gen/FreeBSD/unvis.c

   1 /*      $NetBSD: unvis.c,v 1.41 2012/12/15 04:29:53 matt 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 1.41 2012/12/15 04:29:53 matt Exp $");
  38 #endif
  39 #endif /* LIBC_SCCS and not lint */
  40 #include "xlocale_private.h"
  41
  42 #include <sys/types.h>
  43
  44 #include <assert.h>
  45 #include <ctype.h>
  46 #include <stdint.h>
  47 #include <stdio.h>
  48 #include <errno.h>
  49 #include <vis.h>
  50
  51 #define _DIAGASSERT(x)  assert(x)
  52
  53 /*
  54  * Return the number of elements in a statically-allocated array,
  55  * __x.
  56  */
  57 #define __arraycount(__x)       (sizeof(__x) / sizeof(__x[0]))
  58
  59 #if !HAVE_VIS
  60 /*
  61  * decode driven by state machine
  62  */
  63 #define S_GROUND        0       /* haven't seen escape char */
  64 #define S_START         1       /* start decoding special sequence */
  65 #define S_META          2       /* metachar started (M) */
  66 #define S_META1         3       /* metachar more, regular char (-) */
  67 #define S_CTRL          4       /* control char started (^) */
  68 #define S_OCTAL2        5       /* octal digit 2 */
  69 #define S_OCTAL3        6       /* octal digit 3 */
  70 #define S_HEX           7       /* mandatory hex digit */
  71 #define S_HEX1          8       /* http hex digit */
  72 #define S_HEX2          9       /* http hex digit 2 */
  73 #define S_MIME1         10      /* mime hex digit 1 */
  74 #define S_MIME2         11      /* mime hex digit 2 */
  75 #define S_EATCRNL       12      /* mime eating CRNL */
  76 #define S_AMP           13      /* seen & */
  77 #define S_NUMBER        14      /* collecting number */
  78 #define S_STRING        15      /* collecting string */
  79
  80 #define isoctal(c)      (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
  81 #define xtod(c)         (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10))
  82 #define XTOD(c)         (isdigit(c) ? (c - '0') : ((c - 'A') + 10))
  83
  84 /*
  85  * RFC 1866
  86  */
  87 static const struct nv {
  88         char name[7];
  89         uint8_t value;
  90 } nv[] = {
  91         { "AElig",      198 }, /* capital AE diphthong (ligature)  */
  92         { "Aacute",     193 }, /* capital A, acute accent  */
  93         { "Acirc",      194 }, /* capital A, circumflex accent  */
  94         { "Agrave",     192 }, /* capital A, grave accent  */
  95         { "Aring",      197 }, /* capital A, ring  */
  96         { "Atilde",     195 }, /* capital A, tilde  */
  97         { "Auml",       196 }, /* capital A, dieresis or umlaut mark  */
  98         { "Ccedil",     199 }, /* capital C, cedilla  */
  99         { "ETH",        208 }, /* capital Eth, Icelandic  */
 100         { "Eacute",     201 }, /* capital E, acute accent  */
 101         { "Ecirc",      202 }, /* capital E, circumflex accent  */
 102         { "Egrave",     200 }, /* capital E, grave accent  */
 103         { "Euml",       203 }, /* capital E, dieresis or umlaut mark  */
 104         { "Iacute",     205 }, /* capital I, acute accent  */
 105         { "Icirc",      206 }, /* capital I, circumflex accent  */
 106         { "Igrave",     204 }, /* capital I, grave accent  */
 107         { "Iuml",       207 }, /* capital I, dieresis or umlaut mark  */
 108         { "Ntilde",     209 }, /* capital N, tilde  */
 109         { "Oacute",     211 }, /* capital O, acute accent  */
 110         { "Ocirc",      212 }, /* capital O, circumflex accent  */
 111         { "Ograve",     210 }, /* capital O, grave accent  */
 112         { "Oslash",     216 }, /* capital O, slash  */
 113         { "Otilde",     213 }, /* capital O, tilde  */
 114         { "Ouml",       214 }, /* capital O, dieresis or umlaut mark  */
 115         { "THORN",      222 }, /* capital THORN, Icelandic  */
 116         { "Uacute",     218 }, /* capital U, acute accent  */
 117         { "Ucirc",      219 }, /* capital U, circumflex accent  */
 118         { "Ugrave",     217 }, /* capital U, grave accent  */
 119         { "Uuml",       220 }, /* capital U, dieresis or umlaut mark  */
 120         { "Yacute",     221 }, /* capital Y, acute accent  */
 121         { "aacute",     225 }, /* small a, acute accent  */
 122         { "acirc",      226 }, /* small a, circumflex accent  */
 123         { "acute",      180 }, /* acute accent  */
 124         { "aelig",      230 }, /* small ae diphthong (ligature)  */
 125         { "agrave",     224 }, /* small a, grave accent  */
 126         { "amp",         38 }, /* ampersand  */
 127         { "aring",      229 }, /* small a, ring  */
 128         { "atilde",     227 }, /* small a, tilde  */
 129         { "auml",       228 }, /* small a, dieresis or umlaut mark  */
 130         { "brvbar",     166 }, /* broken (vertical) bar  */
 131         { "ccedil",     231 }, /* small c, cedilla  */
 132         { "cedil",      184 }, /* cedilla  */
 133         { "cent",       162 }, /* cent sign  */
 134         { "copy",       169 }, /* copyright sign  */
 135         { "curren",     164 }, /* general currency sign  */
 136         { "deg",        176 }, /* degree sign  */
 137         { "divide",     247 }, /* divide sign  */
 138         { "eacute",     233 }, /* small e, acute accent  */
 139         { "ecirc",      234 }, /* small e, circumflex accent  */
 140         { "egrave",     232 }, /* small e, grave accent  */
 141         { "eth",        240 }, /* small eth, Icelandic  */
 142         { "euml",       235 }, /* small e, dieresis or umlaut mark  */
 143         { "frac12",     189 }, /* fraction one-half  */
 144         { "frac14",     188 }, /* fraction one-quarter  */
 145         { "frac34",     190 }, /* fraction three-quarters  */
 146         { "gt",          62 }, /* greater than  */
 147         { "iacute",     237 }, /* small i, acute accent  */
 148         { "icirc",      238 }, /* small i, circumflex accent  */
 149         { "iexcl",      161 }, /* inverted exclamation mark  */
 150         { "igrave",     236 }, /* small i, grave accent  */
 151         { "iquest",     191 }, /* inverted question mark  */
 152         { "iuml",       239 }, /* small i, dieresis or umlaut mark  */
 153         { "laquo",      171 }, /* angle quotation mark, left  */
 154         { "lt",          60 }, /* less than  */
 155         { "macr",       175 }, /* macron  */
 156         { "micro",      181 }, /* micro sign  */
 157         { "middot",     183 }, /* middle dot  */
 158         { "nbsp",       160 }, /* no-break space  */
 159         { "not",        172 }, /* not sign  */
 160         { "ntilde",     241 }, /* small n, tilde  */
 161         { "oacute",     243 }, /* small o, acute accent  */
 162         { "ocirc",      244 }, /* small o, circumflex accent  */
 163         { "ograve",     242 }, /* small o, grave accent  */
 164         { "ordf",       170 }, /* ordinal indicator, feminine  */
 165         { "ordm",       186 }, /* ordinal indicator, masculine  */
 166         { "oslash",     248 }, /* small o, slash  */
 167         { "otilde",     245 }, /* small o, tilde  */
 168         { "ouml",       246 }, /* small o, dieresis or umlaut mark  */
 169         { "para",       182 }, /* pilcrow (paragraph sign)  */
 170         { "plusmn",     177 }, /* plus-or-minus sign  */
 171         { "pound",      163 }, /* pound sterling sign  */
 172         { "quot",        34 }, /* double quote  */
 173         { "raquo",      187 }, /* angle quotation mark, right  */
 174         { "reg",        174 }, /* registered sign  */
 175         { "sect",       167 }, /* section sign  */
 176         { "shy",        173 }, /* soft hyphen  */
 177         { "sup1",       185 }, /* superscript one  */
 178         { "sup2",       178 }, /* superscript two  */
 179         { "sup3",       179 }, /* superscript three  */
 180         { "szlig",      223 }, /* small sharp s, German (sz ligature)  */
 181         { "thorn",      254 }, /* small thorn, Icelandic  */
 182         { "times",      215 }, /* multiply sign  */
 183         { "uacute",     250 }, /* small u, acute accent  */
 184         { "ucirc",      251 }, /* small u, circumflex accent  */
 185         { "ugrave",     249 }, /* small u, grave accent  */
 186         { "uml",        168 }, /* umlaut (dieresis)  */
 187         { "uuml",       252 }, /* small u, dieresis or umlaut mark  */
 188         { "yacute",     253 }, /* small y, acute accent  */
 189         { "yen",        165 }, /* yen sign  */
 190         { "yuml",       255 }, /* small y, dieresis or umlaut mark  */
 191 };
 192
 193 /*
 194  * unvis - decode characters previously encoded by vis
 195  */
 196 int
 197 unvis(char *cp, int c, int *astate, int flag)
 198 {
 199         unsigned char uc = (unsigned char)c;
 200         unsigned char st, ia, is, lc;
 201
 202 /*
 203  * Bottom 8 bits of astate hold the state machine state.
 204  * Top 8 bits hold the current character in the http 1866 nv string decoding
 205  */
 206 #define GS(a)           ((a) & 0xff)
 207 #define SS(a, b)        (((uint32_t)(a) << 24) | (b))
 208 #define GI(a)           ((uint32_t)(a) >> 24)
 209
 210         _DIAGASSERT(cp != NULL);
 211         _DIAGASSERT(astate != NULL);
 212         st = GS(*astate);
 213
 214         if (flag & UNVIS_END) {
 215                 switch (st) {
 216                 case S_OCTAL2:
 217                 case S_OCTAL3:
 218                 case S_HEX2:
 219                         *astate = SS(0, S_GROUND);
 220                         return UNVIS_VALID;
 221                 case S_GROUND:
 222                         return UNVIS_NOCHAR;
 223                 default:
 224                         return UNVIS_SYNBAD;
 225                 }
 226         }
 227
 228         switch (st) {
 229
 230         case S_GROUND:
 231                 *cp = 0;
 232                 if ((flag & VIS_NOESCAPE) == 0 && c == '\\') {
 233                         *astate = SS(0, S_START);
 234                         return UNVIS_NOCHAR;
 235                 }
 236                 if ((flag & VIS_HTTP1808) && c == '%') {
 237                         *astate = SS(0, S_HEX1);
 238                         return UNVIS_NOCHAR;
 239                 }
 240                 if ((flag & VIS_HTTP1866) && c == '&') {
 241                         *astate = SS(0, S_AMP);
 242                         return UNVIS_NOCHAR;
 243                 }
 244                 if ((flag & VIS_MIMESTYLE) && c == '=') {
 245                         *astate = SS(0, S_MIME1);
 246                         return UNVIS_NOCHAR;
 247                 }
 248                 *cp = c;
 249                 return UNVIS_VALID;
 250
 251         case S_START:
 252                 switch(c) {
 253                 case '\\':
 254                         *cp = c;
 255                         *astate = SS(0, S_GROUND);
 256                         return UNVIS_VALID;
 257                 case '0': case '1': case '2': case '3':
 258                 case '4': case '5': case '6': case '7':
 259                         *cp = (c - '0');
 260                         *astate = SS(0, S_OCTAL2);
 261                         return UNVIS_NOCHAR;
 262                 case 'M':
 263                         *cp = (char)0200;
 264                         *astate = SS(0, S_META);
 265                         return UNVIS_NOCHAR;
 266                 case '^':
 267                         *astate = SS(0, S_CTRL);
 268                         return UNVIS_NOCHAR;
 269                 case 'n':
 270                         *cp = '\n';
 271                         *astate = SS(0, S_GROUND);
 272                         return UNVIS_VALID;
 273                 case 'r':
 274                         *cp = '\r';
 275                         *astate = SS(0, S_GROUND);
 276                         return UNVIS_VALID;
 277                 case 'b':
 278                         *cp = '\b';
 279                         *astate = SS(0, S_GROUND);
 280                         return UNVIS_VALID;
 281                 case 'a':
 282                         *cp = '\007';
 283                         *astate = SS(0, S_GROUND);
 284                         return UNVIS_VALID;
 285                 case 'v':
 286                         *cp = '\v';
 287                         *astate = SS(0, S_GROUND);
 288                         return UNVIS_VALID;
 289                 case 't':
 290                         *cp = '\t';
 291                         *astate = SS(0, S_GROUND);
 292                         return UNVIS_VALID;
 293                 case 'f':
 294                         *cp = '\f';
 295                         *astate = SS(0, S_GROUND);
 296                         return UNVIS_VALID;
 297                 case 's':
 298                         *cp = ' ';
 299                         *astate = SS(0, S_GROUND);
 300                         return UNVIS_VALID;
 301                 case 'E':
 302                         *cp = '\033';
 303                         *astate = SS(0, S_GROUND);
 304                         return UNVIS_VALID;
 305                 case 'x':
 306                         *astate = SS(0, S_HEX);
 307                         return UNVIS_NOCHAR;
 308                 case '\n':
 309                         /*
 310                          * hidden newline
 311                          */
 312                         *astate = SS(0, S_GROUND);
 313                         return UNVIS_NOCHAR;
 314                 case '$':
 315                         /*
 316                          * hidden marker
 317                          */
 318                         *astate = SS(0, S_GROUND);
 319                         return UNVIS_NOCHAR;
 320                 }
 321                 goto bad;
 322
 323         case S_META:
 324                 if (c == '-')
 325                         *astate = SS(0, S_META1);
 326                 else if (c == '^')
 327                         *astate = SS(0, S_CTRL);
 328                 else
 329                         goto bad;
 330                 return UNVIS_NOCHAR;
 331
 332         case S_META1:
 333                 *astate = SS(0, S_GROUND);
 334                 *cp |= c;
 335                 return UNVIS_VALID;
 336
 337         case S_CTRL:
 338                 if (c == '?')
 339                         *cp |= 0177;
 340                 else
 341                         *cp |= c & 037;
 342                 *astate = SS(0, S_GROUND);
 343                 return UNVIS_VALID;
 344
 345         case S_OCTAL2:  /* second possible octal digit */
 346                 if (isoctal(uc)) {
 347                         /*
 348                          * yes - and maybe a third
 349                          */
 350                         *cp = (*cp << 3) + (c - '0');
 351                         *astate = SS(0, S_OCTAL3);
 352                         return UNVIS_NOCHAR;
 353                 }
 354                 /*
 355                  * no - done with current sequence, push back passed char
 356                  */
 357                 *astate = SS(0, S_GROUND);
 358                 return UNVIS_VALIDPUSH;
 359
 360         case S_OCTAL3:  /* third possible octal digit */
 361                 *astate = SS(0, S_GROUND);
 362                 if (isoctal(uc)) {
 363                         *cp = (*cp << 3) + (c - '0');
 364                         return UNVIS_VALID;
 365                 }
 366                 /*
 367                  * we were done, push back passed char
 368                  */
 369                 return UNVIS_VALIDPUSH;
 370
 371         case S_HEX:
 372                 if (!isxdigit(uc))
 373                         goto bad;
 374                 /*FALLTHROUGH*/
 375         case S_HEX1:
 376                 if (isxdigit(uc)) {
 377                         *cp = xtod(uc);
 378                         *astate = SS(0, S_HEX2);
 379                         return UNVIS_NOCHAR;
 380                 }
 381                 /*
 382                  * no - done with current sequence, push back passed char
 383                  */
 384                 *astate = SS(0, S_GROUND);
 385                 return UNVIS_VALIDPUSH;
 386
 387         case S_HEX2:
 388                 *astate = S_GROUND;
 389                 if (isxdigit(uc)) {
 390                         *cp = xtod(uc) | (*cp << 4);
 391                         return UNVIS_VALID;
 392                 }
 393                 return UNVIS_VALIDPUSH;
 394
 395         case S_MIME1:
 396                 if (uc == '\n' || uc == '\r') {
 397                         *astate = SS(0, S_EATCRNL);
 398                         return UNVIS_NOCHAR;
 399                 }
 400                 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
 401                         *cp = XTOD(uc);
 402                         *astate = SS(0, S_MIME2);
 403                         return UNVIS_NOCHAR;
 404                 }
 405                 goto bad;
 406
 407         case S_MIME2:
 408                 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
 409                         *astate = SS(0, S_GROUND);
 410                         *cp = XTOD(uc) | (*cp << 4);
 411                         return UNVIS_VALID;
 412                 }
 413                 goto bad;
 414
 415         case S_EATCRNL:
 416                 switch (uc) {
 417                 case '\r':
 418                 case '\n':
 419                         return UNVIS_NOCHAR;
 420                 case '=':
 421                         *astate = SS(0, S_MIME1);
 422                         return UNVIS_NOCHAR;
 423                 default:
 424                         *cp = uc;
 425                         *astate = SS(0, S_GROUND);
 426                         return UNVIS_VALID;
 427                 }
 428
 429         case S_AMP:
 430                 *cp = 0;
 431                 if (uc == '#') {
 432                         *astate = SS(0, S_NUMBER);
 433                         return UNVIS_NOCHAR;
 434                 }
 435                 *astate = SS(0, S_STRING);
 436                 /*FALLTHROUGH*/
 437
 438         case S_STRING:
 439                 ia = *cp;               /* index in the array */
 440                 is = GI(*astate);       /* index in the string */
 441                 lc = is == 0 ? 0 : nv[ia].name[is - 1]; /* last character */
 442
 443                 if (uc == ';')
 444                         uc = '\0';
 445
 446                 for (; ia < __arraycount(nv); ia++) {
 447                         if (is != 0 && nv[ia].name[is - 1] != lc)
 448                                 goto bad;
 449                         if (nv[ia].name[is] == uc)
 450                                 break;
 451                 }
 452
 453                 if (ia == __arraycount(nv))
 454                         goto bad;
 455
 456                 if (uc != 0) {
 457                         *cp = ia;
 458                         *astate = SS(is + 1, S_STRING);
 459                         return UNVIS_NOCHAR;
 460                 }
 461
 462                 *cp = nv[ia].value;
 463                 *astate = SS(0, S_GROUND);
 464                 return UNVIS_VALID;
 465
 466         case S_NUMBER:
 467                 if (uc == ';')
 468                         return UNVIS_VALID;
 469                 if (!isdigit(uc))
 470                         goto bad;
 471                 *cp += (*cp * 10) + uc - '0';
 472                 return UNVIS_NOCHAR;
 473
 474         default:
 475         bad:
 476                 /*
 477                  * decoder in unknown state - (probably uninitialized)
 478                  */
 479                 *astate = SS(0, S_GROUND);
 480                 return UNVIS_SYNBAD;
 481         }
 482 }
 483
 484 /*
 485  * strnunvisx - decode src into dst
 486  *
 487  *      Number of chars decoded into dst is returned, -1 on error.
 488  *      Dst is null terminated.
 489  */
 490
 491 int
 492 strnunvisx(char *dst, size_t dlen, const char *src, int flag)
 493 {
 494         char c;
 495         char t = '\0', *start = dst;
 496         int state = 0;
 497
 498         _DIAGASSERT(src != NULL);
 499         _DIAGASSERT(dst != NULL);
 500 #define CHECKSPACE() \
 501         do { \
 502                 if (dlen-- == 0) { \
 503                         errno = ENOSPC; \
 504                         return -1; \
 505                 } \
 506         } while (/*CONSTCOND*/0)
 507
 508         while ((c = *src++) != '\0') {
 509  again:
 510                 switch (unvis(&t, c, &state, flag)) {
 511                 case UNVIS_VALID:
 512                         CHECKSPACE();
 513                         *dst++ = t;
 514                         break;
 515                 case UNVIS_VALIDPUSH:
 516                         CHECKSPACE();
 517                         *dst++ = t;
 518                         goto again;
 519                 case 0:
 520                 case UNVIS_NOCHAR:
 521                         break;
 522                 case UNVIS_SYNBAD:
 523                         errno = EINVAL;
 524                         return -1;
 525                 default:
 526                         _DIAGASSERT(/*CONSTCOND*/0);
 527                         errno = EINVAL;
 528                         return -1;
 529                 }
 530         }
 531         if (unvis(&t, c, &state, UNVIS_END) == UNVIS_VALID) {
 532                 CHECKSPACE();
 533                 *dst++ = t;
 534         }
 535         CHECKSPACE();
 536         *dst = '\0';
 537         return (int)(dst - start);
 538 }
 539
 540 int
 541 strunvisx(char *dst, const char *src, int flag)
 542 {
 543         return strnunvisx(dst, (size_t)~0, src, flag);
 544 }
 545
 546 int
 547 strunvis(char *dst, const char *src)
 548 {
 549         return strnunvisx(dst, (size_t)~0, src, 0);
 550 }
 551
 552 int
 553 strnunvis(char *dst, size_t dlen, const char *src)
 554 {
 555         return strnunvisx(dst, dlen, src, 0);
 556 }
 557 #endif