lib/libc/gen/unvis.c

   1 /*      $NetBSD: unvis.c,v 1.29 2009/02/10 23:06:31 christos 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 #include <sys/cdefs.h>
  33 #if defined(LIBC_SCCS) && !defined(lint)
  34 #if 0
  35 static char sccsid[] = "@(#)unvis.c     8.1 (Berkeley) 6/4/93";
  36 #else
  37 __RCSID("$NetBSD: unvis.c,v 1.29 2009/02/10 23:06:31 christos Exp $");
  38 #endif
  39 #endif /* LIBC_SCCS and not lint */
  40
  41 #include "namespace.h"
  42 #include <sys/types.h>
  43
  44 #include <assert.h>
  45 #include <ctype.h>
  46 #include <stdio.h>
  47 #include <vis.h>
  48
  49 #ifdef __weak_alias
  50 __weak_alias(strunvis,_strunvis)
  51 #endif
  52
  53 #if !HAVE_VIS
  54 /*
  55  * decode driven by state machine
  56  */
  57 #define S_GROUND        0       /* haven't seen escape char */
  58 #define S_START         1       /* start decoding special sequence */
  59 #define S_META          2       /* metachar started (M) */
  60 #define S_META1         3       /* metachar more, regular char (-) */
  61 #define S_CTRL          4       /* control char started (^) */
  62 #define S_OCTAL2        5       /* octal digit 2 */
  63 #define S_OCTAL3        6       /* octal digit 3 */
  64 #define S_HEX1          7       /* http hex digit */
  65 #define S_HEX2          8       /* http hex digit 2 */
  66 #define S_MIME1         9       /* mime hex digit 1 */
  67 #define S_MIME2         10      /* mime hex digit 2 */
  68 #define S_EATCRNL       11      /* mime eating CRNL */
  69
  70 #define isoctal(c)      (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
  71 #define xtod(c)         (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10))
  72 #define XTOD(c)         (isdigit(c) ? (c - '0') : ((c - 'A') + 10))
  73
  74 /*
  75  * unvis - decode characters previously encoded by vis
  76  */
  77 int
  78 unvis(char *cp, int c, int *astate, int flag)
  79 {
  80         unsigned char uc = (unsigned char)c;
  81
  82         _DIAGASSERT(cp != NULL);
  83         _DIAGASSERT(astate != NULL);
  84
  85         if (flag & UNVIS_END) {
  86                 if (*astate == S_OCTAL2 || *astate == S_OCTAL3
  87                     || *astate == S_HEX2) {
  88                         *astate = S_GROUND;
  89                         return UNVIS_VALID;
  90                 }
  91                 return (*astate == S_GROUND ? UNVIS_NOCHAR : UNVIS_SYNBAD);
  92         }
  93
  94         switch (*astate) {
  95
  96         case S_GROUND:
  97                 *cp = 0;
  98                 if (c == '\\') {
  99                         *astate = S_START;
 100                         return UNVIS_NOCHAR;
 101                 }
 102                 if ((flag & VIS_HTTPSTYLE) && c == '%') {
 103                         *astate = S_HEX1;
 104                         return UNVIS_NOCHAR;
 105                 }
 106                 if ((flag & VIS_MIMESTYLE) && c == '=') {
 107                         *astate = S_MIME1;
 108                         return UNVIS_NOCHAR;
 109                 }
 110                 *cp = c;
 111                 return UNVIS_VALID;
 112
 113         case S_START:
 114                 switch(c) {
 115                 case '\\':
 116                         *cp = c;
 117                         *astate = S_GROUND;
 118                         return UNVIS_VALID;
 119                 case '0': case '1': case '2': case '3':
 120                 case '4': case '5': case '6': case '7':
 121                         *cp = (c - '0');
 122                         *astate = S_OCTAL2;
 123                         return UNVIS_NOCHAR;
 124                 case 'M':
 125                         *cp = (char)0200;
 126                         *astate = S_META;
 127                         return UNVIS_NOCHAR;
 128                 case '^':
 129                         *astate = S_CTRL;
 130                         return UNVIS_NOCHAR;
 131                 case 'n':
 132                         *cp = '\n';
 133                         *astate = S_GROUND;
 134                         return UNVIS_VALID;
 135                 case 'r':
 136                         *cp = '\r';
 137                         *astate = S_GROUND;
 138                         return UNVIS_VALID;
 139                 case 'b':
 140                         *cp = '\b';
 141                         *astate = S_GROUND;
 142                         return UNVIS_VALID;
 143                 case 'a':
 144                         *cp = '\007';
 145                         *astate = S_GROUND;
 146                         return UNVIS_VALID;
 147                 case 'v':
 148                         *cp = '\v';
 149                         *astate = S_GROUND;
 150                         return UNVIS_VALID;
 151                 case 't':
 152                         *cp = '\t';
 153                         *astate = S_GROUND;
 154                         return UNVIS_VALID;
 155                 case 'f':
 156                         *cp = '\f';
 157                         *astate = S_GROUND;
 158                         return UNVIS_VALID;
 159                 case 's':
 160                         *cp = ' ';
 161                         *astate = S_GROUND;
 162                         return UNVIS_VALID;
 163                 case 'E':
 164                         *cp = '\033';
 165                         *astate = S_GROUND;
 166                         return UNVIS_VALID;
 167                 case '\n':
 168                         /*
 169                          * hidden newline
 170                          */
 171                         *astate = S_GROUND;
 172                         return (UNVIS_NOCHAR);
 173                 case '$':
 174                         /*
 175                          * hidden marker
 176                          */
 177                         *astate = S_GROUND;
 178                         return (UNVIS_NOCHAR);
 179                 }
 180                 *astate = S_GROUND;
 181                 return (UNVIS_SYNBAD);
 182
 183         case S_META:
 184                 if (c == '-')
 185                         *astate = S_META1;
 186                 else if (c == '^')
 187                         *astate = S_CTRL;
 188                 else {
 189                         *astate = S_GROUND;
 190                         return (UNVIS_SYNBAD);
 191                 }
 192                 return UNVIS_NOCHAR;
 193
 194         case S_META1:
 195                 *astate = S_GROUND;
 196                 *cp |= c;
 197                 return UNVIS_VALID;
 198
 199         case S_CTRL:
 200                 if (c == '?')
 201                         *cp |= 0177;
 202                 else
 203                         *cp |= c & 037;
 204                 *astate = S_GROUND;
 205                 return UNVIS_VALID;
 206
 207         case S_OCTAL2:  /* second possible octal digit */
 208                 if (isoctal(uc)) {
 209                         /*
 210                          * yes - and maybe a third
 211                          */
 212                         *cp = (*cp << 3) + (c - '0');
 213                         *astate = S_OCTAL3;
 214                         return UNVIS_NOCHAR;
 215                 }
 216                 /*
 217                  * no - done with current sequence, push back passed char
 218                  */
 219                 *astate = S_GROUND;
 220                 return UNVIS_VALIDPUSH;
 221
 222         case S_OCTAL3:  /* third possible octal digit */
 223                 *astate = S_GROUND;
 224                 if (isoctal(uc)) {
 225                         *cp = (*cp << 3) + (c - '0');
 226                         return UNVIS_VALID;
 227                 }
 228                 /*
 229                  * we were done, push back passed char
 230                  */
 231                 return UNVIS_VALIDPUSH;
 232
 233         case S_HEX1:
 234                 if (isxdigit(uc)) {
 235                         *cp = xtod(uc);
 236                         *astate = S_HEX2;
 237                         return UNVIS_NOCHAR;
 238                 }
 239                 /*
 240                  * no - done with current sequence, push back passed char
 241                  */
 242                 *astate = S_GROUND;
 243                 return UNVIS_VALIDPUSH;
 244
 245         case S_HEX2:
 246                 *astate = S_GROUND;
 247                 if (isxdigit(uc)) {
 248                         *cp = xtod(uc) | (*cp << 4);
 249                         return UNVIS_VALID;
 250                 }
 251                 return UNVIS_VALIDPUSH;
 252
 253         case S_MIME1:
 254                 if (uc == '\n' || uc == '\r') {
 255                         *astate = S_EATCRNL;
 256                         return UNVIS_NOCHAR;
 257                 }
 258                 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
 259                         *cp = XTOD(uc);
 260                         *astate = S_MIME2;
 261                         return UNVIS_NOCHAR;
 262                 }
 263                 *astate = S_GROUND;
 264                 return UNVIS_SYNBAD;
 265
 266         case S_MIME2:
 267                 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
 268                         *astate = S_GROUND;
 269                         *cp = XTOD(uc) | (*cp << 4);
 270                         return UNVIS_VALID;
 271                 }
 272                 *astate = S_GROUND;
 273                 return UNVIS_SYNBAD;
 274
 275         case S_EATCRNL:
 276                 switch (uc) {
 277                 case '\r':
 278                 case '\n':
 279                         return UNVIS_NOCHAR;
 280                 case '=':
 281                         *astate = S_MIME1;
 282                         return UNVIS_NOCHAR;
 283                 default:
 284                         *cp = uc;
 285                         return UNVIS_VALID;
 286                 }
 287
 288         default:
 289                 /*
 290                  * decoder in unknown state - (probably uninitialized)
 291                  */
 292                 *astate = S_GROUND;
 293                 return UNVIS_SYNBAD;
 294         }
 295 }
 296
 297 /*
 298  * strunvis - decode src into dst
 299  *
 300  *      Number of chars decoded into dst is returned, -1 on error.
 301  *      Dst is null terminated.
 302  */
 303
 304 int
 305 strunvisx(dst, src, flag)
 306         char *dst;
 307         const char *src;
 308         int flag;
 309 {
 310         char c;
 311         char *start = dst;
 312         int state = 0;
 313
 314         _DIAGASSERT(src != NULL);
 315         _DIAGASSERT(dst != NULL);
 316
 317         while ((c = *src++) != '\0') {
 318  again:
 319                 switch (unvis(dst, c, &state, flag)) {
 320                 case UNVIS_VALID:
 321                         dst++;
 322                         break;
 323                 case UNVIS_VALIDPUSH:
 324                         dst++;
 325                         goto again;
 326                 case 0:
 327                 case UNVIS_NOCHAR:
 328                         break;
 329                 default:
 330                         return (-1);
 331                 }
 332         }
 333         if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
 334                 dst++;
 335         *dst = '\0';
 336         return (int)(dst - start);
 337 }
 338
 339 int
 340 strunvis(dst, src)
 341         char *dst;
 342         const char *src;
 343 {
 344         return strunvisx(dst, src, 0);
 345 }
 346 #endif