contrib/libedit/src/unvis.c

   1 /*      $NetBSD: unvis.c,v 1.38 2011/11/18 20:28:17 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 "config.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 1.38 2011/11/18 20:28:17 christos Exp $");
  38 #endif
  39 #endif /* LIBC_SCCS and not lint */
  40
  41 #include <sys/types.h>
  42
  43 #include <assert.h>
  44 #include <ctype.h>
  45 #include <stdint.h>
  46 #include <stdio.h>
  47 #include <errno.h>
  48 #include <vis.h>
  49
  50 #ifdef __weak_alias
  51 __weak_alias(strnunvisx,_strnunvisx)
  52 #endif
  53
  54 #if !HAVE_VIS
  55 /*
  56  * decode driven by state machine
  57  */
  58 #define S_GROUND        0       /* haven't seen escape char */
  59 #define S_START         1       /* start decoding special sequence */
  60 #define S_META          2       /* metachar started (M) */
  61 #define S_META1         3       /* metachar more, regular char (-) */
  62 #define S_CTRL          4       /* control char started (^) */
  63 #define S_OCTAL2        5       /* octal digit 2 */
  64 #define S_OCTAL3        6       /* octal digit 3 */
  65 #define S_HEX           7       /* mandatory hex digit */
  66 #define S_HEX1          8       /* http hex digit */
  67 #define S_HEX2          9       /* http hex digit 2 */
  68 #define S_MIME1         10      /* mime hex digit 1 */
  69 #define S_MIME2         11      /* mime hex digit 2 */
  70 #define S_EATCRNL       12      /* mime eating CRNL */
  71 #define S_AMP           13      /* seen & */
  72 #define S_NUMBER        14      /* collecting number */
  73 #define S_STRING        15      /* collecting string */
  74
  75 #define isoctal(c)      (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
  76 #define xtod(c)         (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10))
  77 #define XTOD(c)         (isdigit(c) ? (c - '0') : ((c - 'A') + 10))
  78
  79 /*
  80  * RFC 1866
  81  */
  82 static const struct nv {
  83         const char *name;
  84         uint8_t value;
  85 } nv[] = {
  86         { "AElig",      198 }, /* capital AE diphthong (ligature)  */
  87         { "Aacute",     193 }, /* capital A, acute accent  */
  88         { "Acirc",      194 }, /* capital A, circumflex accent  */
  89         { "Agrave",     192 }, /* capital A, grave accent  */
  90         { "Aring",      197 }, /* capital A, ring  */
  91         { "Atilde",     195 }, /* capital A, tilde  */
  92         { "Auml",       196 }, /* capital A, dieresis or umlaut mark  */
  93         { "Ccedil",     199 }, /* capital C, cedilla  */
  94         { "ETH",        208 }, /* capital Eth, Icelandic  */
  95         { "Eacute",     201 }, /* capital E, acute accent  */
  96         { "Ecirc",      202 }, /* capital E, circumflex accent  */
  97         { "Egrave",     200 }, /* capital E, grave accent  */
  98         { "Euml",       203 }, /* capital E, dieresis or umlaut mark  */
  99         { "Iacute",     205 }, /* capital I, acute accent  */
 100         { "Icirc",      206 }, /* capital I, circumflex accent  */
 101         { "Igrave",     204 }, /* capital I, grave accent  */
 102         { "Iuml",       207 }, /* capital I, dieresis or umlaut mark  */
 103         { "Ntilde",     209 }, /* capital N, tilde  */
 104         { "Oacute",     211 }, /* capital O, acute accent  */
 105         { "Ocirc",      212 }, /* capital O, circumflex accent  */
 106         { "Ograve",     210 }, /* capital O, grave accent  */
 107         { "Oslash",     216 }, /* capital O, slash  */
 108         { "Otilde",     213 }, /* capital O, tilde  */
 109         { "Ouml",       214 }, /* capital O, dieresis or umlaut mark  */
 110         { "THORN",      222 }, /* capital THORN, Icelandic  */
 111         { "Uacute",     218 }, /* capital U, acute accent  */
 112         { "Ucirc",      219 }, /* capital U, circumflex accent  */
 113         { "Ugrave",     217 }, /* capital U, grave accent  */
 114         { "Uuml",       220 }, /* capital U, dieresis or umlaut mark  */
 115         { "Yacute",     221 }, /* capital Y, acute accent  */
 116         { "aacute",     225 }, /* small a, acute accent  */
 117         { "acirc",      226 }, /* small a, circumflex accent  */
 118         { "acute",      180 }, /* acute accent  */
 119         { "aelig",      230 }, /* small ae diphthong (ligature)  */
 120         { "agrave",     224 }, /* small a, grave accent  */
 121         { "amp",         38 }, /* ampersand  */
 122         { "aring",      229 }, /* small a, ring  */
 123         { "atilde",     227 }, /* small a, tilde  */
 124         { "auml",       228 }, /* small a, dieresis or umlaut mark  */
 125         { "brvbar",     166 }, /* broken (vertical) bar  */
 126         { "ccedil",     231 }, /* small c, cedilla  */
 127         { "cedil",      184 }, /* cedilla  */
 128         { "cent",       162 }, /* cent sign  */
 129         { "copy",       169 }, /* copyright sign  */
 130         { "curren",     164 }, /* general currency sign  */
 131         { "deg",        176 }, /* degree sign  */
 132         { "divide",     247 }, /* divide sign  */
 133         { "eacute",     233 }, /* small e, acute accent  */
 134         { "ecirc",      234 }, /* small e, circumflex accent  */
 135         { "egrave",     232 }, /* small e, grave accent  */
 136         { "eth",        240 }, /* small eth, Icelandic  */
 137         { "euml",       235 }, /* small e, dieresis or umlaut mark  */
 138         { "frac12",     189 }, /* fraction one-half  */
 139         { "frac14",     188 }, /* fraction one-quarter  */
 140         { "frac34",     190 }, /* fraction three-quarters  */
 141         { "gt",          62 }, /* greater than  */
 142         { "iacute",     237 }, /* small i, acute accent  */
 143         { "icirc",      238 }, /* small i, circumflex accent  */
 144         { "iexcl",      161 }, /* inverted exclamation mark  */
 145         { "igrave",     236 }, /* small i, grave accent  */
 146         { "iquest",     191 }, /* inverted question mark  */
 147         { "iuml",       239 }, /* small i, dieresis or umlaut mark  */
 148         { "laquo",      171 }, /* angle quotation mark, left  */
 149         { "lt",          60 }, /* less than  */
 150         { "macr",       175 }, /* macron  */
 151         { "micro",      181 }, /* micro sign  */
 152         { "middot",     183 }, /* middle dot  */
 153         { "nbsp",       160 }, /* no-break space  */
 154         { "not",        172 }, /* not sign  */
 155         { "ntilde",     241 }, /* small n, tilde  */
 156         { "oacute",     243 }, /* small o, acute accent  */
 157         { "ocirc",      244 }, /* small o, circumflex accent  */
 158         { "ograve",     242 }, /* small o, grave accent  */
 159         { "ordf",       170 }, /* ordinal indicator, feminine  */
 160         { "ordm",       186 }, /* ordinal indicator, masculine  */
 161         { "oslash",     248 }, /* small o, slash  */
 162         { "otilde",     245 }, /* small o, tilde  */
 163         { "ouml",       246 }, /* small o, dieresis or umlaut mark  */
 164         { "para",       182 }, /* pilcrow (paragraph sign)  */
 165         { "plusmn",     177 }, /* plus-or-minus sign  */
 166         { "pound",      163 }, /* pound sterling sign  */
 167         { "quot",        34 }, /* double quote  */
 168         { "raquo",      187 }, /* angle quotation mark, right  */
 169         { "reg",        174 }, /* registered sign  */
 170         { "sect",       167 }, /* section sign  */
 171         { "shy",        173 }, /* soft hyphen  */
 172         { "sup1",       185 }, /* superscript one  */
 173         { "sup2",       178 }, /* superscript two  */
 174         { "sup3",       179 }, /* superscript three  */
 175         { "szlig",      223 }, /* small sharp s, German (sz ligature)  */
 176         { "thorn",      254 }, /* small thorn, Icelandic  */
 177         { "times",      215 }, /* multiply sign  */
 178         { "uacute",     250 }, /* small u, acute accent  */
 179         { "ucirc",      251 }, /* small u, circumflex accent  */
 180         { "ugrave",     249 }, /* small u, grave accent  */
 181         { "uml",        168 }, /* umlaut (dieresis)  */
 182         { "uuml",       252 }, /* small u, dieresis or umlaut mark  */
 183         { "yacute",     253 }, /* small y, acute accent  */
 184         { "yen",        165 }, /* yen sign  */
 185         { "yuml",       255 }, /* small y, dieresis or umlaut mark  */
 186 };
 187
 188 /*
 189  * unvis - decode characters previously encoded by vis
 190  */
 191 int
 192 unvis(char *cp, int c, int *astate, int flag)
 193 {
 194         unsigned char uc = (unsigned char)c;
 195         unsigned char st, ia, is, lc;
 196
 197 /*
 198  * Bottom 8 bits of astate hold the state machine state.
 199  * Top 8 bits hold the current character in the http 1866 nv string decoding
 200  */
 201 #define GS(a)           ((a) & 0xff)
 202 #define SS(a, b)        (((uint32_t)(a) << 24) | (b))
 203 #define GI(a)           ((uint32_t)(a) >> 24)
 204
 205         _DIAGASSERT(cp != NULL);
 206         _DIAGASSERT(astate != NULL);
 207         st = GS(*astate);
 208
 209         if (flag & UNVIS_END) {
 210                 switch (st) {
 211                 case S_OCTAL2:
 212                 case S_OCTAL3:
 213                 case S_HEX2:
 214                         *astate = SS(0, S_GROUND);
 215                         return UNVIS_VALID;
 216                 case S_GROUND:
 217                         return UNVIS_NOCHAR;
 218                 default:
 219                         return UNVIS_SYNBAD;
 220                 }
 221         }
 222
 223         switch (st) {
 224
 225         case S_GROUND:
 226                 *cp = 0;
 227                 if ((flag & VIS_NOESCAPE) == 0 && c == '\\') {
 228                         *astate = SS(0, S_START);
 229                         return UNVIS_NOCHAR;
 230                 }
 231                 if ((flag & VIS_HTTP1808) && c == '%') {
 232                         *astate = SS(0, S_HEX1);
 233                         return UNVIS_NOCHAR;
 234                 }
 235                 if ((flag & VIS_HTTP1866) && c == '&') {
 236                         *astate = SS(0, S_AMP);
 237                         return UNVIS_NOCHAR;
 238                 }
 239                 if ((flag & VIS_MIMESTYLE) && c == '=') {
 240                         *astate = SS(0, S_MIME1);
 241                         return UNVIS_NOCHAR;
 242                 }
 243                 *cp = c;
 244                 return UNVIS_VALID;
 245
 246         case S_START:
 247                 switch(c) {
 248                 case '\\':
 249                         *cp = c;
 250                         *astate = SS(0, S_GROUND);
 251                         return UNVIS_VALID;
 252                 case '0': case '1': case '2': case '3':
 253                 case '4': case '5': case '6': case '7':
 254                         *cp = (c - '0');
 255                         *astate = SS(0, S_OCTAL2);
 256                         return UNVIS_NOCHAR;
 257                 case 'M':
 258                         *cp = (char)0200;
 259                         *astate = SS(0, S_META);
 260                         return UNVIS_NOCHAR;
 261                 case '^':
 262                         *astate = SS(0, S_CTRL);
 263                         return UNVIS_NOCHAR;
 264                 case 'n':
 265                         *cp = '\n';
 266                         *astate = SS(0, S_GROUND);
 267                         return UNVIS_VALID;
 268                 case 'r':
 269                         *cp = '\r';
 270                         *astate = SS(0, S_GROUND);
 271                         return UNVIS_VALID;
 272                 case 'b':
 273                         *cp = '\b';
 274                         *astate = SS(0, S_GROUND);
 275                         return UNVIS_VALID;
 276                 case 'a':
 277                         *cp = '\007';
 278                         *astate = SS(0, S_GROUND);
 279                         return UNVIS_VALID;
 280                 case 'v':
 281                         *cp = '\v';
 282                         *astate = SS(0, S_GROUND);
 283                         return UNVIS_VALID;
 284                 case 't':
 285                         *cp = '\t';
 286                         *astate = SS(0, S_GROUND);
 287                         return UNVIS_VALID;
 288                 case 'f':
 289                         *cp = '\f';
 290                         *astate = SS(0, S_GROUND);
 291                         return UNVIS_VALID;
 292                 case 's':
 293                         *cp = ' ';
 294                         *astate = SS(0, S_GROUND);
 295                         return UNVIS_VALID;
 296                 case 'E':
 297                         *cp = '\033';
 298                         *astate = SS(0, S_GROUND);
 299                         return UNVIS_VALID;
 300                 case 'x':
 301                         *astate = SS(0, S_HEX);
 302                         return UNVIS_NOCHAR;
 303                 case '\n':
 304                         /*
 305                          * hidden newline
 306                          */
 307                         *astate = SS(0, S_GROUND);
 308                         return UNVIS_NOCHAR;
 309                 case '$':
 310                         /*
 311                          * hidden marker
 312                          */
 313                         *astate = SS(0, S_GROUND);
 314                         return UNVIS_NOCHAR;
 315                 }
 316                 goto bad;
 317
 318         case S_META:
 319                 if (c == '-')
 320                         *astate = SS(0, S_META1);
 321                 else if (c == '^')
 322                         *astate = SS(0, S_CTRL);
 323                 else
 324                         goto bad;
 325                 return UNVIS_NOCHAR;
 326
 327         case S_META1:
 328                 *astate = SS(0, S_GROUND);
 329                 *cp |= c;
 330                 return UNVIS_VALID;
 331
 332         case S_CTRL:
 333                 if (c == '?')
 334                         *cp |= 0177;
 335                 else
 336                         *cp |= c & 037;
 337                 *astate = SS(0, S_GROUND);
 338                 return UNVIS_VALID;
 339
 340         case S_OCTAL2:  /* second possible octal digit */
 341                 if (isoctal(uc)) {
 342                         /*
 343                          * yes - and maybe a third
 344                          */
 345                         *cp = (*cp << 3) + (c - '0');
 346                         *astate = SS(0, S_OCTAL3);
 347                         return UNVIS_NOCHAR;
 348                 }
 349                 /*
 350                  * no - done with current sequence, push back passed char
 351                  */
 352                 *astate = SS(0, S_GROUND);
 353                 return UNVIS_VALIDPUSH;
 354
 355         case S_OCTAL3:  /* third possible octal digit */
 356                 *astate = SS(0, S_GROUND);
 357                 if (isoctal(uc)) {
 358                         *cp = (*cp << 3) + (c - '0');
 359                         return UNVIS_VALID;
 360                 }
 361                 /*
 362                  * we were done, push back passed char
 363                  */
 364                 return UNVIS_VALIDPUSH;
 365
 366         case S_HEX:
 367                 if (!isxdigit(uc))
 368                         goto bad;
 369                 /*FALLTHROUGH*/
 370         case S_HEX1:
 371                 if (isxdigit(uc)) {
 372                         *cp = xtod(uc);
 373                         *astate = SS(0, S_HEX2);
 374                         return UNVIS_NOCHAR;
 375                 }
 376                 /*
 377                  * no - done with current sequence, push back passed char
 378                  */
 379                 *astate = SS(0, S_GROUND);
 380                 return UNVIS_VALIDPUSH;
 381
 382         case S_HEX2:
 383                 *astate = S_GROUND;
 384                 if (isxdigit(uc)) {
 385                         *cp = xtod(uc) | (*cp << 4);
 386                         return UNVIS_VALID;
 387                 }
 388                 return UNVIS_VALIDPUSH;
 389
 390         case S_MIME1:
 391                 if (uc == '\n' || uc == '\r') {
 392                         *astate = SS(0, S_EATCRNL);
 393                         return UNVIS_NOCHAR;
 394                 }
 395                 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
 396                         *cp = XTOD(uc);
 397                         *astate = SS(0, S_MIME2);
 398                         return UNVIS_NOCHAR;
 399                 }
 400                 goto bad;
 401
 402         case S_MIME2:
 403                 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
 404                         *astate = SS(0, S_GROUND);
 405                         *cp = XTOD(uc) | (*cp << 4);
 406                         return UNVIS_VALID;
 407                 }
 408                 goto bad;
 409
 410         case S_EATCRNL:
 411                 switch (uc) {
 412                 case '\r':
 413                 case '\n':
 414                         return UNVIS_NOCHAR;
 415                 case '=':
 416                         *astate = SS(0, S_MIME1);
 417                         return UNVIS_NOCHAR;
 418                 default:
 419                         *cp = uc;
 420                         *astate = SS(0, S_GROUND);
 421                         return UNVIS_VALID;
 422                 }
 423
 424         case S_AMP:
 425                 *cp = 0;
 426                 if (uc == '#') {
 427                         *astate = SS(0, S_NUMBER);
 428                         return UNVIS_NOCHAR;
 429                 }
 430                 *astate = SS(0, S_STRING);
 431                 /*FALLTHROUGH*/
 432
 433         case S_STRING:
 434                 ia = *cp;               /* index in the array */
 435                 is = GI(*astate);       /* index in the string */
 436                 lc = is == 0 ? 0 : nv[ia].name[is - 1]; /* last character */
 437
 438                 if (uc == ';')
 439                         uc = '\0';
 440
 441                 for (; ia < __arraycount(nv); ia++) {
 442                         if (is != 0 && nv[ia].name[is - 1] != lc)
 443                                 goto bad;
 444                         if (nv[ia].name[is] == uc)
 445                                 break;
 446                 }
 447
 448                 if (ia == __arraycount(nv))
 449                         goto bad;
 450
 451                 if (uc != 0) {
 452                         *cp = ia;
 453                         *astate = SS(is + 1, S_STRING);
 454                         return UNVIS_NOCHAR;
 455                 }
 456
 457                 *cp = nv[ia].value;
 458                 *astate = SS(0, S_GROUND);
 459                 return UNVIS_VALID;
 460
 461         case S_NUMBER:
 462                 if (uc == ';')
 463                         return UNVIS_VALID;
 464                 if (!isdigit(uc))
 465                         goto bad;
 466                 *cp += (*cp * 10) + uc - '0';
 467                 return UNVIS_NOCHAR;
 468
 469         default:
 470         bad:
 471                 /*
 472                  * decoder in unknown state - (probably uninitialized)
 473                  */
 474                 *astate = SS(0, S_GROUND);
 475                 return UNVIS_SYNBAD;
 476         }
 477 }
 478
 479 /*
 480  * strnunvisx - decode src into dst
 481  *
 482  *      Number of chars decoded into dst is returned, -1 on error.
 483  *      Dst is null terminated.
 484  */
 485
 486 int
 487 strnunvisx(char *dst, size_t dlen, const char *src, int flag)
 488 {
 489         char c;
 490         char t = '\0', *start = dst;
 491         int state = 0;
 492
 493         _DIAGASSERT(src != NULL);
 494         _DIAGASSERT(dst != NULL);
 495 #define CHECKSPACE() \
 496         do { \
 497                 if (dlen-- == 0) { \
 498                         errno = ENOSPC; \
 499                         return -1; \
 500                 } \
 501         } while (/*CONSTCOND*/0)
 502
 503         while ((c = *src++) != '\0') {
 504  again:
 505                 switch (unvis(&t, c, &state, flag)) {
 506                 case UNVIS_VALID:
 507                         CHECKSPACE();
 508                         *dst++ = t;
 509                         break;
 510                 case UNVIS_VALIDPUSH:
 511                         CHECKSPACE();
 512                         *dst++ = t;
 513                         goto again;
 514                 case 0:
 515                 case UNVIS_NOCHAR:
 516                         break;
 517                 case UNVIS_SYNBAD:
 518                         errno = EINVAL;
 519                         return -1;
 520                 default:
 521                         _DIAGASSERT(0);
 522                         errno = EINVAL;
 523                         return -1;
 524                 }
 525         }
 526         if (unvis(&t, c, &state, UNVIS_END) == UNVIS_VALID) {
 527                 CHECKSPACE();
 528                 *dst++ = t;
 529         }
 530         CHECKSPACE();
 531         *dst = '\0';
 532         return (int)(dst - start);
 533 }
 534
 535 int
 536 strunvisx(char *dst, const char *src, int flag)
 537 {
 538         return strnunvisx(dst, (size_t)~0, src, flag);
 539 }
 540
 541 int
 542 strunvis(char *dst, const char *src)
 543 {
 544         return strnunvisx(dst, (size_t)~0, src, 0);
 545 }
 546
 547 int
 548 strnunvis(char *dst, size_t dlen, const char *src)
 549 {
 550         return strnunvisx(dst, dlen, src, 0);
 551 }
 552 #endif