digit 2 */
  55 #define S_OCTAL3        6       /* octal digit 3 */
  56 #define S_HEX2          7       /* hex digit 2 */
  57
  58 #define S_HTTP          0x080   /* %HEXHEX escape */
  59
  60 #define isoctal(c)      (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
  61 #define ishex(c)        ((((u_char)(c)) >= '0' && ((u_char)(c)) <= '9') || (((u_char)(c)) >= 'a' && ((u_char)(c)) <= 'f'))
  62
  63 /*
  64  * unvis - decode characters previously encoded by vis
  65  */
  66 int
  67 unvis(char *cp, int c, int *astate, int flag)
  68 {
  69         locale_t loc = __current_locale();
  70
  71         if (flag & UNVIS_END) {
  72                 if (*astate == S_OCTAL2 || *astate == S_OCTAL3) {
  73                         *astate = S_GROUND;
  74                         return (UNVIS_VALID);
  75                 }
  76                 return (*astate == S_GROUND ? UNVIS_NOCHAR : UNVIS_SYNBAD);
  77         }
  78
  79         switch (*astate & ~S_HTTP) {
  80
  81         case S_GROUND:
  82                 *cp = 0;
  83                 if (c == '\\') {
  84                         *astate = S_START;
  85                         return (0);
  86                 }
  87                 if (flag & VIS_HTTPSTYLE && c == '%') {
  88                         *astate = S_START | S_HTTP;
  89                         return (0);
  90                 }
  91                 *cp = c;
  92                 return (UNVIS_VALID);
  93
  94         case S_START:
  95                 if (*astate & S_HTTP) {
  96                     if (ishex(tolower_l(c, loc))) {
  97                         *cp = isdigit_l(c, loc) ? (c - '0') : (tolower_l(c, loc) - 'a');
  98                         *astate = S_HEX2;
  99                         return (0);
 100                     }
 101                 }
 102                 switch(c) {
 103                 case '\\':
 104                         *cp = c;
 105                         *astate = S_GROUND;
 106                         return (UNVIS_VALID);
 107                 case '0': case '1': case '2': case '3':
 108                 case '4': case '5': case '6': case '7':
 109                         *cp = (c - '0');
 110                         *astate = S_OCTAL2;
 111                         return (0);
 112                 case 'M':
 113                         *cp = 0200;
 114                         *astate = S_META;
 115                         return (0);
 116                 case '^':
 117                         *astate = S_CTRL;
 118                         return (0);
 119                 case 'n':
 120                         *cp = '\n';
 121                         *astate = S_GROUND;
 122                         return (UNVIS_VALID);
 123                 case 'r':
 124                         *cp = '\r';
 125                         *astate = S_GROUND;
 126                         return (UNVIS_VALID);
 127                 case 'b':
 128                         *cp = '\b';
 129                         *astate = S_GROUND;
 130                         return (UNVIS_VALID);
 131                 case 'a':
 132                         *cp = '\007';
 133                         *astate = S_GROUND;
 134                         return (UNVIS_VALID);
 135                 case 'v':
 136                         *cp = '\v';
 137                         *astate = S_GROUND;
 138                         return (UNVIS_VALID);
 139                 case 't':
 140                         *cp = '\t';
 141                         *astate = S_GROUND;
 142                         return (UNVIS_VALID);
 143                 case 'f':
 144                         *cp = '\f';
 145                         *astate = S_GROUND;
 146                         return (UNVIS_VALID);
 147                 case 's':
 148                         *cp = ' ';
 149                         *astate = S_GROUND;
 150                         return (UNVIS_VALID);
 151                 case 'E':
 152                         *cp = '\033';
 153                         *astate = S_GROUND;
 154                         return (UNVIS_VALID);
 155                 case '\n':
 156                         /*
 157                          * hidden newline
 158                          */
 159                         *astate = S_GROUND;
 160                         return (UNVIS_NOCHAR);
 161                 case '$':
 162                         /*
 163                          * hidden marker
 164                          */
 165                         *astate = S_GROUND;
 166                         return (UNVIS_NOCHAR);
 167                 }
 168                 *astate = S_GROUND;
 169                 return (UNVIS_SYNBAD);
 170
 171         case S_META:
 172                 if (c == '-')
 173                         *astate = S_META1;
 174                 else if (c == '^')
 175                         *astate = S_CTRL;
 176                 else {
 177                         *astate = S_GROUND;
 178                         return (UNVIS_SYNBAD);
 179                 }
 180                 return (0);
 181
 182         case S_META1:
 183                 *astate = S_GROUND;
 184                 *cp |= c;
 185                 return (UNVIS_VALID);
 186
 187         case S_CTRL:
 188                 if (c == '?')
 189                         *cp |= 0177;
 190                 else
 191                         *cp |= c & 037;
 192                 *astate = S_GROUND;
 193                 return (UNVIS_VALID);
 194
 195         case S_OCTAL2:  /* second possible octal digit */
 196                 if (isoctal(c)) {
 197                         /*
 198                          * yes - and maybe a third
 199                          */
 200                         *cp = (*cp << 3) + (c - '0');
 201                         *astate = S_OCTAL3;
 202                         return (0);
 203                 }
 204                 /*
 205                  * no - done with current sequence, push back passed char
 206                  */
 207                 *astate = S_GROUND;
 208                 return (UNVIS_VALIDPUSH);
 209
 210         case S_OCTAL3:  /* third possible octal digit */
 211                 *astate = S_GROUND;
 212                 if (isoctal(c)) {
 213                         *cp = (*cp << 3) + (c - '0');
 214                         return (UNVIS_VALID);
 215                 }
 216                 /*
 217                  * we were done, push back passed char
 218                  */
 219                 return (UNVIS_VALIDPUSH);
 220
 221         case S_HEX2:    /* second mandatory hex digit */
 222                 if (ishex(tolower_l(c, loc))) {
 223                         *cp = (isdigit_l(c, loc) ? (*cp << 4) + (c - '0') : (*cp << 4) + (tolower_l(c, loc) - 'a' + 10));
 224                 }
 225                 *astate = S_GROUND;
 226                 return (UNVIS_VALID);
 227
 228         default:
 229                 /*
 230                  * decoder in unknown state - (probably uninitialized)
 231                  */
 232                 *astate = S_GROUND;
 233                 return (UNVIS_SYNBAD);
 234         }
 235 }
 236
 237 /*
 238  * strunvis - decode src into dst
 239  *
 240  *      Number of chars decoded into dst is returned, -1 on error.
 241  *      Dst is null terminated.
 242  */
 243
 244 int
 245 strunvis(char *dst, const char *src)
 246 {
 247         char c;
 248         char *start = dst;
 249         int state = 0;
 250
 251         while ( (c = *src++) ) {
 252         again:
 253                 switch (unvis(dst, c, &state, 0)) {
 254                 case UNVIS_VALID:
 255                         dst++;
 256                         break;
 257                 case UNVIS_VALIDPUSH:
 258                         dst++;
 259                         goto again;
 260                 case 0:
 261                 case UNVIS_NOCHAR:
 262                         break;
 263                 default:
 264                         return (-1);
 265                 }
 266         }
 267         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 268                 dst++;
 269         *dst = '\0';
 270         return (dst - start);
 271 }
 272
 273 int
 274 strunvisx(char *dst, const char *src, int flag)
 275 {
 276         char c;
 277         char *start = dst;
 278         int state = 0;
 279
 280         while ( (c = *src++) ) {
 281         again:
 282                 switch (unvis(dst, c, &state, flag)) {
 283                 case UNVIS_VALID:
 284                         dst++;
 285                         break;
 286                 case UNVIS_VALIDPUSH:
 287                         dst++;
 288                         goto again;
 289                 case 0:
 290                 case UNVIS_NOCHAR:
 291                         break;
 292                 default:
 293                         return (-1);
 294                 }
 295         }
 296         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 297                 dst++;
 298         *dst = '\0';
 299         return (dst - start);
 300 }